{"meta":{"query_hash":"203cf04dfb66","filters":{"topic":"Psychometric Methodologies and Testing"},"cohort_total":759,"direct_labels_cover":20,"predictions_cover":759,"exported":759,"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/203cf04dfb66","api":"https://metacan.xera.ac/api/v1/cohort?topic=Psychometric+Methodologies+and+Testing"},"results":[{"id":"W10676430","doi":"10.22237/jmasm/1225512660","title":"Multi-Group Confirmatory Factor Analysis for Testing Measurement Invariance in Mixed Item Format Data","year":2008,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":75,"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":"Measurement invariance; Confirmatory factor analysis; Statistics; Mathematics; Type I and type II errors; Analysis of covariance; Covariance; Econometrics; Missing data; Ordinal data; Sample size determination; Covariance matrix; Observational error; Psychology; Structural equation modeling","score_opus":0.8683162305926121,"score_gpt":0.5560488322846381,"score_spread":0.312267398307974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W10676430","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":[0.0053731757,0.0005215608,0.99275726,0.00005568478,0.00040838175,0.00032617355,0.00020499913,0.000019440673,0.0003333139],"genre_scores_gemma":[0.34815544,0.000013748012,0.6516506,0.000083314044,0.00006354602,0.0000101400765,0.0000042768374,0.00001322985,0.0000057283846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919669,0.0018002846,0.0028331506,0.00067498576,0.0021756028,0.0005491006],"domain_scores_gemma":[0.8831714,0.11274894,0.0018033881,0.0009635507,0.0009797653,0.00033297308],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04084866,0.00027532686,0.0014240358,0.0012241228,0.00022030887,0.00014736886,0.0018832634,0.00014648424,0.000058591962],"category_scores_gemma":[0.2910191,0.00019789765,0.00017772733,0.00275647,0.00016469149,0.00035603862,0.00033439917,0.00054190867,0.0000035039063],"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":[0.0003902628,0.00032990187,0.033005,0.00004268058,0.0004236673,0.000055449753,0.0004624811,0.0020359238,0.016416809,0.0015225207,0.0008952636,0.94442004],"study_design_scores_gemma":[0.0018614487,0.00013114569,0.33502278,0.000027096754,0.00018407266,0.00006156008,0.00025976167,0.61832553,0.00020322134,0.042279895,0.001362783,0.0002806759],"about_ca_topic_score_codex":0.000015647183,"about_ca_topic_score_gemma":0.000018926346,"teacher_disagreement_score":0.94413936,"about_ca_system_score_codex":0.0001595011,"about_ca_system_score_gemma":0.00022530554,"threshold_uncertainty_score":0.9876481},"labels":[],"label_agreement":null},{"id":"W107454019","doi":"10.55016/ojs/ajer.v49i1.54961","title":"An Investigation of the Accuracy of Alternative Methods of True Score Estimation in High-Stakes Mixed-Format Examinations","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Estimation; Psychology; Mathematics education; Econometrics; Mathematics; Engineering","score_opus":0.6078835678103994,"score_gpt":0.5942529116662607,"score_spread":0.01363065614413872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W107454019","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":[0.9927331,0.00021353157,0.0029433311,0.0012871397,0.00043896522,0.00017581011,0.0000054942816,2.2494577e-7,0.0022023832],"genre_scores_gemma":[0.92819405,0.00003494177,0.07147182,0.000011916842,0.00003262157,0.000005964872,0.0000020656223,0.000005435588,0.00024119325],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99124354,0.0049770116,0.0015694574,0.00017643537,0.0018442044,0.00018935376],"domain_scores_gemma":[0.6562556,0.33758318,0.002071387,0.00050255255,0.0034757939,0.00011147061],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02350779,0.00008796576,0.00034105714,0.0016715281,0.00010947221,0.000044314016,0.0011127533,0.000064103144,0.00066495343],"category_scores_gemma":[0.6203342,0.000055547738,0.00010004156,0.0041989447,0.00042290086,0.00081585813,0.00005896736,0.00034525874,0.0000024105768],"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":[0.00006151134,0.0003956578,0.83558357,0.000050579336,0.000048796686,1.3009277e-7,0.0059292,0.0067717424,0.011977286,0.10879407,0.00086645654,0.029520983],"study_design_scores_gemma":[0.00030339888,0.00019728314,0.78935623,0.00014737318,0.000009322251,0.000015061387,0.0031765546,0.0021414966,0.040073756,0.16446084,0.00006774023,0.00005093855],"about_ca_topic_score_codex":0.00094772264,"about_ca_topic_score_gemma":0.00022360153,"teacher_disagreement_score":0.59682643,"about_ca_system_score_codex":0.00009332596,"about_ca_system_score_gemma":0.0011765867,"threshold_uncertainty_score":0.81473786},"labels":[],"label_agreement":null},{"id":"W114458342","doi":"10.1177/070674371005500310","title":"Measure for Measure: New Developments in Measurement and Item Response Theory","year":2010,"lang":"en","type":"article","venue":"The Canadian Journal of Psychiatry","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"","keywords":"Item response theory; Classical test theory; Normative; Measure (data warehouse); Psychology; Econometrics; Psychometrics; Test (biology); Scale (ratio); Interpretation (philosophy); Cognitive psychology; Sample (material); Level of measurement; Statistics; Computer science; Mathematics; Clinical psychology; Epistemology; Data mining","score_opus":0.33430011667710124,"score_gpt":0.3961017540352872,"score_spread":0.061801637358185946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W114458342","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":[0.9139413,0.0074161435,0.011129331,0.050840184,0.013509612,0.00058712286,0.000012374448,0.0000113300275,0.002552596],"genre_scores_gemma":[0.93688816,0.0000036336428,0.061864972,0.00061463553,0.00036952458,0.0000028314662,7.14018e-8,0.000014139081,0.0002420432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963214,0.0010212335,0.000874052,0.00022740506,0.0011637738,0.00039216309],"domain_scores_gemma":[0.9887417,0.0087281065,0.00061379693,0.00040458798,0.0008141404,0.00069765595],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0676444,0.00014724163,0.00030879598,0.0009378194,0.00036305012,0.00025906827,0.0010674447,0.00012091767,0.000067619825],"category_scores_gemma":[0.136943,0.000087471,0.00011320301,0.00108479,0.00012397158,0.00014964602,0.000022152035,0.00058060006,0.0000049058895],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014163879,0.000025984564,0.6180147,0.0000075793437,0.00009372544,0.000014552219,0.0018864254,0.000017109589,0.0008354991,0.019580325,0.037733544,0.32037416],"study_design_scores_gemma":[0.0010798061,0.00011135794,0.63134116,0.000082937724,0.000020329211,0.00017753766,0.00096717116,0.000009413956,0.000046421035,0.34327203,0.022746174,0.00014567636],"about_ca_topic_score_codex":0.0010204184,"about_ca_topic_score_gemma":0.31077996,"teacher_disagreement_score":0.3236917,"about_ca_system_score_codex":0.00011089945,"about_ca_system_score_gemma":0.007382182,"threshold_uncertainty_score":0.99824506},"labels":[],"label_agreement":null},{"id":"W1213465059","doi":"","title":"The Mercer Study","year":2000,"lang":"en","type":"article","venue":"Journal of the Canadian Chiropractic Association","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; World Wide Web; Data science; Information retrieval","score_opus":0.2667220602005683,"score_gpt":0.4381384421137672,"score_spread":0.17141638191319886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1213465059","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":[0.93207955,0.00014881435,0.000014596026,0.03765158,0.0022969143,0.0001485568,0.0000022436154,0.0000035618264,0.027654182],"genre_scores_gemma":[0.9835039,0.000028469152,0.00028366948,0.00060262077,0.0003469174,8.5656933e-7,3.5427327e-8,0.0000053670196,0.015228213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99570876,0.001448989,0.0007139811,0.00010813094,0.0017642159,0.00025590515],"domain_scores_gemma":[0.97651786,0.020337699,0.0019165918,0.00042364834,0.0006181557,0.00018603905],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02412029,0.0000713079,0.0001821355,0.00017960445,0.0011163501,0.0005854941,0.0010591986,0.00006286105,0.00053522526],"category_scores_gemma":[0.20462163,0.0000315105,0.0001584963,0.001327419,0.000022279377,0.0002913711,0.000022350921,0.00048826402,0.00008282838],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002434094,0.000043342334,0.5561968,2.0099823e-7,0.00011575578,0.00001128413,0.0008559164,0.00026162682,0.0000053644535,0.00006503582,0.08515992,0.3572604],"study_design_scores_gemma":[0.00018888338,0.00005140767,0.7342365,0.000002916225,0.00003185883,0.000028171797,0.0010290963,0.00007530978,0.000002064083,0.0056982166,0.2586171,0.000038496815],"about_ca_topic_score_codex":0.009875805,"about_ca_topic_score_gemma":0.09240239,"teacher_disagreement_score":0.3572219,"about_ca_system_score_codex":0.00096125284,"about_ca_system_score_gemma":0.00055686367,"threshold_uncertainty_score":0.9967175},"labels":[],"label_agreement":null},{"id":"W125385871","doi":"10.55016/ojs/ajer.v49i3.54985","title":"The Effects of Examinee Motivation on Multiple-Choice Item Parameter Estimates","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","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":true,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Psychology; Social psychology; Statistics; Econometrics; Mathematics","score_opus":0.5409379066538277,"score_gpt":0.5429896068935227,"score_spread":0.0020517002396950312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125385871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.98745793,0.00071548775,0.000026290185,0.0021748014,0.0009863527,0.00014873501,5.164602e-7,3.638787e-7,0.008489549],"genre_scores_gemma":[0.9943155,0.00004707069,0.0007964217,0.000044536144,0.00016117323,0.000008944536,4.8452796e-7,0.0000077288,0.004618112],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99509245,0.0015372181,0.00081087346,0.00020423355,0.0020501523,0.00030507188],"domain_scores_gemma":[0.026871674,0.9703152,0.0005765953,0.0003955395,0.0017089299,0.00013204718],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009392023,0.00009547519,0.00022884819,0.0007312667,0.00031152414,0.0001578424,0.0008536997,0.000055567147,0.0005271715],"category_scores_gemma":[0.99842125,0.000051120547,0.00011333445,0.0018660071,0.0002021104,0.00020588154,0.00004786781,0.00040711832,0.00002403692],"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":[0.00004298114,0.00015673561,0.98324144,0.000011453038,0.000026545104,2.5666046e-7,0.00012961922,0.00006806749,0.0013505407,0.0045739855,0.007230082,0.0031682977],"study_design_scores_gemma":[0.0003017315,0.0003957625,0.97213465,0.00006533225,0.0000055977625,0.000018917593,0.00021775391,0.00017323841,0.003560534,0.017083371,0.00599339,0.000049742488],"about_ca_topic_score_codex":0.0001269327,"about_ca_topic_score_gemma":0.000026707488,"teacher_disagreement_score":0.9890292,"about_ca_system_score_codex":0.000065185144,"about_ca_system_score_gemma":0.00034171334,"threshold_uncertainty_score":0.57721585},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W128966544","doi":"10.1007/978-3-319-07794-9_6","title":"What Counts as Evidence: A Review of Validity Studies in Educational and Psychological Measurement","year":2014,"lang":"en","type":"review","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":25,"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; External validity; Test (biology); Standards for Educational and Psychological Testing; Test validity; Criterion validity; Validity; Incremental validity; Applied psychology; Construct validity; Psychometrics; Social psychology; Clinical psychology; Higher education; Education theory; Political science","score_opus":0.96993829252238,"score_gpt":0.7425690907147161,"score_spread":0.22736920180766385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W128966544","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000736181,0.99539053,0.0000018907988,0.0011158973,0.0008428867,0.0005995442,0.00000727326,0.000007872752,0.0019604703],"genre_scores_gemma":[0.00009423034,0.9986724,0.00021645053,0.00005836141,0.00029001967,0.0001697238,0.0000025876873,0.000010176067,0.0004860355],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869681,0.006746337,0.0012538487,0.000649069,0.0040133568,0.0003692935],"domain_scores_gemma":[0.9451019,0.05106882,0.0011948238,0.0006864273,0.0017778076,0.00017019639],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06287167,0.00021039402,0.0018404867,0.0012396639,0.00025755097,0.00017389368,0.0010045955,0.00025470016,0.0005483163],"category_scores_gemma":[0.3538786,0.00013189281,0.0002356087,0.004848207,0.0014476352,0.0003069988,0.0004420045,0.00072794984,0.00012372833],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005678979,0.000049243536,0.00017486722,0.019584399,0.000039919174,0.000002081663,0.00025615044,1.2986449e-9,4.8250733e-8,0.0016245202,0.04306836,0.93519473],"study_design_scores_gemma":[0.000032883912,0.0001350744,0.00046735717,0.06414809,0.000030712345,0.00000922529,0.0007935741,1.9729212e-8,1.7524917e-7,0.029094065,0.9051627,0.00012610584],"about_ca_topic_score_codex":0.000008826975,"about_ca_topic_score_gemma":0.000004199469,"teacher_disagreement_score":0.9350686,"about_ca_system_score_codex":0.00022755847,"about_ca_system_score_gemma":0.0007331192,"threshold_uncertainty_score":0.9649708},"labels":[],"label_agreement":null},{"id":"W1491477860","doi":"10.22329/il.v23i1.2160","title":"Model Answer: An Evaluation of a Complex Argument","year":2004,"lang":"en","type":"article","venue":"Informal Logic","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Epistemology; Sociology; Philosophy","score_opus":0.8183411544940141,"score_gpt":0.54089907330947,"score_spread":0.27744208118454416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1491477860","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":[0.84451103,0.000048686303,0.09269119,0.00012587282,0.00017318847,0.00019039065,0.000007872953,0.00003416092,0.062217627],"genre_scores_gemma":[0.908692,0.0000032641085,0.09093961,0.00028878124,0.000024259418,0.000007042264,0.00000447563,0.0000022901966,0.000038300557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700814,0.00014005935,0.00066157,0.00019054643,0.0017941227,0.00020554234],"domain_scores_gemma":[0.997575,0.0009791288,0.00034033332,0.00043601642,0.00059296854,0.00007655346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010976457,0.00008844303,0.00020836752,0.0003216021,0.00008193512,0.000064554064,0.0005433426,0.00005592698,0.00029711408],"category_scores_gemma":[0.014363026,0.000058335667,0.00006863612,0.0009107929,0.00006711295,0.000520485,0.00009464998,0.000075819145,0.000050973784],"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":[0.000028347862,0.00007929558,0.004444571,0.0000029007913,0.0000065284903,6.118965e-7,0.00069661706,0.6757423,0.0006055825,0.017057858,0.00013342877,0.3012019],"study_design_scores_gemma":[0.0008655249,0.0002849107,0.08468075,0.0000058306387,0.00001217906,0.000008149778,0.0006397812,0.5447083,0.00030511813,0.3680175,0.00036253402,0.000109444234],"about_ca_topic_score_codex":0.000036215504,"about_ca_topic_score_gemma":0.000010068436,"teacher_disagreement_score":0.35095963,"about_ca_system_score_codex":0.00004144817,"about_ca_system_score_gemma":0.00012895287,"threshold_uncertainty_score":0.9939394},"labels":[],"label_agreement":null},{"id":"W1509317141","doi":"10.1002/9781118411360.wbcla070","title":"Multifaceted Rasch Analysis for Test Evaluation","year":2013,"lang":"en","type":"other","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"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":"Rasch model; Facet (psychology); Polytomous Rasch model; Test (biology); Task (project management); Scale (ratio); Computer science; Focus (optics); Psychology; Artificial intelligence; Machine learning; Natural language processing; Item response theory; Psychometrics; Social psychology; Developmental psychology; Engineering; Systems engineering","score_opus":0.7058905102004684,"score_gpt":0.5619458144991976,"score_spread":0.14394469570127089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509317141","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006476768,0.000415411,0.3522366,0.00010816351,0.0005217473,0.0008655351,0.00004468739,0.00014101042,0.6456021],"genre_scores_gemma":[0.0010609603,0.00001543673,0.19747078,0.00007765074,0.00019088027,0.00013986876,0.000038458988,0.00007920656,0.80092674],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99628294,0.0003943779,0.0006331873,0.00079447025,0.0016301344,0.00026490117],"domain_scores_gemma":[0.92890614,0.06766586,0.0010368247,0.0013913333,0.00087874575,0.00012111098],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010894677,0.00021400923,0.00070454646,0.0031531726,0.000066165965,0.00026423376,0.00081697636,0.00030074967,0.07696949],"category_scores_gemma":[0.29679316,0.00013138645,0.0003817218,0.00563972,0.000039854407,0.000055905803,0.00008425132,0.00009526107,0.0009825251],"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":[0.0000010704118,0.00001918505,0.0138856545,0.00000268159,0.00019309866,6.6669806e-8,0.000008114486,0.00007241396,0.000012862352,0.00004044859,0.77954835,0.20621608],"study_design_scores_gemma":[0.0006090689,0.000057744353,0.025072243,0.000013250978,0.00071607705,4.067171e-7,0.00023211603,0.23244202,0.000017605635,0.0033638899,0.7371308,0.00034476415],"about_ca_topic_score_codex":0.0004365156,"about_ca_topic_score_gemma":0.00012239235,"teacher_disagreement_score":0.28589848,"about_ca_system_score_codex":0.000030867675,"about_ca_system_score_gemma":0.00005277224,"threshold_uncertainty_score":0.9997953},"labels":[],"label_agreement":null},{"id":"W1523818810","doi":"10.1002/9780470744116.ch10","title":"Start with the Basics","year":2009,"lang":"en","type":"other","venue":"","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":"McGill University","funders":"","keywords":"Outcome (game theory); Statistical inference; Inference; Computer science; Table (database); Scale (ratio); Data science; Statistics; Statistical hypothesis testing; Econometrics; Data mining; Artificial intelligence; Mathematics; Geography; Cartography; Mathematical economics","score_opus":0.503928006793887,"score_gpt":0.46493896158241527,"score_spread":0.038989045211471784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1523818810","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004954428,0.00046342457,0.06546976,0.0017108354,0.00024298827,0.0001219618,0.0000041762532,0.00013098774,0.9318509],"genre_scores_gemma":[0.000082577106,0.00002954159,0.05001175,0.0012206262,0.00024657874,0.000002214381,6.037148e-7,0.000060037062,0.9483461],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979135,0.00023175032,0.00019668262,0.0003716053,0.0010925947,0.00019387844],"domain_scores_gemma":[0.9875001,0.011137364,0.0002876624,0.0009632361,0.000063183856,0.00004846128],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031342208,0.00014824394,0.00027573743,0.00033716724,0.000059498296,0.0001777964,0.0010787129,0.00010964137,0.0135464035],"category_scores_gemma":[0.009843233,0.00005138964,0.000058388683,0.0015668317,0.000081087666,0.000021281623,0.00006279188,0.00017820786,0.0004932713],"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":[0.0000018725519,0.0000043515884,0.00036862644,4.2511965e-7,0.000006852413,0.0000026844987,0.000008774983,0.0000011640846,1.2179689e-7,0.001766574,0.8695903,0.1282483],"study_design_scores_gemma":[0.000067588575,0.000053261065,0.0017498358,0.000011241422,0.000005529345,0.0000045099414,0.00017037326,0.000010651291,0.0000010618596,0.007093573,0.99073476,0.00009761194],"about_ca_topic_score_codex":0.000059727936,"about_ca_topic_score_gemma":0.00015519754,"teacher_disagreement_score":0.12815069,"about_ca_system_score_codex":0.000006137826,"about_ca_system_score_gemma":0.0000379929,"threshold_uncertainty_score":0.9984973},"labels":[],"label_agreement":null},{"id":"W1524280487","doi":"10.22329/amr.v13i2.3020","title":"An Item Response Theory Analysis Of The Self-Monitoring Scale","year":2010,"lang":"en","type":"article","venue":"Applied Multivariate Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Item response theory; Extraversion and introversion; Psychology; Scale (ratio); Construct (python library); Classical test theory; Psychometrics; Rasch model; Construct validity; Cognitive psychology; Social psychology; Developmental psychology; Personality; Big Five personality traits; Computer science","score_opus":0.44513079846902587,"score_gpt":0.5646389123937322,"score_spread":0.11950811392470634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524280487","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":[0.99024343,0.000016273356,0.0018810362,0.0001584398,0.00044705285,0.0003108338,0.000010851737,0.000060058977,0.0068720197],"genre_scores_gemma":[0.97429854,0.000004114212,0.025223171,0.000010074013,0.00012931245,0.000034436332,6.180444e-7,0.0000151124395,0.000284616],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.990187,0.004906212,0.00069716544,0.00074860954,0.002856168,0.0006048454],"domain_scores_gemma":[0.8193312,0.1768459,0.00029214923,0.0024929126,0.000831632,0.00020619937],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09507805,0.00014426078,0.0004492757,0.0020546915,0.00059132656,0.00024900207,0.002835318,0.00018675534,0.0002543469],"category_scores_gemma":[0.12450293,0.000081590944,0.00020664223,0.015443522,0.00036781287,0.0001321461,0.00065129873,0.0010456578,0.000040383242],"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":[0.00068899075,0.00020492835,0.2295477,0.0000034730685,0.00020843743,0.0000017560732,0.0020605815,0.00018562836,0.6758121,0.0073460876,0.00004489731,0.08389537],"study_design_scores_gemma":[0.00026910164,0.000038631973,0.9473425,0.0000040837954,0.000055424556,7.9578837e-7,0.0024951578,0.0035883216,0.030305712,0.015105034,0.0006928391,0.00010237501],"about_ca_topic_score_codex":0.00015179154,"about_ca_topic_score_gemma":0.000020781641,"teacher_disagreement_score":0.71779484,"about_ca_system_score_codex":0.000040923383,"about_ca_system_score_gemma":0.00017766572,"threshold_uncertainty_score":0.9318076},"labels":[],"label_agreement":null},{"id":"W154875592","doi":"10.55016/ojs/ajer.v52i1.55110","title":"The Bookmark Procedure for Setting Cut-Scores and Finalizing Performance Standards: Strengths and Weaknesses","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Strengths and weaknesses; Psychology; Medical education; Mathematics education; Pedagogy; Social psychology; Medicine","score_opus":0.24646341838070204,"score_gpt":0.5308511997150415,"score_spread":0.2843877813343394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W154875592","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":[0.9720524,0.0070631187,0.00006557025,0.0135461185,0.00023206012,0.00016003303,0.0000066893926,5.1129814e-7,0.0068734884],"genre_scores_gemma":[0.98693544,0.0008929413,0.0033775202,0.00003602655,0.0005594223,0.000015647664,0.000001006855,0.000008564387,0.008173452],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970023,0.00032295487,0.00062429084,0.00022056152,0.0014931964,0.00033669136],"domain_scores_gemma":[0.6356755,0.3621181,0.0002978608,0.00012828817,0.0017018069,0.00007846987],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01507249,0.00008838652,0.00017824252,0.00038575835,0.0010693338,0.00057422655,0.0004768092,0.000040467123,0.0001672264],"category_scores_gemma":[0.5130029,0.000049449718,0.000046330486,0.0007460083,0.00028166338,0.00034699985,0.00010449694,0.00027885687,0.000001886118],"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":[0.00026355212,0.00006263394,0.77655417,0.00007370545,0.000032357817,3.459783e-7,0.0003919288,0.000057357465,0.00019213592,0.0135768745,0.11920675,0.0895882],"study_design_scores_gemma":[0.00060628034,0.0004372147,0.65400314,0.00026797457,0.000017342627,0.00025916615,0.0032467013,0.0012518184,0.0003628799,0.07503062,0.2643532,0.00016366248],"about_ca_topic_score_codex":0.000111137495,"about_ca_topic_score_gemma":0.0002610743,"teacher_disagreement_score":0.49793038,"about_ca_system_score_codex":0.00005230592,"about_ca_system_score_gemma":0.00087630807,"threshold_uncertainty_score":0.82245594},"labels":[],"label_agreement":null},{"id":"W1581582674","doi":"10.1023/a:1004181829590","title":"The Measurement of Adult Literacy in Theory and in Practice","year":2000,"lang":"en","type":"article","venue":"International Review of Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Literacy; Adult literacy; Item response theory; Government (linguistics); Sample (material); Quality assurance; Psychology; Test (biology); Mathematics education; Pedagogy; Psychometrics; Business; Developmental psychology; Marketing","score_opus":0.2438883451816002,"score_gpt":0.5511580182259558,"score_spread":0.3072696730443556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581582674","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":[0.6432201,0.17011514,0.0004961341,0.019117791,0.001572054,0.00062982517,0.000004304435,0.000004856247,0.16483974],"genre_scores_gemma":[0.9261303,0.068692625,0.003973651,0.00086196366,0.00003500122,0.00002275288,9.056481e-7,0.0000020129182,0.00028080586],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978136,0.0006086939,0.00068781147,0.00012600642,0.00071389636,0.000050018883],"domain_scores_gemma":[0.97696584,0.020978134,0.0004739891,0.00022726967,0.0013374783,0.00001728935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014691711,0.000037714155,0.000119923054,0.00016673742,0.000012686821,0.000024308416,0.00030858323,0.000012355994,0.00018773026],"category_scores_gemma":[0.23669386,0.000022466511,0.000026198788,0.00062231196,0.000033086464,0.00021025367,0.00001936495,0.000057503225,0.0000051251595],"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":[0.000040033425,0.00007192655,0.0075035924,0.000040608156,0.000003581784,7.60262e-8,0.00017517172,0.0000022951772,0.000014180171,0.008843934,0.0004144226,0.9828902],"study_design_scores_gemma":[0.0002941903,0.00004988537,0.55232656,0.00800256,0.000013724446,0.000013779579,0.0017104547,0.00016610966,0.0001500414,0.1666088,0.2705676,0.000096279015],"about_ca_topic_score_codex":0.000056426652,"about_ca_topic_score_gemma":0.000009900582,"teacher_disagreement_score":0.9827939,"about_ca_system_score_codex":0.00003842329,"about_ca_system_score_gemma":0.00010216939,"threshold_uncertainty_score":0.7697358},"labels":[],"label_agreement":null},{"id":"W1594740803","doi":"10.1111/j.2044-8317.2012.02038.x","title":"Evaluating the performance of different procedures for constructing confidence intervals for coefficient alpha: A simulation study","year":2012,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"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":"Confidence interval; Statistics; Reliability (semiconductor); Parametric statistics; Mathematics; Rubric; Robust confidence intervals; Population; Sample (material); CDF-based nonparametric confidence interval; Arithmetic; Medicine","score_opus":0.5157300170116348,"score_gpt":0.571068175661356,"score_spread":0.05533815864972125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594740803","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":[0.5396488,0.00022139246,0.45943567,0.000068766174,0.00020244447,0.00036621167,0.000015278278,0.0000023042462,0.000039171104],"genre_scores_gemma":[0.9001005,0.000011380122,0.09968421,0.00006774196,0.000096622774,0.00002057283,3.4885775e-7,0.000006210743,0.000012404669],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996898,0.00052220904,0.0014968163,0.00019617451,0.0006051113,0.00028168963],"domain_scores_gemma":[0.9231047,0.075212345,0.0008126289,0.0001284454,0.0006350264,0.000106839885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013156486,0.000105595616,0.00057899265,0.00010321355,0.0001640775,0.00008767207,0.0003217199,0.00005164213,0.000077531105],"category_scores_gemma":[0.17063797,0.00006283245,0.00008894416,0.0001906855,0.0003060947,0.00010608156,0.000058875412,0.00016553917,7.407168e-7],"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":[0.0010261927,0.001860829,0.03135046,0.00042559643,0.0001495085,0.000004996781,0.0021023492,0.00044394104,0.0006260576,0.030903604,0.00072713825,0.93037933],"study_design_scores_gemma":[0.005072211,0.011380591,0.28603932,0.0006926906,0.0003086374,0.0025478234,0.006752347,0.20768985,0.00012780997,0.4789921,0.000072834664,0.00032377185],"about_ca_topic_score_codex":7.522258e-7,"about_ca_topic_score_gemma":6.770212e-7,"teacher_disagreement_score":0.93005556,"about_ca_system_score_codex":0.000008547442,"about_ca_system_score_gemma":0.000023889246,"threshold_uncertainty_score":0.8363481},"labels":[],"label_agreement":null},{"id":"W1595860368","doi":"10.1111/jedm.12072","title":"Extended Mixed‐Effects Item Response Models With the MH‐RM Algorithm","year":2015,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":42,"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":"Item response theory; Random effects model; Curse of dimensionality; Rasch model; Mixed model; Mathematics; Algorithm; Statistics; Monte Carlo method; Linear regression; Generalized linear mixed model; Computer science; Econometrics; Psychometrics; Meta-analysis","score_opus":0.6020280900847433,"score_gpt":0.46003750662039183,"score_spread":0.1419905834643515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595860368","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":[0.5485995,0.008544053,0.34651715,0.08312626,0.0077150655,0.0005823873,0.0000055564365,0.000016790094,0.0048932605],"genre_scores_gemma":[0.86920977,0.00000923224,0.128939,0.0004969473,0.0006752289,0.000013339377,2.1226145e-7,0.0000108754075,0.0006453835],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9919619,0.0018621321,0.000728255,0.00022162174,0.005000205,0.00022591223],"domain_scores_gemma":[0.9642231,0.029295655,0.001064414,0.00042761897,0.004683754,0.0003054469],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042124245,0.00014136368,0.0002961473,0.00046045007,0.00015586088,0.00019620844,0.0008703302,0.000041229832,0.00005347324],"category_scores_gemma":[0.12234189,0.00006653568,0.000121561214,0.001230427,0.00008188427,0.00034092143,0.00005188826,0.00025657198,0.000020929749],"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":[0.0031421983,0.0014453618,0.01330512,0.000015070629,0.00045894188,0.000039625917,0.0039348314,0.007917592,0.0018128294,0.0046340576,0.52108735,0.44220704],"study_design_scores_gemma":[0.002815478,0.002226306,0.6282098,0.00025842653,0.0001315697,0.00092587114,0.0077035204,0.0038900159,0.0011934007,0.31057557,0.04164381,0.0004261646],"about_ca_topic_score_codex":0.000007289361,"about_ca_topic_score_gemma":0.0000028075478,"teacher_disagreement_score":0.6149047,"about_ca_system_score_codex":0.0003165869,"about_ca_system_score_gemma":0.0014482212,"threshold_uncertainty_score":0.9863347},"labels":[],"label_agreement":null},{"id":"W1599450790","doi":"10.22237/jmasm/1114907040","title":"Manifestation Of Differences In Item-Level Characteristics In Scale-Level Measurement Invariance Tests Of Multi-Group Confirmatory Factor Analyses","year":2005,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Measurement invariance; Confirmatory factor analysis; Statistics; Scale (ratio); Mathematics; Rating scale; Item response theory; Psychology; Factor analysis; Econometrics; Level of measurement; Factorial; Psychometrics; Structural equation modeling","score_opus":0.7887541320661162,"score_gpt":0.551971041388997,"score_spread":0.23678309067711922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599450790","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":[0.2461384,0.00020864823,0.7530095,0.00004122448,0.00015339124,0.00015690476,0.00013273038,0.0000039058527,0.00015528656],"genre_scores_gemma":[0.5131163,0.000028191258,0.48679164,0.000022597207,0.000026006746,0.0000035571052,7.620255e-7,0.0000071272193,0.000003788474],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9915523,0.0020105701,0.0036317715,0.00039061968,0.0020711934,0.00034354694],"domain_scores_gemma":[0.9535211,0.04260186,0.0026071093,0.00032342103,0.0007736366,0.00017288288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017077778,0.00024914913,0.0014824512,0.0011733786,0.00003721248,0.000056964396,0.0007368582,0.00015272501,0.00010441443],"category_scores_gemma":[0.08500827,0.00018139213,0.000113126465,0.0011514742,0.00021424674,0.00019210574,0.00009886886,0.00048334518,0.0000018225893],"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":[0.0003060765,0.00058847823,0.10421659,0.00008239286,0.00004703036,0.000013450501,0.0007431602,0.00021329144,0.09306452,0.001985259,0.000020230395,0.7987195],"study_design_scores_gemma":[0.0013039664,0.00014281078,0.9355404,0.00014680813,0.000030213494,0.000011788751,0.0003150646,0.03553731,0.0027356315,0.024052087,0.000015936343,0.00016801392],"about_ca_topic_score_codex":0.000040085208,"about_ca_topic_score_gemma":0.000120651006,"teacher_disagreement_score":0.8313238,"about_ca_system_score_codex":0.00015017002,"about_ca_system_score_gemma":0.00021476507,"threshold_uncertainty_score":0.9226991},"labels":[],"label_agreement":null},{"id":"W1659542063","doi":"","title":"Construct Validity in Cross Cultural Management Research: Classical Test Theory and Latent Trait Theory Approaches","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Generalizability theory; Classical test theory; Construct (python library); Item response theory; Test theory; Equivalence (formal languages); Knowledge management; Construct validity; Development theory; Management science; Field (mathematics); Psychology; Computer science; Psychometrics; Mathematics; Engineering; Economics","score_opus":0.58918939303789,"score_gpt":0.483181745151451,"score_spread":0.10600764788643896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1659542063","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":[0.97582334,0.0015894325,0.009485253,0.00092732144,0.00021197696,0.00032291687,0.0000027557764,0.000025181855,0.011611812],"genre_scores_gemma":[0.99310565,0.00081741257,0.002436592,0.000046196143,0.00014337886,0.000019625691,6.029433e-7,0.000011995124,0.0034185224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9905822,0.0042988234,0.0007627849,0.0005648435,0.0013320857,0.0024592543],"domain_scores_gemma":[0.9581524,0.040424317,0.00032742802,0.00047156887,0.0003733152,0.0002509839],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08887509,0.00019127082,0.0003492673,0.0006698605,0.0004778084,0.0009613388,0.0009911902,0.000120533565,0.00021501504],"category_scores_gemma":[0.041785907,0.000114928196,0.0001216638,0.00147263,0.000824977,0.0005505667,0.0003099352,0.0027275512,0.000051293904],"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":[0.000063755055,0.000060111983,0.07596641,0.0000037669547,0.000035239602,0.0000089220075,0.0002108505,0.000012117416,0.000044375207,0.50185513,0.00020696556,0.42153233],"study_design_scores_gemma":[0.00054629927,0.00018908526,0.20377097,0.000013801463,0.0000061264413,0.00032779193,0.011695279,0.00017959112,0.000014649556,0.78285336,0.00028432728,0.00011872441],"about_ca_topic_score_codex":0.000023322109,"about_ca_topic_score_gemma":0.000038568924,"teacher_disagreement_score":0.4214136,"about_ca_system_score_codex":0.0003857593,"about_ca_system_score_gemma":0.00029684577,"threshold_uncertainty_score":0.9995732},"labels":[],"label_agreement":null},{"id":"W1659872837","doi":"","title":"Rescaling and transforming continuous non-normal data in covariance structure analysis: an essay of taxonomy","year":2006,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","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 du Québec en Outaouais","funders":"","keywords":"Covariance; Observable; Structural equation modeling; Ordinal data; Econometrics; Taxonomy (biology); Analysis of covariance; Mathematics; Computer science; Statistics; Ecology; Physics; Biology","score_opus":0.6657838665290491,"score_gpt":0.6269524898829532,"score_spread":0.03883137664609593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1659872837","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":[0.90313464,0.0064714346,0.08762851,0.000052331314,0.00026329153,0.0003906172,0.00020862391,0.000012857315,0.0018376728],"genre_scores_gemma":[0.97189456,0.00050488714,0.027334206,0.000054276705,0.000107003856,0.0000080864465,0.000027633574,0.000015933947,0.00005338959],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943305,0.000880503,0.0021772159,0.00089230377,0.0012894789,0.0004300014],"domain_scores_gemma":[0.98943317,0.0068176603,0.0018261843,0.0013351833,0.00038544612,0.00020236502],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014955564,0.0002759481,0.0014837777,0.0030149322,0.0002122267,0.0014658922,0.0060883956,0.0001462708,0.0015260796],"category_scores_gemma":[0.009857154,0.00021507552,0.0001390857,0.007584784,0.00020645812,0.0043613478,0.001031396,0.00043301118,6.217076e-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":[0.00013357453,0.000082355225,0.9155246,0.00002376583,0.00012196562,0.000025788384,0.00010947531,0.004669128,0.0115248235,0.000051107643,0.0007917782,0.06694166],"study_design_scores_gemma":[0.0007067734,0.000012793758,0.97492933,0.0001278016,0.0001590196,0.000015693582,0.00049557985,0.007094789,0.0028615908,0.010939027,0.0023479746,0.00030961877],"about_ca_topic_score_codex":0.004329474,"about_ca_topic_score_gemma":0.001040237,"teacher_disagreement_score":0.068759926,"about_ca_system_score_codex":0.00003988189,"about_ca_system_score_gemma":0.00017258366,"threshold_uncertainty_score":0.99957067},"labels":[],"label_agreement":null},{"id":"W1763060499","doi":"10.1002/0470013192.bsa323","title":"Maximum Likelihood Item Response Theory Estimation","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistics in Behavioral Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Maximum likelihood sequence estimation; Maximum likelihood; Marginal likelihood; Restricted maximum likelihood; Estimation; Estimation theory; Expectation–maximization algorithm; Statistics; Computer science; Mathematics; Likelihood function; Likelihood principle; Bayesian probability; Maximum a posteriori estimation; Bayes estimator; Econometrics; Joint (building); Quasi-maximum likelihood; Engineering","score_opus":0.14113003836155422,"score_gpt":0.45593826788999636,"score_spread":0.3148082295284421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1763060499","genre_codex":"other","genre_gemma":"methods","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":[0.016105449,0.00095212687,0.27317277,0.000098551995,0.003986724,0.0009123216,0.0012191941,0.00019228764,0.7033606],"genre_scores_gemma":[0.007944717,0.0004109835,0.83165693,0.00003708085,0.0001772586,0.000028948592,0.000013368354,0.00014384433,0.15958686],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9930577,0.00084872113,0.0013082401,0.0010465827,0.00306018,0.0006785488],"domain_scores_gemma":[0.97771376,0.019340316,0.0012827223,0.0011236157,0.0003129564,0.00022662984],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020735657,0.00034058618,0.0007115284,0.0031400525,0.0001187625,0.00015683525,0.0024236909,0.00025719433,0.00427409],"category_scores_gemma":[0.10119069,0.00027486606,0.00007062923,0.0050980747,0.0012678724,0.00025297073,0.00041566696,0.000428142,0.00015425931],"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":[0.0000772804,0.00016209742,0.009749954,0.000010102203,0.0000018062593,0.000033985256,0.00033697722,0.000029181305,0.00006293092,0.0025537945,0.049379047,0.9376028],"study_design_scores_gemma":[0.0012244025,0.00082037103,0.37117562,0.0005902818,0.00009365434,0.000031371044,0.0013042319,0.0025248965,0.00009571452,0.30873334,0.31178394,0.001622172],"about_ca_topic_score_codex":0.0002774958,"about_ca_topic_score_gemma":0.00015794857,"teacher_disagreement_score":0.9359807,"about_ca_system_score_codex":0.00017792071,"about_ca_system_score_gemma":0.00064348127,"threshold_uncertainty_score":0.9999704},"labels":[],"label_agreement":null},{"id":"W1763331641","doi":"10.1177/0013164415584576","title":"It Might Not Make a Big DIF","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":130,"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":"Differential item functioning; Item response theory; Statistics; Polytomous Rasch model; Computer science; Monte Carlo method; Econometrics; Type I and type II errors; Statistical hypothesis testing; Machine learning; Data mining; Artificial intelligence; Psychometrics; Mathematics","score_opus":0.9118226372485674,"score_gpt":0.5444501445426981,"score_spread":0.36737249270586925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1763331641","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":[0.5929533,0.002606433,0.00848812,0.16969456,0.009603234,0.00044963733,0.000017086873,0.00008240417,0.21610522],"genre_scores_gemma":[0.9806212,0.00002262595,0.011479998,0.0047788606,0.0007407291,0.000041514893,0.0000019464915,0.000005069896,0.0023080264],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99589324,0.000466154,0.000541566,0.00062367745,0.0021950505,0.0002803024],"domain_scores_gemma":[0.99423337,0.0040869103,0.00017826223,0.000395327,0.00071644643,0.00038966478],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010138696,0.00014899787,0.00024056114,0.00020872647,0.00013978122,0.00016674433,0.00048087898,0.00008620465,0.0005668987],"category_scores_gemma":[0.05947007,0.00008797546,0.00007200234,0.0008806389,0.00012229441,0.000040405703,0.00007949272,0.00016401333,0.00025464472],"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":[0.00014594277,0.00089368504,0.06984503,0.0000036354772,0.00002580343,0.0000035264814,0.0005898251,0.000008374251,0.0004786453,0.006006123,0.19425382,0.7277456],"study_design_scores_gemma":[0.00044849116,0.00023733632,0.6071104,0.000011681144,0.000005832416,0.000032370684,0.00038340047,0.000015698592,0.0000282667,0.119155295,0.2724169,0.00015438048],"about_ca_topic_score_codex":0.000013465686,"about_ca_topic_score_gemma":0.000011422254,"teacher_disagreement_score":0.7275912,"about_ca_system_score_codex":0.000054206153,"about_ca_system_score_gemma":0.000084218365,"threshold_uncertainty_score":0.9484524},"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":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W1863917558","doi":"10.1002/9781118445112.stat06521","title":"Structural Equation Modeling and Test Validation","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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; Confirmatory factor analysis; Construct validity; Context (archaeology); Psychology; Predictive validity; Test validity; Test (biology); Scale (ratio); Construct (python library); Econometrics; Computer science; Psychometrics; Statistics; Mathematics; Clinical psychology","score_opus":0.498217150854182,"score_gpt":0.46969201286559187,"score_spread":0.028525137988590132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1863917558","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":[0.0017886219,0.0008724039,0.9648374,0.000107011234,0.00091100554,0.000396059,0.009400828,0.00023494805,0.021451764],"genre_scores_gemma":[0.02468629,0.0015986487,0.879332,0.00014853437,0.0007683589,0.000016552583,0.0035482019,0.0003569337,0.08954446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951953,0.00048001955,0.0011788906,0.0010714044,0.0016106206,0.00046371573],"domain_scores_gemma":[0.97707444,0.019966632,0.0012841233,0.0008973163,0.0005454317,0.00023203275],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022163696,0.0004750568,0.0008191504,0.001046288,0.00017207411,0.00039815746,0.0007236978,0.00036549036,0.0018247949],"category_scores_gemma":[0.09382711,0.00036219426,0.000045103003,0.00087350886,0.00015874645,0.000121552745,0.00024068047,0.0004927613,0.00012415448],"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":[0.00003394479,0.00009080094,0.009904605,0.00015675202,0.000071625574,0.000014899799,0.00018250411,0.0019885784,0.00006486098,0.017724,0.26974064,0.7000268],"study_design_scores_gemma":[0.0006491451,0.00027803847,0.0014122681,0.00034818836,0.00008252393,0.000013969239,0.0003202234,0.78322685,0.000003556342,0.156038,0.0568056,0.00082166994],"about_ca_topic_score_codex":0.00037166587,"about_ca_topic_score_gemma":0.0002357149,"teacher_disagreement_score":0.78123826,"about_ca_system_score_codex":0.000054454926,"about_ca_system_score_gemma":0.00012525612,"threshold_uncertainty_score":0.999883},"labels":[],"label_agreement":null},{"id":"W1876152238","doi":"10.1186/s13104-015-1561-6","title":"A critical review of scoring options for clinical measurement tools","year":2015,"lang":"en","type":"review","venue":"BMC Research Notes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Formative assessment; PsycINFO; CINAHL; Construct (python library); Computer science; MEDLINE; Data science; Psychology; Mathematics education","score_opus":0.9965304775483,"score_gpt":0.810424374674974,"score_spread":0.18610610287332607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1876152238","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.782518e-7,0.9698246,0.025300074,0.00033498995,0.00088309456,0.0023321512,0.00011056466,0.000026548596,0.0011875822],"genre_scores_gemma":[7.9494316e-7,0.89258534,0.106120266,0.000023242594,0.0006239886,0.0005048468,0.000007998486,0.00002845777,0.00010505401],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9725277,0.013369406,0.0042218193,0.0012782585,0.007720236,0.00088260736],"domain_scores_gemma":[0.16489728,0.8124036,0.0012163046,0.003087619,0.01766066,0.00073451194],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33509165,0.00030411806,0.0036822627,0.001240198,0.00026869038,0.00036016654,0.0027315235,0.00033545087,0.0001758045],"category_scores_gemma":[0.9749657,0.00018638995,0.0015349124,0.0048505547,0.0005732819,0.00022721675,0.0009003561,0.0010367801,0.0001787487],"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":[0.000007272563,0.00007698076,0.000057143818,0.04803782,0.000027649257,0.0000014553834,0.0000030106496,1.130513e-7,6.7800606e-8,0.0013528857,0.022692474,0.92774314],"study_design_scores_gemma":[0.00011708461,0.0002556208,0.000041342908,0.097489595,0.00012683273,0.000008061226,0.000021960203,0.000012281891,3.1597446e-7,0.012715227,0.8890415,0.0001702174],"about_ca_topic_score_codex":0.000012183572,"about_ca_topic_score_gemma":0.0000045974048,"teacher_disagreement_score":0.9275729,"about_ca_system_score_codex":0.00024274473,"about_ca_system_score_gemma":0.0031418772,"threshold_uncertainty_score":0.76007617},"labels":[],"label_agreement":null},{"id":"W1910025992","doi":"10.14746/ssllt.2015.5.1.8","title":"The handling of missing binary data in language research","year":2015,"lang":"en","type":"article","venue":"Studies in Second Language Learning and Teaching","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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 TÉLUQ","funders":"","keywords":"Missing data; Cronbach's alpha; Data collection; Psychology; Consistency (knowledge bases); Computer science; Statistics; Natural language processing; Binary data; Binary number; Artificial intelligence; Mathematics; Psychometrics; Arithmetic","score_opus":0.7454257058579518,"score_gpt":0.6274522779588587,"score_spread":0.11797342789909304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1910025992","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":[0.9237959,0.06389719,0.00013876447,0.00027494947,0.00026568462,0.00008417602,0.000002361179,0.000019903286,0.011521061],"genre_scores_gemma":[0.9934682,0.00013792182,0.0052093933,0.000021605996,0.00009917511,0.0000032539706,0.0000021258963,0.000009587742,0.0010487251],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99408185,0.0036156946,0.00062049046,0.00049855054,0.00076585566,0.00041758246],"domain_scores_gemma":[0.9426957,0.056292098,0.00021626973,0.0006206622,0.00011388779,0.00006139411],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07320487,0.000112375565,0.0003864411,0.0006294669,0.00050538545,0.00015588476,0.0008397837,0.000055191493,0.000014306688],"category_scores_gemma":[0.32981536,0.000068349254,0.000023781227,0.0008881725,0.00034434503,0.00021319224,0.0014315137,0.0013011029,0.0000026931657],"study_design_candidate":"qualitative","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":[0.000039031045,0.000023834591,0.15302867,0.000033691867,0.00002251193,0.00015372559,0.12703392,0.000100367964,0.00048054973,0.00021169025,0.0005337817,0.71833825],"study_design_scores_gemma":[0.00064266915,0.000112047885,0.0140370615,0.00028365303,0.000003844636,0.000026406567,0.9687496,0.005384811,0.000048033362,0.002962932,0.0076066023,0.00014236206],"about_ca_topic_score_codex":0.0005732041,"about_ca_topic_score_gemma":0.0005803177,"teacher_disagreement_score":0.84171563,"about_ca_system_score_codex":0.000043120235,"about_ca_system_score_gemma":0.000045664194,"threshold_uncertainty_score":0.9543306},"labels":[],"label_agreement":null},{"id":"W1921155735","doi":"10.1023/a:1023488915557","title":"Use of differential item functioning analysis to assess the equivalence of translations of a questionnaire","year":2003,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Differential item functioning; Contingency table; Psychology; Scale (ratio); Item response theory; Statistics; Logistic regression; Test (biology); Cross-cultural studies; Linguistics; Psychometrics; Mathematics; Social psychology; Developmental psychology; Geography","score_opus":0.9498982239111976,"score_gpt":0.6535681604742923,"score_spread":0.29633006343690527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1921155735","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":[0.75747323,0.00013825638,0.24147627,0.0003328517,0.0000621958,0.00014136452,0.000026239702,0.000004368908,0.0003452372],"genre_scores_gemma":[0.9896286,0.000019408057,0.010184263,0.0000067525343,0.000014095034,0.0000062552813,8.6056406e-7,0.0000034915881,0.00013624555],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.986983,0.007630789,0.0015977166,0.00031953104,0.0032254104,0.0002435679],"domain_scores_gemma":[0.8295501,0.16432323,0.0009791662,0.001348755,0.0036327022,0.00016604856],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03855322,0.00007613962,0.00060365995,0.001395905,0.00015189672,0.000047887585,0.00069735217,0.000066574896,0.00026469646],"category_scores_gemma":[0.41016936,0.000049043265,0.00028690975,0.0104623055,0.00044294016,0.0001530579,0.00010129836,0.00020491093,0.0000015307957],"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":[0.000105251114,0.00016968677,0.9607228,0.00008012241,0.00021344879,1.06781314e-7,0.0012011355,0.0025919129,0.010680488,0.011378371,0.00012767919,0.012728969],"study_design_scores_gemma":[0.00013800467,0.00012746267,0.9875903,0.00005314461,0.000041357842,1.7541677e-7,0.0021996498,0.0016394681,0.003153965,0.0049323803,0.0000704033,0.00005366341],"about_ca_topic_score_codex":0.0013235892,"about_ca_topic_score_gemma":0.00012305872,"teacher_disagreement_score":0.37161615,"about_ca_system_score_codex":0.00001518118,"about_ca_system_score_gemma":0.00020262453,"threshold_uncertainty_score":0.9900118},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"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":"W1953764601","doi":"","title":"The Effect of Removing Examinees with Low Motivation on Item Response Data Calibration","year":2015,"lang":"en","type":"article","venue":"Knowledge Commons (Lakehead University)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Psychology; Item response theory; Test (biology); Expectancy theory; Scale (ratio); Calibration; Statistics; Principal component analysis; Social psychology; Developmental psychology; Psychometrics; Mathematics","score_opus":0.3629131663266415,"score_gpt":0.38536554677008134,"score_spread":0.022452380443439834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953764601","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":[0.9608131,0.00013081283,0.010420815,0.00035780616,0.00029953715,0.00021754132,0.000017684026,0.000059500035,0.0276832],"genre_scores_gemma":[0.9967347,5.7081746e-7,0.00023799868,0.0000015162119,0.000040336836,4.617551e-7,0.000010277494,0.000008864993,0.0029652952],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99499106,0.0034495867,0.00030572354,0.0004362605,0.0006070367,0.00021033663],"domain_scores_gemma":[0.84203416,0.15512222,0.00037746242,0.0018940605,0.0004241717,0.00014795637],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009468969,0.00015039417,0.00028695652,0.00078180176,0.00034367476,0.00011732856,0.0017954721,0.00007651044,0.000006711084],"category_scores_gemma":[0.15117888,0.00008834406,0.000044181823,0.0038319863,0.00020072726,0.00048952014,0.0005179585,0.00018484789,0.000013917122],"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":[0.006392332,0.0001166657,0.819921,0.000018988943,0.000055351586,0.00003999676,0.00089463714,0.00045052555,0.00057071296,0.0027060835,0.016191144,0.15264255],"study_design_scores_gemma":[0.0032377176,0.0033991307,0.8167552,0.00027496257,0.00006582405,0.00001742201,0.0019086032,0.012910283,0.0028461376,0.00050636334,0.15768562,0.00039278038],"about_ca_topic_score_codex":0.00002213213,"about_ca_topic_score_gemma":0.0020915654,"teacher_disagreement_score":0.15295692,"about_ca_system_score_codex":0.000097734,"about_ca_system_score_gemma":0.00014569862,"threshold_uncertainty_score":0.8559711},"labels":[],"label_agreement":null},{"id":"W1964213907","doi":"10.1002/sim.1026","title":"An improved CML estimation procedure for the Rasch model with item response data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research","keywords":"Rasch model; Estimator; Item response theory; Polytomous Rasch model; Computer science; Ordinal data; Statistics; Conditional independence; Independence (probability theory); Goodness of fit; Local independence; Econometrics; Mathematics; Psychometrics","score_opus":0.5951936693828095,"score_gpt":0.5402817360493364,"score_spread":0.054911933333473106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964213907","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":[0.0063227066,0.0002848752,0.98900485,0.0031824897,0.0001986633,0.0005097385,0.0002698137,0.000026981565,0.0001998752],"genre_scores_gemma":[0.27270392,0.000036862537,0.72605586,0.00038855374,0.000094827206,0.000035308592,0.000039741266,0.00001340612,0.0006315366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974725,0.00033224814,0.0005855599,0.000523016,0.0008356152,0.00025106166],"domain_scores_gemma":[0.92254645,0.07542081,0.0002875696,0.001351831,0.00031173648,0.00008158735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0147936335,0.00012975637,0.00028753668,0.000287114,0.00017653682,0.00007139347,0.0013005811,0.00005136018,0.000104334424],"category_scores_gemma":[0.33036822,0.0000622226,0.000008549298,0.001255861,0.00021703837,0.00019515124,0.00008297922,0.00019195197,0.0000034674201],"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":[0.0016066656,0.00013230243,0.0048831063,0.000049702692,0.000028415388,0.0000173801,0.0031467734,0.026031042,0.0005597884,0.0046166647,0.14180453,0.81712365],"study_design_scores_gemma":[0.0009492328,0.00047642173,0.0081775645,0.000034485136,0.000022466087,0.000009516651,0.0010243148,0.9540553,0.000004134343,0.034402452,0.0007586796,0.00008540965],"about_ca_topic_score_codex":0.000029480283,"about_ca_topic_score_gemma":0.00006544147,"teacher_disagreement_score":0.9280243,"about_ca_system_score_codex":0.000025240366,"about_ca_system_score_gemma":0.000061513456,"threshold_uncertainty_score":0.6752724},"labels":[],"label_agreement":null},{"id":"W1964899761","doi":"10.1177/107319110000700208","title":"Comparisons among the Holden Psychological Screening Inventory (HPSI), the Brief Symptom Inventory (BSI), and the Balanced Inventory of Desirable Responding (BIDR)","year":2000,"lang":"en","type":"article","venue":"Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Reliability (semiconductor); Internal consistency; Psychometrics; Psychological testing; Test (biology); Clinical psychology","score_opus":0.36690689551734884,"score_gpt":0.46778107231030047,"score_spread":0.10087417679295163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964899761","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":[0.95366347,0.0017439174,0.005406399,0.0021924255,0.00051196443,0.0007572906,0.000006821525,0.000069594316,0.035648134],"genre_scores_gemma":[0.99242544,0.00027288284,0.0039247926,0.001060404,0.00014910132,0.0000902145,0.0000025766485,0.000020132711,0.0020544662],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99102944,0.0045008557,0.0012589388,0.0007657156,0.0018389024,0.0006061739],"domain_scores_gemma":[0.97646296,0.020800238,0.0008468004,0.0015568951,0.00016803658,0.00016505431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023982754,0.00030780182,0.0006800244,0.00033767716,0.0010145544,0.00043210914,0.002274832,0.00014957493,0.0006837662],"category_scores_gemma":[0.007569807,0.00013705863,0.00027728753,0.0023650115,0.0018167895,0.00030352798,0.00045870894,0.0007883805,0.000014462375],"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":[0.00027834726,0.00014544852,0.9010661,0.000009577439,0.00013861078,0.000008639092,0.0011716189,0.00072987686,0.0001356312,0.012521822,0.03143376,0.052360572],"study_design_scores_gemma":[0.0019371628,0.0001754061,0.9390317,0.00010034182,0.00007029333,0.00002234548,0.0041094758,0.01745107,0.000033293825,0.0122677805,0.024551986,0.00024909858],"about_ca_topic_score_codex":0.00028172182,"about_ca_topic_score_gemma":0.000041996173,"teacher_disagreement_score":0.052111473,"about_ca_system_score_codex":0.00007144566,"about_ca_system_score_gemma":0.00007947807,"threshold_uncertainty_score":0.9062313},"labels":[],"label_agreement":null},{"id":"W1965747485","doi":"10.1007/bf02294370","title":"Does Adaptive Testing Violate Local Independence?","year":2000,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Office of the Chief Medical Examiner","funders":"","keywords":"Independence (probability theory); Computerized adaptive testing; Item response theory; Context (archaeology); Conditional independence; Notation; Econometrics; Selection (genetic algorithm); Mathematics; Local independence; Computer science; Statistics; Artificial intelligence; Psychometrics; Arithmetic","score_opus":0.3770144523253233,"score_gpt":0.4375260516385797,"score_spread":0.06051159931325639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965747485","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":[0.65896004,0.0010263183,0.11747135,0.00059259665,0.0036362421,0.0005021587,0.00003897864,0.0005234151,0.21724889],"genre_scores_gemma":[0.9238174,0.000072959585,0.06880463,0.000428092,0.00036705728,0.000019381907,0.0000011383651,0.000028554812,0.0064608],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935203,0.0006302394,0.0011880379,0.0012878925,0.002546066,0.0008274601],"domain_scores_gemma":[0.9447254,0.052492715,0.00044070935,0.0013371124,0.0006118877,0.00039219446],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009170192,0.00034247592,0.00062701874,0.0019289596,0.00037889704,0.00041192782,0.0018253515,0.0002465154,0.008843364],"category_scores_gemma":[0.07684892,0.00018404266,0.00021203196,0.01759646,0.00026091575,0.0005170793,0.00013731682,0.00062560744,0.0022904756],"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":[0.00007865499,0.000067134795,0.08914058,0.0000017704272,0.000019202744,0.000016879369,0.00008273118,0.00019711767,0.000078134464,0.00012465862,0.0023544608,0.9078387],"study_design_scores_gemma":[0.0017503629,0.00076076476,0.72842,0.000101611724,0.00003311955,0.00010775291,0.0019115878,0.010919451,0.00048451085,0.13373797,0.120661415,0.0011114248],"about_ca_topic_score_codex":0.00017019939,"about_ca_topic_score_gemma":0.000013970698,"teacher_disagreement_score":0.90672725,"about_ca_system_score_codex":0.00007333532,"about_ca_system_score_gemma":0.00007238132,"threshold_uncertainty_score":0.99848634},"labels":[],"label_agreement":null},{"id":"W1966595022","doi":"10.1016/j.jmpt.2006.08.002","title":"The Presence and Impact of Local Item Dependence on Objective Structured Clinical Examinations Scores and the Potential Use of the Polytomous, Many-Facet Rasch Model","year":2006,"lang":"en","type":"article","venue":"Journal of Manipulative and Physiological Therapeutics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Calgary","funders":"","keywords":"Rasch model; Polytomous Rasch model; Cronbach's alpha; Medicine; Statistics; Licensure; Item response theory; Psychometrics; Psychology; Clinical psychology; Mathematics; Medical education","score_opus":0.6821675390066855,"score_gpt":0.4999309688009727,"score_spread":0.18223657020571277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966595022","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":[0.9769248,0.00094640563,0.021608114,0.00019172653,0.00010383806,0.00017739975,0.00001394572,0.000002065074,0.00003174046],"genre_scores_gemma":[0.9979897,0.0007091228,0.0011295603,0.00007407489,0.000063617445,8.5886467e-7,1.574622e-7,0.0000039104434,0.00002898453],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962329,0.0019072613,0.00085147226,0.00020754748,0.000634389,0.00016640913],"domain_scores_gemma":[0.9682336,0.029868633,0.0011694151,0.0002571293,0.00042471132,0.00004655409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003680532,0.00014630143,0.00047790265,0.00007143541,0.0002953862,0.00010365579,0.00046611697,0.00010485544,0.000003684216],"category_scores_gemma":[0.0065613175,0.00004760448,0.00022577113,0.00038225958,0.0017233242,0.00014478252,0.00020842392,0.00043417007,6.127088e-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":[0.007310913,0.0005824411,0.452824,0.000020271686,0.0010235778,0.0000104399505,0.0014462054,0.20255357,0.025262853,0.058270052,0.00040255068,0.2502931],"study_design_scores_gemma":[0.00054706924,0.00046588897,0.754811,0.000017726334,0.000039025017,0.000019187855,0.0003680583,0.09488395,0.0001737455,0.1486234,0.0000042493266,0.000046715857],"about_ca_topic_score_codex":0.000046795165,"about_ca_topic_score_gemma":0.0000066915954,"teacher_disagreement_score":0.30198696,"about_ca_system_score_codex":0.000012502281,"about_ca_system_score_gemma":0.000044628465,"threshold_uncertainty_score":0.7854984},"labels":[],"label_agreement":null},{"id":"W1968457467","doi":"10.1111/j.1745-3984.2006.00019.x","title":"Testing Features of Graphical DIF: Application of a Regression Correction to Three Nonparametric Statistical Tests","year":2006,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":22,"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":"Differential item functioning; Nonparametric statistics; Statistics; Statistical hypothesis testing; Context (archaeology); Mathematics; Statistical power; Item response theory; Matching (statistics); Test (biology); Regression analysis; Econometrics; Computer science; Psychometrics","score_opus":0.32495067350014345,"score_gpt":0.45965203750100464,"score_spread":0.1347013640008612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968457467","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":[0.6878451,0.0013583046,0.30320123,0.0020957678,0.0028404866,0.00036892487,0.000012030116,0.0000073373585,0.0022708192],"genre_scores_gemma":[0.8660614,0.0000018830392,0.1335632,0.000025430001,0.00030850703,0.000007125321,0.0000010910973,0.00000590706,0.000025484964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944184,0.00030600317,0.0015436087,0.00024366392,0.0033199186,0.00016842355],"domain_scores_gemma":[0.9664418,0.026119238,0.0020712046,0.00030120552,0.0049236016,0.00014294717],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0088590635,0.0001247831,0.0004129211,0.0014269868,0.00008324292,0.000041192154,0.00045932102,0.00005667575,0.000047659145],"category_scores_gemma":[0.21138297,0.00008334225,0.00012108552,0.0040737106,0.00007461554,0.00011445616,0.000044393542,0.00021950727,0.0000037615073],"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":[0.00013270942,0.0006661367,0.76439,0.000017670123,0.00002301591,5.708511e-7,0.000036226415,0.0013388293,0.0311418,0.001936294,0.015865209,0.18445155],"study_design_scores_gemma":[0.00022190258,0.00034021743,0.93906564,0.00014663252,0.000025619693,0.00004628023,0.00006508327,0.00029031507,0.0014067581,0.058068745,0.0002494303,0.00007338991],"about_ca_topic_score_codex":0.00018860663,"about_ca_topic_score_gemma":0.000052924825,"teacher_disagreement_score":0.2025239,"about_ca_system_score_codex":0.0001457562,"about_ca_system_score_gemma":0.00037630348,"threshold_uncertainty_score":0.7952599},"labels":[],"label_agreement":null},{"id":"W1969608664","doi":"10.1207/s15324818ame1703_4","title":"Comparability of Bilingual Versions of Assessments: Sources of Incomparability of English and French Versions of Canada's National Achievement Tests","year":2004,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":62,"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":"Comparability; Differential item functioning; Psychology; Reading (process); Item response theory; Psychometrics; Developmental psychology; Linguistics; Mathematics","score_opus":0.2715701847682983,"score_gpt":0.4269062826454618,"score_spread":0.15533609787716351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969608664","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":[0.9961377,0.00015054108,0.0004005036,0.000064529,0.00035070194,0.00036764017,0.000034059092,0.0000031863822,0.0024911787],"genre_scores_gemma":[0.98846006,0.0000063303464,0.011488439,0.000008167554,0.000016233575,0.000010606506,0.000005461011,0.0000028254053,0.0000018673434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956943,0.00021849894,0.0013851082,0.00031440088,0.0022496227,0.00013809375],"domain_scores_gemma":[0.9913903,0.0038278557,0.0012467876,0.00041999336,0.0030480274,0.00006706948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008387373,0.00010965969,0.00049297,0.0004315183,0.000044598753,0.0000046260175,0.00036633777,0.000052347437,0.000026572512],"category_scores_gemma":[0.026859224,0.00009530023,0.00005264134,0.0013880668,0.00023292401,0.00006646567,0.000092976705,0.00010005044,6.989185e-8],"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":[0.00006717769,0.0022823731,0.9710136,0.0001585683,0.000038080714,1.6668752e-8,0.0021943077,0.004583712,0.011880982,0.0023434716,0.00016269449,0.0052749985],"study_design_scores_gemma":[0.0007111569,0.00011608354,0.94602275,0.00010316538,0.000019438783,1.0147029e-7,0.009303373,0.000037042333,0.029265165,0.014269522,0.000078307836,0.00007388488],"about_ca_topic_score_codex":0.03255771,"about_ca_topic_score_gemma":0.015115227,"teacher_disagreement_score":0.02499086,"about_ca_system_score_codex":0.000342068,"about_ca_system_score_gemma":0.003462436,"threshold_uncertainty_score":0.98133796},"labels":[],"label_agreement":null},{"id":"W1970487165","doi":"10.3138/cmlr.57.4.607","title":"Comparaison de deux versions d'un test de classement: version papier-crayon et version informatisée","year":2001,"lang":"fr","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Art","score_opus":0.09822052131697262,"score_gpt":0.35779235775202695,"score_spread":0.2595718364350543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970487165","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":[0.6601984,0.2975511,0.0049512903,0.008456811,0.001129788,0.00085468485,0.0015325578,0.00014506424,0.02518034],"genre_scores_gemma":[0.7518839,0.18871386,0.03675343,0.011853421,0.0006255086,0.00006986012,0.00063990906,0.00017589673,0.009284182],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935033,0.0014994274,0.0012026998,0.00089708733,0.00046453427,0.0024329976],"domain_scores_gemma":[0.98361105,0.011265185,0.0006237016,0.0013228899,0.00043003232,0.00274714],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0066102943,0.0006816171,0.0011753718,0.0011287755,0.0007865823,0.00036370385,0.0016789695,0.00045623165,0.0027376832],"category_scores_gemma":[0.041788097,0.0006692175,0.00045436047,0.0027550452,0.00042826417,0.00079479016,0.0002467386,0.00087362615,0.0005327643],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058273847,0.00018844378,0.09514795,0.00326601,0.00021444836,0.007040863,0.02810101,0.00035541473,0.003274557,0.0010382977,0.11616421,0.7451505],"study_design_scores_gemma":[0.0010261212,0.00030116094,0.06747468,0.0122261485,0.000380242,0.0028896537,0.010339805,0.017771082,0.000092543305,0.0017161737,0.88463897,0.0011434216],"about_ca_topic_score_codex":0.24635199,"about_ca_topic_score_gemma":0.3276125,"teacher_disagreement_score":0.76847476,"about_ca_system_score_codex":0.002602944,"about_ca_system_score_gemma":0.0010410985,"threshold_uncertainty_score":0.9995759},"labels":[],"label_agreement":null},{"id":"W1972479177","doi":"10.1186/1756-0500-3-267","title":"Structural equation modeling in medical research: a primer","year":2010,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":481,"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":"Structural equation modeling; Latent variable; Computer science; Medical research; Set (abstract data type); Data science; Linear regression; Measure (data warehouse); Management science; Data mining; Machine learning; Medicine; Pathology","score_opus":0.9628487103961001,"score_gpt":0.6876974379363604,"score_spread":0.2751512724597397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972479177","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":[0.9794917,0.00016094002,0.0144453235,0.002381529,0.0004743832,0.00030642608,0.0000017585759,0.000033346525,0.0027045838],"genre_scores_gemma":[0.96445495,0.000017202618,0.03488374,0.000022642525,0.00040164034,0.000032058066,0.0000017063466,0.000012350783,0.0001737305],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98121107,0.005320048,0.00084256683,0.0008366094,0.010654356,0.0011353748],"domain_scores_gemma":[0.6549978,0.3397864,0.00012305402,0.0016053006,0.0028766897,0.0006107018],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14899805,0.00011119714,0.00027883117,0.0029106645,0.0005429237,0.00047815003,0.002058518,0.00026308396,0.0016375403],"category_scores_gemma":[0.8455004,0.00007455266,0.00007255365,0.0073754336,0.00050040375,0.00036041546,0.00087696867,0.00272547,0.0002893477],"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":[0.00014832245,0.00007211295,0.49954036,0.000017149252,0.000005489487,0.00003978914,0.0014148798,0.0015226546,0.005549739,0.007831268,0.0008583579,0.4829999],"study_design_scores_gemma":[0.0003036992,0.00005968836,0.044315383,0.000025056182,3.4706684e-7,0.000008331727,0.0007549883,0.73545045,0.0003169608,0.21836178,0.00031337867,0.00008993588],"about_ca_topic_score_codex":0.0021555636,"about_ca_topic_score_gemma":0.0020347543,"teacher_disagreement_score":0.7339278,"about_ca_system_score_codex":0.00007162593,"about_ca_system_score_gemma":0.0006739402,"threshold_uncertainty_score":0.99957526},"labels":[],"label_agreement":null},{"id":"W1972548285","doi":"10.1080/13803611.2013.767624","title":"Assessing statistical aspects of test fairness with structural equation modelling","year":2013,"lang":"en","type":"article","venue":"Educational Research and Evaluation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Structural equation modeling; Test (biology); Measurement invariance; Psychology; Confirmatory factor analysis; Set (abstract data type); Econometrics; Statistical hypothesis testing; Item response theory; Social psychology; Statistics; Psychometrics; Test validity; Interpretation (philosophy); Mathematics; Computer science; Developmental psychology","score_opus":0.8738377455316619,"score_gpt":0.6435779505699563,"score_spread":0.23025979496170568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972548285","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":[0.89039207,0.00013832876,0.10005519,0.0014508304,0.00010529354,0.00035368954,0.0000040160517,0.0000043694604,0.0074962038],"genre_scores_gemma":[0.9462619,0.0000045064203,0.053391933,0.000007885283,0.00011823028,0.00005482688,0.000024879342,0.0000048929887,0.00013098538],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949804,0.00072473165,0.0003956738,0.00034699214,0.0033135405,0.00023865105],"domain_scores_gemma":[0.9068164,0.08746363,0.00021473732,0.00027202076,0.005084917,0.00014828972],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01299373,0.00007252405,0.00013908232,0.0005194827,0.00028933623,0.0005325719,0.00020151008,0.00003988286,0.0019655253],"category_scores_gemma":[0.12122044,0.000048150192,0.000012441731,0.0013836469,0.0002156028,0.0008394137,0.000047546007,0.00016465067,0.00004205663],"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":[0.000051023795,0.00021890251,0.35368782,0.000043873915,0.00002585977,3.675041e-7,0.0010435138,0.020118948,0.0021868218,0.12551624,0.0022573606,0.49484926],"study_design_scores_gemma":[0.00010115971,0.000076186836,0.3260706,0.000012335596,0.0000021949184,0.0000021560893,0.0008300514,0.3031575,0.00005974195,0.3696504,0.0000063462176,0.000031319963],"about_ca_topic_score_codex":0.00027563592,"about_ca_topic_score_gemma":0.000008790206,"teacher_disagreement_score":0.49481794,"about_ca_system_score_codex":0.000078301535,"about_ca_system_score_gemma":0.0007182315,"threshold_uncertainty_score":0.9989468},"labels":[],"label_agreement":null},{"id":"W1972879012","doi":"10.1037/1040-3590.20.1.76","title":"Clarifying problems and offering solutions for correlated error when assessing the validity of selected-subtest short forms.","year":2008,"lang":"en","type":"article","venue":"Psychological Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Normative; Psychology; Short Forms; Variance (accounting); Test validity; Scale (ratio); Psychometrics; Correlation; Measure (data warehouse); Incremental validity; Criterion validity; Test (biology); Statistics; Clinical psychology; Construct validity; Mathematics; Computer science; Data mining; Epistemology","score_opus":0.7746325592886787,"score_gpt":0.5400842570110028,"score_spread":0.23454830227767587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972879012","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":[0.65915316,0.0001521116,0.33612517,0.00077441183,0.00038665772,0.0005629459,0.000010233873,0.000107824904,0.0027274776],"genre_scores_gemma":[0.9157235,0.000059759546,0.08382786,0.00014070777,0.000057480345,0.00010178903,0.0000053923823,0.000015185841,0.000068323745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99603516,0.0006404227,0.0010699144,0.00074147276,0.0008917984,0.00062126043],"domain_scores_gemma":[0.979417,0.018930856,0.00044418004,0.0005730258,0.000504971,0.00012993316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009278447,0.00023090381,0.00054524577,0.0002198575,0.0010536608,0.00018916147,0.0007363603,0.00021843227,0.0000673717],"category_scores_gemma":[0.016690748,0.00012469615,0.00016363128,0.0015351532,0.0003542427,0.0003016973,0.00029069209,0.00053542276,0.0000027686472],"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":[0.00002886312,0.00062575674,0.91220874,0.000030087196,0.00007162969,0.00000870271,0.0004839695,0.00052080204,0.0056673847,0.0021190853,0.0035484985,0.07468648],"study_design_scores_gemma":[0.00044794937,0.00043972937,0.95171684,0.000033529697,0.000029864283,0.000113176706,0.00038167337,0.015716095,0.00006208343,0.029320508,0.001539829,0.00019872483],"about_ca_topic_score_codex":0.000012801236,"about_ca_topic_score_gemma":0.0000039759684,"teacher_disagreement_score":0.25657034,"about_ca_system_score_codex":0.000057643956,"about_ca_system_score_gemma":0.000052955304,"threshold_uncertainty_score":0.9915921},"labels":[],"label_agreement":null},{"id":"W1975610341","doi":"10.5539/jedp.v3n1p88","title":"Construct Validity and Measurement Invariance of Computerized Adaptive Testing: Application to Measures of Academic Progress (MAP) Using Confirmatory Factor Analysis","year":2013,"lang":"en","type":"article","venue":"Journal of Educational and Developmental Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Factorial; Confirmatory factor analysis; Construct (python library); Measurement invariance; Construct validity; Set (abstract data type); Test (biology); Mathematics; Reading (process); Psychology; Computerized adaptive testing; Statistics; Mathematics education; Computer science; Psychometrics; Structural equation modeling; Linguistics","score_opus":0.6578066517400156,"score_gpt":0.487851707198968,"score_spread":0.16995494454104765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975610341","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":[0.9310579,0.00057859876,0.06693415,0.00082101097,0.00029453583,0.00019516244,0.0000070017904,0.0000019772149,0.000109678265],"genre_scores_gemma":[0.7384664,0.000011660557,0.26134893,0.0001272389,0.000036190526,0.0000035971202,4.5566185e-7,0.0000024725575,0.0000030699764],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975112,0.00028254656,0.0010764253,0.00025052932,0.00075100595,0.0001282938],"domain_scores_gemma":[0.9933448,0.0034463196,0.0013517003,0.000108786924,0.0015979371,0.0001504435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002734276,0.000111106434,0.00049748586,0.00061719836,0.00007666647,0.00002708801,0.00029712004,0.00007406524,0.00011737547],"category_scores_gemma":[0.0051645804,0.00008442867,0.000056644978,0.0010638128,0.00027891455,0.00016589333,0.00007364249,0.00014252661,0.0000028027364],"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":[0.000076167766,0.00008322636,0.9088017,0.000011334683,0.00017954803,2.3182238e-7,0.00057893666,0.000028686129,0.023074523,0.000121293444,0.00062312617,0.066421226],"study_design_scores_gemma":[0.0003716862,0.00011098559,0.9870826,0.000040634153,0.000041477426,0.000100842364,0.00056638557,0.0003846575,0.00039295724,0.010645329,0.00017365316,0.000088768335],"about_ca_topic_score_codex":0.000039476352,"about_ca_topic_score_gemma":0.000002132327,"teacher_disagreement_score":0.19441478,"about_ca_system_score_codex":0.000041227293,"about_ca_system_score_gemma":0.00028393703,"threshold_uncertainty_score":0.61828583},"labels":[],"label_agreement":null},{"id":"W1980472079","doi":"10.1136/bmj.c117","title":"Is a subgroup effect believable? Updating criteria to evaluate the credibility of subgroup analyses","year":2010,"lang":"en","type":"article","venue":"BMJ","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":812,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Subgroup analysis; Credibility; Psychology; Computer science; Information retrieval; Mathematics; Statistics; Political science","score_opus":0.5243444902286908,"score_gpt":0.5884504748589897,"score_spread":0.06410598463029893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980472079","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":[0.9839177,0.000077320874,0.003968733,0.0023948231,0.0014288737,0.0005750382,0.000021261421,0.000043604272,0.0075726258],"genre_scores_gemma":[0.96830326,0.0000016798012,0.030633822,0.0005131312,0.00030496548,0.000037123355,0.0000012829038,0.00001086592,0.00019389631],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941485,0.0018214509,0.0012019059,0.0007075477,0.0017161889,0.00040439842],"domain_scores_gemma":[0.92560357,0.07074651,0.0005233983,0.0022798958,0.0006732249,0.00017337892],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052109934,0.0001989426,0.0005820959,0.00038483588,0.00025854653,0.0002472036,0.0015330395,0.00010348045,0.001950391],"category_scores_gemma":[0.36807507,0.000103333754,0.00025760318,0.0034687947,0.00016447266,0.00017836796,0.00046344855,0.0003171815,0.00012819994],"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":[0.00019737196,0.000072858085,0.60270643,0.000029137385,0.000068167625,0.000005413349,0.0010325746,0.0000525382,0.19721107,0.00025063514,0.060770765,0.13760303],"study_design_scores_gemma":[0.00044054244,0.00036187354,0.950068,0.000029479486,0.00006166435,0.000019658748,0.00060444116,0.006016744,0.025821146,0.013042829,0.0032989294,0.0002346762],"about_ca_topic_score_codex":0.00037666236,"about_ca_topic_score_gemma":0.00007445804,"teacher_disagreement_score":0.34736156,"about_ca_system_score_codex":0.000014663917,"about_ca_system_score_gemma":0.00005704839,"threshold_uncertainty_score":0.998962},"labels":[],"label_agreement":null},{"id":"W1981221874","doi":"10.1177/0013164403261051","title":"A Note on How to Quantify and Report Whether Irt Parameter Invariance Holds: When Pearson Correlations are Not Enough","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":37,"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":"Item response theory; Measurement invariance; Pearson product-moment correlation coefficient; Mathematics; Econometrics; Statistics; Scale (ratio); Measure (data warehouse); Correlation; Psychology; Psychometrics; Confirmatory factor analysis; Computer science; Structural equation modeling; Data mining","score_opus":0.7338274295775041,"score_gpt":0.4936132193884701,"score_spread":0.24021421018903405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981221874","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":[0.7591046,0.00044197743,0.031444624,0.20198305,0.0019136121,0.00051117403,0.000016010981,0.00004126283,0.0045436737],"genre_scores_gemma":[0.9336081,0.0000206525,0.061132196,0.00398329,0.00026995066,0.00007005443,0.000002542926,0.000007836528,0.0009053679],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99652,0.0003189657,0.0004921851,0.0009272744,0.0014653844,0.00027620333],"domain_scores_gemma":[0.9934185,0.0050737695,0.00031844046,0.00050536444,0.00042337843,0.00026055632],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005228688,0.00019556766,0.00029579885,0.00023655636,0.00027606203,0.00028835365,0.00029976087,0.00012482589,0.00020892575],"category_scores_gemma":[0.06219046,0.00012873429,0.00006779595,0.00063767814,0.00011268815,0.00012692263,0.00006224519,0.0002604339,0.0000945006],"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":[0.0010608267,0.0055579618,0.4999641,0.000040886654,0.00017028327,0.000121386955,0.0075427745,0.0009446129,0.0056813676,0.06386925,0.12836342,0.28668314],"study_design_scores_gemma":[0.00036207755,0.00032594893,0.87117624,0.00006578492,0.00000814466,0.00009021415,0.00022254052,0.000010193642,0.000033514687,0.10506256,0.022458859,0.00018391528],"about_ca_topic_score_codex":0.000029003048,"about_ca_topic_score_gemma":0.000012742422,"teacher_disagreement_score":0.37121215,"about_ca_system_score_codex":0.00007410339,"about_ca_system_score_gemma":0.000056322573,"threshold_uncertainty_score":0.9457091},"labels":[],"label_agreement":null},{"id":"W1981904861","doi":"10.1016/j.jbusres.2012.08.001","title":"Formative vs. reflective measures: Facets of variation","year":2012,"lang":"en","type":"article","venue":"Journal of Business Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":77,"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 Manitoba; University of Alberta","funders":"","keywords":"Construct (python library); Formative assessment; Respondent; Variance (accounting); Context (archaeology); Causality (physics); Facet (psychology); Common-method variance; Psychology; Econometrics; Marketing; Social psychology; Business; Computer science; Mathematics; Accounting; Political science","score_opus":0.8054801729241423,"score_gpt":0.6042709151174749,"score_spread":0.20120925780666743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981904861","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":[0.7363838,0.0015948093,0.2407069,0.0015335687,0.0015932738,0.00021659919,0.000005644336,0.000007875346,0.017957527],"genre_scores_gemma":[0.9826468,0.00012662026,0.016743332,0.000017682265,0.0003155314,0.0000016767743,1.4157385e-7,0.0000061141313,0.00014207646],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99225074,0.0019631058,0.0010533772,0.0001250493,0.0041967733,0.00041092926],"domain_scores_gemma":[0.9501495,0.035729647,0.0011988205,0.0003314613,0.012422756,0.00016782308],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054064512,0.00008183403,0.00042473385,0.0021041906,0.00016505017,0.00010925782,0.0008100262,0.00008572365,0.00014868399],"category_scores_gemma":[0.3528887,0.00004927128,0.000099459096,0.0072643915,0.00013718533,0.001289537,0.00017126123,0.00049135904,0.00002055104],"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":[0.0021976964,0.0010560476,0.26914018,0.000107939355,0.00028307785,0.000018138746,0.028068785,0.0013259924,0.047484655,0.0032354915,0.028712414,0.6183696],"study_design_scores_gemma":[0.00047076607,0.00022054127,0.96489275,0.00007282611,0.000007397543,0.00006368344,0.0023329488,0.0001690007,0.002950676,0.02352247,0.005229112,0.000067823654],"about_ca_topic_score_codex":0.000040887586,"about_ca_topic_score_gemma":0.0000017710636,"teacher_disagreement_score":0.69575256,"about_ca_system_score_codex":0.00011492182,"about_ca_system_score_gemma":0.0002660417,"threshold_uncertainty_score":0.9740397},"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":"W1984776718","doi":"10.1108/jmp-01-2012-0016","title":"Candidates' integration of individual psychological assessment feedback","year":2014,"lang":"en","type":"article","venue":"Journal of Managerial Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Psychology; Credibility; Session (web analytics); Context (archaeology); Perception; Value (mathematics); Applied psychology; Originality; Process (computing); Social psychology; Computer science","score_opus":0.3839789922493162,"score_gpt":0.5349928325117121,"score_spread":0.15101384026239595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984776718","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":[0.739117,0.00008233144,0.21437147,0.0019199102,0.006590873,0.00011140282,0.000006097594,0.000013922188,0.037786983],"genre_scores_gemma":[0.92965555,0.00004610837,0.06867555,0.00073855225,0.0007396976,0.000001508932,0.0000016746452,0.000009284241,0.00013204534],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941466,0.0018574964,0.0019827478,0.00038934936,0.0013328021,0.00029103516],"domain_scores_gemma":[0.98829794,0.007967443,0.0024473397,0.0006113487,0.000533713,0.00014223994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020296026,0.00017478198,0.0008080155,0.0010606453,0.00007471632,0.00012770067,0.0016996753,0.00021393706,0.00075104856],"category_scores_gemma":[0.0320359,0.00011044901,0.0002688779,0.0013684381,0.0002388102,0.00023770917,0.00014331713,0.0004804548,0.000032781936],"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":[0.0006334853,0.0004218867,0.016659988,0.00000577469,0.00009973631,0.000026000695,0.00019610982,0.00008306621,0.009371986,0.0064122546,0.07593445,0.89015526],"study_design_scores_gemma":[0.0026197282,0.0027691154,0.829342,0.000033614753,0.000053858315,0.00028993518,0.00037133094,0.0001795978,0.00021964614,0.13705765,0.026871484,0.00019204161],"about_ca_topic_score_codex":0.000004616654,"about_ca_topic_score_gemma":0.0000028922452,"teacher_disagreement_score":0.8899632,"about_ca_system_score_codex":0.00002277936,"about_ca_system_score_gemma":0.000026733256,"threshold_uncertainty_score":0.9761177},"labels":[],"label_agreement":null},{"id":"W1985783056","doi":"10.1007/s11218-010-9130-2","title":"Attributional Retraining: reducing the likelihood of failure","year":2010,"lang":"en","type":"article","venue":"Social Psychology of Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Manitoba","funders":"","keywords":"Retraining; Attrition; Psychology; Attribution; Sociology of Education; Medical education; Restructuring; Intervention (counseling); Social psychology; Pedagogy; Political science; Medicine","score_opus":0.3453484145918746,"score_gpt":0.5326211729002635,"score_spread":0.18727275830838885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985783056","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":[0.9551929,0.00008173559,0.001671031,0.015434593,0.0047241286,0.000112530324,0.000009705546,0.000013058993,0.022760315],"genre_scores_gemma":[0.9870521,0.0000023333223,0.011838978,0.00027064528,0.00067818764,0.000007702538,0.0000051621873,0.000004919464,0.00013997029],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980331,0.0003687093,0.0006241383,0.0002918607,0.00049658504,0.00018558414],"domain_scores_gemma":[0.99257255,0.005572872,0.0007433512,0.00042047873,0.00065199455,0.000038773313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006688035,0.00007943239,0.00023114575,0.0002635957,0.00021671034,0.00001932871,0.0007097069,0.00019561977,0.00066820707],"category_scores_gemma":[0.04055025,0.0000542694,0.00012437954,0.0015930027,0.00049657474,0.00008273618,0.00004473009,0.00037590825,0.000013433975],"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":[0.000057730973,0.0003876983,0.07672137,0.0000076272754,0.0000395141,1.2961185e-7,0.0056083314,0.000001279861,0.06239571,0.030165028,0.2161431,0.60847247],"study_design_scores_gemma":[0.0001623013,0.000055575587,0.7742749,0.0000061622954,0.000010122365,0.00000943827,0.0040070512,0.000008734596,0.0006256749,0.21021472,0.010559389,0.000065977765],"about_ca_topic_score_codex":0.00003418629,"about_ca_topic_score_gemma":0.000012546561,"teacher_disagreement_score":0.6975535,"about_ca_system_score_codex":0.000008894117,"about_ca_system_score_gemma":0.00026929998,"threshold_uncertainty_score":0.9675316},"labels":[],"label_agreement":null},{"id":"W1986481484","doi":"10.1007/s11136-014-0699-3","title":"Minimal evidence of response shift in the absence of a catalyst","year":2014,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Trinity Western University; Western University; Centre Hospitalier de l’Université de Montréal; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Item response theory; Public health; Mental health; Structural equation modeling; Cohort; Gerontology; Demography; Psychometrics; Psychology; Clinical psychology; Psychiatry; Statistics; Internal medicine","score_opus":0.9087597228231656,"score_gpt":0.6625896706127817,"score_spread":0.2461700522103839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986481484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.99385065,0.0005998799,0.0013976374,0.002919648,0.000043650485,0.00017062605,0.000007233544,0.000003457031,0.0010072088],"genre_scores_gemma":[0.9967611,0.000024801273,0.0030888624,0.00003606699,0.000026427813,0.0000061914325,1.5346572e-7,0.0000029768648,0.000053460324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95865786,0.032168165,0.0021770298,0.00050632673,0.0060423086,0.00044833188],"domain_scores_gemma":[0.25056154,0.74526685,0.0008761243,0.0019515902,0.001225542,0.00011834138],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33286098,0.00007362179,0.0005334424,0.0009159183,0.00006927851,0.000037241283,0.0025107272,0.00007366038,0.00007180742],"category_scores_gemma":[0.8467833,0.00004379502,0.00011658124,0.0050327857,0.0009337752,0.00014673367,0.0003514286,0.00032941246,0.000014016416],"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":[0.0038677927,0.0002641481,0.92981815,0.00027520358,0.000012482563,0.0000022338584,0.009696234,0.0000333592,0.02242147,0.006088604,0.0014650696,0.026055228],"study_design_scores_gemma":[0.00020513155,0.00039231856,0.97410303,0.00014101832,7.2943584e-7,6.1540544e-7,0.0052612857,0.00019154554,0.0011827073,0.018265538,0.000208333,0.000047747748],"about_ca_topic_score_codex":0.0024004108,"about_ca_topic_score_gemma":0.000109433095,"teacher_disagreement_score":0.7130987,"about_ca_system_score_codex":0.00001567993,"about_ca_system_score_gemma":0.0003029158,"threshold_uncertainty_score":0.68696004},"labels":[],"label_agreement":null},{"id":"W1987045971","doi":"10.1177/0829573510375549","title":"A Review of Psychometric Assessment and Reporting Practices: An Examination of Measurement-Oriented Versus Non-Measurement-Oriented Domains","year":2010,"lang":"en","type":"review","venue":"Canadian Journal of School Psychology","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":"Simon Fraser University","funders":"","keywords":"Psychology; Publishing; Reliability (semiconductor); Test (biology); Psychometrics; Applied psychology; Set (abstract data type); Test validity; Section (typography); Clinical psychology; Medical education; Medicine; Computer science; Political science","score_opus":0.7752840788832364,"score_gpt":0.5887653230023913,"score_spread":0.1865187558808451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987045971","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018983376,0.98211825,0.0046576476,0.00016602346,0.0062371898,0.0009889957,0.00003545159,0.000008322031,0.0038897933],"genre_scores_gemma":[0.0026246288,0.9735474,0.02319259,0.00016118061,0.0003738308,0.000024154457,0.000010370849,0.000053608997,0.000012210957],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97974944,0.004181262,0.01050746,0.0011182317,0.0036362396,0.0008073562],"domain_scores_gemma":[0.8812537,0.008036935,0.093307674,0.0025634172,0.012561228,0.0022770031],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10995962,0.00061215763,0.0045950785,0.007450828,0.00021343096,0.00012534979,0.0018229462,0.00068475615,0.0003874647],"category_scores_gemma":[0.54742014,0.00046004413,0.00079055666,0.009226077,0.00039058132,0.0006798778,0.00007349028,0.0022011779,0.0000064324695],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003817946,0.00013857544,0.0033932237,0.0054558474,0.00031945945,0.000058977646,0.000053141594,1.8819838e-7,0.000023828266,0.00006351721,0.002872353,0.9875827],"study_design_scores_gemma":[0.0020275558,0.002071362,0.04184438,0.04660989,0.0013603144,0.00086487376,0.00047819255,0.0000039295137,0.0000014071962,0.000239977,0.9039785,0.00051959674],"about_ca_topic_score_codex":0.00036581844,"about_ca_topic_score_gemma":0.0013179494,"teacher_disagreement_score":0.9870631,"about_ca_system_score_codex":0.0006959929,"about_ca_system_score_gemma":0.0065640323,"threshold_uncertainty_score":0.9997851},"labels":[],"label_agreement":null},{"id":"W198752860","doi":"","title":"The recovery of the density scale using a stochastic quasi-realization of additive conjoint measurement.","year":2003,"lang":"en","type":"article","venue":"PubMed","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"University of Victoria","funders":"","keywords":"Rasch model; Realization (probability); Scale (ratio); Sample (material); Set (abstract data type); Ordinal Scale; Item response theory; Statistics; Computer science; Mathematics; Econometrics; Psychometrics","score_opus":0.45685447972225335,"score_gpt":0.37306324933524465,"score_spread":0.0837912303870087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W198752860","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":[0.5347005,0.0004319451,0.45838022,0.000093072296,0.0013550834,0.0007731284,0.000018838546,0.000012505212,0.0042347023],"genre_scores_gemma":[0.99885035,0.000007709143,0.0009908013,0.000029873167,0.000019891191,0.000022512084,1.5221802e-7,0.0000042562924,0.00007446438],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996672,0.0011314931,0.0005516752,0.00020616941,0.0012207177,0.00021798215],"domain_scores_gemma":[0.98552823,0.012207772,0.00080351485,0.0005209572,0.00089191453,0.000047586484],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014388085,0.000074246214,0.00021733319,0.000115115676,0.00020019118,0.00004474483,0.000382141,0.00003982214,0.000015124996],"category_scores_gemma":[0.23293155,0.00003708471,0.00013767813,0.001530481,0.00019191176,0.00007837922,0.000073947565,0.00007383795,7.3413713e-7],"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":[0.00012985128,0.00013025386,0.07920831,0.000013012755,0.00011800285,4.965366e-7,0.00044556678,0.004350026,0.00073945796,0.005385264,0.0018653031,0.90761447],"study_design_scores_gemma":[0.00035098108,0.00003342306,0.9284553,0.000030993793,0.000047318692,0.000008762202,0.0013291119,0.001651509,0.004994727,0.062437043,0.00055240665,0.000108434324],"about_ca_topic_score_codex":0.00007124491,"about_ca_topic_score_gemma":0.000050797953,"teacher_disagreement_score":0.90750605,"about_ca_system_score_codex":0.00006179946,"about_ca_system_score_gemma":0.00007291409,"threshold_uncertainty_score":0.77352977},"labels":[],"label_agreement":null},{"id":"W1989941651","doi":"10.1080/14999013.2011.629716","title":"When “Good Enough” Is Just Not Good Enough: Response to Holden and Marjanovic","year":2011,"lang":"en","type":"article","venue":"International Journal of Forensic Mental Health","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":"Simon Fraser University","funders":"","keywords":"Test (biology); Psychology; Construct (python library); Mental health; Applied psychology; Psychotherapist; Computer science","score_opus":0.47220788794984536,"score_gpt":0.48855622715262587,"score_spread":0.016348339202780504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989941651","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":[0.9349647,0.00056732155,0.0032673394,0.0523647,0.004588399,0.00024486438,0.00011609558,0.000017292568,0.0038692513],"genre_scores_gemma":[0.911409,0.00013977393,0.07942459,0.007070869,0.00036661315,0.000002001181,0.000001820939,0.000015112872,0.0015701732],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995073,0.0005881341,0.0014074517,0.00036523954,0.0022109388,0.00035519653],"domain_scores_gemma":[0.9936905,0.0037266538,0.0011698795,0.00028677372,0.00067421765,0.0004519996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01000843,0.00018162288,0.0004591362,0.0010497223,0.00016027743,0.00016128457,0.0011265291,0.000065728535,0.0006574731],"category_scores_gemma":[0.007253619,0.00013275149,0.0001508098,0.00048622218,0.00009850944,0.0003803355,0.0003024224,0.00027389775,0.00006555952],"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":[0.0062490236,0.00037109831,0.03492976,0.000015086594,0.00024295559,0.00018748478,0.026841186,0.000004357222,0.0013226197,0.0034055829,0.10540381,0.82102704],"study_design_scores_gemma":[0.0059661884,0.006832761,0.64723843,0.00063442293,0.00003720671,0.0043835547,0.014258564,0.00020771127,0.0083640395,0.04809584,0.26328388,0.0006974091],"about_ca_topic_score_codex":0.00022404602,"about_ca_topic_score_gemma":0.000032183758,"teacher_disagreement_score":0.8203296,"about_ca_system_score_codex":0.00025992462,"about_ca_system_score_gemma":0.0002643103,"threshold_uncertainty_score":0.86837834},"labels":[],"label_agreement":null},{"id":"W1990922528","doi":"10.1007/s11136-013-0419-4","title":"Development of a paper-and-pencil semi-adaptive questionnaire for 5 domains of health-related quality of life (PAT-5D-QOL)","year":2013,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Richmond Hospital; Toronto Rehabilitation Institute; University Health Network; University of Toronto; McGill University; Arthritis Research Centre of Canada; Public Health Ontario; University of British Columbia","funders":"","keywords":"Computerized adaptive testing; Quality of life (healthcare); Item response theory; Feeling; Ceiling effect; Psychology; Applied psychology; Pencil (optics); Item bank; Population; Psychometrics; Physical therapy; Clinical psychology; Medicine; Social psychology; Engineering; Environmental health; Alternative medicine; Pathology","score_opus":0.8634166684743088,"score_gpt":0.5913843357512336,"score_spread":0.27203233272307514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990922528","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":[0.97817516,0.0021450336,0.015730914,0.0020922176,0.00010492401,0.0010490927,0.000062829924,0.000018702394,0.0006211012],"genre_scores_gemma":[0.925265,0.00009222968,0.07437048,0.000051004474,0.000021241884,0.000059120353,0.0000038009393,0.000011507512,0.00012562308],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9795977,0.008981233,0.005770804,0.0006906917,0.0043200427,0.0006395594],"domain_scores_gemma":[0.8212329,0.16065449,0.005971945,0.0019188083,0.009397786,0.0008240541],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13942942,0.00019125342,0.0017249592,0.0008210428,0.00028191647,0.00003460524,0.0010368775,0.00021666594,0.0002032198],"category_scores_gemma":[0.39559844,0.00014539433,0.0002257289,0.002767643,0.0009838415,0.00025516137,0.000478201,0.00036658545,0.0000092455575],"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":[0.0016717036,0.0015397806,0.4977235,0.00342793,0.00047499654,4.035226e-7,0.025422258,0.000064356966,0.023414392,0.041893825,0.0044879136,0.39987895],"study_design_scores_gemma":[0.0013990849,0.0004986839,0.9232363,0.00032541653,0.000003714623,5.123742e-7,0.017506268,0.0003200736,0.0013844473,0.054906387,0.000233678,0.00018545116],"about_ca_topic_score_codex":0.011439917,"about_ca_topic_score_gemma":0.0003377717,"teacher_disagreement_score":0.4255128,"about_ca_system_score_codex":0.00011246964,"about_ca_system_score_gemma":0.0021532762,"threshold_uncertainty_score":0.995143},"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":"W1992935042","doi":"10.1016/j.respe.2013.12.042","title":"Utilisation des modèles issus de la théorie de réponse à l’item pour la détermination de la différence minimale cliniquement pertinente d’un questionnaire","year":2014,"lang":"fr","type":"article","venue":"Revue d Épidémiologie et de Santé Publique","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Intramolecular force; Isomerization; Chemistry; Physics; Humanities; Physical chemistry; Stereochemistry; Philosophy","score_opus":0.1228182640854009,"score_gpt":0.4394273704078504,"score_spread":0.3166091063224495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992935042","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":[0.5880898,0.0025571596,0.39362666,0.0068787173,0.00045094793,0.0002800277,0.000025646792,0.00021749143,0.007873537],"genre_scores_gemma":[0.77087176,0.0044091847,0.22169541,0.0011705577,0.0005182382,0.0001347866,0.000012695609,0.00004346005,0.0011439273],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9581659,0.037370466,0.0014530075,0.0011457218,0.00050264964,0.0013622496],"domain_scores_gemma":[0.8259843,0.17034385,0.0013081076,0.0010638788,0.000734542,0.0005653227],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07709999,0.00055969605,0.00082524057,0.00072338193,0.00046566073,0.0008822422,0.0014099543,0.0012252554,0.00014860196],"category_scores_gemma":[0.4627102,0.00050682423,0.0003698255,0.0014182283,0.0011218115,0.0007843473,0.00041828185,0.0012022058,0.000024173945],"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":[0.00013386352,0.00034975522,0.55123645,0.0001797831,0.000038467137,0.00010224619,0.0018711631,0.0010663022,0.0022868288,0.033122182,0.0012494716,0.40836346],"study_design_scores_gemma":[0.0005712401,0.0002763419,0.64296657,0.00069159374,0.000057135956,0.00071375543,0.0010201422,0.09294658,0.0011012823,0.25198868,0.00724048,0.00042618325],"about_ca_topic_score_codex":0.000407024,"about_ca_topic_score_gemma":0.000025906078,"teacher_disagreement_score":0.4079373,"about_ca_system_score_codex":0.00092239643,"about_ca_system_score_gemma":0.0018530077,"threshold_uncertainty_score":0.99973834},"labels":[],"label_agreement":null},{"id":"W1993702262","doi":"10.1007/s11136-011-9976-6","title":"Latent variable mixture models: a promising approach for the validation of patient reported outcomes","year":2011,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Arthritis Research Centre of Canada; University of British Columbia; Western University; Trinity Western University","funders":"","keywords":"Latent variable; Latent variable model; Sample (material); Homogeneous; Structural equation modeling; Latent class model; Psychology; Quality of Life Research; Econometrics; Homogeneity (statistics); Item response theory; Statistics; Population; Differential item functioning; Psychometrics; Variable (mathematics); Public health; Clinical psychology; Mathematics; Medicine; Environmental health","score_opus":0.9318021550325525,"score_gpt":0.5885913077670051,"score_spread":0.3432108472655474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993702262","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":[0.5655606,0.00028265978,0.42671424,0.00031907338,0.0001295845,0.0010100793,0.000017098575,0.000017514298,0.0059491745],"genre_scores_gemma":[0.8154925,0.000008391914,0.18420461,0.000020490643,0.000019524134,0.000052176074,0.0000027308017,0.000006963742,0.00019259278],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923321,0.0025566004,0.0016361269,0.00043795598,0.0026935656,0.00034363082],"domain_scores_gemma":[0.913474,0.08060059,0.0013217254,0.0014765272,0.0029957618,0.00013139646],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.074692756,0.00009556526,0.00049683795,0.00039892926,0.00022157987,0.00005960925,0.00085909327,0.00010434097,0.000057486603],"category_scores_gemma":[0.28687748,0.00005097297,0.00016885075,0.0020086362,0.00022531554,0.0001693917,0.00025203577,0.00023417047,8.554018e-7],"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":[0.0019600347,0.002282442,0.7781249,0.00075996364,0.00069668854,0.0000013859321,0.024748882,0.008326347,0.0042074844,0.06874125,0.005856473,0.10429415],"study_design_scores_gemma":[0.0016511101,0.0007675001,0.21217133,0.00007890594,0.000043335458,0.0000035709947,0.018788664,0.08069712,0.010327003,0.67462164,0.00051117485,0.00033864132],"about_ca_topic_score_codex":0.0011139546,"about_ca_topic_score_gemma":0.0000011786034,"teacher_disagreement_score":0.6058804,"about_ca_system_score_codex":0.000024512876,"about_ca_system_score_gemma":0.00020947089,"threshold_uncertainty_score":0.95279855},"labels":[],"label_agreement":null},{"id":"W1994036224","doi":"10.1177/1073191110381717","title":"Augmenting the Core Battery With Supplementary Subtests: Wechsler Adult Intelligence Scale—IV Measurement Invariance Across the United States and Canada","year":2010,"lang":"en","type":"article","venue":"Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"American Psychological Association; American Educational Research Association","keywords":"Psychology; Generalizability theory; Wechsler Adult Intelligence Scale; Measurement invariance; Discriminant validity; Developmental psychology; Test (biology); Set (abstract data type); Clinical psychology; Wechsler Preschool and Primary Scale of Intelligence; Test validity; Convergent validity; Psychometrics; Confirmatory factor analysis; Wechsler Intelligence Scale for Children; Statistics; Cognition; Internal consistency; Structural equation modeling; Psychiatry","score_opus":0.25792246397426,"score_gpt":0.42913006700525325,"score_spread":0.17120760303099325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994036224","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":[0.9688764,0.00004777581,0.017987214,0.011451759,0.0008011808,0.00044374648,0.00007210223,0.00002077341,0.00029900286],"genre_scores_gemma":[0.9834657,0.000053617518,0.012895829,0.0033126075,0.00008504305,0.000063610045,0.000016470845,0.000013860002,0.00009331225],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99543625,0.0004046482,0.0006640383,0.00057615264,0.0023575295,0.000561375],"domain_scores_gemma":[0.9854895,0.012208079,0.00046503378,0.0009084782,0.0007965193,0.00013240048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010618599,0.00023584916,0.00025212616,0.00009111317,0.00088728697,0.0005798973,0.0012203893,0.000041455893,0.00030438032],"category_scores_gemma":[0.004803744,0.00010618702,0.000035117824,0.0013343226,0.00030753147,0.00014207073,0.00043624954,0.0005788246,0.000002526971],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002605279,0.000048021,0.95039487,0.000010110112,0.00007042017,0.000013885466,0.00083390845,0.00043151746,0.00058436504,0.0005898174,0.013487829,0.033509217],"study_design_scores_gemma":[0.0005065205,0.00017286513,0.90986186,0.00008780601,0.0000448975,0.00005833815,0.040087897,0.012737622,0.0011839074,0.006452706,0.02839037,0.0004152299],"about_ca_topic_score_codex":0.38645145,"about_ca_topic_score_gemma":0.7574483,"teacher_disagreement_score":0.37099683,"about_ca_system_score_codex":0.00013377493,"about_ca_system_score_gemma":0.00035171988,"threshold_uncertainty_score":0.6824384},"labels":[],"label_agreement":null},{"id":"W1995348618","doi":"10.1080/00220970109599488","title":"Minimizing the Influence of Item Parameter Estimation Errors in Test Development: A Comparison of Three Selection Procedures","year":2001,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Psychometric Methodologies and Testing","field":"Decision 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 Alberta","funders":"","keywords":"Item response theory; Selection (genetic algorithm); Statistics; Computerized adaptive testing; Function (biology); Test (biology); Range (aeronautics); Estimation; Mathematics; Equating; Estimation theory; Computer science; Artificial intelligence; Psychometrics; Rasch model; Engineering","score_opus":0.2827474909716795,"score_gpt":0.48930927761949283,"score_spread":0.20656178664781333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995348618","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":[0.99648887,0.0010776907,0.001743522,0.00019964899,0.00019211929,0.00015529923,1.6180694e-7,0.0000027445308,0.00013996019],"genre_scores_gemma":[0.9768209,0.000010591028,0.023083154,0.000033503267,0.000028074946,0.0000055499704,2.3433475e-7,0.0000039627357,0.000014016899],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997765,0.00025510663,0.001138072,0.00009294821,0.00064067513,0.000108188215],"domain_scores_gemma":[0.98644376,0.011389312,0.0016372169,0.00015592005,0.00034539725,0.000028367065],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037550423,0.00008281849,0.00023061842,0.0003852775,0.00011055619,0.00003181079,0.00048051425,0.00003482449,0.000022317367],"category_scores_gemma":[0.03782456,0.000043532844,0.000044003307,0.0014630718,0.00009711525,0.00030985213,0.000038738242,0.0001457854,0.0000013370984],"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":[0.00017700852,0.00068235747,0.8139916,0.0000106313655,0.00001560509,1.3161295e-7,0.020562716,0.013386183,0.09219782,0.000046707548,0.00024683127,0.05868241],"study_design_scores_gemma":[0.00020077139,0.0002210539,0.8806845,0.00015386356,0.000010396069,0.000063736035,0.022423884,0.004833436,0.08958915,0.0017120576,0.000048380487,0.00005876478],"about_ca_topic_score_codex":0.00008778492,"about_ca_topic_score_gemma":0.00003300706,"teacher_disagreement_score":0.06669291,"about_ca_system_score_codex":0.000079580284,"about_ca_system_score_gemma":0.00031732794,"threshold_uncertainty_score":0.97028023},"labels":[],"label_agreement":null},{"id":"W1995508717","doi":"10.1037/1082-989x.6.3.258","title":"Testing parameters in structural equation modeling: Every \"one\" matters.","year":2001,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":152,"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; Identification (biology); Standard error; Statistical model; Statistics; Set (abstract data type); Statistical hypothesis testing; Mathematics; Invariant (physics); Econometrics; Likelihood-ratio test; Scale (ratio); Applied mathematics; Computer science; Physics","score_opus":0.8579973400321181,"score_gpt":0.6038590198508541,"score_spread":0.25413832018126403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995508717","genre_codex":"empirical","genre_gemma":"methods","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":[0.5084123,0.00012180033,0.48437968,0.0011194292,0.0006797996,0.00015245266,9.662311e-7,0.00009172027,0.0050418647],"genre_scores_gemma":[0.43951422,0.000007896851,0.55903125,0.0013050131,0.00006788973,0.000016939623,8.6682786e-7,0.000009510721,0.00004641654],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99153066,0.004141248,0.0014255969,0.001205868,0.0009830421,0.00071357394],"domain_scores_gemma":[0.94016427,0.058072023,0.0004330042,0.00089727726,0.00023417712,0.00019927244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021676723,0.00027952713,0.0006644564,0.00082453404,0.00016015391,0.00026304123,0.0011775229,0.0002628037,0.0003658529],"category_scores_gemma":[0.207381,0.0001954142,0.00016612916,0.0052808733,0.00012607974,0.00033510942,0.00020783723,0.0005720123,0.00007996628],"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":[0.000090252644,0.000074251286,0.11348211,0.0000025004206,0.000008132305,0.000024096471,0.000120997014,0.014303021,0.001891585,0.0003249657,0.0001356508,0.8695424],"study_design_scores_gemma":[0.0004569567,0.0001744599,0.24195577,0.000021205109,0.0000072069306,0.00006641295,0.00028170637,0.37058863,0.000049574224,0.38587466,0.0002359724,0.0002874693],"about_ca_topic_score_codex":0.00008028478,"about_ca_topic_score_gemma":0.0000018992379,"teacher_disagreement_score":0.86925495,"about_ca_system_score_codex":0.000066822766,"about_ca_system_score_gemma":0.000012266654,"threshold_uncertainty_score":0.79929554},"labels":[],"label_agreement":null},{"id":"W1995835325","doi":"10.1016/s0895-4356(03)00179-3","title":"Rasch analysis of the western ontariomcmaster (WOMAC) osteoarthritis index: results from community and arthroplasty samples","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Arthritis Research Centre of Canada; Hospital for Sick Children; University of British Columbia; St. Michael's Hospital; Institute for Work & Health; SickKids Foundation; University Health Network; University of Toronto; Sunnybrook Health Science Centre; Toronto Rehabilitation Institute","funders":"","keywords":"Rasch model; WOMAC; Differential item functioning; Physical therapy; Osteoarthritis; Medicine; Psychometrics; Physical medicine and rehabilitation; Statistics; Item response theory; Clinical psychology; Mathematics","score_opus":0.7731182734792174,"score_gpt":0.5772165807063969,"score_spread":0.19590169277282043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995835325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.97960085,0.00065405725,0.015438746,0.0019436659,0.00160082,0.00006621442,0.000063461026,0.000003810893,0.0006283549],"genre_scores_gemma":[0.97912407,0.00026890048,0.018877678,0.0014919185,0.00013117967,5.4723347e-7,0.0000015785624,0.000005272017,0.00009886811],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94436496,0.04577375,0.008522321,0.00037434942,0.0006503774,0.00031421892],"domain_scores_gemma":[0.3104348,0.6782411,0.009189343,0.0012033051,0.00065478263,0.00027667978],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14520681,0.00017030936,0.0033996317,0.00047659647,0.00018608688,0.00003280949,0.00096691964,0.00034072934,0.00014793359],"category_scores_gemma":[0.8349911,0.00008821024,0.0010543264,0.0017452056,0.0008312055,0.0001453371,0.00030498518,0.0016513608,0.0000031821678],"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":[0.0002793502,0.00007568577,0.9116936,0.0000010525706,0.00034714205,0.0000034831316,0.00017460885,0.0003704074,0.0000042624933,0.00010671004,0.00072464166,0.08621906],"study_design_scores_gemma":[0.0016413402,0.0004653557,0.95027214,0.00003630191,0.00023422118,0.000030547497,0.00042666274,0.0001804094,0.0000048707034,0.034827467,0.01180241,0.00007825053],"about_ca_topic_score_codex":0.0012612035,"about_ca_topic_score_gemma":0.003243341,"teacher_disagreement_score":0.6897843,"about_ca_system_score_codex":0.00001514259,"about_ca_system_score_gemma":0.00015034428,"threshold_uncertainty_score":0.8801895},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W1999352987","doi":"10.1186/1471-2288-14-124","title":"Shame for disrespecting evidence: the personal consequences of insufficient respect for structural equation model testing","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"University of Alberta","funders":"","keywords":"Shame; Structural equation modeling; Psychology; MEDLINE; Social psychology; Statistics; Mathematics; Political science","score_opus":0.9656740959597252,"score_gpt":0.6924039766608265,"score_spread":0.27327011929889866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999352987","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.31263816,0.00050778105,0.68298703,0.002406166,0.0004177199,0.00071245973,0.000012544228,0.00002577847,0.00029231378],"genre_scores_gemma":[0.492082,0.000014171218,0.5071292,0.00014016808,0.00036361805,0.00015196469,0.0000012692985,0.000011242488,0.00010640894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9661232,0.024330387,0.0017362717,0.001149969,0.005475449,0.001184724],"domain_scores_gemma":[0.0379243,0.95708275,0.0007434763,0.0007381367,0.0031686786,0.0003426802],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34386772,0.00019466222,0.00079545233,0.0007969818,0.00092224526,0.00015178764,0.002326498,0.00027593202,0.0001374691],"category_scores_gemma":[0.98757493,0.00010649357,0.0002704137,0.0027444635,0.0022384017,0.00015955494,0.0005324286,0.0007292161,0.0000041665376],"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":[0.0019671535,0.0000759493,0.055076808,0.00031835938,0.000054597196,0.0000024531964,0.0044142003,0.007580233,0.0182183,0.11398549,0.0029522695,0.7953542],"study_design_scores_gemma":[0.0004015865,0.00064063363,0.0033068038,0.000114978306,0.000008993927,0.0000174275,0.0021710743,0.6739253,0.0007717029,0.3182881,0.0002629075,0.00009056445],"about_ca_topic_score_codex":0.00018688617,"about_ca_topic_score_gemma":0.00011394121,"teacher_disagreement_score":0.9327523,"about_ca_system_score_codex":0.00009650272,"about_ca_system_score_gemma":0.001730105,"threshold_uncertainty_score":0.82474846},"labels":[],"label_agreement":null},{"id":"W1999387197","doi":"10.1007/s11336-014-9428-7","title":"Maximum Marginal Likelihood Estimation of a Monotonic Polynomial Generalized Partial Credit Model with Applications to Multiple Group Analysis","year":2014,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":35,"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 on Drug Abuse; Social Sciences and Humanities Research Council of Canada; Institute of Education Sciences","keywords":"Polytomous Rasch model; Parametric statistics; Monotonic function; Mathematics; Polynomial; Item response theory; Applied mathematics; Parametric model; Statistics; Estimation theory; Econometrics; Mathematical optimization; Computer science; Psychometrics","score_opus":0.15904771737115542,"score_gpt":0.4020432666111692,"score_spread":0.24299554924001376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999387197","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":[0.2824762,0.00008193731,0.71548027,0.00036968658,0.00015764037,0.00044377267,0.0000416718,0.000063836174,0.00088502205],"genre_scores_gemma":[0.6215081,0.000006225133,0.3779562,0.00010893054,0.00012846915,0.00016760922,0.000013530051,0.000015150065,0.00009574783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99538845,0.0003675954,0.0011464267,0.001001562,0.0015550735,0.0005408865],"domain_scores_gemma":[0.98784596,0.0092456825,0.00071511796,0.0014270603,0.00040148036,0.00036468095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005163725,0.00027849816,0.00084844505,0.0043995734,0.00019931582,0.00019565481,0.0011390401,0.0001306795,0.00013516317],"category_scores_gemma":[0.017951872,0.00020803191,0.00031458054,0.020350311,0.00009676615,0.00023194433,0.00012821628,0.00018050123,0.00007112105],"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":[0.0007560282,0.000444166,0.11893551,0.000014384126,0.00037831452,6.132742e-7,0.00020036766,0.2757103,0.0013517552,0.0008804166,0.0044959746,0.59683216],"study_design_scores_gemma":[0.0017858447,0.00040168504,0.094125845,0.000009328225,0.00027036964,0.0000031902832,0.000084280866,0.8886725,0.00038093858,0.0072249165,0.006693297,0.00034782002],"about_ca_topic_score_codex":0.00014304546,"about_ca_topic_score_gemma":0.00006764436,"teacher_disagreement_score":0.6129622,"about_ca_system_score_codex":0.00005670532,"about_ca_system_score_gemma":0.00005503861,"threshold_uncertainty_score":0.9903203},"labels":[],"label_agreement":null},{"id":"W2000227873","doi":"10.1037/a0020462","title":"Reporting results of latent growth modeling and multilevel modeling analyses: Some recommendations for rehabilitation psychology.","year":2010,"lang":"en","type":"article","venue":"Rehabilitation Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":69,"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 Windsor","funders":"","keywords":"Multilevel model; Latent growth modeling; Popularity; Context (archaeology); Hierarchical database model; Psychology; Computer science; Data science; Applied psychology; Data mining; Social psychology; Developmental psychology; Machine learning","score_opus":0.6260552177537491,"score_gpt":0.5939393468014195,"score_spread":0.032115870952329595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000227873","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":[0.629744,0.00008637055,0.35208458,0.0156194,0.0013908164,0.00060632627,0.000052911786,0.00007117754,0.00034441648],"genre_scores_gemma":[0.5830951,0.000022989527,0.4163748,0.00027232512,0.00008645496,0.000087226384,0.000022876504,0.000017969202,0.00002030121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991048,0.0009277679,0.00543202,0.001527244,0.0005977924,0.00046719122],"domain_scores_gemma":[0.94513375,0.048168134,0.0032130773,0.0013069621,0.0020092137,0.00016889037],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026756192,0.00027664646,0.0008508288,0.0016374704,0.00030609604,0.00007469173,0.00054297573,0.0003806228,0.000036177553],"category_scores_gemma":[0.4625625,0.00023554664,0.00032959288,0.0013251592,0.00030527156,0.00059300364,0.00010105725,0.00046934834,0.00000681087],"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":[0.0028511279,0.0018028554,0.12896004,0.00033349846,0.00029377523,0.0000036442327,0.014560159,0.05649415,0.116383724,0.037507977,0.014898853,0.62591016],"study_design_scores_gemma":[0.0021222914,0.0007695261,0.03298654,0.000043573466,0.000034917,0.000018099434,0.0010565482,0.5105607,0.000039825303,0.4516148,0.0004993732,0.0002538386],"about_ca_topic_score_codex":0.000103955994,"about_ca_topic_score_gemma":0.000025510233,"teacher_disagreement_score":0.62565637,"about_ca_system_score_codex":0.000029884586,"about_ca_system_score_gemma":0.000058636044,"threshold_uncertainty_score":0.96053135},"labels":[],"label_agreement":null},{"id":"W2004471759","doi":"10.7202/1024862ar","title":"Analyse des différentes facettes influant sur la fidélité de l’épreuve d’expression écrite d’un test de français langue étrangère","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Art","score_opus":0.25846524064712445,"score_gpt":0.4527758650486191,"score_spread":0.19431062440149466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004471759","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":[0.8275726,0.0031659824,0.15817666,0.0065609557,0.001021001,0.00032982914,0.000051427553,0.000119462566,0.003002106],"genre_scores_gemma":[0.922462,0.0005670044,0.07354683,0.00055885856,0.00038436113,0.00005855875,0.00007412169,0.00004082909,0.0023074243],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97817963,0.017906416,0.0010638735,0.0008185881,0.0013504983,0.00068096694],"domain_scores_gemma":[0.8881526,0.10882564,0.0007484523,0.0009359641,0.0010456025,0.00029176567],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07018414,0.00040206924,0.0005440397,0.00074219104,0.00046126475,0.00053299975,0.0007494644,0.0005446954,0.0011559153],"category_scores_gemma":[0.31256786,0.00034749188,0.0002462605,0.002179539,0.00021541999,0.00088475033,0.00013637249,0.0006561683,0.00015878184],"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":[0.00001910928,0.00035211557,0.5319726,0.00007646709,0.000040492123,0.0000024657836,0.07399828,0.0024486799,0.025086744,0.00022003103,0.0056560864,0.3601269],"study_design_scores_gemma":[0.0007069566,0.00013337661,0.9163865,0.0003772685,0.00015306124,0.000033393666,0.0033728124,0.044207633,0.008892976,0.015433714,0.009931381,0.00037091647],"about_ca_topic_score_codex":0.00170628,"about_ca_topic_score_gemma":0.00043761224,"teacher_disagreement_score":0.3844139,"about_ca_system_score_codex":0.0002925783,"about_ca_system_score_gemma":0.0006145205,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W2004501768","doi":"10.1177/0013164402239317","title":"Differential Item Functioning Results May Change Depending On How An Item Is Scored: An Illustration With The Center For Epidemiologic Studies Depression Scale","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":97,"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; Item response theory; Logistic regression; Statistics; Psychometrics; Ordered logit; Scale (ratio); Clinical psychology; Center for Epidemiologic Studies Depression Scale; Persistence (discontinuity); Depressive symptoms; Mathematics; Cognition; Psychiatry","score_opus":0.8833118557082188,"score_gpt":0.5341469955629262,"score_spread":0.3491648601452926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004501768","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":[0.9712744,0.0005340384,0.010117543,0.014736181,0.0016048128,0.00071739434,0.000030372828,0.000034291108,0.0009510112],"genre_scores_gemma":[0.9908785,0.00004851168,0.0067388867,0.0012223518,0.00060591876,0.00027339472,0.000020055275,0.000008017185,0.00020434379],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99585414,0.0013445725,0.00046125043,0.00095587136,0.0010516446,0.00033249814],"domain_scores_gemma":[0.98866665,0.009783723,0.0004050175,0.00043504944,0.00054798654,0.000161582],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008030978,0.00022880733,0.00030776407,0.00016296543,0.000825972,0.000238538,0.0003107138,0.00010763405,0.00010452232],"category_scores_gemma":[0.025498893,0.000103585604,0.00007400031,0.0004474425,0.00014703957,0.00027927742,0.000027666581,0.00019956735,0.0000043815144],"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":[0.002155089,0.0022043455,0.63454056,0.000027691714,0.00013191673,0.0000014564039,0.0031052174,0.000097193915,0.0012595322,0.005647318,0.02736664,0.32346302],"study_design_scores_gemma":[0.0010655873,0.0017170797,0.9748963,0.00008042205,0.000023736287,0.00002320208,0.0038548526,0.00022881872,0.00016390903,0.010978049,0.0067367572,0.00023127272],"about_ca_topic_score_codex":0.0000050451154,"about_ca_topic_score_gemma":0.000021116064,"teacher_disagreement_score":0.34035575,"about_ca_system_score_codex":0.000059998394,"about_ca_system_score_gemma":0.000018946977,"threshold_uncertainty_score":0.98270977},"labels":[],"label_agreement":null},{"id":"W2005249146","doi":"10.1007/s11205-011-9843-4","title":"Validity and the Consequences of Test Interpretation and Use","year":2011,"lang":"en","type":"article","venue":"Social Indicators Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":149,"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":"Cognitive reframing; Interpretation (philosophy); Construct validity; Psychology; Test (biology); Construct (python library); Social psychology; Quality of Life Research; Value (mathematics); Meaning (existential); Test validity; External validity; Psychometrics; Applied psychology; Public health; Developmental psychology; Computer science; Medicine; Statistics; Mathematics","score_opus":0.8223478813702115,"score_gpt":0.579589150324663,"score_spread":0.24275873104554857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005249146","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":[0.9926519,0.00013344106,0.0003134373,0.0005012775,0.00006778943,0.00015759202,0.000008085014,0.000008128675,0.006158394],"genre_scores_gemma":[0.99866724,0.00008845067,0.0010709235,0.000025259873,0.000029313618,0.000008635323,1.8787136e-7,0.0000028717536,0.00010713262],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99606633,0.0022288908,0.00032301282,0.00023205543,0.00095945323,0.00019024366],"domain_scores_gemma":[0.88064766,0.11848564,0.00024037922,0.00021222024,0.00033893884,0.00007514451],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.023587622,0.000051950523,0.0001941087,0.0005398933,0.0004242745,0.00014962482,0.00041766049,0.00007010411,0.00008325537],"category_scores_gemma":[0.2629593,0.000028188317,0.00003489508,0.0019728218,0.004191282,0.00016388134,0.00026179125,0.00025511248,0.000004253149],"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":[0.0000934841,0.000023020379,0.912714,0.0000052657633,0.0000075706853,0.0000014349646,0.012595939,1.4759866e-8,0.00017393776,0.010745535,0.00066151447,0.0629783],"study_design_scores_gemma":[0.0002623622,0.000088793335,0.79737574,0.000006781656,0.000004183314,0.0000025480929,0.006516981,0.000054660308,0.00079070794,0.1945829,0.00027132206,0.000043036867],"about_ca_topic_score_codex":0.0005887196,"about_ca_topic_score_gemma":0.000016106142,"teacher_disagreement_score":0.23937169,"about_ca_system_score_codex":0.000010336442,"about_ca_system_score_gemma":0.000069381436,"threshold_uncertainty_score":0.99851876},"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":"W2008020807","doi":"10.1007/s10182-010-0132-3","title":"Nonlinear structural equation modeling: is partial least squares an alternative?","year":2010,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"LISREL; Structural equation modeling; Latent variable; Mathematics; Partial least squares regression; Statistics; Econometrics","score_opus":0.29481605318908566,"score_gpt":0.5122797312166472,"score_spread":0.2174636780275615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008020807","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":[0.38531712,0.000072331975,0.6136181,0.000106073814,0.00030151184,0.00005394808,0.00015139587,0.000019772502,0.00035975437],"genre_scores_gemma":[0.7367756,0.00001976982,0.26290095,0.000063012296,0.00015816843,0.0000060910124,0.000036011894,0.000006873256,0.000033531025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587715,0.00046514583,0.0010103607,0.0008673198,0.0013628722,0.0004171735],"domain_scores_gemma":[0.9885411,0.009927873,0.00030294748,0.0006403557,0.0003733609,0.00021435095],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027478125,0.00020228825,0.0005664062,0.00092510507,0.00016861703,0.00026437605,0.0007761618,0.00008104763,0.0020589575],"category_scores_gemma":[0.038494386,0.00014591945,0.0001348699,0.003977259,0.00020441946,0.0008829711,0.00012502674,0.00039664566,0.000037482685],"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":[0.000095889365,0.00008842007,0.33266285,0.000004053438,0.00008811306,0.000019385558,0.0005142754,0.14811563,0.0001180604,0.018851234,0.000022990214,0.4994191],"study_design_scores_gemma":[0.0001845129,0.000070761496,0.01316246,0.000001957935,0.000068835645,0.0000013922906,0.00047016406,0.8208928,0.00003485267,0.1644349,0.0005164992,0.00016083356],"about_ca_topic_score_codex":0.00040935216,"about_ca_topic_score_gemma":0.0012838631,"teacher_disagreement_score":0.6727772,"about_ca_system_score_codex":0.000023001743,"about_ca_system_score_gemma":0.000034481185,"threshold_uncertainty_score":0.99885327},"labels":[],"label_agreement":null},{"id":"W2008052593","doi":"10.2478/v10038-011-0014-x","title":"A Confirmatory Factor Analysis of the Ottawa Mental Skill Assessment Tool (OMSAT-3*) - Romanian Version","year":2011,"lang":"en","type":"article","venue":"Human Movement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"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":"Romanian; Confirmatory factor analysis; Psychology; Applied psychology; Computer science; Structural equation modeling; Machine learning","score_opus":0.3402077168183095,"score_gpt":0.44007044565976566,"score_spread":0.09986272884145614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008052593","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":[0.9736164,0.000030610594,0.001000744,0.00005366733,0.00051783037,0.0002586147,0.000056808716,0.000023934179,0.02444139],"genre_scores_gemma":[0.9954172,0.000002680019,0.003350044,0.00037885,0.00002062998,0.000009943672,0.000004781684,0.0000069495236,0.0008089627],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964755,0.00044684435,0.0008619733,0.00042782063,0.0015314566,0.00025641645],"domain_scores_gemma":[0.9968762,0.001256712,0.0006726199,0.0009748424,0.00014623853,0.00007340681],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028731925,0.0001601828,0.00041325396,0.0006218909,0.0002945306,0.0000628743,0.0010438856,0.000055393823,0.008038219],"category_scores_gemma":[0.001229882,0.00009562304,0.0003868123,0.0017568415,0.00012758895,0.00012532233,0.00038900634,0.00012524963,0.000024478803],"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":[0.000017517676,0.00038089466,0.96132046,0.00000682376,0.00069100724,0.000003948437,0.0033210688,0.00002456786,0.01037024,0.007871411,0.006434215,0.009557853],"study_design_scores_gemma":[0.00033402978,0.00013651603,0.9891915,0.0000097429265,0.00012242194,1.9934375e-7,0.0016887414,0.00041846084,0.0016165468,0.0027105552,0.0036497607,0.000121542],"about_ca_topic_score_codex":0.0003425621,"about_ca_topic_score_gemma":0.000077302146,"teacher_disagreement_score":0.027871031,"about_ca_system_score_codex":0.000113901166,"about_ca_system_score_gemma":0.000035439185,"threshold_uncertainty_score":0.99286854},"labels":[],"label_agreement":null},{"id":"W2011823397","doi":"10.1007/s11336-015-9461-1","title":"Profile Likelihood-Based Confidence Intervals and Regions for Structural Equation Models","year":2015,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":37,"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":"Structural equation modeling; Latent variable; Confidence interval; Wald test; Multivariate statistics; Statistics; Mathematics; Restricted maximum likelihood; Maximum likelihood; Algorithm; Computer science; Statistical hypothesis testing","score_opus":0.7341033069992505,"score_gpt":0.5068358670053227,"score_spread":0.22726743999392784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011823397","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":[0.11978749,0.0014703653,0.8720392,0.0013440474,0.0014101978,0.00066563627,0.00004949927,0.00010375317,0.0031298234],"genre_scores_gemma":[0.8486422,0.00001683456,0.15032394,0.00036647267,0.00014537618,0.000076343844,0.000009313601,0.000016011778,0.0004035322],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966433,0.0003359464,0.000766284,0.0007416219,0.001086108,0.00042670718],"domain_scores_gemma":[0.97014713,0.027317014,0.0004834269,0.0007143572,0.0009845475,0.0003535028],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008185362,0.0001992816,0.00042410457,0.0014719686,0.00016981932,0.00038421873,0.00071724644,0.00012121111,0.00007827217],"category_scores_gemma":[0.1329558,0.00014611764,0.00012569655,0.0039986414,0.00012936523,0.00051501574,0.000088145556,0.00014760175,0.000029387182],"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":[0.00077739166,0.00015640492,0.06349041,0.000068191446,0.00008138461,0.0000043101873,0.001873215,0.0020812997,0.00055203104,0.063786164,0.118552804,0.7485764],"study_design_scores_gemma":[0.0015777659,0.00041330396,0.008974287,0.000034074026,0.000015730539,0.0000093640865,0.0008560819,0.22279921,0.00023297471,0.75981325,0.0050131697,0.00026079168],"about_ca_topic_score_codex":0.000046807323,"about_ca_topic_score_gemma":0.000006898689,"teacher_disagreement_score":0.7483156,"about_ca_system_score_codex":0.00004763691,"about_ca_system_score_gemma":0.000105822626,"threshold_uncertainty_score":0.8743477},"labels":[],"label_agreement":null},{"id":"W2012846896","doi":"10.3899/jrheum.130814","title":"A Systematic Literature Review on the Application of Rasch Analysis in Musculoskeletal Disease — A Special Interest Group Report of OMERACT 11","year":2013,"lang":"en","type":"review","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rasch model; Medicine; Physical therapy; Construct validity; Differential item functioning; Item response theory; Psychometrics; Scale (ratio); MEDLINE; Clinical psychology; Psychology","score_opus":0.23429004977601514,"score_gpt":0.4714537359766507,"score_spread":0.23716368620063555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012846896","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003403329,0.99246866,0.002040901,0.00038702483,0.00041595686,0.0011953388,0.000011224678,0.0000028760824,0.00007466431],"genre_scores_gemma":[0.0032242374,0.9962068,0.00041282654,0.00002524745,0.00004423485,0.000043272103,0.000006076436,0.000012989166,0.000024269932],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98313725,0.008805195,0.0064129177,0.00031380221,0.0011145931,0.00021625364],"domain_scores_gemma":[0.91665304,0.06354524,0.017239084,0.0017233309,0.0007376477,0.00010164498],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03223158,0.00032987507,0.005798781,0.001997053,0.000053085263,0.000045626562,0.00244683,0.00017747344,0.000117759504],"category_scores_gemma":[0.1294121,0.00012256394,0.0019356655,0.007661334,0.00020671762,0.00011681987,0.00019602552,0.0007939943,0.000014923223],"study_design_candidate":"systematic_review","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":[0.00009641418,0.00042149174,0.009006366,0.4778231,0.0032068985,0.0001525126,0.00036948101,0.00002139619,7.256354e-7,0.006176955,0.0044013564,0.4983233],"study_design_scores_gemma":[0.0003715188,0.00032183857,0.0020184005,0.90074074,0.012552606,0.01155357,0.00044461177,0.0001747819,1.3655637e-7,0.005310982,0.0660541,0.00045672417],"about_ca_topic_score_codex":0.000036637655,"about_ca_topic_score_gemma":0.000031754396,"teacher_disagreement_score":0.49786657,"about_ca_system_score_codex":0.00005275645,"about_ca_system_score_gemma":0.00016206225,"threshold_uncertainty_score":0.99652123},"labels":[],"label_agreement":null},{"id":"W2013676510","doi":"10.1097/00005650-200307000-00002","title":"From the Generic to the Condition-specific? Instrument Order Effects in Quality of Life Assessment","year":2003,"lang":"en","type":"article","venue":"Medical Care","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health","funders":"","keywords":"Quality of life (healthcare); Asthma; Medicine; Quality (philosophy); Internal consistency; Test (biology); Consistency (knowledge bases); Physical therapy; Psychology; Clinical psychology; Psychometrics; Computer science; Nursing","score_opus":0.40777487385048616,"score_gpt":0.5066285099970246,"score_spread":0.09885363614653842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013676510","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":[0.95082474,0.0016887715,0.03581067,0.00640474,0.0014936895,0.00033136053,0.00002228099,0.000011932568,0.0034118434],"genre_scores_gemma":[0.9872353,0.000028518996,0.009809635,0.0027211332,0.00014145668,0.00003893055,0.0000045032793,0.0000041947474,0.000016347121],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9936099,0.0027838612,0.00068892847,0.00033395368,0.0023812957,0.0002020603],"domain_scores_gemma":[0.9450183,0.053549692,0.0002184552,0.000766759,0.0002513263,0.00019547327],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00941142,0.00009640047,0.00031249502,0.00008643865,0.00010554582,0.000055941895,0.00088052906,0.000077835466,0.0014048972],"category_scores_gemma":[0.15853208,0.00004210054,0.00006954691,0.0020081622,0.00010894155,0.000031153788,0.00014850972,0.00025485552,0.00002972735],"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":[0.00001996521,0.000080688165,0.49690452,0.000012783138,0.000020701367,0.000008305231,0.0037150988,0.0001419859,0.000047839836,0.0062991017,0.03295498,0.45979404],"study_design_scores_gemma":[0.00051350263,0.000061488936,0.8947155,0.000027872162,0.0000027538244,5.986034e-7,0.010022581,0.000051441908,0.000054451393,0.004916073,0.08955668,0.00007706046],"about_ca_topic_score_codex":0.0004078641,"about_ca_topic_score_gemma":0.000210035,"teacher_disagreement_score":0.45971698,"about_ca_system_score_codex":0.000054144115,"about_ca_system_score_gemma":0.00020768133,"threshold_uncertainty_score":0.99950796},"labels":[],"label_agreement":null},{"id":"W2014421030","doi":"10.1177/00131640021970970","title":"Structural Equation Models and the Regression Bias for Measuring Correlates of Change","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Manitoba","funders":"","keywords":"Structural equation modeling; Skewness; Analysis of covariance; Regression analysis; Regression; Statistics; Psychology; Linear regression; Econometrics; Regression toward the mean; Covariance; Mathematics","score_opus":0.9410559504515326,"score_gpt":0.523874003364629,"score_spread":0.4171819470869036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014421030","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":[0.98354477,0.004270598,0.0025757097,0.0064765387,0.0005218126,0.0004954164,0.0000060355433,0.000009898579,0.0020992432],"genre_scores_gemma":[0.99453866,0.00017989546,0.004705471,0.00020485745,0.00014405018,0.00008938443,0.0000017741518,0.0000030232209,0.000132882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978947,0.00035241735,0.0004349313,0.00033000464,0.000851439,0.0001364877],"domain_scores_gemma":[0.99248993,0.0067143,0.00020931131,0.00018910815,0.0003355541,0.00006179332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00713073,0.00010110487,0.00021226054,0.00008780471,0.00022180106,0.000061830804,0.00020892246,0.000056888573,0.00029386787],"category_scores_gemma":[0.012463895,0.000045707373,0.000059975566,0.0003169197,0.00018793205,0.00012290414,0.000023471232,0.00008117962,0.0000024588298],"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":[0.00058455416,0.00009645323,0.037963055,0.000011835276,0.000020806792,7.384963e-8,0.0012143386,0.00015450243,0.000085499574,0.025573691,0.0006474599,0.93364775],"study_design_scores_gemma":[0.0008185556,0.00011532497,0.4363746,0.00003717657,0.000010686476,0.000007799115,0.0001739329,0.0072649983,0.000015277416,0.55471563,0.0003920105,0.000073979376],"about_ca_topic_score_codex":0.00001904707,"about_ca_topic_score_gemma":0.0000012811456,"teacher_disagreement_score":0.9335737,"about_ca_system_score_codex":0.000013031611,"about_ca_system_score_gemma":0.000012357713,"threshold_uncertainty_score":0.99585456},"labels":[],"label_agreement":null},{"id":"W2016005933","doi":"10.1037/0021-9010.87.3.517","title":"Measurement equivalence: A comparison of methods based on confirmatory factor analysis and item response theory.","year":2002,"lang":"en","type":"article","venue":"Journal of Applied Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":412,"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":"Equivalence (formal languages); Item response theory; Differential item functioning; Confirmatory factor analysis; Psychology; Raw score; Psychometrics; Factor analysis; Social psychology; Econometrics; Classical test theory; Test (biology); Statistics; Raw data; Mathematics; Structural equation modeling; Developmental psychology","score_opus":0.6434044207719166,"score_gpt":0.5717001743794533,"score_spread":0.07170424639246331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016005933","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":[0.53728575,0.0013863968,0.45123953,0.0006372011,0.00058151764,0.00014230634,0.000006348503,0.000012984272,0.008707982],"genre_scores_gemma":[0.9218976,0.000033349537,0.07744216,0.00055154454,0.00004208385,0.0000025984511,6.7648855e-8,0.000008281786,0.000022345483],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9922427,0.0037019895,0.0018993103,0.00041369282,0.0014592163,0.00028307008],"domain_scores_gemma":[0.95755905,0.038787704,0.0022691959,0.0006443436,0.00055976206,0.00017992653],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038538296,0.00019221156,0.0011834981,0.0026151517,0.000087447435,0.00005117751,0.0007833327,0.00017001017,0.001150554],"category_scores_gemma":[0.032443117,0.00012815087,0.00031372285,0.0028448831,0.00025511108,0.00005717363,0.000048329406,0.00043711564,0.000009820699],"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":[0.010081862,0.00088776526,0.086688906,0.000020064515,0.00091005745,0.000017944378,0.0020068483,0.0011272471,0.05557378,0.0011982527,0.005162079,0.83632517],"study_design_scores_gemma":[0.0039425464,0.0025323043,0.9404571,0.00006187383,0.00056500133,0.000047532787,0.0022301397,0.011955332,0.0069469167,0.01742044,0.013426021,0.00041476954],"about_ca_topic_score_codex":7.5472167e-7,"about_ca_topic_score_gemma":4.1064234e-7,"teacher_disagreement_score":0.8537682,"about_ca_system_score_codex":0.00004177116,"about_ca_system_score_gemma":0.00003398682,"threshold_uncertainty_score":0.99976254},"labels":[],"label_agreement":null},{"id":"W2018155718","doi":"10.1097/acm.0000000000000650","title":"Are Examiners’ Judgments in OSCE-Style Assessments Influenced by Contrast Effects?","year":2015,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":55,"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":"Contrast (vision); Psychology; Formality; Variance (accounting); Clinical psychology; Social psychology; Statistics; Mathematics; Computer science","score_opus":0.5175988496754704,"score_gpt":0.5339994156305645,"score_spread":0.016400565955094093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018155718","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":[0.9805288,0.0023346548,0.0060166633,0.0016280147,0.0016607353,0.00039404642,0.0000059344347,0.000068326175,0.0073628672],"genre_scores_gemma":[0.99314606,0.000106238585,0.0007366165,0.0033492998,0.00025228545,0.00003421454,0.000006064492,0.000015578293,0.0023536587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943112,0.0009473324,0.0012189168,0.00071909884,0.0022343607,0.00056908064],"domain_scores_gemma":[0.97619945,0.02164162,0.0009355826,0.0005521167,0.00021746875,0.00045375753],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0143496515,0.00025463314,0.0007997411,0.00071278005,0.000058308364,0.000029496741,0.0012514897,0.00029320962,0.00013330475],"category_scores_gemma":[0.23488773,0.00016620489,0.000036110596,0.0027932066,0.00022932663,0.0003210555,0.00020706997,0.00086600333,0.00010995717],"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":[0.000051396444,0.000023373515,0.73859304,0.000012456693,0.00001746721,0.00004282937,0.0012252702,0.000018868275,0.004851178,0.000050923074,0.22178586,0.03332733],"study_design_scores_gemma":[0.011571124,0.00080558413,0.90446687,0.00081786804,0.000048905855,0.00003657036,0.015074842,0.002146965,0.0010294078,0.022338036,0.04105727,0.0006065572],"about_ca_topic_score_codex":0.00021269883,"about_ca_topic_score_gemma":0.0000056709578,"teacher_disagreement_score":0.2205381,"about_ca_system_score_codex":0.0001354038,"about_ca_system_score_gemma":0.000054525688,"threshold_uncertainty_score":0.77155715},"labels":[],"label_agreement":null},{"id":"W2020689986","doi":"10.1177/0734282911406646","title":"Test Review: Test of Written Language—Fourth Edition","year":2011,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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 Calgary","funders":"","keywords":"Psychology; Test (biology); Language assessment; Test validity; Norm-referenced test; Achievement test; Standardized test; Mathematics education; Psychometrics; Clinical psychology","score_opus":0.39259951954647454,"score_gpt":0.5303377208322757,"score_spread":0.13773820128580117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020689986","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":[0.42498028,0.0442835,0.12906745,0.05506548,0.025484089,0.0016249691,0.00028683766,0.000082642575,0.31912476],"genre_scores_gemma":[0.6499375,0.0020568748,0.3444064,0.0012917189,0.0012866606,0.000012463996,0.00000621372,0.000015721542,0.0009864192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99590516,0.00026971655,0.0016622714,0.00022551496,0.0017603912,0.00017695072],"domain_scores_gemma":[0.9793496,0.01573634,0.0025601126,0.00043932148,0.001752742,0.00016186188],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00869235,0.00013214887,0.0004530315,0.0005853591,0.00006624689,0.000039143906,0.00085137977,0.000049425504,0.0029087008],"category_scores_gemma":[0.045072317,0.00008872779,0.00023423634,0.0013988013,0.000072391675,0.00033967564,0.000045665172,0.0002763372,0.000031377847],"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":[0.000023670904,0.0023423734,0.46322566,0.00009749458,0.00007051675,0.00001076917,0.0006718414,0.0000064656892,0.0023195234,0.0011731697,0.42045507,0.10960344],"study_design_scores_gemma":[0.00035201572,0.00050543627,0.9666786,0.00051856256,0.00004732423,0.0001681688,0.0016659738,0.000025382586,0.00024272111,0.017595608,0.012080516,0.00011964267],"about_ca_topic_score_codex":0.000014092814,"about_ca_topic_score_gemma":0.0000014605085,"teacher_disagreement_score":0.50345296,"about_ca_system_score_codex":0.00007346179,"about_ca_system_score_gemma":0.00044523654,"threshold_uncertainty_score":0.99800277},"labels":[],"label_agreement":null},{"id":"W2022517452","doi":"10.5057/kei.7.87","title":"DOES NUMBER OF LEVEL-2 UNITS IN MULTILEVEL STRUCTURAL EQUATION MODELING MATTER?","year":2007,"lang":"en","type":"article","venue":"KANSEI Engineering International","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Structural equation modeling; Multilevel model; Mathematics; Computer science; Econometrics; Statistics","score_opus":0.4218212124335487,"score_gpt":0.44963713548303597,"score_spread":0.027815923049487268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022517452","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":[0.5302102,0.000005554465,0.46784613,0.000055518616,0.0010749124,0.00003188779,0.000011715431,0.000015238368,0.0007488892],"genre_scores_gemma":[0.92180955,0.0000012231944,0.077753335,0.000022881097,0.00010489161,0.0000020720943,0.000006040262,0.000008740438,0.00029128426],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980366,0.000033723616,0.0007191147,0.00024310153,0.00076960854,0.00019783078],"domain_scores_gemma":[0.99541795,0.0038489674,0.00015150591,0.00018017027,0.00035894048,0.00004249238],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026169848,0.00010681824,0.00017311773,0.00063212536,0.00002087857,0.00004869212,0.00050259137,0.00006306559,0.00039538345],"category_scores_gemma":[0.015611309,0.00007108983,0.000043894208,0.000832586,0.000014806642,0.00023196738,0.000079531,0.00014312332,0.000025357167],"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":[0.000027461097,0.000013043448,0.48408648,0.000008364957,0.00002019162,0.000006285084,0.0006411737,0.4833918,0.0022563022,0.0028508613,0.000046133697,0.026651885],"study_design_scores_gemma":[0.0002053042,0.0000032802436,0.26655027,0.000028057015,0.0000011209474,0.0000071269574,0.00014708101,0.72862995,0.0005085783,0.003754802,0.000082319224,0.00008209553],"about_ca_topic_score_codex":0.00015423371,"about_ca_topic_score_gemma":0.00001629843,"teacher_disagreement_score":0.39159936,"about_ca_system_score_codex":0.000069343376,"about_ca_system_score_gemma":0.000021475806,"threshold_uncertainty_score":0.9926806},"labels":[],"label_agreement":null},{"id":"W2024075312","doi":"10.1111/j.1745-3984.2009.00082.x","title":"Reliability and Attribute‐Based Scoring in Cognitive Diagnostic Assessment","year":2009,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","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 Alberta","funders":"","keywords":"Reliability (semiconductor); Variance (accounting); Cognition; Set (abstract data type); Strengths and weaknesses; Computer science; Test (biology); Sample (material); Psychology; Statistics; Natural language processing; Artificial intelligence; Mathematics; Social psychology","score_opus":0.5837310786203939,"score_gpt":0.5286242359275425,"score_spread":0.05510684269285138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024075312","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":[0.97443646,0.0010755707,0.010817226,0.011743916,0.00079473277,0.00015534121,0.0000023388768,0.000002188052,0.0009722412],"genre_scores_gemma":[0.98216605,0.000022741822,0.017312909,0.00030968228,0.00017119183,0.0000037464506,3.4544246e-7,0.000002145833,0.000011194924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961172,0.0005253797,0.00093854294,0.00022003507,0.0020348376,0.00016401517],"domain_scores_gemma":[0.9511813,0.045516673,0.0007525489,0.00017194415,0.0022210854,0.000156478],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02112191,0.00009286151,0.0002737568,0.00053106603,0.0000740884,0.00010018078,0.0002432279,0.000032321397,0.0001484668],"category_scores_gemma":[0.33678958,0.00006583975,0.0000707345,0.0008722415,0.000038533773,0.00021272428,0.00001869677,0.0002304264,0.000002322548],"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":[0.000033708227,0.00046176225,0.95614094,0.0000038842327,0.000008330788,0.0000034666796,0.000074672826,0.00046658175,0.00033502182,0.0001839963,0.0008130461,0.04147459],"study_design_scores_gemma":[0.0005618648,0.00024315013,0.96512425,0.00019879459,0.000011904876,0.000013819588,0.0003007777,0.00012667429,0.000113541995,0.03307238,0.00016586174,0.00006697637],"about_ca_topic_score_codex":0.000006256136,"about_ca_topic_score_gemma":0.000004031095,"teacher_disagreement_score":0.31566766,"about_ca_system_score_codex":0.00030461058,"about_ca_system_score_gemma":0.0007044513,"threshold_uncertainty_score":0.7320475},"labels":[],"label_agreement":null},{"id":"W2024532747","doi":"10.1080/10401330701542685","title":"How to Use Structural Equation Modeling in Medical Education Research: A Brief Guide","year":2007,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":135,"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":"Structural equation modeling; Latent variable; Test (biology); Statistical model; Computer science; Psychology; Measure (data warehouse); Statistical hypothesis testing; Medical education; Management science; Medicine; Artificial intelligence; Mathematics; Data mining; Statistics; Machine learning; Engineering","score_opus":0.6828362269846211,"score_gpt":0.5820779485981239,"score_spread":0.1007582783864972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024532747","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":[0.8455474,0.00025996257,0.14108798,0.010670952,0.00029977522,0.00012121189,6.1970646e-8,0.000034141995,0.0019785217],"genre_scores_gemma":[0.9618266,0.000015403788,0.035724223,0.00060459314,0.00030164537,0.0000037325246,0.0000024583558,0.000008711704,0.0015126052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926686,0.003421508,0.00075751723,0.0005299112,0.0021601643,0.00046227706],"domain_scores_gemma":[0.9482799,0.050690453,0.00015235934,0.00031048481,0.00025471917,0.00031209365],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.129585,0.00010825904,0.0003030398,0.0022654412,0.0003349402,0.00017280337,0.00036368982,0.00011481589,0.000040512354],"category_scores_gemma":[0.7725051,0.000075698335,0.000017196215,0.002024768,0.00009395646,0.00027575463,0.0001343511,0.002254471,0.0000022333084],"study_design_candidate":"design_other","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":[0.000029907407,0.000011993386,0.18220158,0.0000045226743,0.0000012257244,0.000011650245,0.008490449,0.002225726,0.00010227213,0.0007376428,0.0005547838,0.80562824],"study_design_scores_gemma":[0.00082321925,0.00027438454,0.26611754,0.0006980201,0.0000027910708,0.00004298294,0.043068405,0.66289353,0.0000022935221,0.010134962,0.01576613,0.00017577263],"about_ca_topic_score_codex":0.0071957516,"about_ca_topic_score_gemma":0.000480917,"teacher_disagreement_score":0.80545247,"about_ca_system_score_codex":0.000104848965,"about_ca_system_score_gemma":0.00013681786,"threshold_uncertainty_score":0.9994154},"labels":[],"label_agreement":null},{"id":"W2025395508","doi":"10.1177/0734282908330937","title":"The Average Distance Between Item Values","year":2009,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Statistic; Psychology; Consistency (knowledge bases); Statistics; Internal consistency; Scale (ratio); Econometrics; Item response theory; Test (biology); Psychometrics; Mathematics; Computer science; Artificial intelligence; Geography","score_opus":0.35955825437160327,"score_gpt":0.5641750242092423,"score_spread":0.204616769837639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025395508","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":[0.4923349,0.0026956394,0.32293883,0.108000346,0.008633468,0.00027649023,0.000014803071,0.000025195266,0.06508033],"genre_scores_gemma":[0.94814086,0.000110331835,0.048335128,0.0004619159,0.0012965039,0.0000018751093,8.719357e-7,0.0000045743427,0.0016479442],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956367,0.0004989553,0.0012799645,0.0002164533,0.0021371625,0.00023074856],"domain_scores_gemma":[0.96677715,0.030333811,0.0014126479,0.00041363074,0.00090689346,0.00015587526],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011571192,0.00012047768,0.00028677244,0.00028003386,0.0003918462,0.00042428824,0.0012474781,0.00004021649,0.00014723958],"category_scores_gemma":[0.017093848,0.000063301624,0.00020894787,0.0011482611,0.00006588898,0.0003055759,0.0000262083,0.00033619846,0.000016486993],"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":[0.000030707302,0.00019708813,0.23795389,0.0000012431882,0.00005480411,0.0000031319096,0.00020842609,0.00015084783,0.00006664241,0.0208615,0.10843803,0.6320337],"study_design_scores_gemma":[0.00014678849,0.00012625243,0.64796245,0.00001433729,0.0000069257617,0.000016995678,0.00040330875,0.000049892587,0.0000072135012,0.2621652,0.08904581,0.000054835535],"about_ca_topic_score_codex":0.0000010736466,"about_ca_topic_score_gemma":4.0620208e-7,"teacher_disagreement_score":0.63197887,"about_ca_system_score_codex":0.0001298954,"about_ca_system_score_gemma":0.00034626198,"threshold_uncertainty_score":0.9911856},"labels":[],"label_agreement":null},{"id":"W2025516546","doi":"10.1080/10705511.2013.742388","title":"A Note on Sample Size and Solution Propriety for Confirmatory Factor Analytic Models","year":2013,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":78,"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 Windsor","funders":"American Psychological Association","keywords":"Sample size determination; Sample (material); Confirmatory factor analysis; Rule of thumb; Statistic; Statistics; Econometrics; Multivariate statistics; Set (abstract data type); Latent variable; Computer science; Structural equation modeling; Mathematics; Algorithm","score_opus":0.44235579597820196,"score_gpt":0.4574590563859317,"score_spread":0.015103260407729746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025516546","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":[0.50284964,0.000052753636,0.4956711,0.0006362171,0.00037134165,0.0003411763,0.000022627948,0.000028473056,0.00002665626],"genre_scores_gemma":[0.76630414,0.000015154162,0.23335236,0.000045943005,0.00019604748,0.000021428583,0.0000035472426,0.000015102369,0.00004627316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963831,0.00034237164,0.0011301372,0.0005685432,0.0011145665,0.0004613331],"domain_scores_gemma":[0.98029745,0.017310428,0.00068561354,0.0003532261,0.0010771514,0.00027616546],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002917684,0.00026349694,0.00041892147,0.00041984543,0.0011654013,0.0006360112,0.00041867734,0.00014820174,0.00014322292],"category_scores_gemma":[0.037919156,0.00017419973,0.00020626553,0.00050111394,0.000085202075,0.0011926716,0.00014265462,0.0004268293,0.000009954959],"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":[0.00027355144,0.000027639824,0.005134259,0.000024957952,0.00004368382,0.0000017926848,0.0032635906,0.8247221,0.0055989977,0.0010972237,0.00010440279,0.15970781],"study_design_scores_gemma":[0.0006056365,0.00014350915,0.0066550323,0.000023776798,0.000010497506,0.0000337872,0.000549934,0.65556633,0.000025776186,0.3362275,0.0000026795844,0.00015551191],"about_ca_topic_score_codex":0.00007247634,"about_ca_topic_score_gemma":0.0000045271036,"teacher_disagreement_score":0.3351303,"about_ca_system_score_codex":0.00012863033,"about_ca_system_score_gemma":0.00012651763,"threshold_uncertainty_score":0.97018486},"labels":[],"label_agreement":null},{"id":"W2026285281","doi":"10.1177/0013164412448652","title":"Linking Cut-Scores Given Changes in the Decision-Making Process, Administration Time, and Proportions of Item Types Between Successive Administrations of a Test for a Large-Scale Assessment Program","year":2012,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Process (computing); Scale (ratio); Psychology; Equating; Test score; Psychometrics; Computer science; Applied psychology; Statistics; Standardized test; Clinical psychology; Mathematics education; Mathematics; Developmental psychology","score_opus":0.4302050027001809,"score_gpt":0.5329682362061104,"score_spread":0.10276323350592953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026285281","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":[0.984461,0.00065039936,0.006269514,0.0051394408,0.00019235836,0.0014929585,0.00028157467,0.000014849297,0.0014979095],"genre_scores_gemma":[0.95313853,0.000010028095,0.046211574,0.000049973714,0.00016910059,0.00037610673,0.00002869573,0.0000036096394,0.000012357426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977934,0.00020814849,0.0006247197,0.00030096262,0.00086473074,0.00020806515],"domain_scores_gemma":[0.9791998,0.019502727,0.00051422627,0.00017858563,0.00053938373,0.000065240114],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056571667,0.00011338738,0.00025125785,0.00018348395,0.00017893134,0.00007223349,0.00025349433,0.00007389515,0.00013530662],"category_scores_gemma":[0.025155237,0.00006552611,0.000044551918,0.0007345604,0.000109016786,0.0001243206,0.000029570901,0.000113198155,7.821893e-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":[0.000041008465,0.0018917772,0.834395,0.00004127644,0.000015713424,1.4484549e-7,0.0009566533,0.0000024100298,0.00012770412,0.0011289711,0.0004911184,0.16090822],"study_design_scores_gemma":[0.00019595106,0.0008120564,0.96247035,0.00015904554,0.000024632773,0.000006001675,0.0009741313,0.00012709905,0.000061043276,0.034384508,0.0007006237,0.00008458436],"about_ca_topic_score_codex":0.0000012132095,"about_ca_topic_score_gemma":0.00003806011,"teacher_disagreement_score":0.16082363,"about_ca_system_score_codex":0.00001673814,"about_ca_system_score_gemma":0.00012497063,"threshold_uncertainty_score":0.9830563},"labels":[],"label_agreement":null},{"id":"W2026642137","doi":"10.5539/elt.v4n2p242","title":"On the Factor Structure of a Reading Comprehension Test","year":2011,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Varimax rotation; Psychology; Construct validity; Test (biology); Test of English as a Foreign Language; Reading comprehension; Exploratory factor analysis; Test validity; Construct (python library); Reading (process); Item analysis; Factor (programming language); Mathematics education; Confirmatory factor analysis; Linguistics; Developmental psychology; Psychometrics; Cronbach's alpha; Language assessment; Statistics; Structural equation modeling; Computer science; Mathematics","score_opus":0.270509993240324,"score_gpt":0.39863488926307983,"score_spread":0.12812489602275584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026642137","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":[0.9687283,0.000086964945,0.0015827083,0.000023210876,0.00058523606,0.000110165915,0.000024753761,0.000088077584,0.028770592],"genre_scores_gemma":[0.98929346,8.2021097e-7,0.010234694,0.0001444484,0.00014902877,9.2037317e-7,0.0000011312933,0.000012084576,0.00016342076],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9975799,0.0007232602,0.00043598792,0.0003274607,0.0007073773,0.00022602084],"domain_scores_gemma":[0.9536477,0.045152415,0.00033146224,0.00072847516,0.00008484882,0.000055155324],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028924663,0.0001396212,0.00026779043,0.00028078092,0.00020562577,0.00007474231,0.0008648853,0.00007246509,0.001075509],"category_scores_gemma":[0.28124923,0.000071756636,0.00009589468,0.0005884889,0.00006040488,0.00013555019,0.00016227414,0.0005632912,0.000010829159],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065305896,0.0001946329,0.1220062,0.000018669332,0.000047596,0.00004433349,0.47697765,0.000051414223,0.13260587,0.024282087,0.0035597894,0.24014646],"study_design_scores_gemma":[0.001946849,0.0013286005,0.33823383,0.00062814215,0.00007186043,0.000053433203,0.4446112,0.0035035692,0.11200355,0.09270048,0.003378647,0.0015398657],"about_ca_topic_score_codex":0.00012478148,"about_ca_topic_score_gemma":0.00000665886,"teacher_disagreement_score":0.27835676,"about_ca_system_score_codex":0.000016907898,"about_ca_system_score_gemma":0.000011187299,"threshold_uncertainty_score":0.99983764},"labels":[],"label_agreement":null},{"id":"W2029082333","doi":"10.1177/0146621607301094","title":"Effects of Semantic Incompatibility on Rating Response","year":2008,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Rating scale; Semantic differential; Internal consistency; Consistency (knowledge bases); Scale (ratio); Cognitive psychology; Social psychology; Statistics; Psychometrics; Developmental psychology; Artificial intelligence; Computer science; Mathematics","score_opus":0.6035678497989727,"score_gpt":0.4659181755804515,"score_spread":0.1376496742185212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029082333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96924627,0.000119856544,0.015433929,0.00021447976,0.00045949686,0.000599736,0.0000010831764,0.00008568002,0.013839476],"genre_scores_gemma":[0.98814034,0.0000074571863,0.011220758,0.00048622006,0.00005565381,0.000051545434,2.1389477e-7,0.000009109419,0.00002867617],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9926154,0.0017882059,0.0011349218,0.000937659,0.0031297347,0.0003940833],"domain_scores_gemma":[0.964433,0.033546984,0.0005319899,0.00099279,0.00033864353,0.00015660797],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021633433,0.00023560252,0.000638536,0.00033359654,0.00023309534,0.00002792511,0.00085909286,0.00013973954,0.00013064753],"category_scores_gemma":[0.1104486,0.00014644148,0.00016750113,0.0017578881,0.00025290638,0.000036771075,0.000117685675,0.0003130742,0.00014708399],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0096789645,0.0045703985,0.087551884,0.000081170634,0.000109388326,0.0001235655,0.0012881783,0.00043195148,0.5420306,0.0041090874,0.010413825,0.339611],"study_design_scores_gemma":[0.0011709575,0.0008601189,0.9592599,0.000033892542,0.000008424147,0.000010310675,0.000089870344,0.000039923118,0.021375077,0.01654827,0.00041315,0.00019010322],"about_ca_topic_score_codex":0.0000054769116,"about_ca_topic_score_gemma":5.6039966e-7,"teacher_disagreement_score":0.87170804,"about_ca_system_score_codex":0.000074795455,"about_ca_system_score_gemma":0.000027289465,"threshold_uncertainty_score":0.8970445},"labels":[],"label_agreement":null},{"id":"W2029517174","doi":"10.1007/s11336-005-1295-9","title":"Limited Information Goodness-of-fit Testing in Multidimensional Contingency Tables","year":2006,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":327,"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":"Goodness of fit; Statistics; Contingency table; Mathematics; Statistical hypothesis testing; Estimator; Null hypothesis; Econometrics; Applied mathematics","score_opus":0.42536190741103713,"score_gpt":0.4361651235139779,"score_spread":0.010803216102940771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029517174","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":[0.95899135,0.0008784543,0.011516058,0.00015183332,0.0011125199,0.00027526918,0.000030329653,0.00008026232,0.026963914],"genre_scores_gemma":[0.8926264,0.00001377235,0.106965,0.00007614618,0.00009641025,0.000012939249,0.00001151637,0.000009823052,0.00018797364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995376,0.00030179106,0.0019412435,0.00043254188,0.0014739316,0.0004744723],"domain_scores_gemma":[0.95204854,0.045186434,0.0011445758,0.00062889716,0.00090037455,0.00009116396],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00781257,0.00021120347,0.00054176647,0.0044600735,0.000116694646,0.00013510606,0.0006696324,0.00014553564,0.00027367985],"category_scores_gemma":[0.2022282,0.00016757207,0.00011671393,0.019745212,0.00009248346,0.0008476142,0.00013245874,0.00023717285,0.00010162417],"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":[0.000031355852,0.00013156132,0.7983192,0.000010759038,0.000005341207,0.0000017603369,0.00007195706,0.00064251997,0.0010944378,0.0008706569,0.0021272807,0.19669314],"study_design_scores_gemma":[0.0011136766,0.00008941839,0.97053444,0.0000619472,0.0000055359324,0.000008643244,0.00040271456,0.0047400934,0.000547709,0.010722058,0.01154721,0.00022654099],"about_ca_topic_score_codex":0.0007460023,"about_ca_topic_score_gemma":0.000030295178,"teacher_disagreement_score":0.1964666,"about_ca_system_score_codex":0.000044904195,"about_ca_system_score_gemma":0.000057636727,"threshold_uncertainty_score":0.948692},"labels":[],"label_agreement":null},{"id":"W2032509967","doi":"10.2466/pms.2003.97.3.716","title":"What Difference Does it Make? Implications of the Size of the Difference between the Means of Two Groups","year":2003,"lang":"en","type":"article","venue":"Perceptual and Motor Skills","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Statistics; Mathematics; Standard deviation; Group (periodic table); Significant difference; Psychology; Physics","score_opus":0.18052972373244588,"score_gpt":0.39751944263648953,"score_spread":0.21698971890404364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032509967","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":[0.9950388,0.00019038311,0.0016852487,0.001409971,0.0004536607,0.00030356806,0.00007576619,0.0000060752404,0.00083649607],"genre_scores_gemma":[0.9965792,0.00021628823,0.0014742371,0.00018398713,0.00003652074,0.000012812067,2.4143927e-7,0.00000542825,0.0014913063],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99731547,0.00078830385,0.0006789993,0.00031725437,0.00069352105,0.00020646866],"domain_scores_gemma":[0.9690196,0.029102193,0.0005275948,0.0010499499,0.00024559276,0.000055090717],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020108777,0.0001439131,0.00038450255,0.00006272642,0.00023503277,0.00006893443,0.0013893995,0.000060280367,0.00017363438],"category_scores_gemma":[0.029563116,0.000048221627,0.00018664537,0.0010341158,0.00084625237,0.00007559904,0.00031424518,0.00016484011,0.000001299931],"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":[0.000004542907,0.00007941917,0.86271536,0.000010608652,0.000022926555,3.4479353e-8,0.0056445473,0.000002586469,0.018732235,0.0028308232,0.00008316657,0.10987378],"study_design_scores_gemma":[0.00016277873,0.00004254058,0.95001304,0.000054302054,0.000027335265,0.000002160343,0.0041757976,0.000010747618,0.0021368305,0.043068215,0.00023930168,0.00006696051],"about_ca_topic_score_codex":0.000092978014,"about_ca_topic_score_gemma":0.000090551526,"teacher_disagreement_score":0.10980681,"about_ca_system_score_codex":0.000009033647,"about_ca_system_score_gemma":0.000040064715,"threshold_uncertainty_score":0.9786113},"labels":[],"label_agreement":null},{"id":"W2032535815","doi":"10.1016/j.jclinepi.2013.10.009","title":"The minimal clinically important difference determined using item response theory models: an attempt to solve the issue of the association with baseline score","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Minimal clinically important difference; Medicine; Rating scale; Baseline (sea); Standard error; Gold standard (test); Physical therapy; Statistics; Randomized controlled trial; Mathematics; Internal medicine","score_opus":0.7097347802422773,"score_gpt":0.5849810002776482,"score_spread":0.12475377996462911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032535815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7817386,0.00013975853,0.1989537,0.017545179,0.0013780063,0.00017340672,0.000005074449,0.0000060036987,0.00006029815],"genre_scores_gemma":[0.9291803,0.00010413661,0.061198458,0.008354609,0.00097154337,0.0000029287153,1.7260675e-7,0.000014976697,0.00017285248],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8880819,0.09343778,0.015217063,0.000739585,0.001770639,0.0007530016],"domain_scores_gemma":[0.045878682,0.93355936,0.017075246,0.0014738543,0.0016686629,0.00034421144],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.56431454,0.00022150758,0.0021457803,0.0001593651,0.00037820684,0.00006290116,0.0027663603,0.00035332103,0.00002368962],"category_scores_gemma":[0.9517832,0.000074053205,0.00075330597,0.00093639374,0.0006442656,0.00015165513,0.00034537265,0.0012738914,0.0000030915057],"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":[0.0072581414,0.00009974975,0.89464295,0.000002320135,0.00008453936,0.0000035353114,0.00016749908,0.0030657395,0.0001249201,0.001389986,0.0010661151,0.09209449],"study_design_scores_gemma":[0.00071514264,0.002556312,0.77553684,0.000078302764,0.000086807086,0.000055018132,0.00048509927,0.102153495,0.000012066887,0.116249755,0.001956506,0.00011468511],"about_ca_topic_score_codex":0.000020004243,"about_ca_topic_score_gemma":0.000037142694,"teacher_disagreement_score":0.84220326,"about_ca_system_score_codex":0.00004779286,"about_ca_system_score_gemma":0.00044142085,"threshold_uncertainty_score":0.5534495},"labels":[],"label_agreement":null},{"id":"W2033872871","doi":"10.3102/1076998613481500","title":"A Two-Decision Model for Responses to Likert-Type Items","year":2013,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kronos (Canada)","funders":"","keywords":"Likert scale; Item response theory; Set (abstract data type); Decision model; Econometrics; Functional response; Model selection; Response time; Statistics; Computer science; Mathematics; Machine learning; Psychometrics","score_opus":0.5866905625763341,"score_gpt":0.5681326453150991,"score_spread":0.018557917261235013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033872871","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":[0.6887818,0.00014349598,0.30833888,0.001527975,0.00095260696,0.0001394314,0.00007961978,0.000001830438,0.00003435371],"genre_scores_gemma":[0.40969947,0.000012503562,0.5879563,0.0001780831,0.00017558566,0.00000654931,0.0000021236103,0.000005373647,0.0019639966],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810445,0.00008530316,0.0007773568,0.00017481974,0.00069353916,0.0001645255],"domain_scores_gemma":[0.9742002,0.022908691,0.00043874906,0.00014035939,0.0020699366,0.00024207536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019348762,0.000096490876,0.00024729426,0.0004270692,0.0001393793,0.0002575074,0.0003133421,0.0000373992,0.00034755812],"category_scores_gemma":[0.040711258,0.00006302931,0.000053574004,0.0005408177,0.000043614156,0.00022443724,0.00005324061,0.000105203624,0.00002547736],"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":[0.00043865104,0.0004316139,0.09845335,0.000005633981,0.000012387683,0.00000236154,0.0006875027,0.0011398002,0.0019450206,0.007118654,0.30129024,0.5884748],"study_design_scores_gemma":[0.00061753724,0.001086615,0.3184436,0.000040822983,0.00004457899,0.0001053425,0.00071941904,0.022784762,0.000031259653,0.64946395,0.0064502372,0.00021187283],"about_ca_topic_score_codex":0.0000560406,"about_ca_topic_score_gemma":0.000007992173,"teacher_disagreement_score":0.6423453,"about_ca_system_score_codex":0.000032614225,"about_ca_system_score_gemma":0.00024883187,"threshold_uncertainty_score":0.96736926},"labels":[],"label_agreement":null},{"id":"W2034257998","doi":"10.1111/emip.12052","title":"What Role Does, and Should, the Test <i>Standards</i> Play Outside of the United States of America?","year":2014,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":19,"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":"Citation; Library science; Test (biology); Sociology; Political science; History; Computer science","score_opus":0.33892563741599147,"score_gpt":0.4786025746879919,"score_spread":0.13967693727200042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034257998","genre_codex":"commentary","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":[0.37470424,0.032265205,0.0033140585,0.5672406,0.004421299,0.000997756,0.00012210575,0.000029396588,0.016905345],"genre_scores_gemma":[0.98721725,0.0025941266,0.0072629326,0.0022705644,0.00017844782,0.000011331847,0.000002689145,0.000007372052,0.0004553016],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99601364,0.0011934075,0.00045003762,0.00023513711,0.001984146,0.0001236305],"domain_scores_gemma":[0.89833283,0.09821402,0.0008656449,0.0005233313,0.0019970099,0.00006715506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016177876,0.000100786354,0.00019704615,0.000110084904,0.00021389639,0.00022595905,0.00037304062,0.00002971321,0.000100645215],"category_scores_gemma":[0.28618333,0.00004396259,0.000035836027,0.0008843489,0.00025941757,0.0003892498,0.00010587816,0.00013328719,0.0000013578052],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005335416,0.0012740765,0.4425583,0.00012908662,0.0003596289,4.3917987e-7,0.032220393,0.0010273219,0.009417335,0.011302497,0.13903862,0.36213878],"study_design_scores_gemma":[0.00017976777,0.00010921686,0.08928046,0.00007528387,0.000054294294,0.000008853614,0.026277313,0.0002275823,0.0014694398,0.03257034,0.849658,0.00008940934],"about_ca_topic_score_codex":0.0007685683,"about_ca_topic_score_gemma":0.00002208641,"teacher_disagreement_score":0.71061945,"about_ca_system_score_codex":0.000019933232,"about_ca_system_score_gemma":0.00011634884,"threshold_uncertainty_score":0.71982944},"labels":[],"label_agreement":null},{"id":"W2034682623","doi":"10.1080/00223891.2011.594129","title":"The Relationship Between Unstandardized and Standardized Alpha, True Reliability, and the Underlying Measurement Model","year":2011,"lang":"en","type":"article","venue":"Journal of Personality Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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 British Columbia","funders":"","keywords":"Cronbach's alpha; Reliability (semiconductor); Psychology; Temptation; Alpha (finance); Statistics; Psychometrics; Reliability engineering; Social psychology; Mathematics; Developmental psychology; Thermodynamics","score_opus":0.7815611179350717,"score_gpt":0.5234816641650977,"score_spread":0.258079453769974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034682623","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":[0.6406168,0.0016130365,0.34551084,0.008127583,0.00030681276,0.0003174166,0.00001583488,0.000010687056,0.0034810256],"genre_scores_gemma":[0.95189255,0.00013229996,0.04776899,0.000081848666,0.00006413029,0.000004734261,1.1336885e-7,0.0000067615215,0.000048560567],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9919304,0.00286663,0.0013739446,0.0002938921,0.0032772506,0.0002578733],"domain_scores_gemma":[0.9360804,0.06005848,0.0016022982,0.00057662016,0.0014620494,0.00022016783],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.106178395,0.00016143575,0.0005899883,0.0001538066,0.00097218755,0.00045473967,0.0005941783,0.00007251647,0.000022499946],"category_scores_gemma":[0.07248462,0.00007119227,0.00022742756,0.0005247717,0.0006227988,0.00031342177,0.00018241542,0.0005597427,3.571157e-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":[0.0009890454,0.000052696334,0.91133124,0.0000191671,0.00021364752,0.0000043634345,0.0038501448,0.000109241846,0.000027326281,0.033974126,0.000885539,0.048543464],"study_design_scores_gemma":[0.0023265365,0.000102331054,0.6351032,0.000032911434,0.0000903827,0.000019998912,0.003278442,0.0020830117,0.000004649797,0.35631126,0.00056921557,0.000078021774],"about_ca_topic_score_codex":0.000049620026,"about_ca_topic_score_gemma":0.000018302155,"teacher_disagreement_score":0.32233715,"about_ca_system_score_codex":0.0002248442,"about_ca_system_score_gemma":0.00041592933,"threshold_uncertainty_score":0.93532825},"labels":[],"label_agreement":null},{"id":"W2034878828","doi":"10.1111/j.1745-3992.2002.tb00087.x","title":"Scoring Examinee Responses for Multiple Inferences: Multiple Scoring in Assessments","year":2002,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","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":"University of British Columbia","funders":"","keywords":"Scoring system; Inference; Scale (ratio); Computer science; Psychology; Artificial intelligence; Medicine; Geography","score_opus":0.8659566286900213,"score_gpt":0.5782094015970195,"score_spread":0.2877472270930018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034878828","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":[0.9215936,0.015707685,0.016543403,0.025536606,0.004173244,0.001457987,0.000027018057,0.00007369718,0.014886753],"genre_scores_gemma":[0.8953777,0.0003440425,0.10240713,0.00021374527,0.00032598726,0.00012258737,0.0000021834092,0.000010202069,0.0011964265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99605566,0.0009064197,0.00066706305,0.0005724049,0.0014854324,0.00031301135],"domain_scores_gemma":[0.8640235,0.13425532,0.0004048414,0.00034515385,0.0008587765,0.00011241561],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016088754,0.00016576496,0.00026172536,0.0004906423,0.0002692019,0.00041040967,0.00035776105,0.00005859238,0.00024958223],"category_scores_gemma":[0.585434,0.00013777669,0.00004555586,0.0009185281,0.00004507967,0.0010193295,0.00008038079,0.00016392185,0.00002724147],"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":[0.00020768156,0.0004573162,0.8855349,0.000028566534,0.00003440274,0.0000016898053,0.0011800578,0.00012547059,0.0012009979,0.00080148154,0.0035127657,0.106914684],"study_design_scores_gemma":[0.0011866252,0.00023250737,0.82253546,0.00016244037,0.00002507749,0.000020273936,0.0051788106,0.005266111,0.00028204283,0.0074212663,0.1573713,0.0003180987],"about_ca_topic_score_codex":0.0003411385,"about_ca_topic_score_gemma":0.0000915038,"teacher_disagreement_score":0.56934524,"about_ca_system_score_codex":0.00010478553,"about_ca_system_score_gemma":0.00009514834,"threshold_uncertainty_score":0.5618371},"labels":[],"label_agreement":null},{"id":"W2036299295","doi":"10.1177/0013164405275668","title":"A Comparison of Four Methods for Detecting Differential Item Functioning in Ordered Response Items","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":92,"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":"Differential item functioning; Statistics; Psychology; Logistic regression; Item response theory; Type I and type II errors; Linear discriminant analysis; Ordinal regression; Skewness; Ordered logit; Discriminant function analysis; Sample (material); Psychometrics; Mathematics","score_opus":0.8267139799800711,"score_gpt":0.6035828191741548,"score_spread":0.22313116080591633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036299295","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":[0.79982466,0.0007578594,0.19470464,0.003047766,0.00087551516,0.0002670674,0.0000022898992,0.000012888537,0.0005073022],"genre_scores_gemma":[0.8085319,0.0000038056967,0.19099265,0.00008508631,0.00020259163,0.00007145528,7.896008e-7,0.000004391317,0.00010732286],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961089,0.0014275819,0.0009758526,0.00051506417,0.00072661426,0.00024596782],"domain_scores_gemma":[0.9650272,0.033789244,0.00039460324,0.0002350469,0.00045923603,0.0000946554],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01660389,0.000134141,0.0003899913,0.00040209419,0.00016388817,0.00007330627,0.00027669274,0.00009501773,0.000329475],"category_scores_gemma":[0.12302102,0.00009296528,0.00009579861,0.0008843424,0.000066718625,0.000078088735,0.000044280816,0.00017240389,0.0000041914495],"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":[0.0010676607,0.0006333358,0.16812888,0.000008109153,0.000017177272,7.877512e-8,0.0005126914,0.00013147808,0.022228692,0.0003845797,0.0007858325,0.8061015],"study_design_scores_gemma":[0.0008067818,0.00043401364,0.9704582,0.00003370296,0.0000084496005,0.000006885484,0.0007167471,0.002786707,0.00076298544,0.017140092,0.0067100893,0.00013536148],"about_ca_topic_score_codex":0.000008133952,"about_ca_topic_score_gemma":0.000010284618,"teacher_disagreement_score":0.80596614,"about_ca_system_score_codex":0.000066179186,"about_ca_system_score_gemma":0.000042885666,"threshold_uncertainty_score":0.88436615},"labels":[],"label_agreement":null},{"id":"W2036831393","doi":"10.1177/0013164411409929","title":"Difference Scores From the Point of View of Reliability and Repeated-Measures ANOVA","year":2011,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":167,"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":"Reliability (semiconductor); Repeated measures design; Significant difference; Statistics; Psychology; Analysis of variance; Point (geometry); Mean difference; Mathematics; Econometrics; Confidence interval","score_opus":0.7554307011056853,"score_gpt":0.4653795213841227,"score_spread":0.29005117972156264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036831393","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":[0.98860765,0.0039974255,0.0012197683,0.0020714342,0.00040152454,0.000173817,0.000015468398,0.0000072714724,0.0035056574],"genre_scores_gemma":[0.99063116,0.00020932732,0.008859892,0.0002046245,0.000051857536,0.000013131721,8.0293455e-7,0.0000022499346,0.000026950762],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99710447,0.0006320529,0.00067854876,0.00045584215,0.0010029314,0.00012615735],"domain_scores_gemma":[0.99117297,0.0072896974,0.00034830376,0.00049262715,0.0006169453,0.00007945801],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070734816,0.00011133879,0.00028862836,0.000064427,0.00008802751,0.000022873754,0.00042112538,0.000057226753,0.000528036],"category_scores_gemma":[0.038842898,0.000052500855,0.00005942115,0.0004552616,0.0004226591,0.00004238106,0.00008314939,0.00011773344,0.0000028071436],"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":[0.000113094444,0.00047318308,0.8170224,0.000008307061,0.000021197777,1.8183279e-7,0.00078176934,5.0417697e-7,0.0019455802,0.0028460885,0.001250037,0.17553766],"study_design_scores_gemma":[0.00012203341,0.00015764173,0.7876037,0.000037415575,0.000008047821,0.0000026728283,0.00021966433,0.0000029281157,0.00027450657,0.21125218,0.0002680671,0.000051180283],"about_ca_topic_score_codex":0.00025032106,"about_ca_topic_score_gemma":0.00001019118,"teacher_disagreement_score":0.2084061,"about_ca_system_score_codex":0.000009741277,"about_ca_system_score_gemma":0.000032058808,"threshold_uncertainty_score":0.96925336},"labels":[],"label_agreement":null},{"id":"W2037416776","doi":"10.3758/brm.42.3.847","title":"A general framework and an R package for the detection of dichotomous differential item functioning","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":288,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Differential item functioning; R package; Set (abstract data type); Differential (mechanical device); Psychometrics; Item response theory; Computer science; Psychology; Cognitive psychology; Artificial intelligence; Developmental psychology; Programming language","score_opus":0.7240286491433732,"score_gpt":0.6707538589519908,"score_spread":0.05327479019138237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037416776","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":[0.5136876,0.00010002043,0.4848782,0.000043572338,0.00084157684,0.00037792922,0.0000066217603,0.000018839837,0.00004565116],"genre_scores_gemma":[0.6185635,0.000012934645,0.38063976,0.000006831375,0.00033666458,0.00021481661,7.2473847e-7,0.000013181761,0.00021159738],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936786,0.003488145,0.0005347093,0.00056838995,0.0012640557,0.00046606566],"domain_scores_gemma":[0.86268574,0.134658,0.0002576457,0.0012177534,0.00095415435,0.00022673643],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041738793,0.00012762654,0.00030229948,0.0006411377,0.00080209365,0.00040973406,0.00080990925,0.00020886371,0.00020636377],"category_scores_gemma":[0.20133327,0.000074320655,0.00012552261,0.0018749585,0.00045167486,0.00018832265,0.00027658237,0.0010347101,0.0000017504],"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":[0.00005341176,0.00004020192,0.017356362,0.0000030908695,0.000004898132,6.9185495e-7,0.00015712183,5.581072e-7,0.35986242,0.00041274072,0.000017669145,0.6220908],"study_design_scores_gemma":[0.00047067506,0.00080425304,0.8548586,0.000012217964,0.00004442828,0.000029331595,0.0015738779,0.007421458,0.08832646,0.04297403,0.003298538,0.00018613189],"about_ca_topic_score_codex":0.00018595847,"about_ca_topic_score_gemma":0.000052446885,"teacher_disagreement_score":0.83750224,"about_ca_system_score_codex":0.000015362084,"about_ca_system_score_gemma":0.000045698092,"threshold_uncertainty_score":0.9867316},"labels":[],"label_agreement":null},{"id":"W2038108124","doi":"10.1177/107319110000700103","title":"Item Response Theory in Personality Assessment: A Demonstration using the MMPI-2 Depression Scale","year":2000,"lang":"en","type":"article","venue":"Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Minnesota Multiphasic Personality Inventory; Psychology; Item response theory; Personality; Context (archaeology); Scale (ratio); Personality test; Clinical psychology; Personality Assessment Inventory; Psychometrics; Depression (economics); Test (biology); Test validity; Social psychology; Cartography","score_opus":0.37289528017612356,"score_gpt":0.534871238714687,"score_spread":0.16197595853856345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038108124","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":[0.93065554,0.00014264476,0.048136722,0.000773702,0.00022633672,0.00029558621,0.0000062655095,0.000038232054,0.019724945],"genre_scores_gemma":[0.9491652,0.00001794327,0.049881533,0.00028048246,0.00006309111,0.000024594974,0.0000016749117,0.000009707348,0.0005557276],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9903077,0.0064233383,0.0007935138,0.0006279632,0.0014668872,0.00038062915],"domain_scores_gemma":[0.96218306,0.036556132,0.0002827542,0.00077647774,0.00011492958,0.000086631575],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.033363078,0.00017476597,0.00029593304,0.00029090812,0.00043115072,0.00035381573,0.0007224966,0.0001013159,0.0016438197],"category_scores_gemma":[0.007691904,0.0001030728,0.000120773606,0.0019292468,0.00013203535,0.00037609178,0.00011642839,0.00037799182,0.000016545204],"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":[0.00024764548,0.00012869683,0.66759,0.0000025192915,0.000010243898,0.000011653094,0.00042128042,0.0010592045,0.0027838794,0.0006591027,0.00019329984,0.32689247],"study_design_scores_gemma":[0.0003943632,0.000051240448,0.93795514,0.000036205463,0.000010936489,0.000021915537,0.0022275585,0.037056707,0.000110416935,0.020590747,0.0014092348,0.00013552056],"about_ca_topic_score_codex":0.00012769719,"about_ca_topic_score_gemma":0.000035055888,"teacher_disagreement_score":0.32675692,"about_ca_system_score_codex":0.00020858245,"about_ca_system_score_gemma":0.00027052677,"threshold_uncertainty_score":0.99926883},"labels":[],"label_agreement":null},{"id":"W2039891070","doi":"10.3758/bf03192810","title":"SPSS and SAS programs for generalizability theory analyses","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":166,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Generalizability theory; Computer science; Psychology; Developmental psychology","score_opus":0.9596454361401149,"score_gpt":0.7860996307771648,"score_spread":0.17354580536295006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039891070","genre_codex":"empirical","genre_gemma":"methods","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":[0.53096986,0.0018392132,0.46192923,0.00016409303,0.00026971044,0.00120033,0.000017377333,0.00008295241,0.0035272632],"genre_scores_gemma":[0.08487267,0.000017585404,0.90919673,0.00001970989,0.00020056318,0.0005560144,0.000006884723,0.00002165477,0.0051081814],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98177874,0.0137589285,0.0008415174,0.0010433798,0.0017319266,0.0008454998],"domain_scores_gemma":[0.89558405,0.10147211,0.00019917676,0.0012035792,0.0013022721,0.00023882955],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14207996,0.00018254081,0.0005040048,0.000957665,0.0005476671,0.0006173577,0.00096600346,0.00015012221,0.00019782264],"category_scores_gemma":[0.15501313,0.00012058576,0.00021610637,0.0036897727,0.0007379934,0.0001900689,0.0004272142,0.00034880606,0.000007480075],"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":[0.00005243669,0.00016504627,0.11431914,0.0000089318455,0.0000065314525,0.0000046802165,0.000048626345,0.0000032703786,0.010093153,0.0034071368,0.0017797992,0.8701112],"study_design_scores_gemma":[0.00044884215,0.0002892646,0.38407546,0.000007947978,0.000030188243,0.000015343232,0.0008686789,0.00052961643,0.007087787,0.57022524,0.036201548,0.0002200477],"about_ca_topic_score_codex":0.0004167868,"about_ca_topic_score_gemma":0.00002452196,"teacher_disagreement_score":0.8698912,"about_ca_system_score_codex":0.000057628815,"about_ca_system_score_gemma":0.00009150364,"threshold_uncertainty_score":0.8834092},"labels":[],"label_agreement":null},{"id":"W2041006315","doi":"10.1002/jhbs.1098","title":"Measurement in psychology: A critical history of a methodological concept","year":2002,"lang":"en","type":"article","venue":"Journal of the History of the Behavioral Sciences","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":135,"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 Calgary","funders":"","keywords":"History of psychology; Citation; Psychology; Library science; Sociology; Psychoanalysis; Computer science","score_opus":0.9088941765489551,"score_gpt":0.5587217495193746,"score_spread":0.3501724270295805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041006315","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":[0.8621019,0.06722978,0.0024244853,0.011026564,0.04392702,0.00037360511,0.000005192367,0.000014845686,0.012896614],"genre_scores_gemma":[0.97927284,0.000035854595,0.019090435,0.00033972468,0.00006628421,0.0000017287504,3.8779064e-9,0.000004270514,0.0011888449],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9910107,0.0036306966,0.0015825391,0.0003053737,0.00317902,0.0002916384],"domain_scores_gemma":[0.99119705,0.0053946706,0.0020633335,0.00062493316,0.00062066765,0.00009934958],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030541144,0.00014180194,0.00066724495,0.00049001764,0.000098723314,0.00001300197,0.0038275495,0.00011207979,0.0006879866],"category_scores_gemma":[0.06613621,0.00006412822,0.00053187035,0.0013019318,0.0041321525,0.00023633723,0.00027255696,0.00049012754,0.0000023518412],"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":[0.00025584255,0.0026201576,0.2481384,0.00002583218,0.000032399363,0.000036996178,0.011303709,0.0005087244,0.073620155,0.0012909916,0.47169533,0.19047146],"study_design_scores_gemma":[0.0023212624,0.0035682996,0.7230331,0.00070183043,0.00027945792,0.0006062029,0.003121234,0.0007757766,0.001224161,0.054759055,0.20896137,0.00064831815],"about_ca_topic_score_codex":0.00008015394,"about_ca_topic_score_gemma":0.000017408103,"teacher_disagreement_score":0.47489464,"about_ca_system_score_codex":0.0010174896,"about_ca_system_score_gemma":0.00037939838,"threshold_uncertainty_score":0.998578},"labels":[],"label_agreement":null},{"id":"W2042334535","doi":"10.1037/a0014269","title":"A proposed framework for conducting data-based test analysis.","year":2008,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Extant taxon; Computer science; Test theory; Test data; Data mining; Psychometrics; Statistics; Mathematics; Software engineering","score_opus":0.9565826883810709,"score_gpt":0.7111345330937316,"score_spread":0.2454481552873392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042334535","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":[0.038662445,0.00037057645,0.9553593,0.0013298559,0.0010498825,0.0005131687,0.000065770706,0.00023619308,0.0024128202],"genre_scores_gemma":[0.18635736,0.000010968673,0.81178796,0.001327331,0.0002629391,0.000039529157,0.000019146188,0.000015936912,0.00017884946],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9914123,0.0033479927,0.001419141,0.002070588,0.0010346805,0.00071532116],"domain_scores_gemma":[0.6658209,0.32879803,0.00091378624,0.0036056393,0.00054292893,0.00031874626],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03781359,0.0003193908,0.0011721522,0.00093750894,0.00057515263,0.00018469113,0.0034264436,0.00037883018,0.0008598824],"category_scores_gemma":[0.69519436,0.00019689795,0.00048519467,0.010056076,0.00043950006,0.00021868784,0.00035424382,0.0005752073,0.00004839182],"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":[0.00018209228,0.00080795796,0.19245046,0.000009683715,0.00022818682,0.000035102446,0.00013149505,0.00030971918,0.0015427574,0.0024691774,0.006091946,0.79574144],"study_design_scores_gemma":[0.0018177568,0.0014009337,0.3585839,0.000025352625,0.00051126746,0.00006721015,0.0005433851,0.06759359,0.0017669871,0.51951885,0.047070842,0.0010999043],"about_ca_topic_score_codex":0.000007286564,"about_ca_topic_score_gemma":6.1420224e-7,"teacher_disagreement_score":0.7946415,"about_ca_system_score_codex":0.000024965513,"about_ca_system_score_gemma":0.00004560177,"threshold_uncertainty_score":0.9907734},"labels":[],"label_agreement":null},{"id":"W2043112308","doi":"10.2466/03.pr0.107.5.535-546","title":"Scale Validation via Quantifying Item Validity Using the <i> D <sub>m</sub> </i> Index","year":2010,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"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":"Criterion validity; Psychology; Construct validity; Scale (ratio); Index (typography); Statistics; External validity; Test validity; Item response theory; Psychometrics; Computer science; Social psychology; Mathematics; Clinical psychology","score_opus":0.6332346981021989,"score_gpt":0.5183237432852831,"score_spread":0.11491095481691582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043112308","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":[0.8746978,0.000032479227,0.115732946,0.0004696797,0.0048895064,0.00028472327,0.0000017793632,0.00015051778,0.0037405442],"genre_scores_gemma":[0.9874748,0.000011358024,0.011511403,0.0004946729,0.0004287364,0.000016272616,0.0000024655355,0.000017303213,0.000042961175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99386257,0.0009451171,0.0015283335,0.0012546607,0.0018229691,0.0005863607],"domain_scores_gemma":[0.977937,0.018070465,0.0013762844,0.0019314559,0.00044456916,0.00024024649],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021115875,0.00027318293,0.00048109083,0.00029166215,0.000635134,0.0004986913,0.0008683054,0.000348524,0.00025446332],"category_scores_gemma":[0.10127179,0.00013377398,0.00028855554,0.0027093727,0.0003290789,0.00031757803,0.00029202295,0.0009766524,0.000057493253],"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":[0.000021648502,0.00013056895,0.53254145,0.00000205325,0.0000069606913,0.00012698832,0.000054140004,0.00006720002,0.23400518,0.000032573647,0.0012321163,0.2317791],"study_design_scores_gemma":[0.00023788131,0.00011368829,0.8446349,0.00001657783,0.000027452157,0.0026540775,0.00016543109,0.002774783,0.044411708,0.09866341,0.0058514834,0.000448591],"about_ca_topic_score_codex":0.000028135,"about_ca_topic_score_gemma":0.00001267699,"teacher_disagreement_score":0.31209344,"about_ca_system_score_codex":0.000024910443,"about_ca_system_score_gemma":0.000028827279,"threshold_uncertainty_score":0.9062986},"labels":[],"label_agreement":null},{"id":"W2044962840","doi":"10.1016/j.jcps.2010.03.003","title":"Some things you should know about structural equation modeling but never thought to ask","year":2010,"lang":"en","type":"article","venue":"Journal of Consumer Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada; Ontario Problem Gambling Research Centre","keywords":"Structural equation modeling; Ask price; Psychology; Sample (material); Causal model; Epistemology; Computer science; Mathematics; Statistics; Philosophy; Economics","score_opus":0.4069029522542973,"score_gpt":0.5005120825237724,"score_spread":0.09360913026947515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044962840","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":[0.8508249,0.0018974275,0.12672389,0.008226991,0.011060037,0.00013336635,0.0000050111416,0.000028874565,0.001099506],"genre_scores_gemma":[0.8429693,0.00019008122,0.14618118,0.008475714,0.0014621662,0.000003157142,7.030203e-7,0.000026820984,0.00069086836],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953356,0.00055779755,0.0017528425,0.0005033958,0.0013523374,0.00049804134],"domain_scores_gemma":[0.9900472,0.0064983736,0.0011908318,0.000732626,0.0011929368,0.00033802656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010020649,0.00023983575,0.00068435946,0.0013152038,0.00019969154,0.00023840176,0.0014915885,0.00031995456,0.00054062845],"category_scores_gemma":[0.047377273,0.00016172983,0.00026808112,0.0012733117,0.00013269576,0.0016441734,0.0001395911,0.001288944,0.00014310775],"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":[0.0006431093,0.000114768714,0.07292837,0.000008111561,0.000189756,0.00009899939,0.0013128895,0.0026440648,0.046285428,0.009137635,0.025432069,0.8412048],"study_design_scores_gemma":[0.0044235047,0.0009539404,0.16314884,0.00012279785,0.00017365141,0.0032509838,0.0012347908,0.058412317,0.0010021436,0.5031003,0.26300016,0.0011765879],"about_ca_topic_score_codex":0.000025058087,"about_ca_topic_score_gemma":0.0000049825294,"teacher_disagreement_score":0.8400282,"about_ca_system_score_codex":0.000025602114,"about_ca_system_score_gemma":0.00011632291,"threshold_uncertainty_score":0.96064705},"labels":[],"label_agreement":null},{"id":"W2045458669","doi":"10.1177/0013164409355689","title":"Construct Commensurability and the Analysis of Change","year":2009,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"University of British Columbia","keywords":"Commensurability (mathematics); Construct (python library); Construct validity; Perspective (graphical); Psychology; Epistemology; Computer science; Psychometrics; Developmental psychology; Mathematics; Artificial intelligence","score_opus":0.8713064096796247,"score_gpt":0.5426906703775654,"score_spread":0.32861573930205934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045458669","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":[0.9444911,0.002050738,0.0004554794,0.046292927,0.00028041343,0.00021557197,0.000008392341,0.0000070067117,0.006198356],"genre_scores_gemma":[0.9960361,0.00006204933,0.0023317155,0.0014802987,0.00005910245,0.000012683387,9.596286e-7,6.881467e-7,0.00001641447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976861,0.00063541986,0.00044362634,0.00031935918,0.0008038876,0.00011159025],"domain_scores_gemma":[0.9897334,0.009370411,0.00020761971,0.00028827737,0.00032918263,0.00007112291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010055331,0.00007949014,0.00032305773,0.00019401281,0.00012208338,0.00004805479,0.00022817051,0.000033267,0.00026048467],"category_scores_gemma":[0.022415357,0.000036683512,0.00008918479,0.0014297498,0.00040027243,0.00004091449,0.000026868125,0.00009553167,0.0000015524076],"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":[0.00011335349,0.00023816127,0.28718925,0.0000014724195,0.000095942014,1.05867706e-7,0.00036340358,0.0000017304383,0.00004686611,0.027822027,0.0010321692,0.6830955],"study_design_scores_gemma":[0.00027342016,0.00006506579,0.8152519,0.0000026881091,0.000052127634,0.0000024827202,0.000103798775,0.000053899294,0.0000020953644,0.18353467,0.00061896443,0.000038885122],"about_ca_topic_score_codex":0.000017281247,"about_ca_topic_score_gemma":0.0000031745776,"teacher_disagreement_score":0.68305665,"about_ca_system_score_codex":0.00001031129,"about_ca_system_score_gemma":0.000010005382,"threshold_uncertainty_score":0.9858193},"labels":[],"label_agreement":null},{"id":"W2046847367","doi":"10.1177/0013164414523618","title":"Binary Logistic Regression Analysis for Detecting Differential Item Functioning","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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; Differential item functioning; Sample size determination; Type I and type II errors; Logistic regression; Mathematics; Statistical power; Statistical hypothesis testing; Regression analysis; Psychology; Econometrics; Item response theory; Psychometrics","score_opus":0.7639754128351917,"score_gpt":0.5122407613224709,"score_spread":0.2517346515127208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046847367","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":[0.6241598,0.00029125196,0.3697023,0.0021410126,0.0016554483,0.00017413041,0.0000036163033,0.00003370863,0.0018386743],"genre_scores_gemma":[0.9831123,0.000006904824,0.01571086,0.00022689908,0.00055914884,0.000068984795,0.0000066363295,0.00000504428,0.00030322725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968578,0.0005254154,0.00057160394,0.0007165021,0.0010654276,0.00026323614],"domain_scores_gemma":[0.9817921,0.016881417,0.00032244824,0.00034041647,0.0005095615,0.00015403917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006831338,0.00015848206,0.0003356064,0.00046037737,0.0004966154,0.00017856807,0.000298738,0.000093054536,0.0006398659],"category_scores_gemma":[0.08741688,0.000093967996,0.00018749737,0.0013966622,0.00008093782,0.00006725208,0.000056481786,0.00014129092,0.000015442529],"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":[0.00025873067,0.0006081151,0.53628665,0.000016851023,0.00021519283,3.6550307e-7,0.00014163075,0.00043744076,0.0037880188,0.0050985976,0.0051787165,0.4479697],"study_design_scores_gemma":[0.00031645037,0.00031645776,0.9364413,0.00001710218,0.00008326254,0.000003941901,0.00013140254,0.0033820306,0.00002667797,0.05620732,0.002932264,0.0001417942],"about_ca_topic_score_codex":0.0000073226997,"about_ca_topic_score_gemma":0.0000032726625,"teacher_disagreement_score":0.4478279,"about_ca_system_score_codex":0.00004066225,"about_ca_system_score_gemma":0.000016466529,"threshold_uncertainty_score":0.9202702},"labels":[],"label_agreement":null},{"id":"W2047205523","doi":"10.7202/1024466ar","title":"Estimation des paramètres d’item et de sujet à partir du modèle de Rasch","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","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":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Art","score_opus":0.5373759280934739,"score_gpt":0.5199049296086186,"score_spread":0.017470998484855338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047205523","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":[0.43952677,0.00062645157,0.53641176,0.01707372,0.0015872377,0.00025487065,0.000008734882,0.00008767914,0.0044227815],"genre_scores_gemma":[0.788124,0.0002843929,0.2086344,0.0007285012,0.00036234016,0.00007416826,0.000064298016,0.00002859397,0.0016992558],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9703934,0.025870979,0.0010586249,0.00071952265,0.0013268755,0.0006305599],"domain_scores_gemma":[0.9337403,0.063556135,0.00084407575,0.00077536725,0.00084141345,0.00024266739],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13111317,0.0003079261,0.00041343333,0.000560018,0.00041772705,0.0006278289,0.0005467769,0.0003384253,0.00072406395],"category_scores_gemma":[0.3122251,0.00029199632,0.00015804709,0.0019433971,0.00018422923,0.001172072,0.00008777267,0.0003677608,0.00031426793],"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":[0.000028553637,0.00024158446,0.151881,0.00006174471,0.000031453674,8.465966e-7,0.048429027,0.08892968,0.0005731467,0.015628356,0.010986063,0.6832085],"study_design_scores_gemma":[0.00031313533,0.00008147517,0.45909262,0.00007760289,0.000059155107,0.000022031816,0.0009347064,0.40513462,0.0005227386,0.1272677,0.006310579,0.00018365042],"about_ca_topic_score_codex":0.0006772375,"about_ca_topic_score_gemma":0.0002497745,"teacher_disagreement_score":0.6830249,"about_ca_system_score_codex":0.00062731653,"about_ca_system_score_gemma":0.0012504224,"threshold_uncertainty_score":0.9999532},"labels":[],"label_agreement":null},{"id":"W2048301263","doi":"10.1097/00001888-200310001-00021","title":"An Evaluation of Local Item Dependencies in the Medical Council of Canada Qualifying Examination Part I","year":2003,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Statistic; Test (biology); Residual; Psychology; Curse of dimensionality; Medicine; Statistics; Computer science; Mathematics","score_opus":0.7671910957259485,"score_gpt":0.5281969235879826,"score_spread":0.2389941721379658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048301263","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":[0.96947235,0.0018957958,0.017538797,0.0009910933,0.00056685787,0.00018635741,0.0000017430108,0.00000518913,0.009341804],"genre_scores_gemma":[0.99919885,0.0000795898,0.00013401762,0.00043390182,0.00008597669,0.000009035669,0.0000016047843,0.000003375537,0.000053641004],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97531354,0.0061822417,0.0017837676,0.00037956575,0.016046278,0.00029461784],"domain_scores_gemma":[0.94688135,0.050450146,0.0007170592,0.0004823863,0.0013526418,0.00011641712],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19214028,0.00009335615,0.00035632917,0.00021707323,0.000051683935,0.0000037434804,0.00082572026,0.00016131697,0.0006276398],"category_scores_gemma":[0.52290756,0.000050427356,0.000017847395,0.0018987224,0.00025075578,0.0001182571,0.000022249738,0.00040423952,5.9365533e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004310636,0.00005867273,0.21003866,0.00006964149,0.000030507246,0.00002178201,0.03710512,0.0017848312,0.0014246807,0.016774843,0.023893142,0.708755],"study_design_scores_gemma":[0.0038633223,0.0005228777,0.4743492,0.00068357814,0.00011579074,0.00015304604,0.3574352,0.07857206,0.0023138141,0.06783411,0.013820715,0.0003362732],"about_ca_topic_score_codex":0.027268412,"about_ca_topic_score_gemma":0.035181265,"teacher_disagreement_score":0.7084187,"about_ca_system_score_codex":0.00027587725,"about_ca_system_score_gemma":0.0031284299,"threshold_uncertainty_score":0.98242414},"labels":[],"label_agreement":null},{"id":"W2050080230","doi":"10.1037/h0088134","title":"Review of Understanding psychological research: An introduction to methods.","year":2001,"lang":"en","type":"article","venue":"Canadian Psychology/Psychologie canadienne","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Psychology; Applied psychology; Psychotherapist; Psychoanalysis","score_opus":0.9079141575623906,"score_gpt":0.6652092897416002,"score_spread":0.24270486782079037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050080230","genre_codex":"commentary","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":[0.24352354,0.026444048,0.14935267,0.35530633,0.023981642,0.004337219,0.00024635717,0.0005504853,0.19625773],"genre_scores_gemma":[0.67777866,0.014385937,0.20011209,0.10121954,0.003463788,0.00036954312,0.00009257509,0.00021603655,0.0023618168],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9844651,0.006335608,0.0021911317,0.003074737,0.0010357554,0.002897631],"domain_scores_gemma":[0.98071957,0.0086916825,0.00059855514,0.004780034,0.0016230798,0.0035871076],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.060885046,0.0005206526,0.0013188946,0.0058455863,0.0006346424,0.00015782578,0.004280748,0.0006132103,0.00453225],"category_scores_gemma":[0.15207784,0.00043743654,0.00029382354,0.016361758,0.000964602,0.0004223416,0.00018167705,0.0013555114,0.0003348218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012401697,0.00013315723,0.004387099,0.00004820015,0.00003598242,0.00015096016,0.00024601232,0.000012361037,0.0008716498,0.014730408,0.5807305,0.39852965],"study_design_scores_gemma":[0.00057893427,0.0016630089,0.04403783,0.00030185937,0.000023834682,0.0007126591,0.0020614034,0.000026864229,0.000022119086,0.15047377,0.7994771,0.000620587],"about_ca_topic_score_codex":0.018706156,"about_ca_topic_score_gemma":0.121169396,"teacher_disagreement_score":0.43425512,"about_ca_system_score_codex":0.001273216,"about_ca_system_score_gemma":0.0003592567,"threshold_uncertainty_score":0.9998077},"labels":[],"label_agreement":null},{"id":"W2053005742","doi":"10.1177/0829573508324458","title":"Test Review: Reynolds, C. R., &amp; Kamphaus, R. W. (2003). RIAS: Reynolds Intellectual Assessment Scales. Lutz, FL: Psychological Assessment Resources, Inc","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reynolds number; Psychology; Mechanics; Turbulence; Physics","score_opus":0.41102439812288927,"score_gpt":0.5055293015693693,"score_spread":0.09450490344648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053005742","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":[0.6319504,0.09083564,0.059950776,0.047568135,0.023345275,0.002355243,0.0003188581,0.00025093756,0.14342473],"genre_scores_gemma":[0.64920145,0.036795456,0.26300266,0.040577803,0.0033697116,0.00006814868,0.000044847497,0.0001820178,0.0067578773],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98752093,0.0028940986,0.0042825188,0.0014730169,0.0021971562,0.0016322865],"domain_scores_gemma":[0.9728068,0.013792091,0.0035116486,0.0026329057,0.0037725747,0.003483993],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019542372,0.00068557705,0.0019756581,0.003091974,0.00087797095,0.00031694295,0.0041748527,0.00070218137,0.010250337],"category_scores_gemma":[0.25003263,0.00051809195,0.0004705933,0.008015662,0.0012008755,0.00053493713,0.00018028238,0.0029487885,0.00082000217],"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":[0.00004177848,0.00017286834,0.2087259,0.000015178075,0.00006274711,0.00066148903,0.000108335254,0.00001209251,0.00008495748,0.00006601604,0.7633941,0.026654523],"study_design_scores_gemma":[0.0011632586,0.0009223912,0.45062512,0.00028441215,0.000042395488,0.004915814,0.0001951849,0.000017494789,0.0000022712131,0.0021176015,0.5392967,0.00041739622],"about_ca_topic_score_codex":0.0005560285,"about_ca_topic_score_gemma":0.002076958,"teacher_disagreement_score":0.24189922,"about_ca_system_score_codex":0.00071414816,"about_ca_system_score_gemma":0.002467327,"threshold_uncertainty_score":0.999958},"labels":[],"label_agreement":null},{"id":"W2053906918","doi":"10.1207/s15324818ame1703_2","title":"Performance of SIBTEST When the Percentage of DIF Items is Large","year":2004,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differential item functioning; Statistics; Psychology; Item response theory; Test (biology); Mathematics; Psychometrics","score_opus":0.3321836598049474,"score_gpt":0.4109344435671419,"score_spread":0.07875078376219452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053906918","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":[0.9838824,0.00031566058,0.0010914255,0.0005940866,0.00050738064,0.00033187887,0.0000026865694,0.000007670061,0.013266777],"genre_scores_gemma":[0.9955154,0.000053251944,0.0040766946,0.00020811245,0.0000530021,0.000035847253,0.000001453847,0.0000052928604,0.000050933304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99745446,0.00008611271,0.0006589605,0.00024643462,0.0013726667,0.000181364],"domain_scores_gemma":[0.99773616,0.0009921847,0.00042165033,0.00053376536,0.00028437053,0.000031898806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008470052,0.00009000178,0.00020229128,0.00027674926,0.000068805486,0.000023383098,0.000544811,0.000042627704,0.000113801136],"category_scores_gemma":[0.004016101,0.00005734235,0.000045559827,0.0009164349,0.000055821976,0.00008708298,0.000051597304,0.00010316695,0.000018113033],"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":[0.0000604955,0.0013008071,0.6753676,0.000067460314,0.000019093557,5.382973e-8,0.011701315,0.0003834654,0.04315415,0.0058060433,0.0029775042,0.25916204],"study_design_scores_gemma":[0.0006949356,0.00008189143,0.93697935,0.000099992016,0.000013562057,0.0000010680244,0.011240992,0.00010860805,0.021653365,0.02301773,0.0059746015,0.00013388664],"about_ca_topic_score_codex":0.00012259648,"about_ca_topic_score_gemma":0.000023959226,"teacher_disagreement_score":0.2616118,"about_ca_system_score_codex":0.00011351701,"about_ca_system_score_gemma":0.00022575862,"threshold_uncertainty_score":0.4807938},"labels":[],"label_agreement":null},{"id":"W2055526333","doi":"10.7202/1025005ar","title":"Item response theory in educational assessment and evaluation","year":2014,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Equating; Item response theory; Polytomous Rasch model; Differential item functioning; Item bank; Variance (accounting); Test (biology); Computerized adaptive testing; Classical test theory; Econometrics; Computer science; Educational assessment; Psychology; Psychometrics; Statistics; Mathematics education; Mathematics; Rasch model; Clinical psychology","score_opus":0.5154681060706208,"score_gpt":0.5912371517400445,"score_spread":0.07576904566942377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055526333","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":[0.9319968,0.000116103525,0.045544874,0.012811779,0.0010034967,0.00043378462,0.0000019056369,0.00002361024,0.008067596],"genre_scores_gemma":[0.97936636,0.000014553515,0.019515503,0.00031361706,0.00011975394,0.00010949271,0.000029781057,0.000009916996,0.0005210461],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.946663,0.049258776,0.00090529484,0.00068177696,0.002274224,0.00021692785],"domain_scores_gemma":[0.8542752,0.14369732,0.00049946335,0.0005831738,0.00087065826,0.000074177275],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3340422,0.00013323264,0.0002124368,0.00093873666,0.00013001422,0.00019906863,0.00025988166,0.000100792735,0.0007186264],"category_scores_gemma":[0.325814,0.00011071083,0.000041182288,0.0013980857,0.00004397123,0.00053804996,0.00005168249,0.00018265782,0.000043901084],"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":[0.00014376438,0.00017435299,0.41263375,0.0000069721877,0.0000115008,9.4917546e-8,0.018042052,0.0018216114,0.0016877506,0.03848671,0.0019948983,0.5249965],"study_design_scores_gemma":[0.00039317037,0.000043462805,0.74754906,0.000014476832,0.000011347522,0.0000030913607,0.00094295916,0.03235268,0.000024032151,0.21779664,0.00077704433,0.000092014365],"about_ca_topic_score_codex":0.000019580011,"about_ca_topic_score_gemma":0.000036723708,"teacher_disagreement_score":0.5249045,"about_ca_system_score_codex":0.00033849408,"about_ca_system_score_gemma":0.0009625778,"threshold_uncertainty_score":0.78684556},"labels":[],"label_agreement":null},{"id":"W2055728918","doi":"10.1177/0146621608329503","title":"A Monte Carlo Study of the Effect of Item Characteristic Curve Estimation on the Accuracy of Three Person-Fit Statistics","year":2009,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"","keywords":"Nonparametric statistics; Statistics; Monte Carlo method; Logistic regression; Parametric statistics; Mathematics; Item response theory; Sample size determination; Econometrics; Psychometrics","score_opus":0.5775002634706006,"score_gpt":0.46070135321883504,"score_spread":0.11679891025176553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055728918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98827547,0.000054982425,0.007697321,0.00028349753,0.00029072494,0.0015999798,0.000022135593,0.00001690672,0.0017589828],"genre_scores_gemma":[0.99816644,0.0000026173368,0.00163128,0.000107071726,0.00002555605,0.000055028613,2.886549e-7,0.0000061132037,0.000005601178],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99422616,0.0011577796,0.001064465,0.0004977254,0.0028097222,0.00024415922],"domain_scores_gemma":[0.97179776,0.025224745,0.0013926706,0.0011685318,0.00036210538,0.0000541638],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01248888,0.00022895006,0.0006595029,0.00014776498,0.0001329312,0.00003660661,0.001252541,0.00008554746,0.000078255405],"category_scores_gemma":[0.0707149,0.00009583058,0.0001395595,0.0013262447,0.00015411321,0.00003080909,0.000068831585,0.00028850773,0.000007693042],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017630247,0.0025870209,0.10695472,0.00004301629,0.00016960196,0.0000034905302,0.0018104761,0.0020961303,0.014114792,0.0031314557,0.0024352132,0.86489105],"study_design_scores_gemma":[0.000994636,0.003882777,0.9877362,0.00004925694,0.000057376317,0.0000012833182,0.00053565815,0.0011277365,0.0010856125,0.0044071157,0.000015300271,0.00010701658],"about_ca_topic_score_codex":0.000023474995,"about_ca_topic_score_gemma":0.0000048784796,"teacher_disagreement_score":0.88078153,"about_ca_system_score_codex":0.00003942763,"about_ca_system_score_gemma":0.00001352414,"threshold_uncertainty_score":0.93711287},"labels":[],"label_agreement":null},{"id":"W2056084675","doi":"10.4006/1.3028141","title":"An experimental method to test DET","year":2008,"lang":"en","type":"article","venue":"Physics Essays","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Physics; Test (biology); Biology","score_opus":0.5614720588339431,"score_gpt":0.5356198158808655,"score_spread":0.025852242953077642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056084675","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":[0.24057671,0.00007272229,0.68167824,0.00014322191,0.00039692532,0.00014135469,0.000013448732,0.000118666205,0.0768587],"genre_scores_gemma":[0.69266677,0.0000013076296,0.30653104,0.0003228491,0.00026391845,0.000013243589,0.0000011763045,0.000011108791,0.00018857155],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974302,0.00038538864,0.00036675984,0.0005711912,0.00092979096,0.00031666193],"domain_scores_gemma":[0.9847589,0.013941999,0.00013738392,0.0007688527,0.00016351319,0.0002293211],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027636243,0.00014841446,0.00030009417,0.00016664226,0.00028550022,0.00011103752,0.00092366524,0.00004179663,0.00017219102],"category_scores_gemma":[0.01208987,0.00011319608,0.000091567556,0.0020561954,0.000045702123,0.0003129916,0.0001668343,0.00011798649,0.00035598042],"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":[0.000054507684,0.002057675,0.13184452,0.000003866458,0.00002349115,0.00007718246,0.0062284227,0.0031199337,0.2252639,0.041530088,0.029145043,0.56065136],"study_design_scores_gemma":[0.0010149431,0.0015498777,0.02665182,0.000016659014,0.000014133804,0.00011966735,0.0032938803,0.020308059,0.23597002,0.70000017,0.0099958675,0.0010649152],"about_ca_topic_score_codex":0.000039496732,"about_ca_topic_score_gemma":9.0443854e-7,"teacher_disagreement_score":0.6584701,"about_ca_system_score_codex":0.00002703252,"about_ca_system_score_gemma":0.000034574026,"threshold_uncertainty_score":0.99623173},"labels":[],"label_agreement":null},{"id":"W2057483415","doi":"10.1080/14999013.2011.627087","title":"Reaching for the Brass Ring of Psychometric Test Standards: Commenting on Slaney, Storey, and Barnes","year":2011,"lang":"en","type":"article","venue":"International Journal of Forensic Mental Health","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":"Queen's University","funders":"","keywords":"Test (biology); Psychology; Field (mathematics); Test theory; Applied psychology; Computer science; Psychometrics; Clinical psychology; Mathematics","score_opus":0.43563726260672836,"score_gpt":0.5015778292471855,"score_spread":0.06594056664045717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057483415","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":[0.9333411,0.0026098755,0.047117446,0.006695713,0.0063154893,0.0004207737,0.0002477561,0.000012884045,0.0032389604],"genre_scores_gemma":[0.97109336,0.0002780218,0.027788071,0.00056973443,0.00022613874,0.0000015948679,0.0000014141098,0.000008482984,0.00003319348],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965639,0.00018833754,0.001148073,0.00018204418,0.0017174829,0.00020014161],"domain_scores_gemma":[0.97982943,0.017375961,0.0017830515,0.00017402072,0.0007287206,0.000108829474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013194735,0.00011139017,0.0003363371,0.0008459426,0.0002086491,0.00008483326,0.00075337506,0.000029753568,0.000041817784],"category_scores_gemma":[0.024519697,0.00006406678,0.00013255492,0.00049477385,0.00010356751,0.00018649816,0.000105847554,0.0002111472,6.1892877e-7],"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":[0.0003463986,0.00012446522,0.124365374,0.000014254397,0.00009731791,0.000002657884,0.0020756274,0.000011032327,0.00007650573,0.0017360662,0.006473184,0.86467713],"study_design_scores_gemma":[0.0073446897,0.0068423734,0.85810894,0.0015006847,0.00005485025,0.0009446237,0.016061231,0.00427737,0.0028961843,0.06600976,0.03552109,0.00043820587],"about_ca_topic_score_codex":0.00013599465,"about_ca_topic_score_gemma":0.00002363516,"teacher_disagreement_score":0.8642389,"about_ca_system_score_codex":0.00016325973,"about_ca_system_score_gemma":0.00009090656,"threshold_uncertainty_score":0.9836972},"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":"W2059908715","doi":"10.1097/brs.0b013e3181732a3b","title":"Computerized Adaptive Testing in Back Pain","year":2008,"lang":"en","type":"article","venue":"Spine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Arthritis Research Centre of Canada; University of British Columbia","funders":"Michael Smith Health Research BC","keywords":"Medicine; Back pain; Physical therapy; Physical medicine and rehabilitation; Alternative medicine; Pathology","score_opus":0.7219829462460442,"score_gpt":0.4569418048655596,"score_spread":0.2650411413804846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059908715","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":[0.5951011,0.00024110412,0.37183422,0.00039060108,0.0005210564,0.00019088552,0.0000022334534,0.00008033048,0.031638492],"genre_scores_gemma":[0.46705657,0.0000051808133,0.5318119,0.0003258352,0.00010057175,0.0000030368494,5.3316813e-7,0.0000056665194,0.0006907078],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99769,0.00064905063,0.0005254956,0.00037212556,0.0004966735,0.00026665448],"domain_scores_gemma":[0.9836241,0.015612437,0.0001917811,0.00034599807,0.0001544611,0.00007124375],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0076440573,0.00010141723,0.00030370796,0.0003897076,0.00008746766,0.000034622757,0.0004695026,0.000045643166,0.00023677024],"category_scores_gemma":[0.09799694,0.000073473515,0.00004760934,0.0034685729,0.00007726458,0.00010571849,0.00014325038,0.00013985671,0.00019311429],"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":[0.000024855182,0.00006613625,0.272626,0.0000035891817,0.000005323118,0.00012617977,0.00022976253,0.00056110485,0.0013620508,0.00022761864,0.0071322345,0.71763515],"study_design_scores_gemma":[0.0009242074,0.0003056073,0.8979914,0.000046157795,8.894833e-7,0.00005261767,0.00018745485,0.08535484,0.00008047372,0.009698877,0.0051609925,0.00019648032],"about_ca_topic_score_codex":0.00008370022,"about_ca_topic_score_gemma":0.00000688003,"teacher_disagreement_score":0.71743864,"about_ca_system_score_codex":0.000022212462,"about_ca_system_score_gemma":0.000037048256,"threshold_uncertainty_score":0.90960103},"labels":[],"label_agreement":null},{"id":"W2061477359","doi":"10.1371/journal.pone.0058067","title":"The Center for Epidemiologic Studies Depression Scale: A Review with a Theoretical and Empirical Examination of Item Content and Factor Structure","year":2013,"lang":"en","type":"review","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":552,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regina Qu'Appelle Health Region; University of Regina","funders":"","keywords":"Differential item functioning; Anhedonia; Center for Epidemiologic Studies Depression Scale; Clinical psychology; Item response theory; Psychology; PsycINFO; Psychometrics; Confirmatory factor analysis; Scale (ratio); Depressive symptoms; Medicine; Psychiatry; MEDLINE; Structural equation modeling; Anxiety; Statistics","score_opus":0.8519675177471471,"score_gpt":0.5481175019615244,"score_spread":0.30385001578562265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061477359","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058023836,0.99137944,0.00030389652,0.00031191428,0.00004637334,0.0020138102,0.00009648666,0.000012145281,0.000033562257],"genre_scores_gemma":[0.00068464555,0.98800635,0.010905528,0.00010814981,0.00004409229,0.0001833303,0.0000061860555,0.000012167868,0.000049572343],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9951573,0.0022151703,0.0011411817,0.00059248076,0.000659908,0.00023395487],"domain_scores_gemma":[0.8756728,0.12221717,0.0010449749,0.00042283343,0.0005617713,0.00008043242],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005837948,0.0002808633,0.002503122,0.00013464574,0.00015759982,0.00006558825,0.00039414328,0.00017375566,0.000025908841],"category_scores_gemma":[0.20270675,0.00009667219,0.0001324104,0.00047677592,0.0006143294,0.000066405686,0.00026850245,0.00025183544,8.481028e-7],"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":[0.0000090259255,0.00004490474,0.0036679294,0.009664284,0.00018369997,2.849137e-7,0.000031842446,3.878146e-9,0.0000017047311,0.00012483388,0.0002792567,0.98599225],"study_design_scores_gemma":[0.0029823324,0.0041098464,0.07951432,0.54318726,0.009755117,0.00026390093,0.0016818299,0.00066096184,0.000052062067,0.0545796,0.30080143,0.0024113653],"about_ca_topic_score_codex":5.427619e-7,"about_ca_topic_score_gemma":9.710417e-7,"teacher_disagreement_score":0.9835809,"about_ca_system_score_codex":0.000020509378,"about_ca_system_score_gemma":0.000024396075,"threshold_uncertainty_score":0.8040092},"labels":[],"label_agreement":null},{"id":"W2061509267","doi":"10.1097/00001888-200310001-00020","title":"Differential Weighting of Errors on a Test of Clinical Reasoning Skills","year":2003,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Weighting; Test (biology); Item response theory; Differential (mechanical device); Differential item functioning; Computer science; Statistics; Psychology; Mathematics; Artificial intelligence; Medicine; Psychometrics","score_opus":0.48362058604734554,"score_gpt":0.5582844268692446,"score_spread":0.07466384082189909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061509267","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":[0.96924376,0.00036287316,0.0076712826,0.00035835983,0.0014427074,0.000119825876,0.000003020966,0.000021821861,0.020776324],"genre_scores_gemma":[0.9929595,0.00018579123,0.005400791,0.00021642116,0.00036764232,0.0000020781308,8.5482156e-7,0.000010242073,0.00085670437],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938087,0.0009836026,0.0027605342,0.00051215925,0.0016256783,0.00030936734],"domain_scores_gemma":[0.8720975,0.124923006,0.0019137533,0.00061009993,0.00026655098,0.00018911275],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01880088,0.00016262638,0.0010603213,0.0005384595,0.000057522408,0.0000035592427,0.0007777026,0.00027768651,0.00093860365],"category_scores_gemma":[0.70853037,0.00009448741,0.0001318957,0.0018781157,0.00042290243,0.00006264285,0.00008593822,0.0008256743,0.00001474037],"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":[0.000034708795,0.00005329633,0.9043301,0.000014462779,0.000023249244,0.000004187815,0.00084456376,0.00000948172,0.0035572706,0.005962529,0.0063484255,0.078817755],"study_design_scores_gemma":[0.005248675,0.0025883946,0.86743397,0.0020893735,0.00013934032,0.000056951892,0.006776743,0.001732312,0.015874863,0.0872156,0.010385098,0.0004586702],"about_ca_topic_score_codex":0.000027564392,"about_ca_topic_score_gemma":4.3934378e-7,"teacher_disagreement_score":0.68972945,"about_ca_system_score_codex":0.000010284629,"about_ca_system_score_gemma":0.000062892446,"threshold_uncertainty_score":0.99997467},"labels":[],"label_agreement":null},{"id":"W2062328254","doi":"10.2466/pr0.2002.90.1.105","title":"Overt Honesty Measures Predicting Admissions: An Index of Validity or Reliability","year":2002,"lang":"en","type":"article","venue":"Psychological Reports","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":"Western University; Royal Military College of Canada","funders":"","keywords":"Honesty; Psychology; Reliability (semiconductor); Criterion validity; Index (typography); Validity; Social psychology; Applied psychology; Clinical psychology; Psychometrics; Internal consistency; Computer science","score_opus":0.7840825416863647,"score_gpt":0.5405867532859306,"score_spread":0.24349578840043407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062328254","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":[0.9708403,0.00019185031,0.010247571,0.00040595175,0.0014724782,0.00029874538,0.000005755935,0.00020637161,0.01633101],"genre_scores_gemma":[0.9846867,0.00006185882,0.014068169,0.0002518409,0.00015214119,0.000018022703,0.0000011012256,0.000011428938,0.00074878254],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99199474,0.001593687,0.0021675578,0.0014274534,0.0023331728,0.00048340502],"domain_scores_gemma":[0.9767261,0.017995873,0.0015554085,0.002416025,0.00066296634,0.0006436055],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019938068,0.0002505241,0.0007282539,0.00029360742,0.00022693284,0.00010721052,0.00078880397,0.00032574157,0.0045731445],"category_scores_gemma":[0.5841277,0.00013433026,0.00024527454,0.0024727732,0.0001886491,0.0003371003,0.0002141386,0.0004478413,0.000019275585],"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":[0.00009984682,0.00068528735,0.8322375,0.000004751481,0.000006542604,0.00023448856,0.00010364463,0.000062314735,0.00024783565,0.000013854066,0.0059598014,0.16034412],"study_design_scores_gemma":[0.00025096047,0.00074335135,0.9396148,0.00003020545,0.000011511521,0.00060435623,0.00026232118,0.0012944816,0.00011698664,0.049069595,0.0077770366,0.00022443634],"about_ca_topic_score_codex":0.000045822493,"about_ca_topic_score_gemma":0.0000046628434,"teacher_disagreement_score":0.5641896,"about_ca_system_score_codex":0.000036474696,"about_ca_system_score_gemma":0.00003588565,"threshold_uncertainty_score":0.9963368},"labels":[],"label_agreement":null},{"id":"W2063141954","doi":"10.2466/pr0.2003.93.1.3","title":"A Brief Introduction to Unified Test Theory","year":2003,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Test (biology); Psychology; Test theory; Classical test theory; Item response theory; Elaboration; Unified field theory; Cognitive psychology; Psychometrics; Clinical psychology; Humanities; Philosophy","score_opus":0.37665866451480706,"score_gpt":0.49121992915069607,"score_spread":0.114561264635889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063141954","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":[0.5869573,0.00019284875,0.11461645,0.0039047543,0.005223624,0.00043875416,0.000002029709,0.00028061724,0.2883836],"genre_scores_gemma":[0.9558537,0.0000075361377,0.035489164,0.0016062983,0.00045303712,0.00002571524,9.998297e-7,0.00001090013,0.0065526576],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951127,0.00097076787,0.0010899414,0.0013341857,0.001040513,0.00045189992],"domain_scores_gemma":[0.97636473,0.02079047,0.0004927706,0.0016727317,0.00034107643,0.00033821043],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021363862,0.0001854209,0.00038349663,0.00039298972,0.00017411733,0.00019379449,0.00041251368,0.00015007937,0.0032532837],"category_scores_gemma":[0.61253345,0.00011633303,0.00013842799,0.003439283,0.00011112002,0.00011576405,0.000084380416,0.00026532065,0.00028746983],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108275475,0.00080202357,0.16959353,0.000002630977,0.000019692554,0.0008998137,0.00017342764,0.00011421115,0.0059926254,0.050689407,0.23271814,0.5388862],"study_design_scores_gemma":[0.000116215684,0.00029897978,0.20433539,0.0000032490093,0.000005037918,0.0011412092,0.00016090543,0.0000028343345,0.00036653836,0.4568595,0.33652773,0.00018241073],"about_ca_topic_score_codex":0.0000032749765,"about_ca_topic_score_gemma":6.88124e-7,"teacher_disagreement_score":0.5911696,"about_ca_system_score_codex":0.00003018519,"about_ca_system_score_gemma":0.000018662808,"threshold_uncertainty_score":0.9976579},"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":"W2064379877","doi":"10.1177/0013164402238082","title":"A Monte Carlo Comparison of Item and Person Statistics Based on Item Response Theory versus Classical Test Theory","year":2002,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":121,"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":"Item response theory; Classical test theory; Monte Carlo method; Statistics; Psychology; Econometrics; Psychometrics; Test theory; Item analysis; Computerized adaptive testing; Test (biology); Differential item functioning; Statistical hypothesis testing; Mathematics","score_opus":0.7790233134897627,"score_gpt":0.505780321916664,"score_spread":0.2732429915730987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064379877","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":[0.97472155,0.0023402777,0.00535482,0.007777893,0.0012348074,0.00031165083,0.00009027667,0.000029971714,0.008138726],"genre_scores_gemma":[0.9894863,0.00001688989,0.009530709,0.0003684703,0.00010583567,0.000022705572,0.0000010193328,0.000006495478,0.0004615909],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951723,0.002010999,0.00054317253,0.0005771259,0.0014644585,0.00023189303],"domain_scores_gemma":[0.88360554,0.11528914,0.00026233093,0.00032079138,0.00034243037,0.00017976965],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010272065,0.00018193231,0.00035307993,0.00025248947,0.00019138474,0.000082195045,0.0002878135,0.00010497924,0.001011047],"category_scores_gemma":[0.17204197,0.000116132425,0.000063057065,0.000536033,0.00032833585,0.000044021486,0.000029994748,0.00024532824,0.00002152588],"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":[0.011648106,0.0060344893,0.27678025,0.00003284093,0.00008277433,0.0000072319654,0.0028754384,0.00015399372,0.0011073834,0.029802186,0.06665417,0.60482115],"study_design_scores_gemma":[0.001347528,0.002614317,0.9663729,0.000048269863,0.000025793242,0.000005199957,0.002115086,0.0057995,0.00002630321,0.018397728,0.003043179,0.00020421586],"about_ca_topic_score_codex":0.0000022476133,"about_ca_topic_score_gemma":0.0000013708054,"teacher_disagreement_score":0.68959266,"about_ca_system_score_codex":0.000054217824,"about_ca_system_score_gemma":0.000031082152,"threshold_uncertainty_score":0.9999022},"labels":[],"label_agreement":null},{"id":"W2064530600","doi":"10.1111/j.1745-3992.2009.01135.x","title":"An NCME Instructional Module on Using Differential Step Functioning to Refine the Analysis of DIF in Polytomous Items","year":2009,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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 Toronto","funders":"","keywords":"Polytomous Rasch model; Differential item functioning; Item response theory; Psychology; Rasch model; Task (project management); Test (biology); Statistics; Differential (mechanical device); Psychometrics; Mathematics; Clinical psychology; Developmental psychology","score_opus":0.5327361304287398,"score_gpt":0.5248611500943309,"score_spread":0.007874980334408921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064530600","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":[0.9744468,0.00059786375,0.006566284,0.016108844,0.0007601034,0.00015081828,0.0000070580204,0.000008392677,0.0013538648],"genre_scores_gemma":[0.97606,0.000018746015,0.023013057,0.00047855097,0.0003175205,0.00000544481,0.00000476732,0.000003796375,0.000098173456],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962616,0.0008634061,0.0005535306,0.0003932663,0.0017657399,0.00016248772],"domain_scores_gemma":[0.9909241,0.0075500906,0.00038795685,0.00037398623,0.0006759188,0.00008795558],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0072387457,0.00011686607,0.00026099329,0.00089789793,0.00022850937,0.00020073976,0.00027304707,0.000040513565,0.00024888682],"category_scores_gemma":[0.043536127,0.00007806699,0.000060096576,0.0030314554,0.00003424635,0.00037976587,0.0000255921,0.00014658127,0.000003774149],"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":[0.0019517561,0.002885353,0.18956992,0.000010884884,0.000793245,0.0000025344868,0.0038549383,0.07914255,0.027042922,0.02859668,0.002302604,0.6638466],"study_design_scores_gemma":[0.00017860682,0.00021797678,0.9834813,0.00001942131,0.000141899,0.0000095698915,0.0014282307,0.006084207,0.00009572852,0.0027128996,0.0055207126,0.0001094544],"about_ca_topic_score_codex":0.0006463495,"about_ca_topic_score_gemma":0.00006197618,"teacher_disagreement_score":0.7939114,"about_ca_system_score_codex":0.0000854115,"about_ca_system_score_gemma":0.000085655716,"threshold_uncertainty_score":0.9645206},"labels":[],"label_agreement":null},{"id":"W2065030780","doi":"10.1177/0013164404273942","title":"Understanding Parameter Invariance in Unidimensional IRT Models","year":2006,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":108,"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":"Item response theory; Measurement invariance; Set (abstract data type); Differential item functioning; Psychology; Feature (linguistics); Property (philosophy); Econometrics; Variable (mathematics); Psychometrics; Cognitive psychology; Mathematics; Statistics; Applied mathematics; Computer science; Structural equation modeling; Confirmatory factor analysis; Mathematical analysis; Epistemology","score_opus":0.9212118758900417,"score_gpt":0.4959208972683364,"score_spread":0.42529097862170534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065030780","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":[0.79976904,0.0016931632,0.098765925,0.019852705,0.0018748252,0.00038201854,0.000007678052,0.000040567975,0.07761406],"genre_scores_gemma":[0.9801323,0.000015525844,0.018761618,0.0006260694,0.00015933353,0.00002558546,0.0000023115597,0.0000041157737,0.00027314102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681085,0.00039214033,0.0005797533,0.0005941061,0.0013560219,0.00026713396],"domain_scores_gemma":[0.9924677,0.006867148,0.00014866501,0.00024663727,0.00017908985,0.000090780566],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059311786,0.00013447698,0.00021876882,0.00029262583,0.00013800473,0.000114055314,0.00027748512,0.00008454702,0.00045133737],"category_scores_gemma":[0.008997417,0.00008952127,0.00005106472,0.0009926866,0.000111996465,0.00015182824,0.00005021436,0.00017735286,0.000027085815],"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":[0.00014719395,0.0014844704,0.25258204,0.000006598603,0.000016629438,0.000007730636,0.00014933867,0.0030568475,0.0009778753,0.6835403,0.04488128,0.013149689],"study_design_scores_gemma":[0.00021426698,0.000044350185,0.38161772,0.000013222142,0.0000014204558,0.000009310204,0.00007674439,0.00054899475,0.0000049172827,0.6166646,0.000720934,0.000083554914],"about_ca_topic_score_codex":0.00004808021,"about_ca_topic_score_gemma":0.000021318705,"teacher_disagreement_score":0.18036324,"about_ca_system_score_codex":0.0001409192,"about_ca_system_score_gemma":0.000044242188,"threshold_uncertainty_score":0.9993502},"labels":[],"label_agreement":null},{"id":"W2066165827","doi":"10.1177/01466210122032046","title":"Nonparametric Item Response Function Estimation for Assessing Parametric Model Fit","year":2001,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Nonparametric statistics; Item response theory; Identifiability; Resampling; Parametric statistics; Consistency (knowledge bases); Econometrics; Parametric model; Statistics; Mathematics; Differential item functioning; Computer science; Artificial intelligence; Psychometrics","score_opus":0.7555750990116348,"score_gpt":0.5231085521292439,"score_spread":0.23246654688239088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066165827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34878436,0.00017109986,0.64158064,0.00042634978,0.0005641344,0.0007463407,0.000003072329,0.00016639671,0.007557622],"genre_scores_gemma":[0.81964797,0.0000131680445,0.17900656,0.000747082,0.00009847182,0.00030787723,0.0000028256086,0.000020689773,0.00015535882],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99273247,0.0006919041,0.0013659289,0.0014057101,0.0030753075,0.0007286822],"domain_scores_gemma":[0.9665034,0.03059806,0.0007346945,0.0010987757,0.0007988521,0.0002662544],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032778114,0.00035532963,0.0006139567,0.0016438065,0.00046236336,0.00056970614,0.00089991273,0.00031929815,0.00017687348],"category_scores_gemma":[0.15302347,0.0002515817,0.00025651068,0.008229246,0.00009922463,0.0002624897,0.00009414135,0.00034784197,0.00017241956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030090455,0.000617484,0.0036376675,0.0000073572837,0.000035518573,0.0000036275417,0.000036931666,0.03958116,0.0045061437,0.0018681949,0.0068414006,0.93985546],"study_design_scores_gemma":[0.0029789032,0.0009280038,0.387059,0.000030114585,0.000088534965,0.000028852706,0.00032371443,0.34014723,0.0002471962,0.25857767,0.008839145,0.00075161894],"about_ca_topic_score_codex":0.0000023818343,"about_ca_topic_score_gemma":5.281879e-7,"teacher_disagreement_score":0.93910384,"about_ca_system_score_codex":0.00025773203,"about_ca_system_score_gemma":0.000050934064,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"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":"W2070673350","doi":"10.1177/0146621606292215","title":"Investigation of IRT-Based Equating Methods in the Presence of Outlier Common Items","year":2008,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Equating; Outlier; Statistics; Item response theory; Calibration; Comparability; Mathematics; Econometrics; Computer science; Psychometrics","score_opus":0.8304468687797645,"score_gpt":0.5388212625480718,"score_spread":0.29162560623169265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070673350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8062878,0.0002468303,0.1744903,0.00049859314,0.00026256873,0.0006356837,0.0000022115503,0.00002679538,0.017549211],"genre_scores_gemma":[0.83624434,0.000005442124,0.16322944,0.00042214885,0.00002501884,0.00006321304,7.035448e-7,0.0000051614143,0.0000045378415],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9919676,0.002857596,0.001580675,0.0005703066,0.002716125,0.00030766983],"domain_scores_gemma":[0.97163993,0.02610949,0.00091937865,0.0009425091,0.0003186446,0.000070069575],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040409517,0.00017177942,0.00054921926,0.00034243928,0.000110647234,0.00002343053,0.0013154738,0.00013291607,0.00007316628],"category_scores_gemma":[0.038884062,0.000094433926,0.000121029116,0.0029106482,0.0004278803,0.00004911671,0.00007648367,0.00031682375,0.000007465493],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029823257,0.0006019457,0.41936296,0.000034586123,0.000028237582,0.000008083509,0.0031654532,0.0019003788,0.2201929,0.006336234,0.0020593787,0.3460116],"study_design_scores_gemma":[0.0010320912,0.0003859058,0.9069838,0.000050490642,0.000011276503,0.0000059600884,0.0011383578,0.0012384999,0.020451078,0.068121634,0.0003843038,0.00019660534],"about_ca_topic_score_codex":0.000042569984,"about_ca_topic_score_gemma":0.000004667187,"teacher_disagreement_score":0.48762083,"about_ca_system_score_codex":0.00003168411,"about_ca_system_score_gemma":0.00003266718,"threshold_uncertainty_score":0.98810035},"labels":[],"label_agreement":null},{"id":"W2071707704","doi":"10.7202/1024416ar","title":"Un processus itératif pour réduire l’impact de réponses aberrantes sur l’identification de patrons de réponses inappropriés","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","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":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Humanities; Philosophy","score_opus":0.23330097523764637,"score_gpt":0.4724513199851181,"score_spread":0.2391503447474717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071707704","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":[0.5956763,0.0021060314,0.37558568,0.023481293,0.0014427212,0.0005356262,0.00003597257,0.00013424791,0.0010021598],"genre_scores_gemma":[0.9357197,0.00060669315,0.058165643,0.00048321852,0.00063036184,0.00016525631,0.00009581003,0.00006077073,0.0040725223],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96940845,0.025070954,0.0016126715,0.0011392498,0.0017164844,0.0010521958],"domain_scores_gemma":[0.9412812,0.052813087,0.0018688054,0.0013816346,0.0022338808,0.00042137003],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10222079,0.0005150835,0.0006217477,0.0009781659,0.0006656378,0.000932864,0.0010231195,0.00054342265,0.0010077145],"category_scores_gemma":[0.3171984,0.00047327008,0.00030418782,0.0030203615,0.00020499229,0.0012173877,0.00011302254,0.00060654944,0.00025602357],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014169772,0.00074882957,0.22962055,0.00016813565,0.00013194147,0.000003294559,0.050314993,0.010119276,0.017516607,0.002195177,0.01375352,0.675286],"study_design_scores_gemma":[0.0006865683,0.00018882647,0.822257,0.0001936596,0.00021565615,0.00013037697,0.0036535526,0.10258466,0.005366056,0.061229926,0.0030340133,0.0004597392],"about_ca_topic_score_codex":0.0013074356,"about_ca_topic_score_gemma":0.00029552725,"teacher_disagreement_score":0.67482626,"about_ca_system_score_codex":0.00097368093,"about_ca_system_score_gemma":0.0058018253,"threshold_uncertainty_score":0.9999055},"labels":[],"label_agreement":null},{"id":"W2072036674","doi":"10.1007/s11136-014-0746-0","title":"Method variation in the impact of missing data on response shift detection","year":2014,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Calgary","funders":"Canadian Institutes of Health Research; Institut National Du Cancer","keywords":"Quality of Life Research; Public health; Variation (astronomy); Missing data; Statistics; Medicine; Mathematics","score_opus":0.934523316319859,"score_gpt":0.7183121467433802,"score_spread":0.2162111695764788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072036674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.7940981,0.000037299615,0.20294504,0.0016068834,0.00004593908,0.00015325518,0.000014959523,0.0000061771793,0.0010923919],"genre_scores_gemma":[0.97773445,0.0000030844108,0.022151936,0.00002824257,0.0000609438,0.0000025309637,0.0000012719976,0.0000042040974,0.000013336103],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9142347,0.07933402,0.0014251637,0.00061686686,0.0040027644,0.0003864761],"domain_scores_gemma":[0.17468184,0.820036,0.00087731157,0.0035210927,0.00074868853,0.00013507098],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4621319,0.00007540933,0.00037874668,0.0011508014,0.00014459695,0.00011298942,0.0019744835,0.00009075522,0.00006021906],"category_scores_gemma":[0.7922478,0.00004222098,0.00008918851,0.0041227336,0.00013721593,0.00019126415,0.00028564982,0.00042108743,0.000010042776],"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":[0.0047499216,0.00035601368,0.06007898,0.000042619453,0.000030711257,0.0000010348551,0.0048851063,0.0007136439,0.032966807,0.0017028908,0.0008950385,0.8935772],"study_design_scores_gemma":[0.00027039787,0.00042321955,0.92172575,0.000019693523,0.0000010419776,6.8164485e-7,0.0007498467,0.014691545,0.0003996839,0.06153151,0.00014351441,0.00004310737],"about_ca_topic_score_codex":0.0048177694,"about_ca_topic_score_gemma":0.000053777974,"teacher_disagreement_score":0.8935341,"about_ca_system_score_codex":0.00004964975,"about_ca_system_score_gemma":0.00021379246,"threshold_uncertainty_score":0.7283058},"labels":[],"label_agreement":null},{"id":"W2072613362","doi":"10.7202/1024848ar","title":"Principes méthodologiques et techniques des enquêtes internationales","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","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":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.5422243669119946,"score_gpt":0.5520840231200843,"score_spread":0.009859656208089707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072613362","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":[0.21606724,0.0027527378,0.7282841,0.022648914,0.003576001,0.00055944757,0.00001830144,0.00030652003,0.025786726],"genre_scores_gemma":[0.45828414,0.0015690591,0.52846605,0.0011027441,0.0005600213,0.0001145307,0.00006654015,0.000032275933,0.009804622],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.955788,0.04001207,0.0012700415,0.000894392,0.001605207,0.00043027356],"domain_scores_gemma":[0.90199864,0.09411731,0.0010980665,0.00079850474,0.0018502413,0.0001372487],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17954156,0.00036240072,0.00049317983,0.0009637874,0.00029801243,0.0006103653,0.0008806193,0.00038845348,0.0010721015],"category_scores_gemma":[0.37266186,0.00031543494,0.00019453435,0.0015404559,0.00033418575,0.0013133845,0.00021035933,0.00047289307,0.0002242669],"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":[0.000019676616,0.00020257528,0.052281585,0.000055292898,0.0000396475,5.610619e-7,0.021275006,0.00031839588,0.001127864,0.07073751,0.005654991,0.84828687],"study_design_scores_gemma":[0.00019481935,0.00022230812,0.53565896,0.0002605017,0.000046399797,0.000025019688,0.0010894922,0.0046662968,0.004301083,0.36510235,0.08810787,0.00032487113],"about_ca_topic_score_codex":0.0003717453,"about_ca_topic_score_gemma":0.00033151315,"teacher_disagreement_score":0.847962,"about_ca_system_score_codex":0.0003957763,"about_ca_system_score_gemma":0.0007148628,"threshold_uncertainty_score":0.9999298},"labels":[],"label_agreement":null},{"id":"W2073056556","doi":"10.1016/j.jclinepi.2005.09.005","title":"“Precision” and “Accuracy”: Two Terms That Are Neither","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; McMaster University; University of Toronto","funders":"","keywords":"Reliability (semiconductor); Conceptualization; Inter-rater reliability; Scale (ratio); Test (biology); Computer science; Synonym (taxonomy); Validity; Criterion validity; Psychology; Process (computing); Cognitive psychology; Psychometrics; Artificial intelligence; Statistics; Mathematics; Rating scale; Construct validity; Geography","score_opus":0.9346514191644626,"score_gpt":0.7216304917470712,"score_spread":0.21302092741739143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073056556","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020844783,0.98062146,0.009252972,0.0012397327,0.0060287,0.00022935623,0.000019652829,0.000014559291,0.0023851444],"genre_scores_gemma":[0.00003590116,0.9553931,0.039566338,0.0011648166,0.002940106,0.0000036015952,0.0000016442411,0.000033583863,0.0008609406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9344106,0.04206487,0.020427722,0.0011825953,0.0011824168,0.0007318214],"domain_scores_gemma":[0.14958537,0.8122269,0.036053997,0.0011204588,0.0004868119,0.0005264995],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24545562,0.00056667026,0.017319467,0.0011259684,0.00012160122,0.00010689382,0.002515462,0.0012604299,0.00029993005],"category_scores_gemma":[0.92399764,0.00027347775,0.0034537567,0.0011742841,0.000592939,0.00024231094,0.0005891158,0.0031848107,0.000101097576],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025848509,0.000050454983,0.06419694,0.00014528782,0.000105130406,0.00006961007,0.0000021085066,0.000006875588,4.0569352e-9,0.00018231837,0.046663705,0.8885517],"study_design_scores_gemma":[0.00047517786,0.00025902045,0.033420056,0.0026172763,0.00026312965,0.0008479923,0.000015749245,0.000031774827,7.143739e-9,0.08696296,0.8748732,0.00023363227],"about_ca_topic_score_codex":0.000017885854,"about_ca_topic_score_gemma":0.000006142411,"teacher_disagreement_score":0.88831806,"about_ca_system_score_codex":0.000038542534,"about_ca_system_score_gemma":0.0002926205,"threshold_uncertainty_score":0.99997175},"labels":[],"label_agreement":null},{"id":"W2074598161","doi":"10.1007/s11136-008-9381-y","title":"Computerized adaptive test for patients with foot or ankle impairments produced valid and responsive measures of function","year":2008,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computerized adaptive testing; Item bank; Ankle; Rehabilitation; Physical therapy; Physical medicine and rehabilitation; Item response theory; Ceiling effect; Quality of Life Research; Psychometrics; Foot (prosody); Construct validity; Differential item functioning; Medicine; Psychology; Clinical psychology; Public health; Surgery","score_opus":0.8758731545460424,"score_gpt":0.5705363505626412,"score_spread":0.30533680398340124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074598161","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":[0.9881512,0.00008260164,0.010161434,0.00022044846,0.00009967326,0.001075064,0.0000779308,0.000014865259,0.00011677727],"genre_scores_gemma":[0.97266567,0.0000173955,0.027020551,0.000021916372,0.000044140834,0.000034721525,0.0000035552916,0.00000911201,0.00018292127],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922139,0.0030109177,0.00093447167,0.0005542204,0.0029369523,0.0003495217],"domain_scores_gemma":[0.8476728,0.14464092,0.0007832375,0.0007439247,0.0059381793,0.00022093837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02616587,0.00012048911,0.00060123624,0.0006731814,0.00029384063,0.000036611174,0.00043016757,0.000071935916,0.000023066515],"category_scores_gemma":[0.35100508,0.00007238524,0.0000700493,0.0020603682,0.00054383854,0.00016910341,0.00020554023,0.0001613366,0.000001802253],"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":[0.018663084,0.0006988046,0.94130236,0.0000899342,0.000079321224,0.0000013732619,0.0011050213,0.000010092076,0.0018859146,0.00008195512,0.002769992,0.033312153],"study_design_scores_gemma":[0.0029347676,0.006972666,0.9848485,0.000046770772,0.0000053296762,0.0000015907002,0.0012540523,0.00017370185,0.0008468614,0.00249941,0.00031183055,0.00010453937],"about_ca_topic_score_codex":0.00018189884,"about_ca_topic_score_gemma":0.000011991134,"teacher_disagreement_score":0.3248392,"about_ca_system_score_codex":0.00003083135,"about_ca_system_score_gemma":0.00037417418,"threshold_uncertainty_score":0.906862},"labels":[],"label_agreement":null},{"id":"W2077199939","doi":"10.1007/s11336-009-9123-2","title":"When Cognitive Diagnosis Meets Computerized Adaptive Testing: CD-CAT","year":2009,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":176,"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":"Heuristics; Computerized adaptive testing; Entropy (arrow of time); Information theory; Item response theory; Computer science; Selection (genetic algorithm); Context (archaeology); Latent class model; Kullback–Leibler divergence; Artificial intelligence; Mathematics; Machine learning; Algorithm; Statistics; Mathematical optimization; Psychometrics","score_opus":0.5850420918789638,"score_gpt":0.47022253240921447,"score_spread":0.11481955946974937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077199939","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":[0.6911383,0.0037005413,0.18764763,0.0065053515,0.0047318307,0.0015148389,0.000121834804,0.000922212,0.10371742],"genre_scores_gemma":[0.7708109,0.00008731737,0.22635503,0.001782506,0.00038777624,0.000044146127,0.0000049783025,0.000023440864,0.0005038718],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9930904,0.00094067905,0.001340946,0.0015212683,0.0022129745,0.000893748],"domain_scores_gemma":[0.87470335,0.12158695,0.00090088026,0.0010662747,0.0012559573,0.0004865816],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0069608605,0.00047049118,0.0010011719,0.0031269228,0.0003822092,0.0005779339,0.0017920677,0.00021772289,0.00089322275],"category_scores_gemma":[0.22433907,0.00036229266,0.00031954696,0.014834925,0.00018674246,0.00048717187,0.00020632957,0.00035198225,0.00065387355],"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":[0.00015408207,0.000317986,0.073257715,0.0000021518874,0.00004723563,0.000024461884,0.0003301675,0.000008981793,0.00023049401,0.00042127518,0.021548051,0.9036574],"study_design_scores_gemma":[0.0029838085,0.0017993089,0.8595602,0.00016137311,0.000060981536,0.000057288362,0.0008752619,0.0020794196,0.0004654514,0.104644716,0.026459143,0.00085306086],"about_ca_topic_score_codex":0.000046810357,"about_ca_topic_score_gemma":0.0000035060696,"teacher_disagreement_score":0.9028043,"about_ca_system_score_codex":0.00008092784,"about_ca_system_score_gemma":0.000071054485,"threshold_uncertainty_score":0.9998829},"labels":[],"label_agreement":null},{"id":"W2078293650","doi":"10.2466/pr0.2001.89.2.291","title":"On the Far Reaching Effects of Using Biased Estimates of Score Reliability: An Examination of the Problem in 20 Data Analyses","year":2001,"lang":"en","type":"article","venue":"Psychological Reports","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 Winnipeg; University of Manitoba","funders":"","keywords":"Reliability (semiconductor); Equivalence (formal languages); Psychology; Econometrics; Statistics; Variety (cybernetics); Test (biology); Mathematics","score_opus":0.7725162137949652,"score_gpt":0.567916555799962,"score_spread":0.20459965799500313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078293650","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":[0.9897842,0.00012753952,0.0077925115,0.00011546875,0.00018685353,0.00040680714,0.000003867197,0.000013915456,0.0015688494],"genre_scores_gemma":[0.97164464,0.000013362413,0.02825805,0.000050762625,0.000012076564,0.000004872692,0.0000030824724,0.0000052513196,0.000007922748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948318,0.0017442562,0.0014363691,0.000706052,0.0010859646,0.0001955617],"domain_scores_gemma":[0.9568011,0.038510334,0.0018325731,0.0025773812,0.00023447594,0.000044123237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020451797,0.00013590419,0.00048939814,0.00030494697,0.00007950821,0.000031103653,0.0011272697,0.00010555406,0.000040306742],"category_scores_gemma":[0.25103813,0.00005849254,0.00009827121,0.0030710346,0.00029036214,0.0001777389,0.0002854326,0.00022930368,2.6404803e-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":[0.00007008101,0.0008027993,0.7515736,0.000036844445,0.000015790783,0.000066182874,0.00025473436,0.003512314,0.048994962,0.00022844646,0.000077918536,0.19436632],"study_design_scores_gemma":[0.00013307897,0.0002293118,0.92436004,0.0001836241,0.00002158322,0.00005278145,0.00014778097,0.0068072258,0.0026444898,0.06532545,0.00002121965,0.000073410316],"about_ca_topic_score_codex":0.00015603313,"about_ca_topic_score_gemma":0.000007779828,"teacher_disagreement_score":0.23058632,"about_ca_system_score_codex":0.000019298508,"about_ca_system_score_gemma":0.00002169807,"threshold_uncertainty_score":0.7552707},"labels":[],"label_agreement":null},{"id":"W2078503709","doi":"10.1177/0146621614557272","title":"Evaluating Person Fit for Cognitive Diagnostic Assessment","year":2014,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Alberta","funders":"","keywords":"Statistic; Cognition; Psychology; Item response theory; Conformity; Cognitive psychology; Context (archaeology); Statistics; Social psychology; Applied psychology; Psychometrics; Clinical psychology; Mathematics","score_opus":0.8911900554521754,"score_gpt":0.6108802067461848,"score_spread":0.2803098487059906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078503709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24524683,0.00015434898,0.65850556,0.0010327937,0.0011805551,0.001764726,0.000011387707,0.00016020269,0.09194363],"genre_scores_gemma":[0.9026748,0.0000046170167,0.094783455,0.0013941631,0.0003110232,0.00074391946,0.0000033375043,0.000016956868,0.000067721],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99314153,0.0008883008,0.0008517151,0.0013134452,0.0031639887,0.0006410378],"domain_scores_gemma":[0.9127549,0.08472498,0.0005727086,0.0007249512,0.0009670576,0.0002554122],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037176665,0.00029553173,0.00057524355,0.00023983115,0.00039109425,0.0002340676,0.0008231875,0.00016666215,0.00056460773],"category_scores_gemma":[0.24483585,0.00019491612,0.00021553082,0.0009920165,0.00012436468,0.000058867285,0.00008897724,0.0003003481,0.0001724475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011437478,0.00035632722,0.0058108643,0.000008610114,0.00003855743,9.062208e-7,0.00010397764,0.00012337472,0.0029698294,0.0051448783,0.00442682,0.9809015],"study_design_scores_gemma":[0.0053147757,0.0031647987,0.81089944,0.000101331265,0.00012754416,0.000009022578,0.0019923456,0.0050450326,0.0006139904,0.16377312,0.008222825,0.0007357649],"about_ca_topic_score_codex":0.0000025965232,"about_ca_topic_score_gemma":0.0000015115847,"teacher_disagreement_score":0.9801657,"about_ca_system_score_codex":0.00010790817,"about_ca_system_score_gemma":0.00002792909,"threshold_uncertainty_score":0.9914292},"labels":[],"label_agreement":null},{"id":"W2080184966","doi":"10.1016/j.artres.2010.10.029","title":"1.3 IS IT TIME TO QUESTION THE VALIDITY OF IMPEDANCE ANALYSIS?","year":2010,"lang":"en","type":"article","venue":"Artery 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":"University of Calgary","funders":"","keywords":"Medicine","score_opus":0.7958080766868204,"score_gpt":0.6301641342664401,"score_spread":0.16564394242038027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080184966","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":[0.9734153,0.000013219945,0.0032477428,0.009334656,0.00016256489,0.00016242557,0.000009113959,0.000012960297,0.013641983],"genre_scores_gemma":[0.9893295,0.000004194506,0.0033054752,0.00023712902,0.00010373328,0.000011238703,5.730722e-7,0.0000039025335,0.007004265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948888,0.0017430593,0.00044535918,0.00041554103,0.0021567228,0.00035054467],"domain_scores_gemma":[0.9362356,0.061116036,0.00012501457,0.0013618169,0.0010305075,0.00013102873],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.049080823,0.000068051806,0.00024139593,0.000992457,0.00023939119,0.00019242738,0.0013716014,0.00006139172,0.0037185368],"category_scores_gemma":[0.14417547,0.00003763711,0.0001381822,0.008849506,0.0002064096,0.00013198222,0.00031224292,0.00044559067,0.0019272781],"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":[0.000053000254,0.00010076642,0.53708905,0.0000047527933,0.000107998676,0.0000056494255,0.0015335619,0.00006371171,0.051539306,0.000696165,0.2158947,0.19291134],"study_design_scores_gemma":[0.00010068063,0.00018829985,0.9245623,0.000007002181,0.00002075567,0.0000051161446,0.0004607787,0.009296199,0.004121369,0.022999117,0.03813937,0.000099046905],"about_ca_topic_score_codex":0.00007942709,"about_ca_topic_score_gemma":0.000049468865,"teacher_disagreement_score":0.38747323,"about_ca_system_score_codex":0.000010782255,"about_ca_system_score_gemma":0.000055246746,"threshold_uncertainty_score":0.9988498},"labels":[],"label_agreement":null},{"id":"W2081705014","doi":"10.1177/0013164414527449","title":"Seeing Perfectly Fitting Factor Models That Are Causally Misspecified","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":53,"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":"Factor (programming language); Factor analysis; Causal model; Econometrics; Causal structure; Psychology; Statistics; Mathematics; Computer science","score_opus":0.8554756584236994,"score_gpt":0.49012879108660357,"score_spread":0.36534686733709587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081705014","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":[0.8962564,0.001363949,0.042248756,0.010497603,0.0021069697,0.000258757,0.000007877064,0.00007308759,0.04718663],"genre_scores_gemma":[0.9855183,0.000029300512,0.012296997,0.0010836825,0.00050583173,0.000024852434,0.0000015030267,0.000008488586,0.00053104083],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957297,0.00069687323,0.0005377262,0.00080988574,0.001836822,0.0003889878],"domain_scores_gemma":[0.9899974,0.008510029,0.0003494757,0.0004280913,0.00047254088,0.00024249937],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007614276,0.0002047761,0.00033174944,0.00020885545,0.00037557803,0.00025802193,0.000505332,0.00010924459,0.0009531891],"category_scores_gemma":[0.031874646,0.00013083685,0.00010117404,0.0005551794,0.0000892616,0.00016152422,0.000087054825,0.0002429453,0.000074227886],"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":[0.00011076456,0.0008389912,0.42631793,0.000022808137,0.00005716894,0.0000027771043,0.00097331,0.00032780756,0.0026146327,0.016781181,0.021206805,0.5307458],"study_design_scores_gemma":[0.0002805086,0.0001288329,0.842547,0.000036790705,0.000005389289,0.000015271451,0.00037349842,0.00057172787,0.00005039683,0.145068,0.010722123,0.00020047797],"about_ca_topic_score_codex":0.000009931778,"about_ca_topic_score_gemma":0.0000035838611,"teacher_disagreement_score":0.53054535,"about_ca_system_score_codex":0.000051734765,"about_ca_system_score_gemma":0.000029047502,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W2082278804","doi":"10.1016/j.jmpt.2006.04.006","title":"Applying the Item Response Theory to Classroom Examinations","year":2006,"lang":"en","type":"article","venue":"Journal of Manipulative and Physiological Therapeutics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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":"Rasch model; Medicine; Item response theory; Chiropractic; Metric (unit); Missing data; Reliability (semiconductor); Psychometrics; Clinical psychology; Statistics; Alternative medicine; Pathology; Mathematics","score_opus":0.8091615709690857,"score_gpt":0.5055948934918802,"score_spread":0.30356667747720545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082278804","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":[0.93217164,0.0006858684,0.06481204,0.0010098658,0.00020786555,0.00022662945,0.0000026312716,0.000009304986,0.0008741687],"genre_scores_gemma":[0.9920695,0.00003624621,0.006099376,0.0012212881,0.00023650522,0.000010186197,2.0086614e-7,0.0000052914806,0.0003214299],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959732,0.002413718,0.00066604634,0.00018714018,0.0005760134,0.00018387292],"domain_scores_gemma":[0.9421426,0.056710523,0.00051371835,0.00021712443,0.0003578771,0.00005816581],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01005622,0.00012371154,0.00031555767,0.00021270012,0.00027339984,0.00013135813,0.00052172574,0.000070760856,0.000054202657],"category_scores_gemma":[0.013247487,0.000054017313,0.00012971048,0.00094083813,0.00014051957,0.00010666007,0.000117049036,0.000285884,0.000007752989],"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":[0.0026566267,0.00032219585,0.043689556,0.0000045245642,0.00017429149,0.00003135415,0.0011813359,0.0030924147,0.12299045,0.06985787,0.0027472423,0.75325215],"study_design_scores_gemma":[0.00014967713,0.00037190208,0.59748113,0.000008044477,0.000014684211,0.000018649307,0.0009999289,0.00039401764,0.00017129889,0.37674055,0.023582844,0.00006727521],"about_ca_topic_score_codex":0.0000020153254,"about_ca_topic_score_gemma":5.283611e-7,"teacher_disagreement_score":0.75318485,"about_ca_system_score_codex":0.000021207097,"about_ca_system_score_gemma":0.000018298282,"threshold_uncertainty_score":0.9950644},"labels":[],"label_agreement":null},{"id":"W2083551948","doi":"10.1186/1472-6920-12-20","title":"Expert validation of fit-for-purpose guidelines for designing programmes of assessment","year":2012,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Rubric; Competence (human resources); Brainstorming; Computer science; Context (archaeology); Judgement; Management science; Set (abstract data type); Process management; Medical education; Psychology; Medicine; Engineering; Artificial intelligence; Pedagogy","score_opus":0.8167830120164873,"score_gpt":0.6580040613090576,"score_spread":0.15877895070742964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083551948","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":[0.14540973,0.0008788073,0.8503226,0.00086437835,0.0017173458,0.00056234916,0.0000029912005,0.000015032197,0.00022677217],"genre_scores_gemma":[0.29013094,0.000019807043,0.7088968,0.00015442194,0.00045902992,0.00021549151,0.000012919149,0.000005469928,0.00010512407],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99729156,0.0002843097,0.0009979048,0.00019809716,0.0010289896,0.00019912446],"domain_scores_gemma":[0.96555334,0.031271223,0.00077979994,0.0003383119,0.0018647497,0.00019254709],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015887575,0.000078661644,0.0002643609,0.00024913915,0.00005737637,0.00002390598,0.0003495681,0.00009395998,0.00015320019],"category_scores_gemma":[0.44388857,0.000053912343,0.000109893124,0.00063102134,0.00006124732,0.0001761488,0.000036604793,0.000042047828,0.0000010701522],"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":[0.000024795292,0.0003312608,0.08680783,0.00007429082,0.0000076774195,4.9848787e-9,0.00047626902,0.000018082037,0.00071563566,0.0019549252,0.029848833,0.8797404],"study_design_scores_gemma":[0.00611675,0.0023303072,0.32289773,0.0019262544,0.00025163693,0.000030576513,0.059541464,0.06794459,0.13651368,0.15214752,0.24886762,0.0014318726],"about_ca_topic_score_codex":0.00003503648,"about_ca_topic_score_gemma":0.0000018317851,"teacher_disagreement_score":0.87830853,"about_ca_system_score_codex":0.000025294788,"about_ca_system_score_gemma":0.0010826169,"threshold_uncertainty_score":0.5607958},"labels":[],"label_agreement":null},{"id":"W2087062758","doi":"10.1207/s15327752jpa8501_02","title":"Factor Analytic Models: Viewing the Structure of an Assessment Instrument From Three Perspectives","year":2005,"lang":"en","type":"review","venue":"Journal of Personality Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":492,"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":"Confirmatory factor analysis; Psychology; Structural equation modeling; CLARITY; Exploratory factor analysis; Psychometrics; Notional amount; Social psychology; Clinical psychology; Statistics","score_opus":0.6885502201466005,"score_gpt":0.588745809497927,"score_spread":0.09980441064867351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087062758","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014243634,0.95686877,0.025754765,0.00041689118,0.0010703568,0.00057343184,0.0005555193,0.000013338458,0.0005033024],"genre_scores_gemma":[0.04454431,0.8336045,0.120427825,0.000059023594,0.0012726492,0.0000049054347,0.000013661747,0.000043696302,0.00002942225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98555213,0.0037244775,0.0040584765,0.0008840506,0.0052993456,0.00048154563],"domain_scores_gemma":[0.9720228,0.017021239,0.00802957,0.0013974804,0.0012207474,0.00030821862],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011231827,0.0007019624,0.00405889,0.00096574915,0.00029650633,0.00059991144,0.003491587,0.00035708392,0.0014694236],"category_scores_gemma":[0.0048738164,0.00035192462,0.0020156351,0.0019448804,0.00024861965,0.0009347469,0.000415276,0.0020244238,0.0000018369626],"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":[0.000011003676,0.00023361071,0.00074237224,0.00026612775,0.0008924569,0.0000138811265,0.001119755,0.00038419187,0.000004799924,0.0006687305,0.000097386706,0.9955657],"study_design_scores_gemma":[0.0027582448,0.0024251027,0.10065332,0.014859541,0.0073727896,0.0006498969,0.047833644,0.028327003,0.0000044051726,0.1281445,0.66426164,0.002709881],"about_ca_topic_score_codex":0.00016511264,"about_ca_topic_score_gemma":0.00008889097,"teacher_disagreement_score":0.9928558,"about_ca_system_score_codex":0.0012910864,"about_ca_system_score_gemma":0.0021043837,"threshold_uncertainty_score":0.99989325},"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":"W2089262464","doi":"10.1007/s11205-010-9682-8","title":"Assessing the Unidimensionality of Psychological Scales: Using Multiple Criteria from Factor Analysis","year":2010,"lang":"en","type":"article","venue":"Social Indicators Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":252,"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":"Statistics; Item response theory; Factor analysis; Sample (material); Sample size determination; Scale (ratio); Psychology; Mathematics; Curse of dimensionality; Econometrics; Quality of Life Research; Psychometrics","score_opus":0.8500569143669792,"score_gpt":0.7003382737954648,"score_spread":0.1497186405715144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089262464","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":[0.99540806,0.000054023694,0.0022939846,0.00046092557,0.00047931148,0.00015726431,0.00008031389,0.000023895045,0.0010422004],"genre_scores_gemma":[0.9885451,0.0000028182897,0.011054491,0.000044153992,0.0003097643,0.0000054107736,0.0000058380715,0.000008925828,0.000023476154],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9901653,0.0044963844,0.0008385339,0.00069789257,0.003268215,0.0005337092],"domain_scores_gemma":[0.92225885,0.07560123,0.00045768905,0.00082511466,0.00069547293,0.00016166971],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023520315,0.00013751005,0.000534253,0.0015366416,0.0012922595,0.0005285779,0.0017841195,0.00031581556,0.0017225837],"category_scores_gemma":[0.14903794,0.0000785664,0.00034504256,0.013748643,0.0016346816,0.000237782,0.0005728418,0.001272524,0.00001932556],"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":[0.00004110009,0.00014239106,0.9253888,0.0000017242445,0.00011742115,0.0000032631533,0.0008616053,0.0000033019599,0.02803477,0.00032799388,0.0005023212,0.044575308],"study_design_scores_gemma":[0.0001446059,0.000037682737,0.97658956,0.000002906943,0.000024788764,5.4968075e-7,0.0029294637,0.0017991887,0.00086833956,0.017076075,0.00043309378,0.000093757655],"about_ca_topic_score_codex":0.000790672,"about_ca_topic_score_gemma":0.00015083786,"teacher_disagreement_score":0.12551762,"about_ca_system_score_codex":0.0000446804,"about_ca_system_score_gemma":0.00011488205,"threshold_uncertainty_score":0.99919},"labels":[],"label_agreement":null},{"id":"W2089944619","doi":"10.1080/00224540009600503","title":"Confirmatory Factor Analyses of the Full and Short Versions of the Marlowe-Crowne Social Desirability Scale","year":2000,"lang":"en","type":"article","venue":"The Journal of Social Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":277,"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 Lethbridge","funders":"","keywords":"Scale (ratio); Confirmatory factor analysis; Short Forms; Psychology; Social desirability; Full scale; Social psychology; Statistics; Econometrics; Structural equation modeling; Computer science; Mathematics; Clinical psychology","score_opus":0.5809835667547556,"score_gpt":0.540996276488838,"score_spread":0.03998729026591763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089944619","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":[0.9913719,0.00027038035,0.00025794873,0.0042001586,0.0006609429,0.0001024814,0.000015532334,0.0000032167875,0.0031173935],"genre_scores_gemma":[0.99900544,0.00005783134,0.00036235034,0.00029588843,0.0001688707,3.5893362e-7,4.98393e-8,0.0000051131706,0.00010408066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99501145,0.0024967806,0.0013325182,0.00015204686,0.0008132125,0.00019401273],"domain_scores_gemma":[0.99114496,0.006478026,0.0015933044,0.00037731449,0.00036070833,0.000045705252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076959403,0.00011360841,0.0005528273,0.00012405327,0.00054729474,0.000019241232,0.0014446306,0.00014461458,0.000783182],"category_scores_gemma":[0.0072687278,0.000047485715,0.0004083397,0.0011962446,0.0016450543,0.0000843515,0.00013721938,0.0004352132,0.000002602683],"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":[0.0017605133,0.0005849162,0.48453826,0.000025467132,0.00045213304,0.0000028824284,0.021583548,0.00004644587,0.12511927,0.00022003392,0.030798757,0.33486778],"study_design_scores_gemma":[0.0003516807,0.00009619832,0.98432326,0.0000075135367,0.000075283184,0.00003706436,0.0018890863,0.000005870098,0.0008063347,0.011123456,0.0012324394,0.000051823798],"about_ca_topic_score_codex":0.000033682572,"about_ca_topic_score_gemma":0.000014457477,"teacher_disagreement_score":0.499785,"about_ca_system_score_codex":0.000022318825,"about_ca_system_score_gemma":0.0000848408,"threshold_uncertainty_score":0.87018716},"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":"W2090570025","doi":"10.1177/00131640021970330","title":"Number-Right, Item-Response, and Finite-State Scoring: Robustness with Respect to Lack of Equally Classifiable Options and Item Option Independence","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Robustness (evolution); Independence (probability theory); Mathematics; Statistics; Econometrics","score_opus":0.6325820280120732,"score_gpt":0.4842413224829055,"score_spread":0.14834070552916767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090570025","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":[0.9847274,0.0005532065,0.0063936724,0.0044867187,0.0001895282,0.00028278006,0.000013042014,0.000018923656,0.0033347209],"genre_scores_gemma":[0.9721106,0.00013805936,0.02553747,0.00020092982,0.00006862933,0.000046562403,0.0000012302969,0.000006612858,0.0018899018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964627,0.000629362,0.0005743394,0.0007245091,0.0013487367,0.00026035393],"domain_scores_gemma":[0.9884093,0.010352986,0.00018846324,0.0003094519,0.00047999484,0.000259814],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007185233,0.00018052741,0.00031206346,0.00024283194,0.0002357434,0.00017941606,0.00026639123,0.0000845103,0.001051625],"category_scores_gemma":[0.013257826,0.00011451685,0.000030871284,0.0011033203,0.0002067146,0.00017434516,0.000053398766,0.00018755277,0.000022476252],"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":[0.0065801586,0.00206298,0.5271822,0.000062456915,0.00012470601,0.000029838404,0.0021470475,0.0071184924,0.0042764824,0.011827021,0.003908586,0.43467999],"study_design_scores_gemma":[0.0005246933,0.00064471684,0.9721419,0.00009819966,0.000010781832,0.00009627269,0.00027261852,0.00031362302,0.00006662245,0.02092715,0.0046982737,0.00020512838],"about_ca_topic_score_codex":0.000022000564,"about_ca_topic_score_gemma":0.000014088469,"teacher_disagreement_score":0.4449597,"about_ca_system_score_codex":0.00004086659,"about_ca_system_score_gemma":0.000086369604,"threshold_uncertainty_score":0.99986154},"labels":[],"label_agreement":null},{"id":"W2093729006","doi":"10.1080/10705511.2013.742385","title":"Multiplicity Control in Structural Equation Modeling: Incorporating Parameter Dependencies","year":2013,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":58,"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":"Bonferroni correction; Mathematics; Statistics; Type I and type II errors; Multiplicity (mathematics); Multiple comparisons problem; Structural equation modeling; Econometrics; Mathematical analysis","score_opus":0.3600477337163394,"score_gpt":0.4263533006677822,"score_spread":0.0663055669514428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093729006","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":[0.5402643,0.00012446765,0.45792425,0.00044858005,0.0007108019,0.00041130962,0.000007024295,0.000055227272,0.000054023858],"genre_scores_gemma":[0.8538043,0.0000083757095,0.14562047,0.00006872851,0.0003855867,0.000036585094,0.000013952305,0.000033642173,0.000028373044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99083626,0.0015031784,0.003224528,0.0010189814,0.002505636,0.00091142295],"domain_scores_gemma":[0.98652095,0.008858918,0.0016730776,0.00071752275,0.001824661,0.00040484476],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008150473,0.00054652465,0.0008917352,0.0015253918,0.0013242688,0.0013432386,0.0012275763,0.00031443595,0.00026995922],"category_scores_gemma":[0.042104654,0.00039011115,0.0003580066,0.0017480813,0.000119127035,0.0031357885,0.00035058416,0.0013512908,0.00005562074],"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":[0.00008692501,0.000011604406,0.10754252,0.0000060235902,0.000020175117,0.000008618397,0.001412868,0.8624508,0.002312873,0.00017312904,0.000005818459,0.02596869],"study_design_scores_gemma":[0.0014120104,0.00008846659,0.019877693,0.00004809271,0.000013862768,0.000117550015,0.0032955718,0.70293516,0.00002231079,0.2718379,1.340989e-7,0.00035126618],"about_ca_topic_score_codex":0.0007929025,"about_ca_topic_score_gemma":0.000097555574,"teacher_disagreement_score":0.31353998,"about_ca_system_score_codex":0.000361403,"about_ca_system_score_gemma":0.00022219199,"threshold_uncertainty_score":0.99997586},"labels":[],"label_agreement":null},{"id":"W2093980226","doi":"10.1177/00131640021971005","title":"Implications of Test Dimensionality for Unidimensional Irt Scoring: An Investigation of a High-Stakes Testing Program","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"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":"Item response theory; Psychology; Curse of dimensionality; Test (biology); Statistics; Psychometrics; Item analysis; Equating; Test validity; Homogeneous; Social psychology; Econometrics; Mathematics; Clinical psychology; Developmental psychology; Rasch model","score_opus":0.7984940592344482,"score_gpt":0.517856493671935,"score_spread":0.2806375655625132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093980226","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":[0.9937441,0.0002021197,0.00059670804,0.0034860328,0.00020922782,0.00056511845,0.000054933622,0.000028731916,0.0011130525],"genre_scores_gemma":[0.8504468,0.0000061183628,0.14903587,0.0001679182,0.00011136513,0.00014116334,0.000018587098,0.000005223329,0.00006696021],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969567,0.00028684756,0.0009214913,0.0005919157,0.0010356135,0.00020740481],"domain_scores_gemma":[0.984076,0.013222607,0.00043643024,0.00042343297,0.0016547948,0.000186716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005544698,0.0001461046,0.00031477143,0.00017397407,0.00020171859,0.000038594742,0.00033678842,0.00008099141,0.00041491725],"category_scores_gemma":[0.025710337,0.000101210746,0.000071658375,0.0010182635,0.00028820962,0.00013236383,0.000027044774,0.00009658598,0.0000038219464],"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":[0.000120659926,0.0023374727,0.48206806,0.000029770748,0.000026435002,1.04050436e-7,0.00018627054,0.00017779302,0.01624948,0.01931993,0.0018472747,0.47763675],"study_design_scores_gemma":[0.00025091766,0.0007390978,0.7217013,0.00003186986,0.000010780818,0.00000645732,0.00005236245,0.00009603452,0.000321545,0.27637053,0.00033319302,0.0000859018],"about_ca_topic_score_codex":0.00004625928,"about_ca_topic_score_gemma":0.0000036125402,"teacher_disagreement_score":0.47755083,"about_ca_system_score_codex":0.000029858955,"about_ca_system_score_gemma":0.00012236451,"threshold_uncertainty_score":0.9824965},"labels":[],"label_agreement":null},{"id":"W2095820822","doi":"10.3102/1076998610397052","title":"Sampling Variability and Axioms of Classical Test Theory","year":2011,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Statistics; Sampling (signal processing); Sample size determination; Statistical hypothesis testing; Test theory; Sample (material); Test (biology); Axiom; Reliability (semiconductor); Population; Applied mathematics; Psychometrics; Computer science; Geometry","score_opus":0.6043028112079372,"score_gpt":0.5189607433140067,"score_spread":0.0853420678939305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095820822","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":[0.90815973,0.0001541333,0.09057342,0.0001906162,0.00044113206,0.000036910576,0.0000921003,0.0000012188265,0.00035072383],"genre_scores_gemma":[0.74670196,0.00001991147,0.25308722,0.000015265494,0.0000731183,4.5746455e-7,7.6158034e-7,0.0000023020634,0.000099007564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984322,0.00020498995,0.0007058194,0.00012849116,0.0004336511,0.00009480095],"domain_scores_gemma":[0.9658836,0.03264575,0.00061892194,0.00010470113,0.00062398,0.00012301879],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043551717,0.00006953646,0.0002456592,0.00016824855,0.000070283415,0.00003915594,0.00017866811,0.000041535535,0.0005616203],"category_scores_gemma":[0.04670079,0.000044661585,0.000033977274,0.0002836991,0.00025127738,0.0001131022,0.000051540963,0.00014298095,9.951376e-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":[0.00004533863,0.00048243452,0.78752583,0.0000071270897,0.0000068704576,0.0000016641899,0.0005504552,6.6082777e-7,0.0002734412,0.059807274,0.0005136216,0.15078527],"study_design_scores_gemma":[0.00009113545,0.00021065338,0.6393028,0.000008906598,0.000025495363,0.00005158123,0.00037867416,0.000019709467,0.000020833852,0.3597346,0.00011869108,0.000036932746],"about_ca_topic_score_codex":0.000016171414,"about_ca_topic_score_gemma":0.000001400932,"teacher_disagreement_score":0.29992732,"about_ca_system_score_codex":0.000012918025,"about_ca_system_score_gemma":0.00012746271,"threshold_uncertainty_score":0.9613293},"labels":[],"label_agreement":null},{"id":"W2096343999","doi":"10.1191/0265532203lt248oa","title":"Does item-level DIF manifest itself in scale-level analyses? Implications for translating language tests","year":2003,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":92,"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; Equivalence (formal languages); Psychology; Scale (ratio); Measurement invariance; Item response theory; Item analysis; Statistics; Test (biology); Psychometrics; Developmental psychology; Linguistics; Structural equation modeling; Mathematics; Confirmatory factor analysis","score_opus":0.6773012489253456,"score_gpt":0.5390986227521983,"score_spread":0.13820262617314727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096343999","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":[0.9085241,0.000791975,0.07255301,0.00050009455,0.0003716465,0.0006680805,0.00022360127,0.00027219008,0.016095296],"genre_scores_gemma":[0.67267895,0.0000014885725,0.3261494,0.00017053753,0.0001277178,0.00006777591,0.000010476823,0.00003100654,0.0007626727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958195,0.0005375626,0.001269155,0.00097087893,0.00059234165,0.00081057823],"domain_scores_gemma":[0.9392038,0.05879252,0.00057977653,0.0009333737,0.00030845153,0.00018210015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067473818,0.00032961855,0.00060644554,0.0008460847,0.00038192733,0.00031472635,0.0008995,0.0001509855,0.00012601065],"category_scores_gemma":[0.25759593,0.00020998971,0.00019117874,0.004788593,0.00007689429,0.00032620228,0.00008801077,0.00032671777,0.000022061904],"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":[0.000007264762,0.00009430339,0.68711156,0.00003705266,0.000016420128,0.000028158827,0.004096707,0.00019680226,0.052141923,0.00043189642,0.00011171434,0.2557262],"study_design_scores_gemma":[0.0011228053,0.000077574325,0.96406627,0.00015316941,0.00004474372,0.000088666464,0.015527273,0.0037632782,0.0028780722,0.011484906,0.00018875708,0.0006045162],"about_ca_topic_score_codex":0.0004920563,"about_ca_topic_score_gemma":0.0011195227,"teacher_disagreement_score":0.27695468,"about_ca_system_score_codex":0.00006955244,"about_ca_system_score_gemma":0.000095446296,"threshold_uncertainty_score":0.85631317},"labels":[],"label_agreement":null},{"id":"W2097672163","doi":"10.3102/1076998610396894","title":"A Didactic Presentation of Snijders’s <i> l <sub>z</sub> * </i> Index of Person Fit With Emphasis on Response Model Selection and Ability Estimation","year":2011,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"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":"Ambiguity; Estimator; Item response theory; Index (typography); Generalization; Statistics; Set (abstract data type); Mathematics; Sample (material); Computer science; Type (biology); Psychology; Artificial intelligence; Psychometrics","score_opus":0.4831390672638221,"score_gpt":0.47795792141914767,"score_spread":0.00518114584467444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097672163","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":[0.9279968,0.00003815647,0.071567535,0.00015644224,0.0000835257,0.00008466758,0.000048242917,0.0000014234174,0.000023207976],"genre_scores_gemma":[0.8923694,0.00001445079,0.10756717,0.000010455364,0.000015798867,0.0000022369043,0.0000017168503,0.0000041440717,0.000014669223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982486,0.00025728793,0.0005771857,0.0001544537,0.0006749631,0.00008753399],"domain_scores_gemma":[0.99228877,0.005593052,0.0010355064,0.00009161624,0.0009087942,0.000082275415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019126848,0.000090215304,0.00023594213,0.0003616071,0.00007528978,0.000031894655,0.00009640965,0.000047494206,0.000040643212],"category_scores_gemma":[0.00794147,0.00006276628,0.000031625295,0.00046804867,0.000130071,0.00025985946,0.000012929553,0.00012318336,3.1224158e-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":[0.004490989,0.0013119689,0.76510715,0.000047920817,0.00003472242,0.000002079413,0.0045299265,0.0031261935,0.0136751495,0.0008443357,0.00076732604,0.20606223],"study_design_scores_gemma":[0.0004317582,0.001378456,0.96429616,0.000040597686,0.00007357756,0.00005593544,0.0010517716,0.013429319,0.0029222446,0.01624481,0.0000020961006,0.00007328355],"about_ca_topic_score_codex":0.00007048729,"about_ca_topic_score_gemma":0.000015342885,"teacher_disagreement_score":0.20598894,"about_ca_system_score_codex":0.000038075577,"about_ca_system_score_gemma":0.00022566725,"threshold_uncertainty_score":0.95072544},"labels":[],"label_agreement":null},{"id":"W2100391776","doi":"10.1177/0146621606286206","title":"The Effect of Examinee Motivation on Test Construction Within an IRT Framework","year":2006,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Item response theory; Test (biology); Psychology; Statistics; Econometrics; Bayesian probability; Differential item functioning; Equating; Response bias; Computerized adaptive testing; Logistic regression; Social psychology; Mathematics; Psychometrics; Rasch model","score_opus":0.39513929299412376,"score_gpt":0.43041902804549487,"score_spread":0.03527973505137111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100391776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9554009,0.00006381226,0.018577538,0.00021735336,0.0011039231,0.0005712484,0.0000029720468,0.00008951559,0.023972757],"genre_scores_gemma":[0.9913583,0.0000032502846,0.008198657,0.00010469082,0.00023464453,0.00007033618,0.0000017088707,0.000009388245,0.000019062785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99499226,0.0007461641,0.000959552,0.00068082206,0.0023170086,0.0003042256],"domain_scores_gemma":[0.900653,0.09741246,0.0006613971,0.0009514213,0.00024084706,0.00008084677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01601647,0.00021961483,0.00037108126,0.00017840268,0.00030212864,0.00013059967,0.00072443555,0.00019430615,0.000060931445],"category_scores_gemma":[0.18148594,0.00010648172,0.000092076145,0.0014514823,0.00028319893,0.000051992425,0.000043052405,0.0003484516,0.00003054664],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007214034,0.00049939577,0.47882426,0.000007900531,0.000025914116,0.0000022681643,0.00007001842,0.0010970787,0.031194208,0.044846177,0.0019524766,0.4407589],"study_design_scores_gemma":[0.00056066096,0.0018524843,0.86367625,0.000019516157,0.000010324007,0.000004507788,0.0001194327,0.000060061397,0.0100764735,0.12312372,0.00035856717,0.00013798702],"about_ca_topic_score_codex":0.0000105858,"about_ca_topic_score_gemma":0.0000022632598,"teacher_disagreement_score":0.44062093,"about_ca_system_score_codex":0.00005631713,"about_ca_system_score_gemma":0.0000076658625,"threshold_uncertainty_score":0.82540876},"labels":[],"label_agreement":null},{"id":"W2100487390","doi":"10.1177/0022022105284492","title":"Evaluating the Effectiveness of Two-Stage Testing on English and French Versions of a Science Achievement Test","year":2006,"lang":"en","type":"article","venue":"Journal of Cross-Cultural Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision 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":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Ethnic group; Achievement test; Psychology; Differential item functioning; Sample (material); Mathematics education; Standardized test; Developmental psychology; Item response theory; Psychometrics; Sociology","score_opus":0.44850492638622674,"score_gpt":0.5900866364199733,"score_spread":0.14158171003374653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100487390","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":[0.9909627,0.00022104957,0.00040746684,0.00013351678,0.001086318,0.00015410568,0.000010183824,0.000006777417,0.007017868],"genre_scores_gemma":[0.9895878,0.0000054085385,0.010120637,0.000056905687,0.00016663624,0.0000017713,2.3032757e-7,0.000004982991,0.000055650005],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99556714,0.00094572414,0.0013162658,0.00037010503,0.0014826449,0.0003181297],"domain_scores_gemma":[0.9305409,0.06260883,0.002062175,0.0003805353,0.0043249773,0.000082576946],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033738643,0.00015524995,0.00051166303,0.00049591664,0.00043317606,0.00021248001,0.001058239,0.000066477034,0.000024139275],"category_scores_gemma":[0.2391281,0.00007762541,0.00013675264,0.0027752193,0.0025889461,0.0005231047,0.00018419907,0.00038645166,0.0000013541273],"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":[0.0002168598,0.00021474529,0.6462756,0.000018525056,0.000016832777,0.0000067576575,0.0003705038,0.0021748198,0.32805908,0.00083480024,0.00014593,0.0216656],"study_design_scores_gemma":[0.0015884218,0.0022022976,0.97766334,0.000114141956,0.000016402315,0.00007287588,0.00043671118,0.00045735034,0.0054053892,0.011849575,0.000104270126,0.00008924223],"about_ca_topic_score_codex":0.00007783158,"about_ca_topic_score_gemma":0.000003783492,"teacher_disagreement_score":0.33138776,"about_ca_system_score_codex":0.00004519997,"about_ca_system_score_gemma":0.00008929193,"threshold_uncertainty_score":0.9949694},"labels":[],"label_agreement":null},{"id":"W2102743086","doi":"10.1016/j.jpsychores.2010.01.006","title":"Introduction to health measurement scales","year":2010,"lang":"en","type":"review","venue":"Journal of Psychosomatic Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":499,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University Health Network; University of Toronto","funders":"","keywords":"Scale (ratio); Psychometrics; Psychology; Applied psychology; Psychometric testing; Clinical psychology; Internal consistency; Geography; Cartography","score_opus":0.8911488147396245,"score_gpt":0.6819205607602203,"score_spread":0.20922825397940414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102743086","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027156508,0.9759157,0.006309311,0.009985338,0.0059374855,0.00087427534,0.000004191028,0.000011540266,0.0009350312],"genre_scores_gemma":[0.0000065175973,0.952333,0.040998895,0.000058056386,0.0061401688,0.000024154571,4.3483212e-7,0.000036410936,0.0004023836],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.970606,0.008701554,0.0052780826,0.00079700816,0.013705105,0.00091220165],"domain_scores_gemma":[0.9483413,0.03946687,0.0041231983,0.002067543,0.005009593,0.0009915147],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19084466,0.00033561824,0.0030879132,0.0067835487,0.000360333,0.0007336563,0.0036268092,0.00030764472,0.0004872826],"category_scores_gemma":[0.36679786,0.00018874301,0.0008403392,0.010176538,0.00015044087,0.00022949147,0.00027486545,0.0031945538,0.00061488274],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008793988,0.00007718319,0.0000148113,0.00094260654,0.000042680847,0.0000053385616,0.00007470898,8.143766e-7,0.0000021006715,0.000060180384,0.23570621,0.76306456],"study_design_scores_gemma":[0.0001286453,0.00057907595,0.00020395298,0.0062745647,0.000023080624,0.0003682495,0.00021098374,0.0000028805482,4.451162e-7,0.008333193,0.9837253,0.00014963232],"about_ca_topic_score_codex":0.000010444334,"about_ca_topic_score_gemma":0.000012356034,"teacher_disagreement_score":0.76291496,"about_ca_system_score_codex":0.0005678665,"about_ca_system_score_gemma":0.0015059012,"threshold_uncertainty_score":0.9991051},"labels":[],"label_agreement":null},{"id":"W2103094000","doi":"10.1016/j.cct.2004.11.014","title":"Reliability, effect size, and responsiveness of health status measures in the design of randomized and cluster-randomized trials","year":2005,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute","keywords":"Intraclass correlation; Sample size determination; Reliability (semiconductor); Medicine; Randomized controlled trial; Statistics; Cluster randomised controlled trial; Cluster (spacecraft); Statistic; Sample (material); Statistical power; Measure (data warehouse); Psychometrics; Clinical psychology; Data mining; Power (physics); Computer science; Mathematics","score_opus":0.8355482434160791,"score_gpt":0.6232227419120829,"score_spread":0.2123255015039962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103094000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7994703,0.06518188,0.09964131,0.011075718,0.0014404849,0.022372952,0.00007018893,0.000042503114,0.0007046574],"genre_scores_gemma":[0.9771716,0.004052261,0.017856091,0.0005599059,0.00015535946,0.00015368979,0.0000011445272,0.000011396707,0.00003852562],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.06977646,0.8982386,0.027926318,0.0012895592,0.0022318542,0.00053722714],"domain_scores_gemma":[0.0067463154,0.98254687,0.00909231,0.0009477394,0.0004840302,0.00018273618],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.91542476,0.00030011183,0.015921041,0.000513338,0.00009647176,0.00012217075,0.0006901131,0.0002702024,0.00003082704],"category_scores_gemma":[0.9912652,0.00013265405,0.0014103849,0.0010190649,0.001546513,0.00023053886,0.00020493015,0.00037143865,0.0000011607152],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8099121,0.00015362688,0.008045722,0.000048613543,0.00016680772,0.0000015588832,0.00042499346,0.000069127476,0.000075527096,0.00014503802,0.0012773223,0.17967956],"study_design_scores_gemma":[0.9226895,0.0010757031,0.012182161,0.00024687644,0.00016427277,0.0000027810913,0.0003439481,0.0008078718,0.00011702009,0.06140933,0.00078508,0.00017543518],"about_ca_topic_score_codex":0.00020835864,"about_ca_topic_score_gemma":0.0000046431596,"teacher_disagreement_score":0.17950411,"about_ca_system_score_codex":0.000015994628,"about_ca_system_score_gemma":0.0005653197,"threshold_uncertainty_score":0.99868864},"labels":[],"label_agreement":null},{"id":"W2103615853","doi":"10.1080/10705510802154323","title":"Avoiding and Correcting Bias in Score-Based Latent Variable Regression With Discrete Manifest Items","year":2008,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","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":false,"ca_institutions":"Carleton University","funders":"","keywords":"Latent variable; Structural equation modeling; Latent variable model; Ordinary least squares; Econometrics; Statistics; Local independence; Regression; Regression analysis; Item response theory; Latent class model; Mathematics; Computer science; Psychometrics","score_opus":0.5332678160292689,"score_gpt":0.43389796024411,"score_spread":0.09936985578515889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103615853","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":[0.64377445,0.00020342834,0.35518602,0.00015637002,0.00046481504,0.00013351219,0.000001967481,0.000030400211,0.00004905509],"genre_scores_gemma":[0.89342904,0.00003419973,0.10628421,0.00001567535,0.00016100009,0.0000047051253,0.000004998209,0.000020293022,0.000045873887],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952086,0.001117767,0.0012118898,0.00062722806,0.0013455331,0.00048894185],"domain_scores_gemma":[0.9907226,0.007471005,0.00086353783,0.0002958621,0.00042312298,0.00022384794],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008550977,0.00029211357,0.0004612922,0.00094175496,0.002122996,0.000354241,0.00039792387,0.00011607484,0.00003354684],"category_scores_gemma":[0.01934883,0.00017268152,0.00008369859,0.0016053019,0.000107079264,0.0008362953,0.00017320328,0.0010578912,0.0000017685869],"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":[0.00018388114,0.000007922117,0.3796799,0.0000056460162,0.000005753995,0.00008098867,0.0010351652,0.6115899,0.00046664363,0.000041313226,0.0000023778043,0.0069005354],"study_design_scores_gemma":[0.0011891078,0.00015420548,0.07178511,0.00039632723,0.000009002414,0.0018437282,0.0020021354,0.91325873,0.00006525953,0.0090522785,8.0402634e-7,0.00024330548],"about_ca_topic_score_codex":0.00013401371,"about_ca_topic_score_gemma":0.000021279464,"teacher_disagreement_score":0.3078948,"about_ca_system_score_codex":0.00017515049,"about_ca_system_score_gemma":0.00018440293,"threshold_uncertainty_score":0.9991761},"labels":[],"label_agreement":null},{"id":"W2104137131","doi":"10.1177/0894845310384593","title":"Using the Self-Directed Search in Research","year":2011,"lang":"en","type":"article","venue":"Journal of Career Development","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":true,"ca_institutions":"Université Laval","funders":"","keywords":"Psychology; Construct (python library); Item response theory; Confirmatory factor analysis; Psychometrics; Construct validity; Test validity; Social psychology; Item analysis; Developmental psychology; Statistics; Structural equation modeling; Computer science; Mathematics","score_opus":0.9420385114053806,"score_gpt":0.5890046795798196,"score_spread":0.35303383182556103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104137131","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":[0.98886836,0.00048724192,0.0019160919,0.00024048144,0.00064342277,0.000110550536,2.1207066e-7,0.000017616356,0.0077160127],"genre_scores_gemma":[0.69731635,0.000022133943,0.30240163,0.000039610808,0.0000733927,0.0000012550406,3.1864786e-8,0.0000060630377,0.00013956192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99360025,0.0016400887,0.0010708887,0.0001857054,0.0031082944,0.00039478694],"domain_scores_gemma":[0.9865709,0.010469152,0.00033025522,0.00031566687,0.0021921494,0.00012190593],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055696104,0.00008401947,0.00026845225,0.0014878499,0.00019843846,0.00012738327,0.0013534762,0.00005938462,0.00019889392],"category_scores_gemma":[0.026763039,0.000043228185,0.00006608634,0.0040130415,0.00007239525,0.00017208715,0.0002895262,0.00064137706,0.000016411981],"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":[0.00014270852,0.00018962464,0.7045145,0.000009127759,0.000094245624,0.00029791557,0.040510386,0.00014862725,0.00059234403,0.00019353039,0.0069114994,0.24639548],"study_design_scores_gemma":[0.0004017862,0.000086913526,0.970082,0.00007080875,0.000004331755,0.00018346528,0.0093920585,0.0007906931,0.0024888874,0.0046261624,0.011761519,0.000111394525],"about_ca_topic_score_codex":0.000051763403,"about_ca_topic_score_gemma":0.000021999538,"teacher_disagreement_score":0.30048552,"about_ca_system_score_codex":0.00023764504,"about_ca_system_score_gemma":0.00088793505,"threshold_uncertainty_score":0.98143494},"labels":[],"label_agreement":null},{"id":"W2104142541","doi":"10.1016/j.erap.2010.07.001","title":"Measuring tolerance of ambiguity: Item polarity, dimensionality, and criterion validity","year":2010,"lang":"en","type":"article","venue":"European Review of Applied Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":25,"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 Guelph; University of Toronto","funders":"","keywords":"Psychology; Confirmatory factor analysis; Ambiguity; Trait; Humanities; Mathematics; Statistics; Structural equation modeling; Philosophy; Computer science","score_opus":0.5184182334434937,"score_gpt":0.4799720529830927,"score_spread":0.03844618046040099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104142541","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":[0.8375918,0.009379253,0.0017658428,0.0008253124,0.0012251126,0.0003650829,0.000018293795,0.00004084698,0.14878845],"genre_scores_gemma":[0.9658988,0.0047198315,0.026734928,0.0024538566,0.0001277219,0.0000035872233,0.0000026587777,0.000019887193,0.000038729355],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99572736,0.0011451715,0.0014290847,0.0006908186,0.0007583678,0.0002492236],"domain_scores_gemma":[0.9925132,0.004930441,0.0009499173,0.0011606363,0.00032907727,0.000116749674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020793974,0.00018470675,0.0008397234,0.00024015071,0.000079763086,0.00002661472,0.00092056877,0.00006899395,0.00027156645],"category_scores_gemma":[0.01785488,0.00013879602,0.00013694134,0.0010043789,0.00034771743,0.00006828779,0.0004364687,0.00040201287,0.000044639666],"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":[0.00010930873,0.00026238803,0.055911135,0.0018037907,0.000034596756,0.000015055935,0.0001832239,8.670172e-7,0.12639259,0.009465321,0.0076270355,0.7981947],"study_design_scores_gemma":[0.00052149117,0.00011675907,0.9002275,0.0007883152,0.00003194797,0.00007336518,0.000019813182,0.0000107421765,0.0011522038,0.01693306,0.079890124,0.00023471533],"about_ca_topic_score_codex":0.000007268244,"about_ca_topic_score_gemma":0.0000018990763,"teacher_disagreement_score":0.8443163,"about_ca_system_score_codex":0.0000036137533,"about_ca_system_score_gemma":0.00001562761,"threshold_uncertainty_score":0.99041814},"labels":[],"label_agreement":null},{"id":"W2104638892","doi":"10.1177/0163278709356192","title":"Identifying the Unauthorized Use of Examination Material","year":2009,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Medical Council of Canada","funders":"","keywords":"Outlier; Computer science; Psychology; Artificial intelligence","score_opus":0.8765739870349761,"score_gpt":0.6346960718444731,"score_spread":0.24187791519050306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104638892","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":[0.85906434,0.00040194538,0.06813454,0.06314167,0.0055373316,0.002608415,0.000019081184,0.000077615994,0.0010150349],"genre_scores_gemma":[0.9893186,0.000035299006,0.008552177,0.0011183653,0.00015386088,0.000050328836,0.000008121026,0.000005293841,0.00075791817],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9834226,0.012494371,0.0011826307,0.00030678115,0.0023081193,0.00028550648],"domain_scores_gemma":[0.97111297,0.025796698,0.0013023434,0.0008664715,0.00085214386,0.000069353686],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.070570536,0.00010011108,0.00024879747,0.00027570166,0.0012215448,0.00015608579,0.00064825173,0.00006697598,0.0005115719],"category_scores_gemma":[0.103820086,0.000044331355,0.000073473304,0.0021011191,0.00007846837,0.00031875665,0.00010463754,0.0002300602,0.000029862555],"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":[0.00005264199,0.0000673855,0.0012219683,0.0000075319967,0.0000075032076,1.3317455e-7,0.0063459454,0.00019658211,0.0014319725,0.005681551,0.013993337,0.97099346],"study_design_scores_gemma":[0.00045278954,0.00015368551,0.8450583,0.00010077326,0.000022529826,0.0000028672382,0.005427888,0.013215254,0.00022096555,0.13251156,0.0027508598,0.000082511615],"about_ca_topic_score_codex":0.00004894241,"about_ca_topic_score_gemma":0.000008281407,"teacher_disagreement_score":0.9709109,"about_ca_system_score_codex":0.00007135788,"about_ca_system_score_gemma":0.0003299636,"threshold_uncertainty_score":0.95704323},"labels":[],"label_agreement":null},{"id":"W2108880484","doi":"10.7202/1014757ar","title":"Évaluation d’un test de lecture en anglais par deux méthodes de détection du fonctionnement différentiel d’items","year":2013,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","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":true,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Humanities; Psychology; Philosophy","score_opus":0.6684438635785914,"score_gpt":0.4918251299314452,"score_spread":0.1766187336471462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108880484","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":[0.56622183,0.002028257,0.42189407,0.003990508,0.0029135568,0.0003679371,0.0000051559864,0.00006938173,0.0025092822],"genre_scores_gemma":[0.6713371,0.0008877827,0.32535678,0.00027631028,0.0009453542,0.00012812993,0.000005794287,0.000015358277,0.0010473655],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935093,0.0028373336,0.00086111703,0.0009193657,0.00090812694,0.0009647819],"domain_scores_gemma":[0.97967184,0.018041119,0.00072455674,0.0005425901,0.00070151984,0.0003183654],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021924457,0.0003126785,0.0003494884,0.0008277429,0.0019988345,0.0012981303,0.00095587113,0.00032009764,0.0011428904],"category_scores_gemma":[0.09250521,0.00028148424,0.00018630581,0.0048017907,0.00088729634,0.0013080376,0.00013256654,0.00034016473,0.00020272986],"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":[0.0000058222076,0.00033289005,0.28498018,0.00008276851,0.00001802919,0.0000020520235,0.014988124,0.00842576,0.009631605,0.0008607202,0.0034688252,0.67720324],"study_design_scores_gemma":[0.0002931882,0.00042324665,0.4889393,0.00020725903,0.00007488315,0.00038911137,0.0065960553,0.29837883,0.003006,0.19787149,0.0034698718,0.00035077147],"about_ca_topic_score_codex":0.003386979,"about_ca_topic_score_gemma":0.00035293263,"teacher_disagreement_score":0.67685246,"about_ca_system_score_codex":0.001665566,"about_ca_system_score_gemma":0.0008390356,"threshold_uncertainty_score":0.99996376},"labels":[],"label_agreement":null},{"id":"W2109560181","doi":"10.1111/j.1745-3992.2005.00002.x","title":"Using Dimensionality‐Based DIF Analyses to Identify and Interpret Constructs That Elicit Group Differences","year":2005,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Matching (statistics); Psychology; Selection (genetic algorithm); Curse of dimensionality; Contrast (vision); Cognitive psychology; Test (biology); Social psychology; Computer science; Statistics; Artificial intelligence; Mathematics","score_opus":0.8614623269368624,"score_gpt":0.6322567921565106,"score_spread":0.22920553478035177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109560181","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":[0.92710334,0.007943781,0.014774793,0.0469338,0.0009059166,0.00026780384,0.000012032606,0.000024513947,0.0020340176],"genre_scores_gemma":[0.8506394,0.00007271052,0.14711201,0.0018262304,0.0002556107,0.00000926067,0.0000019582046,0.000006194981,0.00007663307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956569,0.0010880899,0.00050174334,0.00057934725,0.001947805,0.00022612959],"domain_scores_gemma":[0.97234774,0.026050944,0.0003006471,0.00030843375,0.0007749212,0.00021730026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008691677,0.00018181783,0.00029999416,0.0003893523,0.00032935978,0.00062832015,0.00027635577,0.000052060353,0.00042145076],"category_scores_gemma":[0.10309957,0.00013318083,0.00004545771,0.0007507514,0.00011303038,0.0007332371,0.00012816882,0.00013179766,0.000021198057],"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":[0.000685163,0.0009832658,0.7105658,0.00007674759,0.0003353155,0.0000058897062,0.0037447189,0.00035707306,0.05656612,0.0129467035,0.016259607,0.19747359],"study_design_scores_gemma":[0.00041660672,0.00013552945,0.92905724,0.00017403427,0.00014781112,0.00008626118,0.0045570727,0.0014112875,0.0009648817,0.015176036,0.047465898,0.00040731873],"about_ca_topic_score_codex":0.0003800329,"about_ca_topic_score_gemma":0.0000348302,"teacher_disagreement_score":0.21849145,"about_ca_system_score_codex":0.00006594827,"about_ca_system_score_gemma":0.00011427232,"threshold_uncertainty_score":0.9044554},"labels":[],"label_agreement":null},{"id":"W2110072926","doi":"10.1007/bf03405008","title":"Is There Regional Variation in the SF-36 Scores of Canadian Adults?","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Eli Lilly (Canada); University of Toronto; Université Laval; Kingston Health Sciences Centre; University of Calgary; McGill University; McMaster University; Queen's University","funders":"Medical Research Council; Health Canada; Promotion and Mutual Aid Corporation for Private Schools of Japan; Medical Research Council Canada; Eli Lilly Canada; Dairy Farmers of Canada; Procter and Gamble; Eli Lilly and Company","keywords":"Normative; Multilevel model; SF-36; Variation (astronomy); Demography; Quality of life (healthcare); Psychology; Regional variation; Bayesian hierarchical modeling; Gerontology; Medicine; Bayesian probability; Health related quality of life; Bayesian inference; Statistics; Sociology; Disease; Pathology; Political science; Mathematics","score_opus":0.6952606420739589,"score_gpt":0.4414378629931276,"score_spread":0.2538227790808313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110072926","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":[0.6903034,0.0057336586,0.0008824501,0.292436,0.00084813364,0.00019699521,0.000053886004,0.0000029116136,0.0095425695],"genre_scores_gemma":[0.98984057,0.00022486785,0.002059463,0.0075828433,0.00015527797,0.0000010788459,6.0772874e-7,0.000005933588,0.00012935705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959353,0.0013024192,0.0010984376,0.00018071095,0.00085595384,0.0006271283],"domain_scores_gemma":[0.99137276,0.0051514567,0.0009606974,0.00039006822,0.0006535219,0.0014714933],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020655572,0.000093862676,0.00031639723,0.0043633645,0.0002241169,0.00020208013,0.0012085321,0.000080062746,0.001411024],"category_scores_gemma":[0.044596408,0.000058834285,0.000100277466,0.005478853,0.00010099708,0.00031053892,0.000007691103,0.00035841906,0.000013801709],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039499764,0.000023668412,0.45173198,0.00001038665,0.000016161543,0.00005598633,0.017803082,0.000026709453,7.3362276e-7,0.0049558952,0.28360465,0.24176678],"study_design_scores_gemma":[0.0002514346,0.00013650247,0.7930148,0.000051509818,0.0000012215713,0.00011344673,0.0047420394,0.00046962113,2.1016318e-7,0.004779771,0.19638117,0.000058231355],"about_ca_topic_score_codex":0.7349159,"about_ca_topic_score_gemma":0.91769564,"teacher_disagreement_score":0.34128287,"about_ca_system_score_codex":0.00035610198,"about_ca_system_score_gemma":0.0053068968,"threshold_uncertainty_score":0.9995018},"labels":[],"label_agreement":null},{"id":"W2111039219","doi":"10.1177/0734282909335781","title":"Psychometric Assessment and Reporting Practices","year":2009,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Reliability (semiconductor); Test (biology); Sample (material); Psychometrics; Clinical psychology; External validity; Applied psychology; Social psychology","score_opus":0.7018021314899303,"score_gpt":0.6593700263291641,"score_spread":0.04243210516076623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111039219","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":[0.88096017,0.0012776144,0.040889997,0.034313243,0.0036899177,0.00019091289,0.0000024576714,0.000017994087,0.038657676],"genre_scores_gemma":[0.71635085,0.00016631006,0.281886,0.00067933265,0.0006018408,0.0000027618912,8.483646e-7,0.000006024067,0.00030605638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922867,0.00049455935,0.0037389523,0.00045712083,0.002733883,0.000288789],"domain_scores_gemma":[0.9537895,0.013365392,0.03023716,0.00053242967,0.0017535868,0.00032195004],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028729832,0.00019415082,0.0006192375,0.0018289221,0.00022828302,0.00056115724,0.00071991346,0.00007757963,0.0003834686],"category_scores_gemma":[0.10468954,0.00013143223,0.00021413414,0.0031875693,0.00005439462,0.0008420121,0.000044694567,0.0005607331,0.00000573232],"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":[0.000025989691,0.0005994338,0.6010333,0.0000043295836,0.00005433541,0.000008288184,0.000109467765,0.000052295214,0.0008484839,0.005339345,0.023596251,0.3683285],"study_design_scores_gemma":[0.00040612358,0.0004628793,0.8898313,0.000034202174,0.00002652413,0.0006033437,0.0011434222,0.00015916575,0.000009416333,0.09223736,0.014955943,0.0001303065],"about_ca_topic_score_codex":0.000004991594,"about_ca_topic_score_gemma":5.538276e-7,"teacher_disagreement_score":0.36819822,"about_ca_system_score_codex":0.00018216435,"about_ca_system_score_gemma":0.0007985333,"threshold_uncertainty_score":0.9957244},"labels":[],"label_agreement":null},{"id":"W2112868871","doi":"10.1111/medu.12202","title":"Evaluating the quality of medical multiple‐choice items created with automated processes","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quality (philosophy); Multiple choice; MEDLINE; Medical education; Psychology; Computer science; Medicine; Internal medicine; Political science","score_opus":0.5970176373843434,"score_gpt":0.6240804864393285,"score_spread":0.027062849054985016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112868871","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":[0.97726965,0.00034414604,0.0031435583,0.016819201,0.00057438674,0.0003760415,0.0000011312054,0.00014822625,0.0013236763],"genre_scores_gemma":[0.9920486,0.00001871809,0.0058902605,0.0014328558,0.00020505632,0.00012101476,0.0000070630067,0.000008458255,0.00026793126],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99012804,0.0016315728,0.0011173688,0.00040235865,0.0064698267,0.0002508088],"domain_scores_gemma":[0.49476242,0.48978558,0.0033969753,0.0026951004,0.008199539,0.0011603842],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024025438,0.00012584995,0.00033465383,0.00019318848,0.00017387434,0.00013390117,0.0013168553,0.00017851994,0.0036708985],"category_scores_gemma":[0.87695265,0.00005760076,0.0000427623,0.0032323017,0.0003574711,0.00020578454,0.00011645486,0.00030369338,0.000059591774],"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":[0.000027701768,0.00043110925,0.40899822,0.00007718059,0.00002504313,3.668148e-7,0.0010531889,0.000030436158,0.00018067822,0.00011374491,0.027230946,0.56183136],"study_design_scores_gemma":[0.0006574755,0.0002062282,0.87355816,0.0002453778,0.000013446503,0.000017278908,0.0032616016,0.11776553,0.00013525377,0.0019345767,0.002058564,0.00014652582],"about_ca_topic_score_codex":0.0040442483,"about_ca_topic_score_gemma":0.00016649844,"teacher_disagreement_score":0.8529272,"about_ca_system_score_codex":0.000027798906,"about_ca_system_score_gemma":0.0028046619,"threshold_uncertainty_score":0.9972399},"labels":[],"label_agreement":null},{"id":"W2113547422","doi":"","title":"Assessment of a Master of Education Counselling Application Selection Process Using Rasch Analysis and Generalizability Theory","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Northern British Columbia; Queen's University","funders":"","keywords":"Generalizability theory; Rasch model; Selection (genetic algorithm); Psychology; Item response theory; Process (computing); Rank (graph theory); Facet (psychology); Medical education; Applied psychology; Social psychology; Medicine; Psychometrics; Computer science; Clinical psychology; Artificial intelligence; Developmental psychology","score_opus":0.15720143135741146,"score_gpt":0.4492533197615061,"score_spread":0.2920518884040947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113547422","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":[0.48888788,0.0016719041,0.50920606,0.000027510061,0.00011216416,0.000050807957,0.0000022881159,0.0000011986164,0.000040172054],"genre_scores_gemma":[0.9772331,0.0046310434,0.017929567,0.00008766467,0.00009296466,0.0000015244206,7.0918924e-7,0.000007787234,0.00001562137],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99782693,0.00054014905,0.0008406269,0.00023123946,0.0004189493,0.00014208624],"domain_scores_gemma":[0.995171,0.0021860024,0.0011566806,0.00020512338,0.0010938123,0.000187351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01019353,0.00010610854,0.0004297342,0.0011366174,0.00012521222,0.000092560615,0.00020201186,0.000076442266,0.00004296003],"category_scores_gemma":[0.00012508231,0.00008330811,0.00009407471,0.0018481493,0.0001232404,0.00014765265,1.5717437e-7,0.00012717028,1.2666077e-7],"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":[0.000092531605,0.00006592986,0.65625733,0.0000666253,0.00028166332,1.7979072e-7,0.003907654,0.01582909,0.004961138,0.0034482577,0.00004065245,0.31504896],"study_design_scores_gemma":[0.00064885785,0.00031707715,0.07130142,0.000113620314,0.0003006281,0.000045775607,0.0005819576,0.14720988,0.0006915674,0.7740137,0.0045393426,0.00023616145],"about_ca_topic_score_codex":0.00030636444,"about_ca_topic_score_gemma":0.00060818676,"teacher_disagreement_score":0.77056545,"about_ca_system_score_codex":0.000014422337,"about_ca_system_score_gemma":0.00026969935,"threshold_uncertainty_score":0.35328943},"labels":[],"label_agreement":null},{"id":"W2116643860","doi":"10.1177/0013164410366683","title":"Using Cochran’s Z Statistic to Test the Kernel-Smoothed Item Response Function Differences Between Focal and Reference Groups","year":2010,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"University of Alberta","funders":"","keywords":"Type I and type II errors; Mathematics; Statistics; Kernel smoother; Kernel (algebra); Statistic; Smoothing; Nonparametric statistics; Test statistic; Differential item functioning; Kernel method; Statistical hypothesis testing; Item response theory; Computer science; Radial basis function kernel; Artificial intelligence; Psychometrics; Support vector machine","score_opus":0.7546464432633119,"score_gpt":0.5131096502165755,"score_spread":0.24153679304673636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116643860","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":[0.97388226,0.00019796133,0.016381906,0.0076525896,0.0009526667,0.00025925427,0.000024567822,0.000019808576,0.00062896305],"genre_scores_gemma":[0.9889438,0.000008548801,0.010009923,0.00054481876,0.000336088,0.00003620147,0.00000163886,0.000005355997,0.000113582806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965477,0.00076220644,0.0005129216,0.00064973714,0.0012643371,0.00026308038],"domain_scores_gemma":[0.9611433,0.037626605,0.0001991402,0.00037121453,0.0004102784,0.0002494255],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009894867,0.00017463563,0.00025736034,0.00017966423,0.00046467292,0.00027992454,0.0004132916,0.00010071898,0.00046757504],"category_scores_gemma":[0.087902226,0.00009121013,0.000033901564,0.0006948858,0.0002113241,0.00007913038,0.00008927649,0.00034849186,0.000029866358],"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":[0.00045897783,0.00035649101,0.85932845,0.000005839088,0.000022967435,8.722597e-7,0.0003994482,0.000002887369,0.012052662,0.0054362733,0.0021523172,0.11978284],"study_design_scores_gemma":[0.00019462257,0.000496687,0.9158918,0.000016451535,0.000015125699,0.000015026511,0.00027731434,0.000060094357,0.0000107090955,0.08085998,0.0020343869,0.00012778662],"about_ca_topic_score_codex":0.00003325279,"about_ca_topic_score_gemma":0.000026196001,"teacher_disagreement_score":0.11965506,"about_ca_system_score_codex":0.000027862472,"about_ca_system_score_gemma":0.00005713376,"threshold_uncertainty_score":0.91978073},"labels":[],"label_agreement":null},{"id":"W2123520859","doi":"10.1177/0013164407313371","title":"Note on a Confidence Interval for the Squared Semipartial Correlation Coefficient","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Confidence interval; Percentile; Mathematics; Coverage probability; Correlation coefficient; Sample size determination; Correlation; Mean squared error; Regression analysis; Linear regression; Interval (graph theory); Combinatorics","score_opus":0.7435488238248646,"score_gpt":0.511461499220875,"score_spread":0.23208732460398962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123520859","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":[0.34348157,0.001336987,0.60196227,0.03777026,0.0070470553,0.0011464411,0.000021286964,0.000050058326,0.0071840845],"genre_scores_gemma":[0.99441576,0.000027171249,0.00330133,0.0013141003,0.00038243472,0.00011784686,0.0000021643161,0.000003689284,0.00043550011],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99728316,0.00028019006,0.00046055453,0.00047831633,0.001293839,0.00020396675],"domain_scores_gemma":[0.9799644,0.018928284,0.0001980473,0.0003023308,0.00050862564,0.000098309145],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0053136954,0.00011969467,0.00016948198,0.000101130645,0.00052168156,0.0000744916,0.00037589882,0.000062901956,0.0003545678],"category_scores_gemma":[0.042883024,0.00006127334,0.00009273494,0.00046223108,0.0001942408,0.00004630456,0.00003217218,0.0001491296,0.00006251136],"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":[0.0019657041,0.00312241,0.06542368,0.000014144909,0.00008606559,0.0000042075667,0.0038759834,0.004963069,0.001535176,0.068518974,0.28997084,0.56051975],"study_design_scores_gemma":[0.0006899783,0.00085133174,0.9083482,0.000027788272,0.0000124586495,0.000050448012,0.00027367787,0.004612749,0.000067575595,0.044340298,0.040555235,0.00017023041],"about_ca_topic_score_codex":0.000007214739,"about_ca_topic_score_gemma":0.0000020337461,"teacher_disagreement_score":0.84292454,"about_ca_system_score_codex":0.000045257744,"about_ca_system_score_gemma":0.000051079856,"threshold_uncertainty_score":0.9651792},"labels":[],"label_agreement":null},{"id":"W2124330658","doi":"10.1002/per.771","title":"What multi‐method data tell us about construct validity","year":2010,"lang":"en","type":"article","venue":"European Journal of Personality","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Personality; Construct validity; Construct (python library); Structural equation modeling; Variance (accounting); Incremental validity; Econometrics; Psychometrics; Social psychology; Statistics; Developmental psychology; Computer science; Mathematics","score_opus":0.7336730929157311,"score_gpt":0.5325128347794967,"score_spread":0.2011602581362344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124330658","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":[0.86533684,0.000492609,0.11919713,0.0006157104,0.00800319,0.00007439668,0.00006368871,0.000025067277,0.0061913556],"genre_scores_gemma":[0.4811368,0.0001025642,0.51679367,0.0004188213,0.0011194802,9.649362e-8,0.0000026504451,0.00001956371,0.00040633048],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98864883,0.0069005885,0.0016298481,0.0006489394,0.0017928712,0.00037891706],"domain_scores_gemma":[0.9736817,0.020979136,0.0020256455,0.0018660378,0.0010125805,0.00043492918],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0893423,0.00021520245,0.0005783364,0.00033284593,0.00024476554,0.0009970164,0.0040674345,0.00005521471,0.0013275795],"category_scores_gemma":[0.15522642,0.00014276695,0.00026940965,0.0009896321,0.00033159144,0.0015172489,0.0007519927,0.00120992,0.00014498878],"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":[0.000092514056,0.00015801363,0.4115552,0.000010650002,0.00006228285,0.00042319088,0.0007271726,0.000014971534,0.004398362,0.00012381103,0.014280543,0.56815326],"study_design_scores_gemma":[0.0008485973,0.000113522445,0.8477405,0.00004270922,0.000034604785,0.0011248561,0.0010938905,0.0012223921,0.00017733799,0.00081928255,0.14656717,0.00021518282],"about_ca_topic_score_codex":0.000023238426,"about_ca_topic_score_gemma":0.00001531353,"teacher_disagreement_score":0.5679381,"about_ca_system_score_codex":0.000018561752,"about_ca_system_score_gemma":0.00014353191,"threshold_uncertainty_score":0.99958533},"labels":[],"label_agreement":null},{"id":"W2124721134","doi":"10.6000/1929-6029.2013.02.04.7","title":"Longitudinal Data Analysis of Symptom Score Trajectories Using Linear Mixed Models in a Clinical Trial","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","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":true,"route_about_ca":false,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Longitudinal data; Clinical trial; Mixed model; Generalized linear mixed model; Longitudinal study; Linear model; Flow chart; Repeated measures design; Statistics; Chart; Computer science; Sample size determination; Mathematics; Data mining; Medicine","score_opus":0.9085991657182378,"score_gpt":0.7010326407567958,"score_spread":0.207566524961442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124721134","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":[0.7009669,0.00012397734,0.29698285,0.0004768827,0.0011203613,0.00011162911,0.000106923755,0.0000013812138,0.000109083885],"genre_scores_gemma":[0.88977486,0.00034272159,0.10936446,0.0000278586,0.0004524177,0.000002054711,0.000012817882,0.000006352547,0.000016464253],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98229206,0.0027722062,0.0037935309,0.00043185076,0.010359905,0.00035042243],"domain_scores_gemma":[0.7218342,0.2672759,0.0017502754,0.0009737661,0.0076428293,0.0005230722],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07898181,0.00010498383,0.00085584883,0.004481344,0.00003755523,0.00016643046,0.004318073,0.00017237994,0.0011290379],"category_scores_gemma":[0.6311961,0.000073456344,0.00014753222,0.004595609,0.00061329355,0.00047530883,0.00089545734,0.001418311,0.000004562311],"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":[0.004298888,0.00088540296,0.6687354,0.000009470293,0.0007635109,0.00072682713,0.00028710547,0.006442528,0.000018317165,0.0053155343,0.0031733573,0.3093437],"study_design_scores_gemma":[0.005345694,0.00027149273,0.2760392,0.00013062732,0.000034106677,0.000018398596,0.00045487308,0.6426274,0.0000031073755,0.07495002,0.00006115417,0.00006389807],"about_ca_topic_score_codex":0.0011310471,"about_ca_topic_score_gemma":0.00040787918,"teacher_disagreement_score":0.6361849,"about_ca_system_score_codex":0.00013725809,"about_ca_system_score_gemma":0.0010952242,"threshold_uncertainty_score":0.99978405},"labels":[],"label_agreement":null},{"id":"W2125001590","doi":"10.1016/j.jml.2007.12.005","title":"Mixed-effects modeling with crossed random effects for subjects and items","year":2008,"lang":"en","type":"article","venue":"Journal of Memory and Language","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8560,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Developmental psychology; Cognitive psychology; Social psychology","score_opus":0.2151326486886005,"score_gpt":0.3957748843215883,"score_spread":0.1806422356329878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125001590","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":[0.8803278,0.006127556,0.11269323,0.000052603587,0.00035954555,0.00019101074,0.0000012502665,0.000009345242,0.000237654],"genre_scores_gemma":[0.9763307,0.00010403158,0.022999806,0.00013448342,0.00023428143,0.0000035439102,1.9514232e-7,0.000009140691,0.00018382876],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983518,0.00031099457,0.00043270717,0.0002041264,0.00049578934,0.00020455132],"domain_scores_gemma":[0.97488385,0.024242338,0.00038579825,0.00015728404,0.000183739,0.00014698517],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004823345,0.00012748945,0.0005011257,0.0003192356,0.00023637727,0.000109468565,0.00019447497,0.00006378157,0.0000054496013],"category_scores_gemma":[0.026852837,0.000070428105,0.00008893481,0.00038675795,0.000088923705,0.00024245302,0.000035284513,0.00017634228,5.405618e-7],"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":[0.009282594,0.00037730913,0.04519222,0.0009080021,0.00047631082,0.0045795776,0.036253855,0.006151386,0.06749357,0.00031214027,0.0047190506,0.824254],"study_design_scores_gemma":[0.17775229,0.019665143,0.28763208,0.0034471825,0.0010530356,0.037462533,0.056154408,0.23789853,0.14535388,0.027531628,0.002470763,0.0035785444],"about_ca_topic_score_codex":0.000010210779,"about_ca_topic_score_gemma":0.0000032448374,"teacher_disagreement_score":0.82067543,"about_ca_system_score_codex":0.000007771281,"about_ca_system_score_gemma":0.000035394278,"threshold_uncertainty_score":0.9813444},"labels":[],"label_agreement":null},{"id":"W2125389120","doi":"10.1177/0272989x04265483","title":"From Diagnostic Accuracy to Accurate Diagnosis: Interpreting a Test Result with Confidence","year":2004,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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":"Statistics; Confidence interval; Logit; Logistic regression; Statement (logic); Transformation (genetics); Computer science; Sample (material); Positive predicative value; Test (biology); Econometrics; Diagnostic accuracy; Pre- and post-test probability; Mathematics; Data mining; Predictive value; Medicine","score_opus":0.202435274144168,"score_gpt":0.48219096307565,"score_spread":0.279755688931482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125389120","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.4003288,0.00032294003,0.59241724,0.004393571,0.00093073753,0.00031086005,0.00002263647,0.00013367123,0.0011395396],"genre_scores_gemma":[0.85422707,0.000068110574,0.14127271,0.00391722,0.00037422165,0.000090709436,0.0000016776296,0.00002719168,0.000021074407],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901219,0.000471482,0.0017766065,0.0014783348,0.0053952644,0.00075640064],"domain_scores_gemma":[0.19334711,0.8016982,0.0010122436,0.0019818149,0.00084029586,0.0011202998],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010527752,0.0003686668,0.00074801204,0.0007365003,0.00036172275,0.0008680262,0.0029593573,0.00023513305,0.0019759838],"category_scores_gemma":[0.9380154,0.00022833073,0.0001443811,0.004300513,0.00021018158,0.00048518024,0.0010863113,0.00070323906,0.00088946125],"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":[0.00017117639,0.00011617738,0.054590635,0.000003207943,0.000015559572,0.00075029494,0.0010039174,0.0014587262,0.00004561034,0.0002918347,0.005796375,0.9357565],"study_design_scores_gemma":[0.0050507183,0.0019737156,0.36676586,0.020477114,0.00008363756,0.00035513646,0.006240654,0.007926827,0.00094866444,0.55587614,0.03244492,0.0018566188],"about_ca_topic_score_codex":0.0002591902,"about_ca_topic_score_gemma":0.00015297292,"teacher_disagreement_score":0.9338999,"about_ca_system_score_codex":0.00012506027,"about_ca_system_score_gemma":0.00029604963,"threshold_uncertainty_score":0.9998885},"labels":[],"label_agreement":null},{"id":"W2125395656","doi":"10.1348/135910706x147781","title":"Does the easy–difficult item measure attitude or perceived behavioural control?","year":2007,"lang":"en","type":"article","venue":"British Journal of Health Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"Health Canada; Université Laval","funders":"","keywords":"Structural equation modeling; Psychology; Confirmatory factor analysis; Discriminant validity; Variance (accounting); Dimension (graph theory); Set (abstract data type); Measure (data warehouse); Control (management); Path analysis (statistics); Theory of planned behavior; Psychometrics; Social psychology; Cognitive psychology; Clinical psychology; Statistics; Computer science; Data mining; Mathematics; Artificial intelligence","score_opus":0.4398585706074593,"score_gpt":0.520169215833287,"score_spread":0.0803106452258277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125395656","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":[0.903535,0.007805133,0.03930061,0.036397852,0.010525783,0.00057455606,0.000072936804,0.000056901303,0.0017311986],"genre_scores_gemma":[0.9763779,0.0005605237,0.0065658274,0.015156315,0.00072948553,0.0000029565313,0.0000014068437,0.000019483958,0.00058607274],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99128246,0.0030305292,0.0027764365,0.00045435032,0.0016099121,0.0008463195],"domain_scores_gemma":[0.97308713,0.022249535,0.0023649808,0.0005030977,0.0014236317,0.00037159602],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043917112,0.00019373983,0.00091420294,0.00045993432,0.00062597333,0.00024208357,0.0016587304,0.0001997519,0.0009386955],"category_scores_gemma":[0.08805233,0.00009023741,0.00028266478,0.0015770026,0.00024839683,0.00021448518,0.000061731866,0.001070871,0.00003724701],"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":[0.0004301048,0.0001896845,0.13993901,0.000006869003,0.00004666578,0.0006685543,0.00027375936,0.000006201652,0.00008393874,0.00002131473,0.07243079,0.7859031],"study_design_scores_gemma":[0.0020745674,0.00055249134,0.9400322,0.00014234816,0.000014661156,0.0115073705,0.00082100584,0.0000076915585,0.0000015451183,0.00065059285,0.04407099,0.00012456722],"about_ca_topic_score_codex":0.00014296721,"about_ca_topic_score_gemma":0.00067573274,"teacher_disagreement_score":0.8000932,"about_ca_system_score_codex":0.00008616647,"about_ca_system_score_gemma":0.00034484835,"threshold_uncertainty_score":0.9999746},"labels":[],"label_agreement":null},{"id":"W2126395473","doi":"","title":"Testing for multigroup equivalence of a measuring instrument: a walk through the process.","year":2008,"lang":"en","type":"article","venue":"PubMed","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":737,"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":"Equivalence (formal languages); Psychology; Covariance; Social psychology; Computer science; Cognitive psychology; Mathematics; Statistics; Pure mathematics","score_opus":0.7434047361636618,"score_gpt":0.42969997137856575,"score_spread":0.313704764785096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126395473","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":[0.96311295,0.0005849348,0.022613766,0.00043810878,0.00044720175,0.0012264856,0.000008758398,0.00007505967,0.011492739],"genre_scores_gemma":[0.960082,0.000008873384,0.03863442,0.00009816324,0.000095014,0.0008996253,2.1025744e-7,0.00000962799,0.0001720832],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971178,0.00018600606,0.0007090909,0.00042906485,0.0010632415,0.00049478054],"domain_scores_gemma":[0.9677932,0.03052096,0.00058744324,0.0005225024,0.000505537,0.00007031243],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064506764,0.00012861706,0.00030472077,0.00015449687,0.00036923462,0.000057590078,0.0010981865,0.000049384034,0.000007608812],"category_scores_gemma":[0.25541753,0.00007262335,0.000112249945,0.0024255987,0.00021752958,0.000306575,0.00015203157,0.000120012555,0.0000024241467],"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":[0.000034041062,0.000045574394,0.14137554,0.0000310717,0.000016060396,0.0000020332025,0.0012522481,0.00017046824,0.00013211419,0.00020304603,0.0002460282,0.8564918],"study_design_scores_gemma":[0.0006892073,0.00006326734,0.95323277,0.000029049594,0.000013498565,0.000053964297,0.0012030292,0.0015706053,0.0023262529,0.03890895,0.001736098,0.00017330029],"about_ca_topic_score_codex":0.000058391102,"about_ca_topic_score_gemma":0.0000021513713,"teacher_disagreement_score":0.8563185,"about_ca_system_score_codex":0.000023659153,"about_ca_system_score_gemma":0.000045583776,"threshold_uncertainty_score":0.7508544},"labels":[],"label_agreement":null},{"id":"W2128090963","doi":"10.1080/00223980009598225","title":"Common Method Variance and Specification Errors: A Practical Approach to Detection","year":2000,"lang":"en","type":"article","venue":"The Journal of Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":274,"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":"LISREL; Variance (accounting); Bivariate analysis; Psychology; Social desirability; Econometrics; Construct (python library); Common-method variance; Structural equation modeling; Specification; Point (geometry); Statistics; Correlation; Variable (mathematics); Social psychology; Computer science; Mathematics","score_opus":0.5461551079132649,"score_gpt":0.5639502931705979,"score_spread":0.017795185257332924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128090963","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":[0.18376586,0.00019979259,0.7880756,0.007297485,0.00044433706,0.000102269,6.0105833e-7,0.000008329318,0.020105701],"genre_scores_gemma":[0.6077578,0.00013950113,0.390294,0.0012415999,0.00028466462,0.0000018955242,6.5159426e-8,0.0000067816204,0.00027367222],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957063,0.0026591416,0.00074380706,0.00021620166,0.0004959443,0.0001785835],"domain_scores_gemma":[0.9858345,0.012889736,0.0005371762,0.00044941143,0.00017979635,0.00010941042],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020398088,0.00008812518,0.00029504465,0.0003172632,0.00013248995,0.00006194514,0.00054195087,0.00008443445,0.00022613976],"category_scores_gemma":[0.014074911,0.00004844493,0.000054895798,0.0013265184,0.00008536795,0.00017484723,0.000033377553,0.00039997057,0.00005053737],"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":[0.0006054457,0.00011119648,0.0006805756,0.0000010744344,0.000019885394,0.0000037735365,0.0007762831,0.0002630278,0.0035795267,0.00043302707,0.0054016598,0.98812455],"study_design_scores_gemma":[0.0014363647,0.0016666705,0.57984966,0.000020224017,0.00009772756,0.013438401,0.0022355611,0.0041143335,0.0005920613,0.17503816,0.2212329,0.00027792758],"about_ca_topic_score_codex":0.0000110781075,"about_ca_topic_score_gemma":0.0000026308237,"teacher_disagreement_score":0.9878466,"about_ca_system_score_codex":0.00001577018,"about_ca_system_score_gemma":0.000015403846,"threshold_uncertainty_score":0.99423},"labels":[],"label_agreement":null},{"id":"W2128248024","doi":"10.1177/0146621609336540","title":"An Iterative Maximum a Posteriori Estimation of Proficiency Level to Detect Multiple Local Likelihood Maxima","year":2009,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Maximum a posteriori estimation; Estimator; Maxima; Maximum likelihood; Mathematics; Statistics; Focus (optics); A priori and a posteriori; Restricted maximum likelihood; M-estimator; Maximum likelihood sequence estimation; Estimation theory; Computer science","score_opus":0.4601168525429778,"score_gpt":0.45762144688310985,"score_spread":0.002495405659867944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128248024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34517577,0.000077496225,0.6483945,0.0004313317,0.00026558034,0.00082054385,0.000011653567,0.000087486915,0.004735601],"genre_scores_gemma":[0.8092932,0.0000020141554,0.18967657,0.00090184354,0.000046796344,0.00006251227,0.0000020622574,0.000008688827,0.000006283319],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9938284,0.0004766414,0.0012581142,0.0011847051,0.0026450476,0.00060704787],"domain_scores_gemma":[0.9959558,0.0015910215,0.00045229038,0.0010427701,0.00060905615,0.00034906235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008970705,0.0003241305,0.0006146411,0.00049982104,0.000181227,0.00015899453,0.0011871536,0.0001845597,0.00014595104],"category_scores_gemma":[0.012014431,0.0002167376,0.00013504199,0.0023767853,0.00011854831,0.00014949271,0.000082045706,0.0002538236,0.00012524436],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039521253,0.0004750317,0.0007481046,0.0000031273319,0.000008281066,0.0000040271284,0.0003432378,0.00089766283,0.07339801,0.0004868015,0.000262995,0.9229775],"study_design_scores_gemma":[0.0018030982,0.0057616984,0.7897471,0.00005121161,0.00002110837,0.000020431487,0.0008258669,0.0030818095,0.023216736,0.1745421,0.00034525053,0.0005835426],"about_ca_topic_score_codex":0.000009326013,"about_ca_topic_score_gemma":0.000004888982,"teacher_disagreement_score":0.922394,"about_ca_system_score_codex":0.00011294928,"about_ca_system_score_gemma":0.00003368443,"threshold_uncertainty_score":0.9963078},"labels":[],"label_agreement":null},{"id":"W2128389046","doi":"10.1080/00223980109603692","title":"Path Model Analyzed With Ordinary Least Squares Multiple Regression Versus LISREL","year":2001,"lang":"en","type":"article","venue":"The Journal of Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada; University of Calgary","funders":"","keywords":"LISREL; Structural equation modeling; Path coefficient; Ordinary least squares; Psychology; Path analysis (statistics); Statistics; Regression analysis; Econometrics; Social psychology; Mathematics","score_opus":0.5391317331368484,"score_gpt":0.5175969073043144,"score_spread":0.021534825832533966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128389046","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":[0.8616808,0.0010729673,0.1252914,0.0030512519,0.0011225514,0.00007782878,0.0000024003125,0.00001755392,0.0076832054],"genre_scores_gemma":[0.9696207,0.00043041314,0.028910547,0.00034785783,0.00024388786,0.0000010251586,2.5356925e-7,0.000013526696,0.00043176793],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99638283,0.0011801354,0.00086394453,0.00026088872,0.00097167684,0.00034053242],"domain_scores_gemma":[0.98276615,0.014722806,0.0012612971,0.0006517236,0.00045426487,0.00014373525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008554536,0.00017367164,0.00048131502,0.000591692,0.000224992,0.000055002918,0.0014491933,0.000110712106,0.00017750659],"category_scores_gemma":[0.01717223,0.00007442489,0.00014996753,0.0018238375,0.00022008298,0.00022887997,0.00010618573,0.0005202077,0.0000279429],"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":[0.054023135,0.0008709273,0.17994969,0.000009288864,0.00039564277,0.0010112994,0.0024948772,0.03805889,0.012505578,0.0002867337,0.15132026,0.5590737],"study_design_scores_gemma":[0.039531656,0.016006218,0.62300676,0.0005086504,0.00058763876,0.019862223,0.014083903,0.14520122,0.00033005283,0.09748926,0.041957036,0.0014353662],"about_ca_topic_score_codex":0.000013294391,"about_ca_topic_score_gemma":0.000009238654,"teacher_disagreement_score":0.5576383,"about_ca_system_score_codex":0.000025366273,"about_ca_system_score_gemma":0.00005170792,"threshold_uncertainty_score":0.99110657},"labels":[],"label_agreement":null},{"id":"W2130454355","doi":"10.1037/a0035213","title":"Situational bandwidth and the criterion-related validity of assessment center ratings: Is cross-exercise convergence always desirable?","year":2013,"lang":"en","type":"article","venue":"Journal of Applied Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Situational ethics; Convergence (economics); Criterion validity; Construct validity; Applied psychology; Perspective (graphical); Social psychology; Dimension (graph theory); Viewpoints; Incremental validity; Test validity; Assessment center; Psychometrics; Clinical psychology; Computer science; Artificial intelligence; Mathematics","score_opus":0.2605245428498293,"score_gpt":0.4825179232277115,"score_spread":0.2219933803778822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130454355","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":[0.9593643,0.00024832328,0.023682527,0.002477389,0.001352487,0.00032068754,0.0000074059662,0.000008149454,0.012538726],"genre_scores_gemma":[0.96889997,0.00027132191,0.029502332,0.0011249782,0.000075793105,0.000010397508,7.330022e-7,0.000007915325,0.00010656368],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99632627,0.00044868956,0.0017148146,0.0003291806,0.00092852267,0.00025252922],"domain_scores_gemma":[0.98621225,0.010459007,0.0019333373,0.00041439992,0.000860799,0.00012020624],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010980857,0.00015923474,0.0006447812,0.00034245974,0.00017962123,0.0001727665,0.00079031114,0.00014209763,0.0028593375],"category_scores_gemma":[0.0039826706,0.00008782946,0.0001671018,0.0007888132,0.00060605956,0.0002451615,0.000117433854,0.00040544954,0.000032224325],"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":[0.0017267009,0.0006878603,0.67686164,0.00004104265,0.00031256923,0.000014588448,0.004558988,0.00031061814,0.013216093,0.012038733,0.099558316,0.19067284],"study_design_scores_gemma":[0.0046522683,0.00020394934,0.728787,0.000034378558,0.000035359262,0.00018848441,0.00052008196,0.001235042,0.00035158938,0.26234674,0.0015043273,0.00014077972],"about_ca_topic_score_codex":0.0000083873565,"about_ca_topic_score_gemma":2.8557506e-7,"teacher_disagreement_score":0.25030804,"about_ca_system_score_codex":0.000017713464,"about_ca_system_score_gemma":0.00006374692,"threshold_uncertainty_score":0.9980522},"labels":[],"label_agreement":null},{"id":"W2130969147","doi":"10.1177/0013164412452564","title":"The Relationship Between Root Mean Square Error of Approximation and Model Misspecification in Confirmatory Factor Analysis Models","year":2012,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":123,"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; Confirmatory factor analysis; Statistics; Mathematics; Population; Cutoff; Factor analysis; Econometrics; Physics","score_opus":0.8678825713483123,"score_gpt":0.5198963884873063,"score_spread":0.3479861828610059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130969147","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":[0.9509001,0.0017421886,0.042977232,0.002387522,0.00014046534,0.00021925179,0.000012858667,0.000008379014,0.0016120244],"genre_scores_gemma":[0.99444175,0.000017142685,0.005340768,0.000030677445,0.00007110826,0.000035202218,0.000006359273,0.0000031077593,0.00005390581],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99722916,0.0005539751,0.0007073024,0.00031441118,0.0010033204,0.00019181555],"domain_scores_gemma":[0.988543,0.01038811,0.00034521802,0.00029735605,0.00030187788,0.00012445229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075779576,0.00010864872,0.00023779267,0.00034485338,0.00019952397,0.00006301185,0.00022926531,0.000083916304,0.00004083526],"category_scores_gemma":[0.012377111,0.00006407404,0.000063589076,0.001205762,0.0001245797,0.00021060395,0.000029994348,0.00014426814,0.0000033080094],"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":[0.000017031365,0.00013033047,0.964588,0.000004486167,0.000022145665,9.8313775e-9,0.00084108283,0.00037946057,0.000040608127,0.024627909,0.00014803218,0.009200902],"study_design_scores_gemma":[0.00012459508,0.000020854544,0.8544398,0.000006883301,0.000022625769,5.772437e-7,0.00045310773,0.0031969687,0.000006812667,0.14159171,0.00006805847,0.0000679831],"about_ca_topic_score_codex":0.000009985933,"about_ca_topic_score_gemma":0.000011623998,"teacher_disagreement_score":0.116963804,"about_ca_system_score_codex":0.000043961223,"about_ca_system_score_gemma":0.00002529704,"threshold_uncertainty_score":0.99594206},"labels":[],"label_agreement":null},{"id":"W2132885336","doi":"","title":"Comparison and Properties of Correlational and Agreement Methods for Determining Whether or Not to Report Subtest Scores","year":2014,"lang":"en","type":"article","venue":"International Journal of Learning Teaching and Educational 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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Statistics; Estimator; Scale (ratio); Test (biology); Psychology; Population; Econometrics; Clinical psychology; Mathematics; Medicine; Geography; Cartography; Environmental health","score_opus":0.7641883607625612,"score_gpt":0.6669834294211824,"score_spread":0.09720493134137886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132885336","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":[0.917543,0.00033890843,0.07565917,0.0054808226,0.00049157493,0.000098561075,0.0000013824285,0.0000026586968,0.0003839464],"genre_scores_gemma":[0.7863569,0.000019201836,0.2118317,0.00004374952,0.00028478677,0.000005345419,0.0000010237472,0.0000059827826,0.0014512769],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956926,0.0016550961,0.0008732156,0.00026183148,0.00134844,0.00016881875],"domain_scores_gemma":[0.913164,0.08361878,0.0007292099,0.000122948,0.0021949245,0.0001701184],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043028705,0.00008673425,0.00028182854,0.0009705829,0.0003483511,0.00028961606,0.00037624632,0.00004415776,0.0000412117],"category_scores_gemma":[0.42581928,0.00005706758,0.000043659555,0.00021076597,0.00016170587,0.00019786044,0.00020423718,0.0005603347,9.606606e-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":[0.00046893622,0.00007115002,0.5576235,0.000017521099,0.000055911107,0.0000012760942,0.0033241285,0.0006469046,0.0054532387,0.0014692047,0.0008373237,0.4300309],"study_design_scores_gemma":[0.00079464604,0.001145887,0.92129934,0.00060088583,0.000018857538,0.0008034591,0.006119225,0.024227126,0.000974563,0.012496833,0.03133276,0.00018642574],"about_ca_topic_score_codex":0.000054455006,"about_ca_topic_score_gemma":0.0000030615247,"teacher_disagreement_score":0.4298445,"about_ca_system_score_codex":0.0000430124,"about_ca_system_score_gemma":0.00020875897,"threshold_uncertainty_score":0.98540336},"labels":[],"label_agreement":null},{"id":"W2134792407","doi":"10.1186/1471-2288-12-159","title":"Should researchers use single indicators, best indicators, or multiple indicators in structural equation models?","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":422,"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":"Structural equation modeling; Latent variable; Path analysis (statistics); Econometrics; Computer science; Statistical model; Performance indicator; Confounding; Statistics; Risk analysis (engineering); Mathematics; Machine learning; Medicine; Economics","score_opus":0.9615285550475937,"score_gpt":0.6606017935692375,"score_spread":0.3009267614783562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134792407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.8312503,0.0017249936,0.16127895,0.0010477388,0.0013034514,0.0009707824,0.00002700877,0.000110688445,0.0022860453],"genre_scores_gemma":[0.7845387,0.00030499027,0.2131133,0.0002796279,0.0006282906,0.00016097663,0.00002340782,0.00006083049,0.0008898939],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.90006804,0.07724222,0.0029249238,0.0018473308,0.0140522765,0.0038651815],"domain_scores_gemma":[0.19536665,0.79659873,0.0010396732,0.0024140428,0.0007218213,0.0038591],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","research_integrity"],"category_scores_codex":[0.2797406,0.0004901982,0.0016074346,0.019172596,0.00055547367,0.00038098166,0.004226325,0.0015492885,0.0038931486],"category_scores_gemma":[0.93268144,0.00032583866,0.00029369813,0.02976135,0.0026445952,0.0016240469,0.0023370865,0.004276934,0.00019182298],"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":[0.00062986737,0.00029545717,0.65682465,0.000037798167,0.00003448917,0.000049767918,0.0014975249,0.00007872343,0.00017919876,0.005745786,0.0013952096,0.3332315],"study_design_scores_gemma":[0.007153624,0.0024055955,0.75109595,0.0004744467,0.000057487054,0.0002498536,0.02222594,0.06022914,0.0026702452,0.10261958,0.04893985,0.0018782992],"about_ca_topic_score_codex":0.0015309831,"about_ca_topic_score_gemma":0.0011562316,"teacher_disagreement_score":0.7193565,"about_ca_system_score_codex":0.0006479849,"about_ca_system_score_gemma":0.0025908367,"threshold_uncertainty_score":0.99991935},"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":"W2135663628","doi":"10.1177/0265532208097336","title":"Cognitive diagnostic assessment of L2 reading comprehension ability: Validity arguments for Fusion Model application to <i>LanguEdge</i> assessment","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":175,"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":"Reading comprehension; Psychology; Cognition; Test (biology); Profiling (computer programming); Dependability; Comprehension; Reading (process); Cognitive psychology; Computer science; Linguistics","score_opus":0.48241198306348876,"score_gpt":0.5159648486704076,"score_spread":0.033552865606918836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135663628","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":[0.53282154,0.00002596287,0.4643598,0.00004385342,0.00011908979,0.00073168735,0.000042698666,0.00007494368,0.0017804038],"genre_scores_gemma":[0.65655917,0.000003071366,0.34297705,0.00016932332,0.0000724407,0.00012644133,0.000022874297,0.000015533375,0.000054077384],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615526,0.00041592028,0.0010049554,0.00082364917,0.0011815485,0.0004186427],"domain_scores_gemma":[0.9124872,0.0851215,0.00071015797,0.0006375588,0.0008672672,0.0001762872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056074806,0.00023332296,0.00056621403,0.00035971837,0.0004046212,0.000060828457,0.00050980196,0.00009164836,0.000020187248],"category_scores_gemma":[0.13390343,0.00019093376,0.00012710292,0.0016911458,0.000076053315,0.00017613792,0.0003434014,0.00019873977,0.000007722714],"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":[0.000037648875,0.00037824857,0.6663653,0.000087881446,0.000023498758,0.000017019802,0.0021402892,0.011272374,0.10087872,0.00018096002,0.00061853585,0.21799952],"study_design_scores_gemma":[0.0009548515,0.00039295235,0.48630923,0.00024255402,0.000052464566,0.000025155636,0.0022547827,0.50187296,0.0033400976,0.0041631595,0.00004141528,0.00035041242],"about_ca_topic_score_codex":0.00012941996,"about_ca_topic_score_gemma":0.0000062281733,"teacher_disagreement_score":0.49060056,"about_ca_system_score_codex":0.00012656604,"about_ca_system_score_gemma":0.00012643693,"threshold_uncertainty_score":0.87339205},"labels":[],"label_agreement":null},{"id":"W2136085695","doi":"10.5539/ies.v6n6p185","title":"Rasch Model Analysis on the Effectiveness of Early Evaluation Questions as a Benchmark for New Students Ability","year":2013,"lang":"en","type":"article","venue":"International Education Studies","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rasch model; Cronbach's alpha; Psychology; Benchmark (surveying); Mathematics education; Relevance (law); Item analysis; Measure (data warehouse); Polytomous Rasch model; Item response theory; Psychometrics; Computer science; Developmental psychology; Data mining","score_opus":0.5771839040710531,"score_gpt":0.6243995894698064,"score_spread":0.047215685398753315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136085695","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":[0.9694271,0.00027948245,0.023533892,0.0019633048,0.0015512942,0.0008623137,0.00001126555,0.000012269197,0.0023590876],"genre_scores_gemma":[0.9918962,0.00002025626,0.006117557,0.00013936397,0.000086073014,0.0007319037,0.000008342729,0.000004117739,0.0009961895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996309,0.0008902167,0.00057822943,0.00039165132,0.001719973,0.000110928064],"domain_scores_gemma":[0.9080394,0.078257814,0.0006766324,0.0006948979,0.012256599,0.000074645664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012777668,0.00011222522,0.00028977176,0.000635107,0.00016810991,0.00016138563,0.000762678,0.000036292025,0.00026379694],"category_scores_gemma":[0.23481388,0.00006765957,0.00020307596,0.001562051,0.00008695855,0.00023893901,0.00011184067,0.00007404006,0.000037826074],"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":[0.00025626694,0.0008380691,0.76414555,0.000018307917,0.0028043787,2.8867793e-8,0.0024631089,0.029420491,0.00040175274,0.030365553,0.016746571,0.15253992],"study_design_scores_gemma":[0.00016701107,0.000045955145,0.62707585,0.000023731953,0.000110985835,1.51646e-7,0.0010867497,0.010082838,0.0000746512,0.36116537,0.00011529068,0.000051385134],"about_ca_topic_score_codex":0.00056391594,"about_ca_topic_score_gemma":0.000015110395,"teacher_disagreement_score":0.33079982,"about_ca_system_score_codex":0.00016449447,"about_ca_system_score_gemma":0.00030591135,"threshold_uncertainty_score":0.7716316},"labels":[],"label_agreement":null},{"id":"W2138855913","doi":"10.1109/vts.2009.65","title":"Panel: Analog Characterization and Test: The Long Road to Realization","year":2009,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Realization (probability); Test (biology); Characterization (materials science); Computer science; Materials science; Mathematics; Geology; Statistics","score_opus":0.4509411871263442,"score_gpt":0.4595981933710589,"score_spread":0.008657006244714716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138855913","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":[0.5780879,0.000031562926,0.4096962,0.005363639,0.00015609546,0.0001700931,0.0000027012663,0.00006422007,0.0064275884],"genre_scores_gemma":[0.9919625,0.000027813443,0.0032131844,0.0024604343,0.00007924855,0.0000021821927,0.0000044319677,0.0000028503348,0.0022473813],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99867624,0.0001667675,0.0003132376,0.00027559427,0.00042714318,0.00014101216],"domain_scores_gemma":[0.99284333,0.0064752717,0.00012633154,0.0003342556,0.00015167019,0.00006916979],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030673433,0.00006970468,0.00012259737,0.00023108936,0.00016011982,0.00027653735,0.0002948158,0.00003622726,0.000109458844],"category_scores_gemma":[0.068400964,0.000035808785,0.00002068199,0.0021732762,0.000020133239,0.00017104845,0.000047833564,0.000045929417,0.000031244927],"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":[0.00000341968,0.000009904696,0.14644031,2.956148e-7,8.9679827e-7,8.8305455e-7,0.00013360364,0.00001260685,0.001869022,0.0011949476,0.0007762859,0.8495578],"study_design_scores_gemma":[0.000055235807,0.00008069981,0.9902195,0.0000037134646,0.0000022879858,0.0000075812713,0.00009436772,0.001841854,0.00013797813,0.004822486,0.0026781997,0.000056100882],"about_ca_topic_score_codex":0.000024173236,"about_ca_topic_score_gemma":0.000008182886,"teacher_disagreement_score":0.8495017,"about_ca_system_score_codex":0.0000075310886,"about_ca_system_score_gemma":0.000008857015,"threshold_uncertainty_score":0.9394463},"labels":[],"label_agreement":null},{"id":"W2139763558","doi":"10.1007/0-306-47642-8_24","title":"Effects of Adaptations on Comparability of Test Items and Test Scores","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":20,"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":"Comparability; Test (biology); Statistics; Psychology; Econometrics; Computer science; Mathematics; Biology; Ecology","score_opus":0.25990932440754516,"score_gpt":0.3990953364307693,"score_spread":0.13918601202322411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139763558","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02534537,0.0027717664,0.00033164016,0.0003438874,0.00090235996,0.0010722239,0.00016961405,0.00010659499,0.96895653],"genre_scores_gemma":[0.67500484,0.00013048024,0.0056653637,0.00045565979,0.0005596187,0.000044697823,0.000014808758,0.000099588346,0.31802493],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99427986,0.00021145461,0.0020696274,0.0010754506,0.0019474068,0.00041622864],"domain_scores_gemma":[0.8464647,0.14990407,0.0018888512,0.00088426465,0.0006142434,0.0002438834],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0056261136,0.00050071947,0.0014049156,0.0015549033,0.00012097135,0.00019745517,0.0016183942,0.00092939084,0.00015014682],"category_scores_gemma":[0.17483549,0.00038769393,0.00029058542,0.00032680412,0.0010573203,0.00042159494,0.00037767008,0.0016236661,0.000017133209],"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":[0.00015758265,0.0002297543,0.08177638,0.0004941011,0.00023996655,0.000014324191,0.001452134,0.00006083725,0.0028554252,0.050284415,0.1397145,0.72272056],"study_design_scores_gemma":[0.0028743113,0.0015916468,0.19985475,0.0022371467,0.00037884238,0.00004412421,0.0003867527,0.00064131187,0.0024844261,0.40483436,0.38293153,0.0017408007],"about_ca_topic_score_codex":0.000044599776,"about_ca_topic_score_gemma":0.000008376515,"teacher_disagreement_score":0.7209798,"about_ca_system_score_codex":0.00007654722,"about_ca_system_score_gemma":0.00020652816,"threshold_uncertainty_score":0.9998575},"labels":[],"label_agreement":null},{"id":"W2139990047","doi":"10.1111/j.1745-3984.2011.00158.x","title":"Estimating Classification Consistency and Accuracy for Cognitive Diagnostic Assessment","year":2012,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":90,"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":"Consistency (knowledge bases); Reliability (semiconductor); Computation; Subtraction; Statistical inference; Fraction (chemistry); Inference; Sampling (signal processing); Computer science; Statistics; Cognitive test; Artificial intelligence; Cognition; Mathematics; Data mining; Pattern recognition (psychology); Algorithm; Psychology; Arithmetic","score_opus":0.7019996993223337,"score_gpt":0.5564925005972196,"score_spread":0.1455071987251142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139990047","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":[0.58665234,0.006511315,0.377991,0.016993066,0.007250973,0.00072237203,0.000015140549,0.0000070645992,0.0038567658],"genre_scores_gemma":[0.82965004,0.000015589521,0.16940598,0.00012705004,0.0007489567,0.000025736348,0.0000010177753,0.00000455033,0.000021083082],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969359,0.00033698537,0.00092437153,0.00014742394,0.0014636525,0.00019168895],"domain_scores_gemma":[0.84997684,0.14284824,0.0021388344,0.00018416549,0.004572833,0.00027909677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017558808,0.000093679846,0.00023304056,0.0003115727,0.00020032827,0.00012535001,0.0001975389,0.00003293531,0.000119017066],"category_scores_gemma":[0.5315195,0.00006586008,0.000087130415,0.00036701487,0.00006919448,0.00043805133,0.000026058246,0.00012299452,0.000004801077],"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":[0.000033282966,0.00048739565,0.7835364,0.000024465002,0.000085204476,1.8902321e-7,0.00048426323,0.00003324269,0.0009818539,0.007219022,0.006334284,0.20078039],"study_design_scores_gemma":[0.0004115498,0.00011554969,0.96144456,0.00012415549,0.000061725914,0.000049668753,0.0014492653,0.0005093646,0.000060753544,0.03462409,0.0010688805,0.00008043635],"about_ca_topic_score_codex":0.0000017025367,"about_ca_topic_score_gemma":5.771904e-7,"teacher_disagreement_score":0.51396066,"about_ca_system_score_codex":0.00015284776,"about_ca_system_score_gemma":0.00049172714,"threshold_uncertainty_score":0.60855675},"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":"W2142004159","doi":"10.3899/jrheum.130813","title":"Item Response Theory, Computerized Adaptive Testing, and PROMIS: Assessment of Physical Function","year":2013,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":208,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Computerized adaptive testing; Patient-Reported Outcomes Measurement Information System; Item response theory; Item bank; CLARITY; Medicine; Reliability (semiconductor); Standardization; Perspective (graphical); Short Forms; Construct (python library); Applied psychology; Function (biology); Psychometrics; Computer science; Psychology; Clinical psychology; Artificial intelligence","score_opus":0.23358601003491478,"score_gpt":0.4218876205134344,"score_spread":0.18830161047851965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142004159","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":[0.90419817,0.000121906785,0.0945632,0.00039939047,0.000283187,0.00012522635,7.284783e-7,0.000007852213,0.0003003129],"genre_scores_gemma":[0.9639931,0.000015074303,0.03589916,0.00003888801,0.000011670398,0.0000019866518,2.905115e-8,0.0000050120175,0.000035096495],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.993971,0.004418541,0.00080961845,0.000132092,0.0005059398,0.00016281176],"domain_scores_gemma":[0.85013586,0.147348,0.0015241792,0.00025024885,0.00067645,0.00006528357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015480898,0.00010315692,0.0005673713,0.00031051403,0.00010745173,0.000043464504,0.0005097551,0.000049591843,0.00005912826],"category_scores_gemma":[0.05904254,0.000049790666,0.000076972436,0.0006533259,0.00029402116,0.00016811882,0.00015330402,0.0002538413,0.0000056127337],"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":[0.0048678643,0.00029608907,0.5812816,0.00002271852,0.0003053717,0.0000059272647,0.002366733,0.00038023372,0.022717044,0.010727818,0.0033070133,0.3737216],"study_design_scores_gemma":[0.001060213,0.0024421643,0.7784851,0.00008228234,0.000042818636,0.0015931024,0.0019279938,0.0320612,0.00008814554,0.18202832,0.00010069169,0.000087927736],"about_ca_topic_score_codex":0.000039636143,"about_ca_topic_score_gemma":5.6068643e-7,"teacher_disagreement_score":0.37363368,"about_ca_system_score_codex":0.000014641913,"about_ca_system_score_gemma":0.00009269891,"threshold_uncertainty_score":0.94888353},"labels":[],"label_agreement":null},{"id":"W2142922174","doi":"10.1007/s11336-011-9233-5","title":"On the Relationships Between Jeffreys Modal and Weighted Likelihood Estimation of Ability Under Logistic IRT Models","year":2011,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Estimator; Statistics; Mathematics; Bayes estimator; Consistent estimator; Invariant estimator; Trimmed estimator; Bias of an estimator; Minimax estimator; Minimum-variance unbiased estimator; Efficient estimator; Item response theory; Modal; Econometrics; Logistic regression; Psychometrics","score_opus":0.7090760072091058,"score_gpt":0.4442213828420286,"score_spread":0.2648546243670772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142922174","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":[0.5941976,0.00020084433,0.39125627,0.00036821334,0.00024426568,0.0002541792,0.000021417047,0.00004271626,0.0134145245],"genre_scores_gemma":[0.9594801,0.000022147042,0.04030108,0.00006262405,0.000041259766,0.0000146699995,0.000003026639,0.00001279026,0.00006229197],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956795,0.0012143385,0.0010043628,0.0006396659,0.0011404474,0.00032171473],"domain_scores_gemma":[0.90401816,0.093661465,0.0006169114,0.0012030373,0.0003323088,0.00016811078],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0136354705,0.00020490118,0.0004478614,0.001273678,0.00029229367,0.00008920819,0.0007942107,0.00017890806,0.00032493647],"category_scores_gemma":[0.103213,0.00012117562,0.00011898748,0.0056767524,0.00031419584,0.00027811498,0.000115169234,0.00043657285,0.000053390286],"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":[0.00020326712,0.00045275394,0.42799684,0.000029651384,0.0001327484,0.0000012921323,0.0019015728,0.0022636654,0.000047366044,0.19542912,0.0021661886,0.36937556],"study_design_scores_gemma":[0.00019847708,0.000109439876,0.42176655,0.000011999708,0.000016316118,0.0000011269842,0.0002477995,0.014765526,0.00004539293,0.5627395,0.000012504278,0.00008537956],"about_ca_topic_score_codex":0.0000872723,"about_ca_topic_score_gemma":0.0000063740267,"teacher_disagreement_score":0.36929017,"about_ca_system_score_codex":0.00003562094,"about_ca_system_score_gemma":0.00003504231,"threshold_uncertainty_score":0.90434104},"labels":[],"label_agreement":null},{"id":"W2144487201","doi":"10.1080/10705510903008220","title":"Exploratory Structural Equation Modeling, Integrating CFA and EFA: Application to Students' Evaluations of University Teaching","year":2009,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1080,"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 Sherbrooke","funders":"Economic and Social Research Council","keywords":"Structural equation modeling; Confirmatory factor analysis; Goodness of fit; Latent variable; Psychology; Statistics; Measurement invariance; Environmental scanning electron microscope; Exploratory factor analysis; Econometrics; Mathematics","score_opus":0.3055562692897275,"score_gpt":0.48058043964339947,"score_spread":0.17502417035367196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144487201","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":[0.50777125,0.000086875974,0.49126208,0.00034012413,0.00021370055,0.00023270262,0.0000066832617,0.00003170827,0.000054867553],"genre_scores_gemma":[0.8408621,0.000014827256,0.15885419,0.00002798587,0.00018759971,0.0000024047583,0.000013977013,0.0000122339625,0.000024704588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940871,0.0013330525,0.0014639272,0.0006875217,0.0020470908,0.00038128233],"domain_scores_gemma":[0.994534,0.0024034905,0.0009797879,0.00047145464,0.0013230692,0.00028816957],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.010308223,0.0003011278,0.00048315647,0.0011791028,0.0016125882,0.00036329986,0.0009051192,0.00013961211,0.000021003458],"category_scores_gemma":[0.016854273,0.00024181322,0.00016020035,0.001194232,0.00005465569,0.001418235,0.00029213054,0.0007023928,0.000004364087],"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":[0.00013887385,0.000015652235,0.011120522,0.0000043279083,0.00001852908,0.0000016608922,0.0068221022,0.85617197,0.00450882,0.0012854321,0.000007472349,0.11990464],"study_design_scores_gemma":[0.00064695306,0.00023803533,0.009929092,0.00006863029,0.00003769656,0.000036114972,0.013139464,0.874589,0.000028284441,0.101053014,0.0000012820423,0.0002324252],"about_ca_topic_score_codex":0.00006261094,"about_ca_topic_score_gemma":0.00001568596,"teacher_disagreement_score":0.3330908,"about_ca_system_score_codex":0.00024915332,"about_ca_system_score_gemma":0.00014676152,"threshold_uncertainty_score":0.9996872},"labels":[],"label_agreement":null},{"id":"W2145470674","doi":"10.3138/ptc.59.2.142","title":"Factor Analysis: An Overview in the Field of Measurement","year":2007,"lang":"en","type":"article","venue":"Physiotherapy Canada","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Exploratory factor analysis; Factor (programming language); Computer science; Factor analysis; Principal component analysis; Confirmatory factor analysis; Field (mathematics); Set (abstract data type); Domain (mathematical analysis); A priori and a posteriori; Data mining; Statistics; Artificial intelligence; Machine learning; Mathematics; Structural equation modeling","score_opus":0.5499761139104052,"score_gpt":0.5421191846639567,"score_spread":0.00785692924644854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145470674","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":[0.9814422,0.00298021,0.0121152,0.001140763,0.00032189887,0.00016846997,0.000009233059,0.000008083284,0.0018139265],"genre_scores_gemma":[0.99647695,0.0000514517,0.00090224674,0.0025056812,0.00003993299,0.000001816977,4.180343e-7,0.000003019953,0.000018464289],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969538,0.00034335477,0.0004652996,0.00022340227,0.0018187161,0.00019541864],"domain_scores_gemma":[0.9893886,0.009595814,0.00021072986,0.000594441,0.00016218035,0.00004825053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062248153,0.00008144832,0.0002772302,0.00036502825,0.000043674565,0.000032052183,0.0007816002,0.00002340252,0.00034643168],"category_scores_gemma":[0.0045802346,0.00004493091,0.00008833105,0.004677918,0.000014509969,0.00006681608,0.000014467402,0.00008144386,6.560816e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009772956,0.00020062977,0.2637182,0.00001665998,0.0002711195,0.000015118784,0.0015307459,0.0006006471,0.007402888,0.0011572004,0.011088448,0.7139006],"study_design_scores_gemma":[0.00016617664,0.0000978978,0.9788576,0.000009606029,0.000013320451,3.3709628e-7,0.0013531308,0.00045790794,0.0016433232,0.0034525513,0.013838989,0.00010917875],"about_ca_topic_score_codex":0.4934032,"about_ca_topic_score_gemma":0.8447179,"teacher_disagreement_score":0.7151394,"about_ca_system_score_codex":0.000065726184,"about_ca_system_score_gemma":0.00017478944,"threshold_uncertainty_score":0.54832995},"labels":[],"label_agreement":null},{"id":"W2146332347","doi":"10.3968/j.css.1923669720120805.1148","title":"The Modification of Dichotomous and Polytomous Item Response Theory to Structural Equation Modeling Analysis","year":2012,"lang":"en","type":"article","venue":"Canadian social science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Structural equation modeling; LISREL; Polytomous Rasch model; Path analysis (statistics); Item response theory; Latent variable; Path coefficient; Statistics; Econometrics; Mathematics; Computer science; Psychometrics","score_opus":0.38125095853280105,"score_gpt":0.4669194581403637,"score_spread":0.08566849960756262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146332347","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":[0.959014,0.00022097537,0.038081236,0.00047686073,0.00021320472,0.00011197865,0.000011308464,0.000008411893,0.0018620351],"genre_scores_gemma":[0.99816084,0.000002487722,0.001564076,0.00011934875,0.000058676444,0.000004465649,3.4529364e-7,0.0000026003454,0.00008715381],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99755275,0.0005755394,0.00032914808,0.00026544603,0.00083256885,0.00044455816],"domain_scores_gemma":[0.99040806,0.008393265,0.00016572855,0.0002902998,0.0003386588,0.00040399973],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02374244,0.00006815252,0.00015040263,0.0009775374,0.001254355,0.000239228,0.0007173267,0.0000417939,0.000013172129],"category_scores_gemma":[0.07654815,0.000044715525,0.00005133172,0.0065257177,0.00038094647,0.0003171035,0.00006416471,0.00006799429,0.0000037349073],"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":[0.00015197646,0.0000059324207,0.26139027,0.00000141638,0.00003453278,8.6696815e-7,0.017780019,0.0012083495,0.005523205,0.04458933,0.000060219554,0.6692539],"study_design_scores_gemma":[0.0000921574,0.00003346845,0.7903298,0.0000027043964,0.000051584106,0.000002248315,0.017097915,0.16529562,0.00027603187,0.026043655,0.00057720474,0.00019757466],"about_ca_topic_score_codex":0.0040860535,"about_ca_topic_score_gemma":0.0018644197,"teacher_disagreement_score":0.6690563,"about_ca_system_score_codex":0.00017990281,"about_ca_system_score_gemma":0.00024132692,"threshold_uncertainty_score":0.9647611},"labels":[],"label_agreement":null},{"id":"W2146894730","doi":"10.1111/j.1745-3984.2011.00142.x","title":"Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees’ Cognitive Skills in Critical Reading","year":2011,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Cognition; Reading (process); Psychology; Reading comprehension; Set (abstract data type); Test (biology); Sample (material); Cognitive psychology; Hierarchy; Comprehension; Natural language processing; Computer science; Artificial intelligence; Linguistics","score_opus":0.7841432219145653,"score_gpt":0.5727164674921034,"score_spread":0.21142675442246195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146894730","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":[0.5697789,0.0015615835,0.41506308,0.0064773206,0.0030653388,0.00038100104,0.000012131861,0.000004992206,0.0036556215],"genre_scores_gemma":[0.83004683,0.000016325388,0.16911285,0.00043053186,0.0003407778,0.000011111352,2.2691854e-7,0.0000063139973,0.000035013432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938505,0.0018456966,0.0012844728,0.00027802368,0.0024136463,0.00032764007],"domain_scores_gemma":[0.7824945,0.20950288,0.0011439653,0.00043339978,0.005976571,0.00044870572],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030560607,0.00014967081,0.00038099886,0.00097401754,0.00017788821,0.00015256008,0.0007516015,0.00005307499,0.0005150815],"category_scores_gemma":[0.5533034,0.00008913259,0.00011936652,0.001946201,0.00009943532,0.0002297983,0.00009893554,0.00035189907,0.000015204718],"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":[0.00008297951,0.0007735586,0.8810499,0.000011353601,0.0000875634,0.00001818726,0.005708713,0.00030417828,0.0008558539,0.0060086204,0.0012066922,0.10389246],"study_design_scores_gemma":[0.00022912491,0.00017458553,0.9399502,0.0004299094,0.000039815313,0.000097209864,0.0031362067,0.00005977749,0.00053209753,0.054826837,0.0004018724,0.00012234577],"about_ca_topic_score_codex":0.00008189293,"about_ca_topic_score_gemma":0.000026222899,"teacher_disagreement_score":0.5227428,"about_ca_system_score_codex":0.00023448748,"about_ca_system_score_gemma":0.00065847125,"threshold_uncertainty_score":0.99824184},"labels":[],"label_agreement":null},{"id":"W2148623326","doi":"10.1111/j.1365-2923.2012.04289.x","title":"Using automatic item generation to create multiple‐choice test items","year":2012,"lang":"en","type":"article","venue":"Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":142,"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; Multiple choice; Licensure; Item bank; Context (archaeology); Test (biology); Certification; Item response theory; Process (computing); Artificial intelligence; Machine learning; Information retrieval; Psychometrics; Psychology; Medical education; Medicine","score_opus":0.6054844956655376,"score_gpt":0.5574866617688159,"score_spread":0.04799783389672174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148623326","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":[0.94129837,0.0003112696,0.049529888,0.0024847856,0.004477044,0.00022463693,0.0000016505635,0.000075470016,0.0015969004],"genre_scores_gemma":[0.9324903,0.00000447327,0.061688714,0.0029292735,0.0022286035,0.000031031104,0.0000070896776,0.00001155873,0.00060895225],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965877,0.00043269762,0.00068037387,0.0003338678,0.0015973639,0.00036801284],"domain_scores_gemma":[0.93504566,0.06236453,0.0004350242,0.00081241265,0.00048668665,0.0008556939],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00754963,0.0001246295,0.00022515777,0.00047376243,0.00020387134,0.00016235642,0.0004606701,0.00012444673,0.0011592926],"category_scores_gemma":[0.7219349,0.00009067009,0.000054440476,0.0020727764,0.00004246828,0.0003726033,0.00008944729,0.00015218774,0.0002914871],"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":[9.746194e-7,0.00022114275,0.5474888,0.00000503039,0.0000029981818,1.9625547e-7,0.0005292401,0.000023016377,0.0016262567,0.000045445275,0.027739171,0.4223177],"study_design_scores_gemma":[0.00022610096,0.00005248256,0.6983389,0.000073954,0.000016792166,0.000033855515,0.0006942624,0.23279716,0.00049557624,0.00036885784,0.06666813,0.00023387246],"about_ca_topic_score_codex":0.00024726635,"about_ca_topic_score_gemma":0.000020856867,"teacher_disagreement_score":0.71438533,"about_ca_system_score_codex":0.000111057736,"about_ca_system_score_gemma":0.0003857977,"threshold_uncertainty_score":0.9997538},"labels":[],"label_agreement":null},{"id":"W2148707490","doi":"10.1186/1472-6920-12-121","title":"Temporal stability of objective structured clinical exams: a longitudinal study employing item response theory","year":2012,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"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":"Generalizability theory; Objective structured clinical examination; Internal consistency; Competence (human resources); Reliability (semiconductor); Educational measurement; Consistency (knowledge bases); Psychology; Medicine; Medical education; Psychometrics; Statistics; Clinical psychology; Computer science; Mathematics; Social psychology; Developmental psychology; Curriculum; Artificial intelligence; Pedagogy","score_opus":0.664638114578315,"score_gpt":0.5950031946609595,"score_spread":0.06963491991735549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148707490","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":[0.9744554,0.00036764838,0.02061552,0.00010428754,0.003467131,0.00047345157,0.00000339067,0.000041460717,0.00047170848],"genre_scores_gemma":[0.9841602,0.0000031472373,0.0150689585,0.00009992248,0.0005510695,0.000032466996,0.0000021505118,0.000010059982,0.000072045565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.980445,0.014371548,0.0017689611,0.00062218483,0.0024194685,0.00037282973],"domain_scores_gemma":[0.66733515,0.32734615,0.001526907,0.0017940718,0.00097492436,0.0010228246],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10351694,0.00016613165,0.00057160633,0.0003890398,0.00013922981,0.00005014435,0.00078030844,0.00019604474,0.0016780361],"category_scores_gemma":[0.8037912,0.000110477326,0.00017491521,0.0017930609,0.0003560031,0.00030334588,0.00022148952,0.00040744626,0.000020838295],"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":[0.0008362519,0.0012076637,0.8862678,0.000008928533,0.000017031862,4.2344794e-7,0.0023173084,2.5254565e-7,0.00000810097,0.00034092378,0.00035836143,0.10863696],"study_design_scores_gemma":[0.00047331845,0.00030901752,0.961052,0.000028572207,0.000023364535,0.00000913865,0.026822574,0.000047942453,0.000029279283,0.010983329,0.00011187744,0.0001095928],"about_ca_topic_score_codex":0.00013481545,"about_ca_topic_score_gemma":0.00007912155,"teacher_disagreement_score":0.7002743,"about_ca_system_score_codex":0.000085805346,"about_ca_system_score_gemma":0.0024967254,"threshold_uncertainty_score":0.99923456},"labels":[],"label_agreement":null},{"id":"W2150705942","doi":"10.1016/j.ijpsycho.2003.12.009","title":"Analysis of covariance (ANCOVA) with difference scores","year":2004,"lang":"en","type":"article","venue":"International Journal of Psychophysiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Analysis of covariance; Covariate; Statistics; Significant difference; Mathematics; Analysis of variance; Covariance; Variable (mathematics); Psychology","score_opus":0.22769576273670725,"score_gpt":0.4703214309101297,"score_spread":0.24262566817342243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150705942","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":[0.81838936,0.00012537953,0.17918803,0.0006705691,0.0012050675,0.00002738641,0.000013296411,0.0000044114113,0.00037652464],"genre_scores_gemma":[0.96297467,0.00007047207,0.036451478,0.0002652264,0.0001896934,9.403578e-7,0.0000012700693,0.00000430654,0.000041957643],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997238,0.00018597874,0.0009857576,0.00024908854,0.0011961971,0.00014499406],"domain_scores_gemma":[0.9914934,0.004756662,0.0016822901,0.00025684774,0.001741343,0.00006945229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001441498,0.00011068677,0.00059172953,0.0016584088,0.000028859535,0.000043207692,0.0015672694,0.00005887303,0.00012963885],"category_scores_gemma":[0.00923151,0.00006570546,0.0002702376,0.00237305,0.00019675332,0.00014804034,0.00006526628,0.00018457593,0.0000066823404],"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":[0.003926929,0.00085079955,0.43828043,0.000006538122,0.0073735807,0.00018106581,0.00089239614,0.16457011,0.1838035,0.013818797,0.0005564532,0.1857394],"study_design_scores_gemma":[0.0011773729,0.00053677685,0.8962338,0.000041963358,0.00011665486,0.00007315034,0.00013909997,0.00031479553,0.0010270411,0.10003726,0.00021069823,0.00009138474],"about_ca_topic_score_codex":0.00004421202,"about_ca_topic_score_gemma":0.000011992903,"teacher_disagreement_score":0.45795336,"about_ca_system_score_codex":0.00004037534,"about_ca_system_score_gemma":0.000096191645,"threshold_uncertainty_score":0.99911416},"labels":[],"label_agreement":null},{"id":"W2151525783","doi":"10.1177/0146621610378289","title":"A Test-Length Correction to the Estimation of Extreme Proficiency Levels","year":2010,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Maximum a posteriori estimation; Estimator; Statistics; Rasch model; Mathematics; Bayes estimator; Item response theory; Bayesian probability; Estimation; Bias of an estimator; Scale (ratio); Econometrics; Maximum likelihood; Minimum-variance unbiased estimator; Psychometrics","score_opus":0.6476178436147106,"score_gpt":0.4734027822600229,"score_spread":0.17421506135468773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151525783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54486835,0.000049284346,0.37814662,0.0023933218,0.0057072346,0.0014812317,0.0000074629916,0.00014351636,0.06720301],"genre_scores_gemma":[0.96428055,0.0000012160931,0.034853183,0.00047752072,0.00012880638,0.00013098077,4.166328e-7,0.000007989258,0.00011936719],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952479,0.00025235806,0.00090379646,0.0007240631,0.0025154043,0.00035650452],"domain_scores_gemma":[0.9894258,0.0083786985,0.00044525342,0.0010809128,0.0005227833,0.00014658232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018966364,0.00018849279,0.00032017208,0.0002723295,0.0002334786,0.00010322131,0.0011758885,0.00011261047,0.0005033629],"category_scores_gemma":[0.1078829,0.00009739503,0.00010487176,0.0025489142,0.00013193984,0.000057082827,0.00011873562,0.0004382833,0.000245997],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052090018,0.0003987245,0.004799329,0.0000022676222,0.0000071785244,5.5887335e-7,0.00024151278,0.0005349847,0.0856842,0.002205799,0.011021877,0.8950515],"study_design_scores_gemma":[0.0005386989,0.00060526637,0.94775057,0.000018548655,0.000017721099,0.000017343395,0.00044047882,0.002573303,0.008017817,0.033295635,0.0064427964,0.00028180628],"about_ca_topic_score_codex":0.00001122123,"about_ca_topic_score_gemma":0.000015881495,"teacher_disagreement_score":0.94295126,"about_ca_system_score_codex":0.00003374953,"about_ca_system_score_gemma":0.000027254153,"threshold_uncertainty_score":0.8996318},"labels":[],"label_agreement":null},{"id":"W2152229558","doi":"10.1016/j.jclinepi.2003.08.011","title":"Clinimetrics vs. psychometrics: an unnecessary distinction","year":2003,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital","funders":"","keywords":"Psychometrics; Intraclass correlation; Structural equation modeling; Scale (ratio); Item response theory; Term (time); Reliability (semiconductor); Psychology; Cognition; Classical test theory; Econometrics; Clinical psychology; Statistics; Psychiatry; Mathematics","score_opus":0.8990231872981096,"score_gpt":0.6721006755354438,"score_spread":0.22692251176266576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152229558","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010021828,0.0048274994,0.232338,0.6762461,0.07001129,0.00032349362,0.00005906503,0.00006584348,0.0061068553],"genre_scores_gemma":[0.0010463411,0.004174062,0.14579612,0.8172343,0.029878069,0.00000404214,0.00002772832,0.00008435083,0.0017550025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.86392754,0.092765644,0.035384502,0.0023397375,0.003922088,0.0016604972],"domain_scores_gemma":[0.08439421,0.86641604,0.04213278,0.0025359215,0.0035827335,0.0009383437],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3998392,0.0007493227,0.010994962,0.006449618,0.00022218627,0.00017420803,0.0048679276,0.005406087,0.0011989194],"category_scores_gemma":[0.97568125,0.00047629708,0.0036406647,0.009401352,0.0008288512,0.00059465296,0.000279495,0.014611927,0.00024222898],"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":[0.00013964571,0.00013329841,0.24483357,0.000014233195,0.000109026274,0.0001937285,0.0000035672895,0.000040627994,6.5002745e-8,0.00006259901,0.5853647,0.16910492],"study_design_scores_gemma":[0.0008597703,0.0025900307,0.14827281,0.00004575847,0.00013851763,0.00043636296,0.00003628791,0.00025979595,1.9269416e-7,0.12964362,0.7173606,0.00035625367],"about_ca_topic_score_codex":0.000023155668,"about_ca_topic_score_gemma":0.0000028698314,"teacher_disagreement_score":0.7795333,"about_ca_system_score_codex":0.000117251126,"about_ca_system_score_gemma":0.00065899873,"threshold_uncertainty_score":0.99976885},"labels":[],"label_agreement":null},{"id":"W2154633345","doi":"10.1177/0013164403258393","title":"Impact of Test Design, Item Quality, and Item Bank Size on the Psychometric Properties of Computer-Based Credentialing Examinations","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care","funders":"","keywords":"Credentialing; Computerized adaptive testing; Item bank; Test (biology); Quality (philosophy); Computer science; Consistency (knowledge bases); Test design; Item response theory; Psychology; Psychometrics; Applied psychology; Statistics; Reliability engineering; Artificial intelligence; Medical education; Test method; Medicine; Mathematics; Clinical psychology","score_opus":0.8330425941791564,"score_gpt":0.5172334143779688,"score_spread":0.3158091798011876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154633345","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":[0.97582203,0.00080441724,0.018032275,0.004136453,0.0003508073,0.000358375,0.00001169164,0.000012015777,0.00047191017],"genre_scores_gemma":[0.98531806,0.000027048129,0.014260613,0.0002388922,0.00010062269,0.000030235631,7.1142745e-7,0.000004948118,0.00001884103],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996316,0.0007359767,0.0008326067,0.0004527099,0.0014749139,0.0001877484],"domain_scores_gemma":[0.9602904,0.037679374,0.00053639023,0.0003807231,0.0010008994,0.00011224202],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008970078,0.0001673623,0.00033434803,0.00040080203,0.00019844565,0.00010376129,0.0004178979,0.00007152487,0.00018736791],"category_scores_gemma":[0.10974809,0.00008266083,0.000111165,0.0021079066,0.00027755013,0.00006438365,0.000044198685,0.00014264033,0.000003959107],"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":[0.0004194061,0.008656241,0.7963242,0.000084072606,0.00018950677,7.959198e-7,0.0009826015,0.0023584673,0.04658718,0.008919579,0.003256941,0.132221],"study_design_scores_gemma":[0.00052108965,0.0011105608,0.97960484,0.000098217344,0.0000100467905,0.0000048982997,0.00011081848,0.00010333683,0.0007538317,0.017553251,0.000022589373,0.00010649413],"about_ca_topic_score_codex":0.000050902756,"about_ca_topic_score_gemma":0.0000014217205,"teacher_disagreement_score":0.18328066,"about_ca_system_score_codex":0.000059529455,"about_ca_system_score_gemma":0.000118530654,"threshold_uncertainty_score":0.89775085},"labels":[],"label_agreement":null},{"id":"W2154840878","doi":"10.1007/s11136-013-0465-y","title":"Strengthening the assessment of factorial invariance across population subgroups: a commentary on Varni et al. (2013)","year":2013,"lang":"en","type":"letter","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Safety Canada","funders":"","keywords":"Confirmatory factor analysis; Inference; Measurement invariance; Factorial; Econometrics; Bayesian probability; Statistics; Population; Outcome (game theory); Invariant (physics); Bayesian inference; Psychology; Mathematics; Computer science; Structural equation modeling; Artificial intelligence; Demography; Mathematical economics; Sociology","score_opus":0.8138820778811203,"score_gpt":0.6403933952146522,"score_spread":0.1734886826664681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154840878","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17628671,0.00014349869,0.0035730598,0.81608546,0.0016581925,0.00089263223,0.00034432457,0.00002618732,0.0009899181],"genre_scores_gemma":[0.5694421,0.00022134211,0.013861407,0.41144523,0.0038562461,0.00012984483,0.00032546712,0.000070262584,0.0006480815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9617821,0.023627577,0.0027165376,0.000979421,0.010036038,0.0008583127],"domain_scores_gemma":[0.6907259,0.30282152,0.002402287,0.0023920478,0.0015269121,0.00013131594],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11298933,0.00030003683,0.001212228,0.00066418323,0.00043464112,0.00041823788,0.0029791377,0.00047716536,0.00051744125],"category_scores_gemma":[0.18484943,0.00018259065,0.000311839,0.002065899,0.0005200123,0.00026806144,0.00092116516,0.004005715,0.000026017105],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000493748,0.000080816346,0.053190116,0.000075475094,0.00007061286,0.0000017066352,0.00051119365,0.00006558795,0.00006191532,0.00036757928,0.93713295,0.008392653],"study_design_scores_gemma":[0.0008755474,0.00053089485,0.37677887,0.00027216645,0.000008061056,7.4352596e-7,0.0020716884,0.000884889,0.000024953686,0.021327509,0.59686697,0.0003577311],"about_ca_topic_score_codex":0.022004606,"about_ca_topic_score_gemma":0.00011124819,"teacher_disagreement_score":0.40464023,"about_ca_system_score_codex":0.00016174273,"about_ca_system_score_gemma":0.00024247447,"threshold_uncertainty_score":0.9982921},"labels":[],"label_agreement":null},{"id":"W2155150582","doi":"10.2466/pr0.2001.88.3.813","title":"Note on Objectives of Psychological Assessment Procedures and the Value of Multidimensional Questionnaires and Inventories","year":2001,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Value (mathematics); Psychological testing; Limit (mathematics); Applied psychology; Clinical psychology; Statistics; Mathematics","score_opus":0.25075151363940057,"score_gpt":0.5212137075108079,"score_spread":0.2704621938714073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155150582","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":[0.9854585,0.0007543117,0.0029498301,0.0011678641,0.00054348155,0.0003181601,0.000002246127,0.00003129744,0.0087743215],"genre_scores_gemma":[0.97890973,0.00034531747,0.02028788,0.00029453775,0.000053107935,0.000023514667,6.0478806e-7,0.0000052700298,0.000080037986],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958047,0.00092979474,0.0011509348,0.00078755704,0.0010986457,0.0002283456],"domain_scores_gemma":[0.97783375,0.02020663,0.0009769413,0.00058041967,0.000290334,0.00011194679],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008189074,0.00018916978,0.0005875888,0.000211851,0.00015348525,0.000044638695,0.00023640085,0.00015427494,0.000065667184],"category_scores_gemma":[0.11552879,0.00008682129,0.000119113596,0.00084691896,0.001371293,0.00008626339,0.00016689576,0.00025972433,8.350985e-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":[0.0010166651,0.0007400741,0.8632706,0.000015292826,0.00003155459,0.00012993904,0.00046666173,0.00008683663,0.0013904205,0.04326958,0.00068175467,0.08890065],"study_design_scores_gemma":[0.0005639655,0.0005297334,0.79624707,0.000048641476,0.000009942608,0.00048241578,0.000178704,0.00014063,0.000071943636,0.20138279,0.00025887418,0.00008532146],"about_ca_topic_score_codex":0.000032802855,"about_ca_topic_score_gemma":0.000003731388,"teacher_disagreement_score":0.15811321,"about_ca_system_score_codex":0.000011420648,"about_ca_system_score_gemma":0.000021575108,"threshold_uncertainty_score":0.89192146},"labels":[],"label_agreement":null},{"id":"W2157620189","doi":"10.3899/jrheum.110402","title":"The PROMIS of Better Outcome Assessment: Responsiveness, Floor and Ceiling Effects, and Internet Administration","year":2011,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institutes of Health; Stony Brook University; University of Pittsburgh; University of Washington; Northwestern University","keywords":"Ceiling effect; Medicine; Ceiling (cloud); Computerized adaptive testing; Item response theory; Sample size determination; Physical therapy; Rheumatoid arthritis; Physical medicine and rehabilitation; Psychometrics; Internal medicine; Statistics; Alternative medicine; Pathology; Clinical psychology","score_opus":0.25445435164446234,"score_gpt":0.4364932432144383,"score_spread":0.18203889156997594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157620189","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":[0.9892507,0.0009447613,0.008166923,0.00090723054,0.00043459726,0.00008050245,5.300368e-7,0.0000028780091,0.00021188679],"genre_scores_gemma":[0.9908513,0.0002926945,0.008760765,0.00004709504,0.0000056847175,9.660139e-7,3.933418e-8,0.0000037329287,0.000037741444],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970454,0.0015528272,0.00086913514,0.000101279154,0.00030113017,0.00013022253],"domain_scores_gemma":[0.9679457,0.030479182,0.0011029851,0.00021402756,0.00021526053,0.00004286928],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012625115,0.00007908969,0.0003630234,0.00016969054,0.000116588955,0.00004359068,0.00046579383,0.000053722077,0.000020735386],"category_scores_gemma":[0.027863689,0.00003388341,0.000045675984,0.0002433053,0.00029325418,0.00011420564,0.00012080008,0.00021479627,0.0000010966643],"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":[0.00035678057,0.000015227444,0.94990283,0.000019469615,0.00004229432,0.0000047725507,0.0008012524,4.9383493e-7,0.00029351065,0.001053297,0.00014550658,0.047364566],"study_design_scores_gemma":[0.00057938066,0.0006747261,0.9616826,0.000069932255,0.000040855928,0.0025270241,0.0013816576,0.00032047942,0.0008975437,0.031444922,0.0003176105,0.00006322919],"about_ca_topic_score_codex":0.000038174065,"about_ca_topic_score_gemma":0.000012658952,"teacher_disagreement_score":0.047301337,"about_ca_system_score_codex":0.0000064193864,"about_ca_system_score_gemma":0.000053316006,"threshold_uncertainty_score":0.98032504},"labels":[],"label_agreement":null},{"id":"W2159184328","doi":"10.1007/978-1-4614-8118-8_9","title":"Research Problems: An Overview","year":2013,"lang":"en","type":"book-chapter","venue":"Fields Institute monographs","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Calgary","funders":"","keywords":"Computer science","score_opus":0.8333114704402071,"score_gpt":0.5470843435179588,"score_spread":0.2862271269222484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159184328","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067962526,0.011379042,0.0020807444,0.0005523899,0.0029724196,0.0008142483,0.00004620925,0.00018664295,0.9812887],"genre_scores_gemma":[0.00512981,0.011361291,0.030775497,0.0009128506,0.001237874,0.00015532534,0.000080015765,0.00010736314,0.95023996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.993048,0.00042942422,0.0013703894,0.0014631834,0.0029310326,0.00075796345],"domain_scores_gemma":[0.9873214,0.0078035314,0.0005615846,0.002691319,0.0012254133,0.00039679394],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011009893,0.00048726334,0.0009244044,0.0031741972,0.00055550627,0.00083747995,0.0030468006,0.0011447114,0.0062700254],"category_scores_gemma":[0.011342109,0.00036006447,0.00046715018,0.0015742147,0.00065307185,0.0008397922,0.0007292417,0.0020827877,0.0020239083],"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":[0.000010172364,0.00004010287,0.000290153,0.00005122405,0.00007001111,0.000040161056,0.00023196093,0.00007943807,0.000002264215,0.3432196,0.1724863,0.4834786],"study_design_scores_gemma":[0.00009342283,0.0001598867,0.00026305908,0.00015256426,0.000009958285,0.000009717593,0.000056681278,0.00006416157,0.0000017845786,0.44158578,0.5573438,0.0002591897],"about_ca_topic_score_codex":0.0003198899,"about_ca_topic_score_gemma":0.00019098335,"teacher_disagreement_score":0.48321941,"about_ca_system_score_codex":0.000046306905,"about_ca_system_score_gemma":0.00018897795,"threshold_uncertainty_score":0.99988514},"labels":[],"label_agreement":null},{"id":"W2159759566","doi":"10.1177/1094428114529165","title":"Reflections on Partial Least Squares Path Modeling","year":2014,"lang":"en","type":"article","venue":"Organizational Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Safety Canada","funders":"","keywords":"Structural equation modeling; Partial least squares regression; Econometrics; Path analysis (statistics); Path (computing); Null hypothesis; Sample (material); Computer science; Key (lock); Management science; Data mining; Mathematics; Machine learning; Economics","score_opus":0.8883201917735504,"score_gpt":0.7223769447242043,"score_spread":0.16594324704934604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159759566","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":[0.0071505476,0.000046845078,0.92069554,0.0019041251,0.0005489531,0.00013537696,0.0000054696316,0.000087526416,0.06942562],"genre_scores_gemma":[0.5071223,0.00001539478,0.49070972,0.00020522405,0.0005935716,0.000014638219,0.0000065060494,0.000025992182,0.0013066459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98477864,0.009993893,0.00063482777,0.00077647273,0.0032401853,0.0005759626],"domain_scores_gemma":[0.89963484,0.0960344,0.00014738455,0.00093076215,0.0029396466,0.0003129803],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062535785,0.00014673748,0.00028834888,0.0012821491,0.0010609502,0.00046738124,0.0010356564,0.00012776407,0.0020424533],"category_scores_gemma":[0.6258862,0.00010814889,0.000078703255,0.008319179,0.00016001082,0.00019841453,0.00033449425,0.00060414727,0.00049334194],"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":[0.000100603516,0.00022574447,0.005737127,0.000008848325,0.00003064167,0.0000038388616,0.0005542514,0.04064928,0.01221176,0.47749776,0.009631028,0.4533491],"study_design_scores_gemma":[0.00030971356,0.00032491115,0.0042274003,0.000023796583,0.0000046442415,0.000011288829,0.00079263665,0.37036064,0.0022960142,0.57353246,0.047886983,0.00022950907],"about_ca_topic_score_codex":0.00003713503,"about_ca_topic_score_gemma":0.0000034867946,"teacher_disagreement_score":0.56335044,"about_ca_system_score_codex":0.000099939774,"about_ca_system_score_gemma":0.00020298343,"threshold_uncertainty_score":0.99886984},"labels":[],"label_agreement":null},{"id":"W2162746574","doi":"10.1186/1477-7525-4-33","title":"Assessment of health-related quality of life in arthritis: conceptualization and development of five item banks using item response theory","year":2006,"lang":"en","type":"article","venue":"Health and Quality of Life Outcomes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; Institute of Population and Public Health; University of British Columbia; Simon Fraser University; McGill University; Arthritis Research Centre of Canada","funders":"Canadian Arthritis Network; Toronto Rehabilitation Institute; Canadian Institutes of Health Research; University of Toronto; Michael Smith Health Research BC; McGill University","keywords":"Conceptualization; Item response theory; Quality of life (healthcare); Quality of Life Research; Psychometrics; Health related quality of life; Psychology; Item bank; Arthritis; MEDLINE; Clinical psychology; Medicine; Gerontology; Public health; Psychotherapist; Computer science; Internal medicine; Nursing; Artificial intelligence; Political science","score_opus":0.5845356508953597,"score_gpt":0.5458059788282811,"score_spread":0.03872967206707867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162746574","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":[0.9792939,0.008867275,0.0105247265,0.00067765196,0.00012234716,0.00037525367,0.000057602232,0.000012002698,0.000069271024],"genre_scores_gemma":[0.9597983,0.00018842967,0.039515488,0.00044415385,0.0000061526416,0.0000034555055,0.000008517941,0.0000068259014,0.00002871332],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98024005,0.011140987,0.006698674,0.00043830107,0.0011496778,0.000332293],"domain_scores_gemma":[0.93144387,0.061971843,0.0055361465,0.00039523287,0.00040881618,0.00024407612],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06931985,0.00017222122,0.0019610755,0.0005976644,0.00013528492,0.000015714511,0.00019312245,0.00012501974,0.000023436278],"category_scores_gemma":[0.0923331,0.00013875455,0.00008458579,0.0010316658,0.0003439212,0.00013005179,0.00011333699,0.00014248736,1.2868657e-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":[0.00036036465,0.00013468937,0.9656706,0.0005294036,0.000019749767,1.1958724e-7,0.0043715048,0.000077348246,0.00009827172,0.0070015066,0.00001796979,0.021718511],"study_design_scores_gemma":[0.0016959818,0.00014605556,0.9824404,0.00027871632,0.0000015945417,5.07532e-7,0.012093737,0.00023682861,0.000033242555,0.0029315,0.000030155394,0.000111261405],"about_ca_topic_score_codex":0.0035371354,"about_ca_topic_score_gemma":0.00030646907,"teacher_disagreement_score":0.050830856,"about_ca_system_score_codex":0.000069407135,"about_ca_system_score_gemma":0.0016995171,"threshold_uncertainty_score":0.95833105},"labels":[],"label_agreement":null},{"id":"W2166319027","doi":"10.1177/070674370605100507","title":"Building a Better Model: An Introduction to Structural Equation Modelling","year":2006,"lang":"en","type":"article","venue":"The Canadian Journal of Psychiatry","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":183,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Structural equation modeling; Latent variable; Confirmatory factor analysis; Path analysis (statistics); Exploratory factor analysis; Path coefficient; A priori and a posteriori; Econometrics; Latent variable model; Variable (mathematics); Scale (ratio); Statistics; Psychology; Factor analysis; Variables; Construct (python library); Path (computing); Psychometrics; Mathematics; Computer science","score_opus":0.2531690852912864,"score_gpt":0.3971817068862711,"score_spread":0.14401262159498468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166319027","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":[0.5284681,0.00012685145,0.43711883,0.0317776,0.0023125117,0.000049952545,0.0000027093026,0.0000049619753,0.00013849905],"genre_scores_gemma":[0.61801624,2.2346883e-7,0.37884548,0.00040893425,0.0026780728,4.5459927e-7,3.6113784e-7,0.0000074736718,0.000042724554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99778,0.00027889916,0.0007471875,0.00022291642,0.0006621503,0.00030881685],"domain_scores_gemma":[0.9977983,0.0006204514,0.0004883633,0.00037402185,0.00041321423,0.0003056451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005708815,0.000109872926,0.00019748938,0.00089020655,0.00049312436,0.00041414774,0.0008283066,0.000060500268,0.00006746744],"category_scores_gemma":[0.0024429397,0.00006824152,0.00010122138,0.0012165634,0.000049865892,0.0004133783,0.000014802309,0.00029821772,0.0000058598034],"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":[0.000013893267,0.000002751406,0.017723748,8.259983e-7,0.0000061378532,0.0000013001788,0.00015304676,0.923503,0.000067680005,0.03873902,0.008825503,0.010963114],"study_design_scores_gemma":[0.000097193755,0.000057217003,0.0054292977,0.0000067540113,0.000011471395,0.000067778696,0.00015659531,0.31902698,0.00001862028,0.67424834,0.00079815835,0.000081578284],"about_ca_topic_score_codex":0.0065145968,"about_ca_topic_score_gemma":0.044703256,"teacher_disagreement_score":0.6355093,"about_ca_system_score_codex":0.00011165071,"about_ca_system_score_gemma":0.00063894084,"threshold_uncertainty_score":0.9848165},"labels":[],"label_agreement":null},{"id":"W2168109053","doi":"10.1177/0013164413492419","title":"Effectiveness of Combining Statistical Tests and Effect Sizes When Using Logistic Discriminant Function Regression to Detect Differential Item Functioning for Polytomous Items","year":2013,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":43,"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; Differential item functioning; Polytomous Rasch model; Discriminant function analysis; Sample size determination; Mathematics; Logistic regression; Linear discriminant analysis; Psychology; Statistical hypothesis testing; Econometrics; Psychometrics; Item response theory","score_opus":0.5320350509278347,"score_gpt":0.4801596014508845,"score_spread":0.051875449476950164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168109053","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":[0.7450351,0.00034898665,0.25248644,0.00017984022,0.0011492791,0.0006821795,0.000009389906,0.000014879931,0.00009390678],"genre_scores_gemma":[0.97647905,0.0000045876955,0.02311096,0.00004264078,0.00013863112,0.00018877257,0.0000056611943,0.000009192694,0.000020528118],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965783,0.000995175,0.00057625014,0.0006816829,0.00088083587,0.00028775865],"domain_scores_gemma":[0.96487254,0.033960678,0.00025463512,0.0002200931,0.0004835558,0.00020850831],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004952921,0.00021501699,0.00045910996,0.00025510843,0.0003139445,0.0001738374,0.00017225055,0.00009801979,0.00018420485],"category_scores_gemma":[0.051269073,0.0001256745,0.00006770079,0.000361326,0.00014456484,0.0001099424,0.00008164125,0.00013277646,0.0000059327913],"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":[0.0021564967,0.000564463,0.3081382,0.00033645576,0.00009710169,9.382959e-7,0.0002681679,0.00010837487,0.18882313,0.002678513,0.0016174507,0.4952107],"study_design_scores_gemma":[0.0007151644,0.002334883,0.9229598,0.0002352608,0.000046708614,0.000015587893,0.00010788087,0.00070518366,0.0003875064,0.07228404,0.000046731224,0.00016121854],"about_ca_topic_score_codex":0.00007661951,"about_ca_topic_score_gemma":0.0000020679827,"teacher_disagreement_score":0.6148217,"about_ca_system_score_codex":0.000057897752,"about_ca_system_score_gemma":0.000027442196,"threshold_uncertainty_score":0.9567225},"labels":[],"label_agreement":null},{"id":"W2169512351","doi":"","title":"A Multi-Group Investigation of the CES-D's Measurement Structure Across Adolescents, Young Adults and Middle-Aged Adults","year":2002,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":27,"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":"Discriminant validity; Internal consistency; Humanities; Psychology; Structural equation modeling; Demography; Mathematics; Statistics; Clinical psychology; Psychometrics; Sociology; Art","score_opus":0.35825445614704937,"score_gpt":0.4109770154701915,"score_spread":0.052722559323142126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169512351","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":[0.99603397,0.0006560449,0.000038374215,0.0001322521,0.0010672979,0.0012201231,0.00022544322,0.000023313742,0.00060320075],"genre_scores_gemma":[0.9911531,0.0017068466,0.0067364126,0.00004232434,0.000118710275,0.000054805572,0.000006727218,0.000033714143,0.00014734408],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9916219,0.002294678,0.0016528951,0.0016210384,0.001970801,0.0008386603],"domain_scores_gemma":[0.9917078,0.0042011044,0.0011541272,0.0019648152,0.00072584394,0.00024628302],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.016709728,0.00038959703,0.00080146914,0.00064591237,0.00036627537,0.00038356666,0.0022740543,0.00055207877,0.000039726652],"category_scores_gemma":[0.062475834,0.00027818422,0.00023082079,0.0009801317,0.00079378113,0.00016014157,0.002686398,0.0020866927,0.0000018838114],"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":[0.00019244669,0.00007103423,0.7175557,0.0003811149,0.000041123138,0.0000041659573,0.0036365956,0.0010337664,0.0004497575,0.000005859184,0.000029273604,0.2765992],"study_design_scores_gemma":[0.0015381231,0.00006928904,0.97028035,0.0021879585,0.000005968786,0.000008223098,0.0038260168,0.019572483,0.00024276438,0.0018085068,0.0001536902,0.0003066125],"about_ca_topic_score_codex":0.00037368687,"about_ca_topic_score_gemma":0.0032080547,"teacher_disagreement_score":0.27629256,"about_ca_system_score_codex":0.0005459206,"about_ca_system_score_gemma":0.00020183614,"threshold_uncertainty_score":0.99996704},"labels":[],"label_agreement":null},{"id":"W2170853093","doi":"10.1111/j.1745-3992.2003.tb00136.x","title":"Using Multidimensional Item Response Theory to Evaluate Educational and Psychological Tests","year":2003,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":192,"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":"Item response theory; Test (biology); Measure (data warehouse); Ninth; Computer science; Process (computing); Meaning (existential); Multidimensional analysis; Psychology; Mathematics education; Psychometrics; Management science; Econometrics; Mathematics; Data mining; Developmental psychology; Psychotherapist","score_opus":0.8128600435609681,"score_gpt":0.6116511900217015,"score_spread":0.20120885353926654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170853093","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":[0.913103,0.007822783,0.003829669,0.06630247,0.0017711519,0.00045248642,0.000007636509,0.000020466636,0.0066903713],"genre_scores_gemma":[0.63279766,0.00006669179,0.36349753,0.0020331214,0.000256745,0.00003090728,0.0000014165988,0.000011563038,0.0013043681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9904012,0.0058802897,0.0005715716,0.0007551193,0.0021081744,0.00028365204],"domain_scores_gemma":[0.8754453,0.121753804,0.00034177813,0.00041560523,0.0017189502,0.00032457677],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05058032,0.0001947472,0.00023882971,0.00037527274,0.00046011695,0.0002583107,0.00020983403,0.0000757461,0.0012049885],"category_scores_gemma":[0.6463413,0.00014605027,0.000042061598,0.0009438032,0.0001126364,0.0004408504,0.000076131124,0.00018324803,0.00009124365],"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":[0.010542296,0.005656771,0.22539754,0.00004733429,0.00039703184,0.000015853648,0.008179787,0.0007752535,0.07944028,0.43856186,0.08696332,0.14402269],"study_design_scores_gemma":[0.00050903857,0.00028137284,0.66209435,0.00005153928,0.000052192518,0.00044903133,0.0021370107,0.00009915711,0.00014080881,0.13285889,0.20101209,0.00031448054],"about_ca_topic_score_codex":0.000024547635,"about_ca_topic_score_gemma":0.0000017455881,"teacher_disagreement_score":0.595761,"about_ca_system_score_codex":0.00009356135,"about_ca_system_score_gemma":0.00034460946,"threshold_uncertainty_score":0.99970806},"labels":[],"label_agreement":null},{"id":"W2171625237","doi":"10.1111/j.1745-3984.2007.00024.x","title":"An Investigation into the Dimensionality of TOEFL Using Conditional Covariance‐Based Nonparametric Approach","year":2007,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":82,"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":"Test of English as a Foreign Language; Reading comprehension; Curse of dimensionality; Psychology; Covariance; Nonparametric statistics; Natural language processing; Computer science; Reading (process); Artificial intelligence; Statistics; Mathematics education; Mathematics; Linguistics; Language assessment","score_opus":0.6245000768597356,"score_gpt":0.5087043214551444,"score_spread":0.1157957554045912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171625237","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":[0.70649105,0.00048054144,0.2904174,0.0013052009,0.00088993716,0.00013093563,0.0000032733008,0.0000022298934,0.0002794167],"genre_scores_gemma":[0.7780539,0.0000012691513,0.22127344,0.00031149993,0.00034436528,0.0000016891257,0.0000032036726,0.0000045407664,0.0000061037344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99281734,0.0008380974,0.0015437144,0.0002350922,0.00438582,0.00017993542],"domain_scores_gemma":[0.9770635,0.015327364,0.0021657422,0.00038749928,0.004859741,0.00019619615],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044816136,0.000121726895,0.00030371005,0.0008840276,0.00023223291,0.00007878846,0.000685219,0.000061318045,0.00017345442],"category_scores_gemma":[0.04865053,0.000073909745,0.0001562452,0.0026923667,0.00021597208,0.0003290494,0.000026086298,0.00022997412,0.0000025381783],"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":[0.0004795206,0.0024402698,0.7611208,0.00004385879,0.00024015902,0.000002470654,0.0026076664,0.10016535,0.0745033,0.030107968,0.0030450874,0.025243523],"study_design_scores_gemma":[0.00044287916,0.00016480451,0.8532051,0.000042742813,0.000040017985,0.000038188788,0.001191709,0.0053161373,0.003720192,0.1355324,0.00019894404,0.00010688915],"about_ca_topic_score_codex":0.00007506497,"about_ca_topic_score_gemma":0.0000058072615,"teacher_disagreement_score":0.10542442,"about_ca_system_score_codex":0.0003231888,"about_ca_system_score_gemma":0.0013926508,"threshold_uncertainty_score":0.98356277},"labels":[],"label_agreement":null},{"id":"W2171716385","doi":"10.1177/0146621614520958","title":"Maximum-Likelihood Estimation of Noncompensatory IRT Models With the MH-RM Algorithm","year":2014,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Item response theory; Estimation; Maximum likelihood; Latent variable; Statistics; Computer science; Econometrics; Population; Estimation theory; Expectation–maximization algorithm; Mathematics; Algorithm; Artificial intelligence; Machine learning; Psychometrics; Engineering","score_opus":0.3757797696663633,"score_gpt":0.40160231143503256,"score_spread":0.02582254176866927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171716385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040106766,0.00011884035,0.89278513,0.0007797897,0.0003044304,0.0005083523,0.000002921853,0.00008104049,0.06531275],"genre_scores_gemma":[0.8049097,0.0000050677586,0.19421335,0.0006948803,0.00007831468,0.00007166786,9.894686e-7,0.000012020318,0.000014037627],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99399275,0.0006013524,0.00084995595,0.0008182541,0.0032829985,0.0004546724],"domain_scores_gemma":[0.9925699,0.0049685566,0.0006205798,0.0012196526,0.00046553204,0.00015574285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01794613,0.00026875155,0.0005432332,0.0002043824,0.0002199564,0.000104368046,0.0012754836,0.00014207563,0.00015147313],"category_scores_gemma":[0.0037392706,0.00012773873,0.00012304162,0.0014240784,0.00027834997,0.00009046604,0.00011942141,0.00032164267,0.00009133641],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093207884,0.00021492754,0.00021223321,0.000003946574,0.000028834827,9.582546e-7,0.00012477963,0.00333622,0.00070703164,0.006621474,0.002270075,0.9863863],"study_design_scores_gemma":[0.0027869365,0.0013544795,0.08148589,0.000053010903,0.00007556499,0.00002677387,0.00092074974,0.04608518,0.0011875669,0.8581313,0.0072558345,0.0006367466],"about_ca_topic_score_codex":0.000010272451,"about_ca_topic_score_gemma":0.0000033156846,"teacher_disagreement_score":0.98574954,"about_ca_system_score_codex":0.00005461424,"about_ca_system_score_gemma":0.000026086822,"threshold_uncertainty_score":0.6219806},"labels":[],"label_agreement":null},{"id":"W2180735259","doi":"10.1177/2158244014545964","title":"The Conscientious Responders Scale","year":2014,"lang":"en","type":"article","venue":"SAGE Open","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":146,"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; Thompson Rivers University","funders":"","keywords":"Scale (ratio); Reliability (semiconductor); Item response theory; Psychology; Odds; Clinical psychology; Psychometrics; Statistics; Social psychology; Medicine; Applied psychology; Logistic regression; Mathematics","score_opus":0.4342120929580178,"score_gpt":0.5144347334499795,"score_spread":0.08022264049196165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180735259","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16035864,0.0003198089,0.047580678,0.0055085584,0.002205593,0.0004474046,0.0000038845496,0.000051614836,0.7835238],"genre_scores_gemma":[0.9132119,0.000018013472,0.019015918,0.0010432524,0.00008946461,0.000009843649,3.9841098e-7,0.00000816056,0.06660309],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973832,0.0009937388,0.00032934695,0.00035216464,0.00068726274,0.00025431294],"domain_scores_gemma":[0.95756596,0.04106586,0.00019070007,0.00097605423,0.000113116745,0.00008831194],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.027754312,0.000065305096,0.0001532013,0.00012057186,0.0007172967,0.0016208867,0.0029796492,0.00003227888,0.00039042567],"category_scores_gemma":[0.11485794,0.000032955722,0.000054041662,0.0015682053,0.00020196593,0.00018939556,0.00075665483,0.00009799492,0.00046001354],"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":[0.000025086341,0.000008031149,0.013918013,2.9033188e-7,0.0000033091837,0.0000011168688,0.00012818363,0.000007379249,0.00019144987,0.0025396592,0.040489633,0.94268787],"study_design_scores_gemma":[0.00032939544,0.000051196566,0.063696615,0.0000070436386,0.0000024728758,0.0000059929107,0.0011115803,0.00056787435,0.00016547808,0.17738311,0.7565902,0.000089054185],"about_ca_topic_score_codex":0.000054480075,"about_ca_topic_score_gemma":0.00011123498,"teacher_disagreement_score":0.9425988,"about_ca_system_score_codex":0.000010700669,"about_ca_system_score_gemma":0.000036490204,"threshold_uncertainty_score":0.9994155},"labels":[],"label_agreement":null},{"id":"W2184642750","doi":"","title":"Item Consistency Index: An Item-Fit Index for Cognitive Diagnostic Assessment","year":2017,"lang":"en","type":"article","venue":"","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 Alberta","funders":"","keywords":"Index (typography); Consistency (knowledge bases); Measure (data warehouse); Item response theory; Set (abstract data type); Statistics; Computer science; Test (biology); Item analysis; Data set; Data mining; Psychometrics; Mathematics; Artificial intelligence","score_opus":0.6650316028496002,"score_gpt":0.5782935083466494,"score_spread":0.08673809450295078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184642750","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":[0.546912,0.00009954912,0.3351892,0.0011466948,0.0018358743,0.0009659901,0.00006874485,0.000121943376,0.11366],"genre_scores_gemma":[0.97552633,0.000016462645,0.020627815,0.0005204398,0.00019306107,0.00010214691,0.000004312066,0.000015641934,0.0029938126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99639654,0.00038773508,0.000789898,0.00085208635,0.0010918204,0.00048193944],"domain_scores_gemma":[0.7680007,0.22834104,0.00091467623,0.0013873413,0.0010635143,0.0002927202],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00796772,0.00022209619,0.000517631,0.00043609735,0.0011180623,0.0013258475,0.001530614,0.00015234787,0.00071638636],"category_scores_gemma":[0.5437045,0.0001353415,0.00017026698,0.00047703786,0.0002778892,0.00073667563,0.00036614414,0.00020806024,0.000055231292],"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":[0.000022074493,0.00008377306,0.72066677,0.0000042931856,0.000020373538,0.000008681471,0.0000486443,0.0000045834536,0.000009169006,0.0012791086,0.0016042554,0.27624828],"study_design_scores_gemma":[0.0010533703,0.0002939007,0.9351001,0.000039470182,0.000021792386,0.000009641437,0.0023418614,0.008620417,0.000050794555,0.049608313,0.0026182982,0.00024204768],"about_ca_topic_score_codex":0.00017473401,"about_ca_topic_score_gemma":0.00013641102,"teacher_disagreement_score":0.53573674,"about_ca_system_score_codex":0.000042371063,"about_ca_system_score_gemma":0.00019181882,"threshold_uncertainty_score":0.99971086},"labels":[],"label_agreement":null},{"id":"W2193158494","doi":"10.1037/met0000059","title":"A flexible full-information approach to the modeling of response styles.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":120,"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":"Social Sciences and Humanities Research Council of Canada; Institute of Education Sciences","keywords":"Item response theory; PsycINFO; Trait; Set (abstract data type); Computer science; Factor analysis; Statistics; Estimation; Structural equation modeling; Econometrics; Psychometrics; Psychology; Data mining; Machine learning; Mathematics","score_opus":0.8157017601333325,"score_gpt":0.6109273046144487,"score_spread":0.20477445551888385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2193158494","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":[0.053339552,0.00017725024,0.87648314,0.0014945735,0.00059186644,0.00031328725,0.0000055263995,0.000082886414,0.067511946],"genre_scores_gemma":[0.26790404,0.000003539025,0.7310196,0.0008372551,0.00006373021,0.00003529468,7.3053235e-7,0.000004878409,0.00013089692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9900044,0.006632881,0.0011933143,0.00050122716,0.0012812456,0.00038688275],"domain_scores_gemma":[0.9728836,0.024554437,0.00039188497,0.0012298712,0.0006500877,0.00029012823],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08815691,0.0001737857,0.0004751481,0.0005652232,0.00012470646,0.00017313322,0.0017245549,0.00016226155,0.000058575126],"category_scores_gemma":[0.3209161,0.000085578096,0.00016232734,0.0042740325,0.0001075888,0.00029881854,0.00033239246,0.00030437886,0.000135265],"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":[0.002304121,0.0001720246,0.0003812743,0.0000037093198,0.000014586828,6.47763e-7,0.0016469153,0.041871265,0.0006618742,0.0044945343,0.009821615,0.9386274],"study_design_scores_gemma":[0.001963468,0.0023261267,0.020566395,0.000027369782,0.00003463091,0.00013900375,0.01881212,0.5326486,0.0005395664,0.30043623,0.12180885,0.0006976451],"about_ca_topic_score_codex":0.00001302408,"about_ca_topic_score_gemma":1.3962264e-7,"teacher_disagreement_score":0.9379298,"about_ca_system_score_codex":0.00003401548,"about_ca_system_score_gemma":0.000035390785,"threshold_uncertainty_score":0.9389343},"labels":[],"label_agreement":null},{"id":"W2205642516","doi":"10.22237/jmasm/1446350640","title":"Resolving the Issue of How Reliability is Related to Statistical Power: Adhering to Mathematical Definitions","year":2015,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of British Columbia","funders":"","keywords":"Variance (accounting); Mathematics; Reliability (semiconductor); Statistics; Consistency (knowledge bases); Statistical power; Population variance; Dependability; Score; Variance decomposition of forecast errors; Power function; Function (biology); Statistical hypothesis testing; One-way analysis of variance; Econometrics; Analysis of variance; Power (physics); Computer science","score_opus":0.48781763575606363,"score_gpt":0.5258201580953441,"score_spread":0.038002522339280476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2205642516","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":[0.006256028,0.000096036136,0.97597367,0.0067060315,0.00045559724,0.00033422656,0.00011220401,0.00002155025,0.01004468],"genre_scores_gemma":[0.21176057,0.000004142272,0.7875237,0.00054317946,0.000050407085,0.000010595494,5.3347947e-7,0.000021670174,0.00008524723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991645,0.0024785048,0.0023387687,0.00054510124,0.0024648588,0.0005277801],"domain_scores_gemma":[0.8805508,0.11555339,0.0008374419,0.0009065652,0.0012173278,0.00093449285],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04025394,0.00026391877,0.0011544526,0.0004853272,0.00016022725,0.00023903558,0.0012491585,0.00016348109,0.0007106547],"category_scores_gemma":[0.38343018,0.00015718755,0.00015544593,0.0018886728,0.00029400547,0.00011866936,0.0004325519,0.00076936465,0.00008373693],"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":[0.0007252587,0.00033225032,0.0004525477,0.00004161197,0.000113857306,0.00004650936,0.0069083367,0.0018759111,0.0048286864,0.33110398,0.058182236,0.5953888],"study_design_scores_gemma":[0.0004411718,0.00055750314,0.0034474516,0.00004000775,0.00006509169,0.00008505131,0.002107417,0.009766112,0.0005311675,0.97707933,0.0056837355,0.00019597402],"about_ca_topic_score_codex":0.0000049697,"about_ca_topic_score_gemma":4.769757e-7,"teacher_disagreement_score":0.64597535,"about_ca_system_score_codex":0.00012179658,"about_ca_system_score_gemma":0.00021127079,"threshold_uncertainty_score":0.9882605},"labels":[],"label_agreement":null},{"id":"W2234202768","doi":"","title":"Prevalence of Gender DIF in Mixed Format High School Exit Examinations.","year":2001,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"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":"Polytomous Rasch model; Differential item functioning; Item response theory; Psychology; Statistics; Social psychology; Developmental psychology; Psychometrics; Mathematics","score_opus":0.5182594646204142,"score_gpt":0.46066098004428163,"score_spread":0.057598484576132536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2234202768","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":[0.8803766,0.00023017351,0.066717945,0.000116929135,0.00030343747,0.00012848026,0.0000034220955,0.00003167688,0.052091368],"genre_scores_gemma":[0.9495864,0.00024073981,0.046612944,0.00007875594,0.000022865064,0.000008558752,4.0264652e-7,0.000003776274,0.003445554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975604,0.0003210321,0.0007322408,0.00030719745,0.0008444142,0.00023472586],"domain_scores_gemma":[0.9865406,0.012404495,0.0002370588,0.0005190928,0.00021927543,0.00007944003],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055025956,0.00008937193,0.00021886358,0.0012297704,0.00004849799,0.000057210073,0.00070941384,0.00005079709,0.003259221],"category_scores_gemma":[0.06817585,0.000059829996,0.00005235268,0.003654932,0.000056387802,0.00040572163,0.0001481372,0.00010338052,0.000113074144],"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":[0.000010878885,0.00006519441,0.8894633,0.00001598066,0.0000036743352,0.0000053425265,0.00007610345,0.00008381408,0.00025154254,0.0022207787,0.0057891523,0.102014236],"study_design_scores_gemma":[0.00027818055,0.00003082595,0.951727,0.000010782205,0.0000024800427,0.000010622847,0.00049744186,0.0014606344,0.00050347357,0.044605616,0.0007952703,0.00007767692],"about_ca_topic_score_codex":0.000091774484,"about_ca_topic_score_gemma":0.000010042427,"teacher_disagreement_score":0.101936564,"about_ca_system_score_codex":0.000021377711,"about_ca_system_score_gemma":0.0000264145,"threshold_uncertainty_score":0.99765193},"labels":[],"label_agreement":null},{"id":"W2237927442","doi":"10.1186/s12955-015-0395-1","title":"Detecting short-term change and variation in health-related quality of life: within- and between-person factor structure of the SF-36 health survey","year":2015,"lang":"en","type":"article","venue":"Health and Quality of Life Outcomes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"College of Family Physicians of Canada; Island Health; University of Victoria","funders":"","keywords":"Confirmatory factor analysis; Prom; Quality of life (healthcare); SF-36; Psychology; Reliability (semiconductor); Gerontology; Medicine; Repeated measures design; Clinical psychology; Structural equation modeling; Health related quality of life; Statistics; Disease","score_opus":0.8487737988843177,"score_gpt":0.5470002642813732,"score_spread":0.30177353460294454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237927442","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":[0.98887634,0.0041053803,0.0003491687,0.005440683,0.00034539917,0.00057633745,0.0002879978,0.0000146220145,0.000004088906],"genre_scores_gemma":[0.99650574,0.00013378519,0.0021149213,0.0011951735,0.000027851454,0.0000017754603,0.000006166439,0.000008665624,0.000005947918],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98565996,0.008867046,0.0034532328,0.00051033637,0.001106582,0.0004028575],"domain_scores_gemma":[0.97266245,0.022024956,0.0038927046,0.0004794473,0.00026716077,0.0006732758],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043693043,0.00019955533,0.0018397176,0.00034444212,0.00019813816,0.00003424936,0.00026534018,0.00015721098,0.0000045187676],"category_scores_gemma":[0.10705933,0.00013089893,0.00006798847,0.0011606076,0.00019898717,0.00017808212,0.00013675216,0.00033747355,7.475688e-8],"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":[0.00010697307,0.000021953902,0.9629923,0.00056159,0.000017275872,2.29216e-8,0.016463997,0.0000020047955,0.00001612535,0.00012452564,0.000012133497,0.019681113],"study_design_scores_gemma":[0.000937948,0.00028355743,0.99380666,0.00009719118,0.0000017779078,6.440353e-7,0.003713763,0.00006137673,0.0000056939266,0.0009813395,0.00000432687,0.00010572352],"about_ca_topic_score_codex":0.05082928,"about_ca_topic_score_gemma":0.007906824,"teacher_disagreement_score":0.06336629,"about_ca_system_score_codex":0.00006318941,"about_ca_system_score_gemma":0.00076124084,"threshold_uncertainty_score":0.9847193},"labels":[],"label_agreement":null},{"id":"W2240102487","doi":"10.1007/s12144-015-9404-0","title":"Using the Gamma Generalized Linear Model for Modeling Continuous, Skewed and Heteroscedastic Outcomes in Psychology","year":2016,"lang":"en","type":"article","venue":"Current Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":178,"is_retracted":false,"has_abstract":false,"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":"Homoscedasticity; Heteroscedasticity; Psychology; Normality; Econometrics; Outcome (game theory); Linear regression; Linear model; Generalized linear model; Variance (accounting); Statistics; General linear model; Range (aeronautics); Mathematics; Social psychology; Mathematical economics; Engineering; Economics","score_opus":0.7652380167565765,"score_gpt":0.5944211459043176,"score_spread":0.17081687085225894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2240102487","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":[0.4154688,0.0009342447,0.57964,0.0017773258,0.0017563264,0.0003143248,0.000019564355,0.000028978668,0.000060469585],"genre_scores_gemma":[0.9209019,0.00044331423,0.07697678,0.0012192372,0.00019936099,0.00009220515,0.0000018315725,0.00003335583,0.00013198778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99592364,0.0007338884,0.001196179,0.0010841631,0.0003702295,0.00069189275],"domain_scores_gemma":[0.98907375,0.009243663,0.00039372846,0.00094955903,0.00021962967,0.00011966119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00503241,0.00028783985,0.0007622971,0.0006362856,0.00017826133,0.00006579859,0.00094735296,0.00019207822,0.000032515156],"category_scores_gemma":[0.020403512,0.00014395402,0.00017889695,0.0006904498,0.00027719935,0.00015720089,0.00017993287,0.0002409606,0.000011274691],"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":[0.00058360223,0.00037192376,0.24503452,0.000019183813,0.00006139676,0.0000050608646,0.00053800305,0.009254752,0.011942657,0.0029584821,0.0024897093,0.7267407],"study_design_scores_gemma":[0.0036845303,0.00010688442,0.008147021,0.00003802588,0.00001952997,0.000032200092,0.00003926379,0.8601441,0.000009515151,0.12549774,0.002013007,0.0002681761],"about_ca_topic_score_codex":0.0000062916165,"about_ca_topic_score_gemma":0.000011565372,"teacher_disagreement_score":0.8508893,"about_ca_system_score_codex":0.000024798504,"about_ca_system_score_gemma":0.000033313085,"threshold_uncertainty_score":0.98784804},"labels":[],"label_agreement":null},{"id":"W2259831407","doi":"10.14288/1.0055674","title":"The validity and applicability of two modified cloze procedures (beginning of the page procedure and \"instant\" beginning of the page procedure) measured against the Stanford Diagnostic Reading Test and equated with the cloze procedure and Fry Readability Graph","year":2010,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Instant; Test (biology); Reading (process); Computer science; Natural language processing; Linguistics; Philosophy","score_opus":0.06321896158872539,"score_gpt":0.27288947488753457,"score_spread":0.20967051329880917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2259831407","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":[0.9957616,0.0006123165,0.00023245485,0.00092125905,0.0000657284,0.0018758909,0.00014647096,0.00003397178,0.00035030473],"genre_scores_gemma":[0.99907905,0.00027451105,0.0005049171,0.00005223729,0.000019848112,0.00001181022,0.0000011985511,0.000018062832,0.000038352755],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962002,0.0006575229,0.00061754853,0.00087270234,0.0012279734,0.00042407765],"domain_scores_gemma":[0.97620887,0.020000659,0.001447932,0.0012047826,0.0009966296,0.00014111631],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.00785513,0.00019662266,0.00067997084,0.000082660496,0.001788965,0.00029058044,0.0013587055,0.00018546513,0.00000271082],"category_scores_gemma":[0.047527395,0.00016449144,0.00013239283,0.0022176146,0.005248041,0.00034180112,0.00077026733,0.00072743703,4.7371536e-8],"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":[0.00009675244,0.00011581114,0.9482162,0.00052468065,0.000062680236,0.00000390243,0.0023137399,0.000034624438,0.00557886,0.00005058598,0.00027193603,0.042730223],"study_design_scores_gemma":[0.00084451085,0.00014386115,0.9767397,0.00042950112,0.00012486777,0.00010235002,0.014895958,0.0008878584,0.00010753062,0.005497985,0.000025906327,0.00019994605],"about_ca_topic_score_codex":0.0033498711,"about_ca_topic_score_gemma":0.0400783,"teacher_disagreement_score":0.042530276,"about_ca_system_score_codex":0.000027352744,"about_ca_system_score_gemma":0.00036798042,"threshold_uncertainty_score":0.9995106},"labels":[],"label_agreement":null},{"id":"W2262777419","doi":"10.3352/jeehp.2016.13.6","title":"Calibrating the Medical Council of Canada’s Qualifying Examination Part I using an integrated item response theory framework: a comparison of models and designs","year":2016,"lang":"en","type":"article","venue":"Journal of Educational Evaluation for Health Professions","topic":"Psychometric Methodologies and Testing","field":"Decision 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":true,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Polytomous Rasch model; Item response theory; Calibration; Statistics; Set (abstract data type); Test (biology); Computer science; Type I and type II errors; Econometrics; Multiple choice; Psychology; Mathematics; Significant difference; Psychometrics; Programming language","score_opus":0.8970046108208954,"score_gpt":0.6521780930522075,"score_spread":0.2448265177686879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262777419","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":[0.56569576,0.00069085165,0.40875283,0.023454482,0.0009149691,0.0004218635,0.000029407993,0.0000019806575,0.000037870654],"genre_scores_gemma":[0.951415,0.000015866732,0.048032235,0.0002993594,0.00012783134,0.000016562904,0.000001977556,0.0000066406433,0.0000845068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98186755,0.011224175,0.002383324,0.00020172825,0.00410068,0.00022255631],"domain_scores_gemma":[0.67409503,0.30980793,0.0060066096,0.00039694872,0.009329663,0.000363798],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14279008,0.00009618183,0.0004048758,0.00023100898,0.0005184228,0.000023907058,0.00038612122,0.00010655619,0.00026063682],"category_scores_gemma":[0.52214307,0.000047332916,0.000055959452,0.00070691,0.00013267387,0.00038733365,0.000040219365,0.0002443042,7.739854e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003576893,0.0015414023,0.049497023,0.00030345697,0.0002057733,4.9924637e-7,0.076856606,0.021139776,0.0022340696,0.074847594,0.01813458,0.7516623],"study_design_scores_gemma":[0.0014760824,0.0007535015,0.08482438,0.0030520742,0.00007378865,0.00003660316,0.07649538,0.47247827,0.00017733,0.3594216,0.0010252221,0.00018575456],"about_ca_topic_score_codex":0.0010255048,"about_ca_topic_score_gemma":0.002235562,"teacher_disagreement_score":0.7514766,"about_ca_system_score_codex":0.0007136277,"about_ca_system_score_gemma":0.044389762,"threshold_uncertainty_score":0.9610277},"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":"W2274105452","doi":"10.1186/s12887-016-0543-8","title":"The Early Development Instrument: an evaluation of its five domains using Rasch analysis","year":2016,"lang":"en","type":"article","venue":"BMC Pediatrics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":19,"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":"Health Research Board; McMaster University","keywords":"Rasch model; Differential item functioning; Scale (ratio); Psychometrics; Developmental psychology; Item response theory; Rating scale; Construct (python library); Population; Item analysis; Psychology; Medicine; Clinical psychology; Computer science","score_opus":0.5895214533752752,"score_gpt":0.4855253153518973,"score_spread":0.10399613802337787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274105452","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":[0.90782154,0.00046610445,0.09075167,0.000027496922,0.00034793324,0.00017111664,0.0000076200254,0.000014873449,0.00039164114],"genre_scores_gemma":[0.9425382,0.00007548373,0.057084125,0.00000754527,0.0001285454,0.000007678196,9.2172473e-7,0.000005555227,0.00015192716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944745,0.0012333207,0.0008514451,0.00039514105,0.0027751327,0.00027046472],"domain_scores_gemma":[0.9784563,0.018769493,0.000775647,0.00061712804,0.0012803999,0.00010099306],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025738692,0.00011374816,0.0002580624,0.0009021269,0.00032669373,0.00013261652,0.00075838086,0.00007270502,0.00008219192],"category_scores_gemma":[0.08332578,0.000054767468,0.00012661531,0.006156624,0.00005176985,0.00029623858,0.00016484917,0.00005785676,0.00002200307],"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":[0.000017123557,0.000024757746,0.73584586,0.0000022232034,0.000038769173,2.0586988e-7,0.0003306295,0.0008299716,0.000121120436,0.00016314127,0.000043430533,0.26258278],"study_design_scores_gemma":[0.0005740413,0.000046059416,0.9794341,0.0000041189996,0.00036569725,8.787694e-7,0.0005394293,0.013705072,0.00033285964,0.004405606,0.0004510472,0.00014112027],"about_ca_topic_score_codex":0.000024917474,"about_ca_topic_score_gemma":0.000065600674,"teacher_disagreement_score":0.26244166,"about_ca_system_score_codex":0.000117613505,"about_ca_system_score_gemma":0.00042049107,"threshold_uncertainty_score":0.92439574},"labels":[],"label_agreement":null},{"id":"W2277863828","doi":"10.1007/978-0-387-76978-3_30","title":"Reliability and Validity in Neuropsychology","year":2010,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Reliability (semiconductor); Psychology; Test (biology); Neuropsychology; Validity; Context (archaeology); Ecological validity; Cognition; Applied psychology; Computer science; Cognitive psychology; Psychometrics; Clinical psychology","score_opus":0.5983288851590297,"score_gpt":0.4817479239932682,"score_spread":0.1165809611657615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2277863828","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026401184,0.000103403356,0.0012486468,0.0005296651,0.0018034633,0.00018140618,0.000008874389,0.000052096904,0.96967125],"genre_scores_gemma":[0.046206962,0.0002930321,0.053414322,0.0010698413,0.00030655484,0.000005696091,0.0000025396896,0.000042586922,0.89865845],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967568,0.00028920523,0.00090493064,0.0011423712,0.0006610469,0.00024566712],"domain_scores_gemma":[0.96024454,0.037838776,0.0003617818,0.0012501162,0.00018623158,0.0001185381],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011004146,0.00023976309,0.00064607064,0.0007359898,0.000061790655,0.000099373596,0.0007379309,0.00059781317,0.0036912342],"category_scores_gemma":[0.09811942,0.00016077189,0.000105750565,0.00025098235,0.00032881787,0.00008017354,0.00036253833,0.0011263513,0.00018605085],"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":[0.00009253986,0.00007165801,0.07248569,0.000020952268,0.00001130351,0.00014610683,0.00011693871,0.000003937656,0.0003775302,0.12566493,0.014866811,0.7861416],"study_design_scores_gemma":[0.00012963288,0.00006008387,0.1036904,0.0000060882544,0.0000031111408,0.000026912761,0.000005937935,0.0000212727,0.000003760563,0.6076975,0.28820434,0.00015094555],"about_ca_topic_score_codex":0.000037422287,"about_ca_topic_score_gemma":0.000071224895,"teacher_disagreement_score":0.78599066,"about_ca_system_score_codex":0.000013466816,"about_ca_system_score_gemma":0.000032294156,"threshold_uncertainty_score":0.9972195},"labels":[],"label_agreement":null},{"id":"W2282238149","doi":"10.3138/jvme.0115-008r","title":"Using the <i>Nudge</i> and <i>Shove</i> Methods to Adjust Item Difficulty Values","year":2015,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Simple (philosophy); Computer science; Cognitive psychology; Applied psychology; Mathematics education","score_opus":0.7883825166976349,"score_gpt":0.6299458838527838,"score_spread":0.1584366328448511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2282238149","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":[0.8820703,0.0022371423,0.098845646,0.01144773,0.0045275274,0.000095127856,8.03188e-7,0.000008679834,0.0007670345],"genre_scores_gemma":[0.43379807,0.00011813953,0.5580748,0.006309983,0.0014518788,0.000003975278,4.421458e-7,0.000013701502,0.00022903095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951989,0.0017286745,0.0009193864,0.00021531513,0.0017442445,0.0001934534],"domain_scores_gemma":[0.98021126,0.016763596,0.0007963877,0.00038849586,0.00096273236,0.0008775525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022669954,0.00011768216,0.00033844507,0.00029628983,0.00013015787,0.00015948572,0.00077405723,0.000090789865,0.00007862973],"category_scores_gemma":[0.24505137,0.00006037121,0.00008976578,0.0012105131,0.00012584812,0.00028130756,0.00022566688,0.00032981063,0.0000045739494],"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":[0.00013681773,0.0001732223,0.0051832697,0.000007131173,0.000018532728,0.000018202818,0.001957537,0.000045550372,0.002865496,0.00007587384,0.06958883,0.91992956],"study_design_scores_gemma":[0.0018620903,0.003946256,0.1273686,0.00041653676,0.00014649835,0.016897196,0.04073865,0.008822026,0.00060446945,0.033281393,0.765328,0.0005882895],"about_ca_topic_score_codex":0.000020642545,"about_ca_topic_score_gemma":4.725009e-7,"teacher_disagreement_score":0.91934127,"about_ca_system_score_codex":0.00007212612,"about_ca_system_score_gemma":0.00079142826,"threshold_uncertainty_score":0.7856999},"labels":[],"label_agreement":null},{"id":"W2282454180","doi":"10.1007/s00464-015-4595-x","title":"Remote FLS testing in the real world: ready for “prime time”","year":2015,"lang":"en","type":"article","venue":"Surgical Endoscopy","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal General Hospital; University of Toronto; McGill University; University Health Network","funders":"University of Toronto","keywords":"Test (biology); Medicine; Certification; Inter-rater reliability; Reliability (semiconductor); Medical physics; Psychology; Rating scale","score_opus":0.6853903300768591,"score_gpt":0.5364910110413021,"score_spread":0.14889931903555698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2282454180","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4579284,0.0003677588,0.004218404,0.0021310623,0.0011839033,0.00083355507,0.000024997675,0.00018955428,0.53312236],"genre_scores_gemma":[0.5472519,0.000027773718,0.43407118,0.00079659215,0.001406271,0.000058556256,0.000018388433,0.00005378007,0.01631558],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99586046,0.001083086,0.00079085404,0.0005590304,0.0011760496,0.0005305041],"domain_scores_gemma":[0.885588,0.11288651,0.00028567956,0.0007419313,0.0003173085,0.00018059068],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022314219,0.00016943795,0.00044627365,0.00048258228,0.00012956123,0.00021989885,0.001143966,0.00008275621,0.00011552506],"category_scores_gemma":[0.15221202,0.00009315946,0.00010355322,0.0043743555,0.000107469496,0.00014569578,0.00014235772,0.0002678198,0.00025810476],"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":[0.0010985929,0.00023500161,0.09162174,0.000011361414,0.00002519924,0.00036396473,0.0011032071,0.00043446082,0.0004423725,0.0077487486,0.045197114,0.85171825],"study_design_scores_gemma":[0.012006907,0.00089189486,0.028867265,0.000113008595,0.000028839075,0.00012119961,0.0014059619,0.04427431,0.0006254753,0.3111474,0.5997855,0.0007321993],"about_ca_topic_score_codex":0.00046102348,"about_ca_topic_score_gemma":0.000026115096,"teacher_disagreement_score":0.85098606,"about_ca_system_score_codex":0.00005140389,"about_ca_system_score_gemma":0.000116132345,"threshold_uncertainty_score":0.85492927},"labels":[],"label_agreement":null},{"id":"W2285879792","doi":"10.1080/00224499.2015.1137538","title":"A Methodological Review of Exploratory Factor Analysis in Sexuality Research: Used Practices, Best Practices, and Data Analysis Resources","year":2016,"lang":"en","type":"review","venue":"The Journal of Sex Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":161,"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":"Human sexuality; Exploratory factor analysis; Sample (material); Psychology; Exploratory research; Set (abstract data type); Best practice; Social psychology; Sociology; Psychometrics; Computer science; Clinical psychology; Social science; Political science; Gender studies","score_opus":0.9901045164332588,"score_gpt":0.7777037022173531,"score_spread":0.21240081421590573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2285879792","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012022479,0.99467194,0.0009134263,0.0016053384,0.00009558643,0.0008245584,0.00022046104,0.0000060743887,0.00046039317],"genre_scores_gemma":[0.00013000626,0.99234945,0.006643302,0.000026713555,0.00030822586,0.000015442636,0.000010619096,0.000025992354,0.0004902744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7270305,0.25068405,0.0064712064,0.0016036793,0.0130578205,0.0011527351],"domain_scores_gemma":[0.22162046,0.74607193,0.020949628,0.0059092,0.00495362,0.00049518375],"candidate_categories":["metaresearch","bibliometrics","open_science","research_integrity"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.68756497,0.00046673967,0.007260805,0.013864801,0.0004407231,0.0005323901,0.012041484,0.0004958027,0.0008139887],"category_scores_gemma":[0.8970699,0.00019953906,0.00092219637,0.05776187,0.0015981691,0.0012986554,0.0051910626,0.005545404,0.000029249544],"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":[0.00014405727,0.00026345564,0.004212082,0.007511061,0.0045665116,0.000091915645,0.0007359001,0.000001513311,0.0000066250427,0.000010355804,0.0024821733,0.9799743],"study_design_scores_gemma":[0.00023467466,0.00049430924,0.0012019315,0.017599037,0.005948533,0.0001039578,0.0063159172,0.00004459356,0.0000013032458,0.0009917235,0.9667926,0.00027142768],"about_ca_topic_score_codex":0.0007105875,"about_ca_topic_score_gemma":0.00024783006,"teacher_disagreement_score":0.97970295,"about_ca_system_score_codex":0.00024990237,"about_ca_system_score_gemma":0.0015855879,"threshold_uncertainty_score":0.9973122},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2286860047","doi":"10.1016/j.rcp.2015.12.002","title":"Validación por modelo de Rasch del Cuestionario de Calidad de Vida (PedsQL 4.0®) en niños y adolescentes colombianos","year":2016,"lang":"es","type":"article","venue":"Revista Colombiana de Psiquiatría","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Rasch model; Humanities; Internal consistency; Psychology; Philosophy; Clinical psychology; Developmental psychology; Psychometrics","score_opus":0.10927513839183671,"score_gpt":0.39470197556103,"score_spread":0.28542683716919326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286860047","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":[0.6983277,0.0067655304,0.28101906,0.009538796,0.0006286366,0.0013031935,0.00036868,0.000431374,0.001616983],"genre_scores_gemma":[0.9165841,0.0040222323,0.07075072,0.0027747545,0.00084792415,0.00016451722,0.0000132373525,0.00017395715,0.0046686064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98183405,0.0075976416,0.0029072056,0.0022303625,0.002090888,0.0033398457],"domain_scores_gemma":[0.9516336,0.041342508,0.0018630481,0.002314118,0.0010468069,0.0017999446],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027820496,0.0011220331,0.0021046442,0.0013003281,0.0008935245,0.0020258215,0.0035707997,0.0012920803,0.0010083533],"category_scores_gemma":[0.1316827,0.00091805373,0.0010767716,0.003636996,0.00065195636,0.0006944326,0.0009283849,0.0011743527,0.0005488844],"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":[0.0005909648,0.00074843556,0.76752347,0.0004872115,0.0002929206,0.00042895868,0.0007547964,0.0004120161,0.013529558,0.014842317,0.065004095,0.13538527],"study_design_scores_gemma":[0.0077750194,0.0019734544,0.59658176,0.006396339,0.0013568036,0.0018163703,0.001576031,0.032777626,0.0049256734,0.057254672,0.28312483,0.0044414266],"about_ca_topic_score_codex":0.0015980749,"about_ca_topic_score_gemma":0.00009423608,"teacher_disagreement_score":0.21825631,"about_ca_system_score_codex":0.003127904,"about_ca_system_score_gemma":0.004219135,"threshold_uncertainty_score":0.9999049},"labels":[],"label_agreement":null},{"id":"W2287310496","doi":"10.5539/ijsp.v5n6p94","title":"Reliability Estimates for Three Factor Score Estimators","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Reliability (semiconductor); Factor analysis; Computation; Factor (programming language); Regression","score_opus":0.32949740672133737,"score_gpt":0.4612226797329361,"score_spread":0.13172527301159875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287310496","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":[0.3301715,0.00007781493,0.6671687,0.0009341921,0.001010543,0.00011494506,0.00046596452,0.0000061890532,0.000050206683],"genre_scores_gemma":[0.6234495,0.000014778989,0.3763801,0.000026555308,0.00010216137,0.0000028520528,7.545592e-7,0.0000042376996,0.000019065012],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975072,0.000102198544,0.001022518,0.00027128003,0.00094266946,0.00015410941],"domain_scores_gemma":[0.9534308,0.04263369,0.000785907,0.00021580598,0.0028075273,0.0001263138],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050945776,0.00011381078,0.00031108627,0.00019082183,0.00006872589,0.00016802979,0.0006500065,0.00005161348,0.00018187566],"category_scores_gemma":[0.23129839,0.000057685353,0.000095746014,0.00015469462,0.00022516292,0.0002670917,0.00010886575,0.00008866037,0.000002837214],"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":[0.00016062132,0.00004820491,0.48240772,0.0000089311825,0.000034446904,0.0000042062325,0.000036107544,0.000027079552,0.00019850569,0.009510534,0.0009838458,0.5065798],"study_design_scores_gemma":[0.0003483111,0.00013442879,0.40321475,0.000027181433,0.0000070877963,0.000022596356,0.00000680408,0.00097409467,0.00007885703,0.5939359,0.0011971093,0.000052876803],"about_ca_topic_score_codex":0.000010580295,"about_ca_topic_score_gemma":0.000011774472,"teacher_disagreement_score":0.5844254,"about_ca_system_score_codex":0.00007129693,"about_ca_system_score_gemma":0.00010897303,"threshold_uncertainty_score":0.7751767},"labels":[],"label_agreement":null},{"id":"W2287432865","doi":"","title":"An overview of the CAT: framework, R package, and applications","year":2012,"lang":"en","type":"article","venue":"ORBi (University of Liège)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Computer science","score_opus":0.439721280944141,"score_gpt":0.4416799801344344,"score_spread":0.0019586991902934003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287432865","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":[0.8989136,0.001356073,0.093636416,0.00082774577,0.000155149,0.00016287186,0.00002063779,0.00001705245,0.004910413],"genre_scores_gemma":[0.958652,0.0001593381,0.0408391,0.00004046818,0.000029539333,1.3508175e-7,2.8522925e-7,0.0000021960348,0.00027695062],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990569,0.00021289676,0.00012551011,0.00014745264,0.00033653507,0.00012073651],"domain_scores_gemma":[0.99532336,0.0036070284,0.00025861323,0.0006204147,0.000108728236,0.00008183589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016719061,0.00005021383,0.00016660448,0.000119049786,0.0001485087,0.000011923424,0.0006714537,0.00006280726,0.00024159653],"category_scores_gemma":[0.000797439,0.000037038415,0.000059823342,0.001186706,0.00015988092,0.00023384781,0.0001962831,0.000073974894,0.000012810354],"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":[0.000006824948,0.00009386853,0.8461702,0.000018423569,0.000012970392,2.575677e-7,0.0014808247,0.0000045478114,0.0006708648,0.044277668,0.00073196075,0.10653161],"study_design_scores_gemma":[0.000085488515,0.000023919354,0.960353,0.000018425062,0.000018142891,0.0000027640904,0.003321873,0.00006892938,0.000078157,0.026164133,0.009806805,0.00005832952],"about_ca_topic_score_codex":0.0002690777,"about_ca_topic_score_gemma":0.000017812663,"teacher_disagreement_score":0.11418286,"about_ca_system_score_codex":0.000008085184,"about_ca_system_score_gemma":0.000019050553,"threshold_uncertainty_score":0.26453125},"labels":[],"label_agreement":null},{"id":"W2292070591","doi":"10.1371/journal.pone.0150563","title":"The Accuracy of Computerized Adaptive Testing in Heterogeneous Populations: A Mixture Item-Response Theory Analysis","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Arthritis Research Centre of Canada; University of British Columbia; Western University; Trinity Western University; Providence Health Care Research Institute; Providence Health Care","funders":"Canadian Arthritis Network; Canada Research Chairs; Trinity Western University","keywords":"Latent class model; Statistics; Latent variable; Item response theory; Computerized adaptive testing; Population; Categorical variable; Polytomous Rasch model; Sample (material); Sample size determination; Latent variable model; Referent; Mathematics; Psychology; Medicine; Psychometrics","score_opus":0.6519117362826303,"score_gpt":0.42946199383306954,"score_spread":0.22244974244956078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292070591","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":[0.9464118,0.00043437636,0.052229572,0.00048218464,0.00005521669,0.00020008326,0.00001858689,0.000032667303,0.0001355546],"genre_scores_gemma":[0.90605414,0.000014674273,0.0936441,0.000056233428,0.000028763527,0.000015348027,4.075824e-7,0.000006536926,0.0001798235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99465996,0.002977157,0.00084590825,0.00037800256,0.00088277884,0.00025621997],"domain_scores_gemma":[0.6935288,0.30452073,0.00069762056,0.0007427942,0.00044982333,0.0000602253],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011415567,0.00012266145,0.00049032224,0.0007854021,0.00016005435,0.00008047854,0.0007831053,0.00006265773,0.00006681073],"category_scores_gemma":[0.4145085,0.000057964622,0.00014203491,0.0053863022,0.00012772641,0.00013355426,0.0001973834,0.000098799486,0.000012954016],"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":[0.0024126286,0.00064215105,0.5015641,0.0000069280495,0.0008781728,0.00002183377,0.0005707229,0.0006212259,0.056126993,0.0010645909,0.00005357862,0.43603706],"study_design_scores_gemma":[0.0010145401,0.00030961487,0.85753673,0.00024761082,0.0002776879,0.0000054095563,0.00038597785,0.03424765,0.004298618,0.101357944,0.000056002023,0.00026218453],"about_ca_topic_score_codex":0.00003062233,"about_ca_topic_score_gemma":0.0000231855,"teacher_disagreement_score":0.4357749,"about_ca_system_score_codex":0.000035628836,"about_ca_system_score_gemma":0.000041652656,"threshold_uncertainty_score":0.59042335},"labels":[],"label_agreement":null},{"id":"W2298555240","doi":"10.20982/tqmp.12.1.p057","title":"Impact on Cronbach's alpha of simple treatment methods for missing data","year":2016,"lang":"en","type":"article","venue":"The Quantitative Methods for Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":22,"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; Université de Montréal","funders":"","keywords":"Cronbach's alpha; Simple (philosophy); Alpha (finance); Missing data; Computer science; Statistics; Psychology; Mathematics; Psychometrics; Philosophy; Epistemology","score_opus":0.8902946363437428,"score_gpt":0.7558070855239161,"score_spread":0.13448755081982677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298555240","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":[0.00999468,0.0013437044,0.98059374,0.003939667,0.0012884219,0.0011594737,0.0005390034,0.000043307777,0.001098013],"genre_scores_gemma":[0.006744815,0.00008420274,0.99218,0.00031947708,0.00011996812,0.00012698259,0.000016042015,0.000042198895,0.0003663284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98632187,0.009992881,0.001325641,0.0013429051,0.00030843602,0.00070829707],"domain_scores_gemma":[0.63014716,0.36545238,0.0010817598,0.0027251733,0.0004728172,0.000120717865],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05476688,0.00038862744,0.0012095434,0.00062070496,0.00034162222,0.00006747951,0.002672318,0.00016766769,0.00022195485],"category_scores_gemma":[0.22755007,0.00015661452,0.00052715564,0.0013237052,0.0006350706,0.00021906548,0.00022747833,0.000115067385,0.000017113078],"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":[0.0014044135,0.00017582375,0.00068065966,0.000005499571,0.00024281385,3.113094e-7,0.00031448161,0.000007992682,0.029716525,0.011059524,0.0043545235,0.95203745],"study_design_scores_gemma":[0.002942519,0.007397469,0.015581744,0.000028143639,0.00013555541,0.000015530823,0.0004577175,0.0042485604,0.0076692235,0.8204565,0.14075825,0.0003087654],"about_ca_topic_score_codex":0.00003878852,"about_ca_topic_score_gemma":0.0000034921238,"teacher_disagreement_score":0.95172864,"about_ca_system_score_codex":0.000076824865,"about_ca_system_score_gemma":0.00009632066,"threshold_uncertainty_score":0.97331643},"labels":[],"label_agreement":null},{"id":"W2300285189","doi":"10.1177/0829573515621531","title":"Book Review: <i>WISC-V assessment and interpretation: Scientist-practitioner perspectives</i> by Weiss, L. G., Saklofske, D. H., Holdnack, J. A., &amp; Prifitera, A.","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Calgary","funders":"","keywords":"Psychology; Interpretation (philosophy); Wechsler Intelligence Scale for Children; Psychoanalysis; Humanities; Clinical psychology; Intelligence quotient; Psychiatry; Philosophy; Cognition; Linguistics","score_opus":0.252120968845472,"score_gpt":0.49430708814250285,"score_spread":0.24218611929703082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300285189","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010914857,0.7922878,0.05659978,0.09175103,0.0067681447,0.0004734457,0.00008351098,0.000024996421,0.041096415],"genre_scores_gemma":[0.28611833,0.066628404,0.1905879,0.3945152,0.0031943442,0.00006992453,0.000060086288,0.00018568066,0.05864016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956599,0.0010886597,0.0012811773,0.0005890923,0.00090360024,0.00047760704],"domain_scores_gemma":[0.9925053,0.0018879293,0.0011767986,0.0006787363,0.0018218628,0.0019293444],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010816987,0.00022169296,0.0006260416,0.0011974031,0.00022983056,0.00046122706,0.0009730807,0.00014363023,0.002828487],"category_scores_gemma":[0.037270676,0.00017353598,0.00014966814,0.0016219509,0.00044155537,0.0010800562,0.000049429163,0.00077712885,0.00016671952],"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":[0.000024543655,0.000023907704,0.01156824,0.000007637716,0.00002947592,0.000049697024,0.00020857969,0.000004601062,0.00004948572,0.000107196836,0.97602504,0.011901612],"study_design_scores_gemma":[0.0007260809,0.00026817722,0.021281708,0.00019731213,0.000031591087,0.00095871574,0.0007049547,0.000017585278,0.0000021726523,0.0041677286,0.9714553,0.0001887021],"about_ca_topic_score_codex":0.0001839613,"about_ca_topic_score_gemma":0.00026014567,"teacher_disagreement_score":0.72565943,"about_ca_system_score_codex":0.00028898264,"about_ca_system_score_gemma":0.0013336281,"threshold_uncertainty_score":0.99808306},"labels":[],"label_agreement":null},{"id":"W2315260934","doi":"10.1080/10401334.2016.1146608","title":"Using Automatic Item Generation to Improve the Quality of MCQ Distractors","year":2016,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Psychometric Methodologies and Testing","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":true,"ca_institutions":"University of Ottawa; Medical Council of Canada; University of Alberta","funders":"","keywords":"Test (biology); Computer science; Item bank; Quality (philosophy); Process (computing); Field (mathematics); Construct (python library); Multiple choice; Item response theory; Cognition; Applied psychology; Psychology; Psychometrics; Clinical psychology; Medicine","score_opus":0.5912255297888322,"score_gpt":0.5498694737714378,"score_spread":0.04135605601739445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315260934","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":[0.91934884,0.000111453664,0.07720145,0.002407549,0.00028388246,0.000082576,5.0879856e-7,0.000026259735,0.0005374884],"genre_scores_gemma":[0.9879853,0.0000039385077,0.011365331,0.0001117643,0.00018112508,0.0000017834634,2.6849318e-7,0.000004703465,0.00034576925],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953025,0.002961829,0.0007129223,0.00026655625,0.0005982818,0.00015788666],"domain_scores_gemma":[0.9537168,0.045510225,0.00039169475,0.0002650598,0.0000580968,0.000058087757],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04211424,0.00008417641,0.00030798002,0.00026321193,0.00024508126,0.00002712571,0.00023129473,0.000039572173,0.00004623717],"category_scores_gemma":[0.38355285,0.00003441628,0.000025319283,0.0004721742,0.00010529956,0.00008161987,0.000064170876,0.00038066154,0.0000018313783],"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":[0.0000060148877,0.000008289615,0.1778515,0.0000069917464,0.0000036636025,5.304261e-7,0.0032712729,0.0001579135,0.060055688,0.00024209803,0.00017581397,0.7582202],"study_design_scores_gemma":[0.00063247356,0.00025671988,0.9535796,0.00028946,0.000010829557,0.0000065688887,0.006206157,0.035281073,0.00015721163,0.0013663156,0.0020840662,0.00012951596],"about_ca_topic_score_codex":0.0007598299,"about_ca_topic_score_gemma":0.000015897725,"teacher_disagreement_score":0.7757281,"about_ca_system_score_codex":0.000026702743,"about_ca_system_score_gemma":0.000016199416,"threshold_uncertainty_score":0.986345},"labels":[],"label_agreement":null},{"id":"W2319025097","doi":"10.1371/journal.pone.0151519","title":"Differential Item Functioning in the SF-36 Physical Functioning and Mental Health Sub-Scales: A Population-Based Investigation in the Canadian Multicentre Osteoporosis Study","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Trinity Western University; Providence Health Care; University of Toronto; Western University; University of British Columbia; University of Saskatchewan; University of Victoria; University of Calgary; McGill University Health Centre; McMaster University; Queen's University; Dalhousie University; University of Manitoba","funders":"Canadian Institutes of Health Research; Université Laval; University of Alberta; Queen's University; McMaster University; McGill University; University of Toronto; Dalhousie University","keywords":"Differential item functioning; Mental health; Osteoporosis; Medicine; Clinical psychology; Population; Psychology; Gerontology; Psychiatry; Psychometrics; Item response theory; Environmental health; Internal medicine","score_opus":0.30399342873468915,"score_gpt":0.36454973632627463,"score_spread":0.06055630759158548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319025097","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":[0.990164,0.00003504062,0.00017689679,0.0087180715,0.00011239183,0.00071506645,0.00001029918,0.000016879452,0.000051368046],"genre_scores_gemma":[0.99881804,0.000003070541,0.00048452464,0.0005150092,0.00009229931,0.000052687603,0.000010080433,0.0000068665368,0.00001743102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99602467,0.0016747683,0.00047935167,0.00039850763,0.0011159693,0.00030675862],"domain_scores_gemma":[0.9867962,0.012480696,0.00023190184,0.0003169417,0.00006997315,0.00010426287],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038019656,0.00012847484,0.00026368286,0.00046688507,0.000586606,0.00027819542,0.00030049976,0.00004140417,0.000027653492],"category_scores_gemma":[0.012185659,0.00006289167,0.000035743393,0.0014683045,0.00006136803,0.00019696783,0.000032129516,0.00019285745,0.0000073073334],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025037241,0.00039547734,0.98358494,0.0000043790183,0.000009109757,9.559218e-7,0.0062152063,0.000020421841,0.00024294914,0.000024398902,0.00006228665,0.009414816],"study_design_scores_gemma":[0.00090672926,0.00019107453,0.9811461,0.00008395814,0.000010568725,6.9299483e-7,0.010510662,0.0063225063,0.000026952048,0.0007112818,0.0000070223696,0.00008246697],"about_ca_topic_score_codex":0.046916574,"about_ca_topic_score_gemma":0.30960843,"teacher_disagreement_score":0.26269186,"about_ca_system_score_codex":0.00020430503,"about_ca_system_score_gemma":0.00009251896,"threshold_uncertainty_score":0.9961351},"labels":[],"label_agreement":null},{"id":"W2329561122","doi":"10.4995/head15.2015.364","title":"Mixed-format exams in higher education: Assessment of internal consistency reliability","year":2015,"lang":"en","type":"article","venue":"","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":"Saint Mary's University","funders":"","keywords":"Reliability (semiconductor); Internal consistency; Measure (data warehouse); Consistency (knowledge bases); Computer science; Multiple choice; Reproducibility; Mathematics education; Test (biology); Psychology; Statistics; Mathematics; Significant difference; Psychometrics; Artificial intelligence; Data mining","score_opus":0.7094676573679086,"score_gpt":0.5307209581113188,"score_spread":0.1787466992565898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2329561122","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":[0.5947873,0.00013218244,0.0046918876,0.0012014385,0.0027315668,0.00009814505,0.0000012299524,0.00001927255,0.39633697],"genre_scores_gemma":[0.91097856,0.000002740844,0.08480059,0.00033259747,0.00004824125,0.000007165039,4.4911e-7,0.000002552923,0.0038271265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973218,0.00047133034,0.0009038846,0.00028640372,0.000862712,0.00015390369],"domain_scores_gemma":[0.99046123,0.008015019,0.00031705573,0.0006166985,0.00046624074,0.0001237703],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010728774,0.000081806764,0.0002837961,0.00034544122,0.000020605119,0.000058954363,0.0005634594,0.000053129246,0.001161704],"category_scores_gemma":[0.02627532,0.000051432056,0.000060571158,0.0013812871,0.000093674,0.00024379717,0.00018032748,0.00012316703,0.000024974315],"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":[0.000007993032,0.00014239652,0.87606454,0.0000042440515,0.000002396508,6.1489584e-7,0.000073332805,0.000037094633,0.000012118238,0.008427791,0.023759834,0.09146765],"study_design_scores_gemma":[0.00027718794,0.00008300789,0.9066481,0.000016728256,0.000002010512,0.000005278683,0.002002694,0.00063751364,0.00006281462,0.067510046,0.02267858,0.000076020515],"about_ca_topic_score_codex":0.0003056858,"about_ca_topic_score_gemma":0.000016962173,"teacher_disagreement_score":0.39250985,"about_ca_system_score_codex":0.00008676514,"about_ca_system_score_gemma":0.00028026928,"threshold_uncertainty_score":0.9997514},"labels":[],"label_agreement":null},{"id":"W2339611273","doi":"","title":"Evaluating PCK-EC in Practice – Case Study","year":2016,"lang":"en","type":"article","venue":"Society for Information Technology & Teacher Education International Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Victoria","funders":"","keywords":"Computer science","score_opus":0.446721655282395,"score_gpt":0.5718684213299559,"score_spread":0.12514676604756086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339611273","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":[0.8278961,0.00005421431,0.1335186,0.023498116,0.0020804056,0.0011882944,0.000023812416,0.00021735182,0.011523109],"genre_scores_gemma":[0.92043895,0.000016617525,0.07741999,0.0004963182,0.00008854928,0.0005108041,0.00000868062,0.000006768383,0.001013305],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99708575,0.00019322404,0.0011958402,0.00038553984,0.0008799841,0.00025967704],"domain_scores_gemma":[0.9892671,0.00615915,0.0010021194,0.0005326934,0.0029839964,0.000054906737],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008619495,0.0001641705,0.00022183896,0.0009826592,0.0002054893,0.00027029138,0.0010026202,0.00020971161,0.00031813953],"category_scores_gemma":[0.09669551,0.00011745554,0.00014765422,0.00163203,0.00013855223,0.0025947737,0.00019856547,0.00026936716,0.00009595116],"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":[0.0000266162,0.00035203574,0.072523125,0.0000035833086,0.000055310855,0.0000015319406,0.005451352,0.000011824857,0.00011363137,0.025460316,0.0035086535,0.892492],"study_design_scores_gemma":[0.0033962275,0.00060547027,0.016094526,0.00009617094,0.0000640667,0.0007521243,0.7817106,0.009084935,0.00020066083,0.10503736,0.0823899,0.00056792516],"about_ca_topic_score_codex":0.00014245056,"about_ca_topic_score_gemma":0.00002432688,"teacher_disagreement_score":0.8919241,"about_ca_system_score_codex":0.00031705495,"about_ca_system_score_gemma":0.0005800021,"threshold_uncertainty_score":0.9109134},"labels":[],"label_agreement":null},{"id":"W2345626319","doi":"10.1186/s12955-016-0472-0","title":"Colombian Rasch validation of KIDSCREEN-27 quality of life questionnaire","year":2016,"lang":"en","type":"article","venue":"Health and Quality of Life Outcomes","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":"McMaster University","funders":"Universidad de Antioquia","keywords":"Rasch model; Differential item functioning; Psychology; Polytomous Rasch model; Psychometrics; Proxy (statistics); Separation (statistics); Classical test theory; Item response theory; Clinical psychology; Socioeconomic status; Developmental psychology; Demography; Statistics","score_opus":0.669465832533903,"score_gpt":0.5634706798882609,"score_spread":0.10599515264564208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345626319","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":[0.9670114,0.0011605876,0.01657265,0.014044667,0.00042466927,0.00026623663,0.00008246819,0.000030157766,0.00040715627],"genre_scores_gemma":[0.9895081,0.00023579795,0.008586007,0.001321861,0.000040187293,0.0000035886826,0.0000029376913,0.0000068604686,0.00029464185],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99042994,0.0038740034,0.003491029,0.0004409722,0.0014458318,0.00031822617],"domain_scores_gemma":[0.9423966,0.05020348,0.004716324,0.0010168377,0.0009177872,0.0007489892],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032747794,0.00016339113,0.00148345,0.0003770805,0.00011634053,0.000020186806,0.00042166,0.00013124592,0.000087814915],"category_scores_gemma":[0.31597063,0.00009892497,0.00020318254,0.0008720334,0.00034085067,0.00021622685,0.00012395452,0.00009794403,0.0000053663466],"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":[0.00016182274,0.000089371584,0.9561237,0.00033710638,0.000022306662,3.4924064e-8,0.00037044854,0.0000012124086,0.00016498545,0.009763593,0.0009662867,0.031999115],"study_design_scores_gemma":[0.0012351323,0.00024117937,0.9878778,0.00011086223,0.0000036729173,2.371336e-7,0.0011564322,0.000005226403,0.0002290073,0.008429872,0.00059517106,0.00011542086],"about_ca_topic_score_codex":0.0028081955,"about_ca_topic_score_gemma":0.00013215862,"teacher_disagreement_score":0.28322282,"about_ca_system_score_codex":0.000027308573,"about_ca_system_score_gemma":0.00056981033,"threshold_uncertainty_score":0.9959897},"labels":[],"label_agreement":null},{"id":"W2364328457","doi":"10.1007/978-3-319-07794-9","title":"Validity and Validation in Social, Behavioral, and Health Sciences","year":2014,"lang":"en","type":"book","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"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":"Behavioural sciences; Psychology; Data science; Computer science; Psychotherapist","score_opus":0.8242681565438117,"score_gpt":0.6357213862676169,"score_spread":0.18854677027619482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2364328457","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":[0.6481026,0.0042430502,0.00021584828,0.025647271,0.0012494883,0.0024824997,0.00026747512,0.00022812869,0.31756365],"genre_scores_gemma":[0.6803824,0.0054693082,0.0059480425,0.00056101556,0.004195553,0.00024175453,0.00012458689,0.00016436761,0.30291298],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9899892,0.0037105174,0.000922724,0.001076957,0.0034565195,0.00084404816],"domain_scores_gemma":[0.9882886,0.010183604,0.00074348773,0.0002629685,0.0002974275,0.00022394123],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.059420343,0.00026617982,0.00089781464,0.0036217996,0.0033399723,0.0010960025,0.00095670065,0.0005170724,0.00011205889],"category_scores_gemma":[0.015170002,0.00022070944,0.000087276574,0.003649401,0.004319981,0.00045431431,0.00083488296,0.0012041619,0.000016396145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005494879,0.000118280266,0.15109801,0.00022458425,0.000018608003,0.000013860986,0.010643564,2.8790836e-7,0.000011638714,0.061386608,0.42719522,0.34923437],"study_design_scores_gemma":[0.0003483068,0.0008745419,0.16109852,0.00010461157,0.00000870614,0.000007071831,0.005416601,0.000004920154,0.000023377135,0.5843072,0.24734102,0.0004651004],"about_ca_topic_score_codex":0.00032063716,"about_ca_topic_score_gemma":0.00020348714,"teacher_disagreement_score":0.5229206,"about_ca_system_score_codex":0.00030978204,"about_ca_system_score_gemma":0.0014541905,"threshold_uncertainty_score":0.99994093},"labels":[],"label_agreement":null},{"id":"W2364583314","doi":"","title":"Strengthening Organization Regulation Improving Regional Test Quality","year":2007,"lang":"en","type":"article","venue":"Seed","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Test (biology); Business; Biology; Ecology","score_opus":0.3742664240417701,"score_gpt":0.4604939390145097,"score_spread":0.08622751497273962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2364583314","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":[0.6987158,0.00003190966,0.2965147,0.0002662618,0.0003285364,0.000067402965,0.0000015119557,0.000106275904,0.0039676195],"genre_scores_gemma":[0.95376515,9.525911e-7,0.04507281,0.00011678807,0.00020480713,3.926083e-7,0.000006936848,0.000008654018,0.0008234813],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99767476,0.00017968047,0.0006980929,0.00034936695,0.0008739704,0.00022413486],"domain_scores_gemma":[0.96245474,0.035720512,0.0006032384,0.00046645387,0.0006623447,0.00009273917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012913655,0.00008644024,0.00015906787,0.0003403139,0.00022181873,0.00013652272,0.0003232578,0.00007905218,0.00013291452],"category_scores_gemma":[0.2292,0.000067214445,0.000032855663,0.0030564817,0.0000422387,0.00022752646,0.00007737537,0.00010630065,0.000063718784],"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":[0.000010679496,0.00002301971,0.81739473,0.0000024824883,0.0000029150194,0.0000010258308,0.00028661382,0.000067733396,0.052758247,0.0016563452,0.00029334967,0.12750286],"study_design_scores_gemma":[0.00017370301,0.00002215905,0.98509043,0.000005125644,0.000002537268,0.000005119708,0.0007480852,0.0009447708,0.0022148895,0.010161188,0.00053888414,0.00009311298],"about_ca_topic_score_codex":0.000069508584,"about_ca_topic_score_gemma":0.000016070187,"teacher_disagreement_score":0.2550494,"about_ca_system_score_codex":0.000046441222,"about_ca_system_score_gemma":0.000035500492,"threshold_uncertainty_score":0.7772928},"labels":[],"label_agreement":null},{"id":"W2405236066","doi":"","title":"Theorems About PI Indices.","year":2012,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Pi; Pure mathematics; Geometry","score_opus":0.2720963887838566,"score_gpt":0.4342377935633694,"score_spread":0.16214140477951278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405236066","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":[0.8881428,0.0015007969,0.00035821728,0.00017883044,0.009541209,0.00010715553,0.000002417044,0.000100384685,0.100068174],"genre_scores_gemma":[0.9961478,0.000022614357,0.002559817,0.0002646962,0.000060698552,0.000008376789,0.0000010114433,0.000012912688,0.0009220455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99697775,0.00050280854,0.0005191329,0.00033370836,0.0011036718,0.00056294614],"domain_scores_gemma":[0.98143727,0.017041204,0.0003255106,0.0007839431,0.00016295095,0.00024915452],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010597724,0.00014911435,0.00030672294,0.00037456525,0.00020641992,0.0001809444,0.0010504666,0.00011168085,0.000731858],"category_scores_gemma":[0.052632425,0.00010279835,0.00011032672,0.0022305145,0.00011484288,0.00045044936,0.00024415384,0.00022598305,0.00090714655],"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":[0.0000061144865,0.00007417644,0.41805196,0.0000014251143,0.000009963194,0.0000017294674,0.00039245206,9.456732e-7,0.00007054035,0.50838566,0.011659979,0.061345074],"study_design_scores_gemma":[0.00027099228,0.00003393328,0.2974767,0.000005711031,0.0000049448627,0.000007204517,0.00028601423,0.000026448592,0.00022493236,0.66680294,0.034736224,0.00012396168],"about_ca_topic_score_codex":0.000025610512,"about_ca_topic_score_gemma":5.018325e-7,"teacher_disagreement_score":0.15841728,"about_ca_system_score_codex":0.00003204343,"about_ca_system_score_gemma":0.000028526312,"threshold_uncertainty_score":0.9998708},"labels":[],"label_agreement":null},{"id":"W2420346645","doi":"10.1017/s148180350001126x","title":"Factor analyze this","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Emergency Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Action (physics)","score_opus":0.6784303586328619,"score_gpt":0.5269095683773355,"score_spread":0.15152079025552645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2420346645","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":[0.5795298,0.025713649,0.017924672,0.05335935,0.05934577,0.00021387954,0.000023881657,0.000026270494,0.2638627],"genre_scores_gemma":[0.9908286,0.0002572063,0.0017527618,0.00055334385,0.0017358962,1.578581e-7,4.4283132e-7,0.000006231412,0.004865387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968645,0.00023295208,0.0014218772,0.00018922143,0.0009285638,0.00036290032],"domain_scores_gemma":[0.99482864,0.0020105136,0.0007789108,0.00036503025,0.00091811497,0.0010988048],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0050852373,0.00012759122,0.00046938966,0.0015904701,0.00014708737,0.000017569737,0.0010005158,0.000066431836,0.046198353],"category_scores_gemma":[0.1307503,0.000075894226,0.0001654366,0.0029374254,0.00006888025,0.00019276296,0.000006692829,0.00028370065,0.000048135],"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":[0.000009776405,0.000008938533,0.10019204,0.0000015765282,0.000027417384,0.00012350213,0.0009575822,0.000018739462,0.00046903887,0.0005845524,0.70725244,0.19035442],"study_design_scores_gemma":[0.00042201014,0.000841881,0.43799227,0.000059706585,0.000031856336,0.000051842442,0.0008683341,0.000080988095,0.00003121766,0.044458088,0.5149951,0.00016672439],"about_ca_topic_score_codex":0.0015540734,"about_ca_topic_score_gemma":0.0017730582,"teacher_disagreement_score":0.41129875,"about_ca_system_score_codex":0.000060266804,"about_ca_system_score_gemma":0.00042564346,"threshold_uncertainty_score":0.9546735},"labels":[],"label_agreement":null},{"id":"W2423451015","doi":"10.71781/32372","title":"Évaluation de la performance du score de propension à hautes dimensions dans le cadre d’études observationnelles québécoises","year":2014,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Canadian Institutes of Health Research","keywords":"Psychology; Humanities; Physics; Philosophy","score_opus":0.4133723944608735,"score_gpt":0.4350642139983816,"score_spread":0.021691819537508095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2423451015","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":[0.96467924,0.00058706326,0.0063123954,0.000726501,0.0009365188,0.0009766326,0.000024353261,0.000010881814,0.025746442],"genre_scores_gemma":[0.7509529,0.0005084797,0.23649764,0.00010959258,0.000188869,0.00007693767,0.00022223926,0.0000441946,0.011399152],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9929575,0.0029073276,0.0012412488,0.0011451184,0.0011153421,0.00063349423],"domain_scores_gemma":[0.9743192,0.022569496,0.0011853783,0.00081342785,0.0008731706,0.00023929616],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017485974,0.00050098175,0.0007987897,0.00048909284,0.0017379062,0.0014189036,0.0021011182,0.00059586635,0.0010209883],"category_scores_gemma":[0.06795242,0.00041166332,0.00018391381,0.0018219774,0.00032059435,0.0009587399,0.00042208048,0.00054876006,0.0002743348],"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":[0.00012221077,0.00023128904,0.4611105,0.00006576408,0.000050117702,0.000014131773,0.008411725,0.008471039,0.015046794,0.001024046,0.0008354701,0.5046169],"study_design_scores_gemma":[0.0007336414,0.00026260797,0.86783427,0.0012981633,0.00016140078,0.00006663669,0.015049774,0.07174314,0.018525515,0.0024981734,0.021185655,0.00064101495],"about_ca_topic_score_codex":0.013683865,"about_ca_topic_score_gemma":0.0067364303,"teacher_disagreement_score":0.50397587,"about_ca_system_score_codex":0.00020965634,"about_ca_system_score_gemma":0.00272346,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W2431662475","doi":"10.1371/journal.pone.0157795","title":"Examining the Effect of Reverse Worded Items on the Factor Structure of the Need for Cognition Scale","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"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":"Psychology; Confirmatory factor analysis; Scale (ratio); Covariance; Factor analysis; Scale factor (cosmology); Factor (programming language); Cognition; Statistics; Psychometrics; Structural equation modeling; Developmental psychology; Mathematics; Computer science","score_opus":0.5134880551927866,"score_gpt":0.38725504049072906,"score_spread":0.12623301470205756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2431662475","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":[0.9970346,0.00003024631,0.00059434364,0.0009898776,0.00017617921,0.0006082615,0.00008655232,0.000010222287,0.00046970937],"genre_scores_gemma":[0.9985786,0.000004089968,0.000949436,0.00009311851,0.00006808597,0.000013913607,3.5064852e-7,0.0000062731488,0.00028612604],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977569,0.00079314713,0.00033650536,0.00019160367,0.00078285404,0.00013898684],"domain_scores_gemma":[0.90393364,0.094901286,0.0004288244,0.00054502045,0.00017241354,0.000018835319],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029548898,0.00008888976,0.00026207755,0.000088264904,0.00013875066,0.000025632009,0.0006718894,0.000054414595,0.00016699817],"category_scores_gemma":[0.1144728,0.000024922598,0.00008978553,0.0008098178,0.00015493379,0.000051364732,0.00008516367,0.000094658564,0.0000041288836],"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":[0.0002535573,0.00006345341,0.09818943,0.000031211788,0.000099775316,8.098268e-8,0.00039908112,0.0000038064832,0.8369696,0.000093861876,0.0010405664,0.06285558],"study_design_scores_gemma":[0.000994087,0.0006974579,0.16991545,0.00046917156,0.000094475225,6.353125e-7,0.0006098493,0.0001819316,0.81726664,0.009574395,0.000102270016,0.0000936535],"about_ca_topic_score_codex":0.0000061263154,"about_ca_topic_score_gemma":0.0000034253055,"teacher_disagreement_score":0.111517906,"about_ca_system_score_codex":0.000008881929,"about_ca_system_score_gemma":0.000011300827,"threshold_uncertainty_score":0.89298636},"labels":[],"label_agreement":null},{"id":"W2462736196","doi":"10.2310/6620.2007.07011","title":"Improvement of the T.R.U.E. Test: Launch of Panel 3","year":2008,"lang":"en","type":"letter","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Test (biology); Aeronautics; Panel discussion; Launch vehicle; Aerospace engineering; Engineering; Advertising; Geology","score_opus":0.41410546086462713,"score_gpt":0.39262798386199227,"score_spread":0.02147747700263486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2462736196","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026211439,0.0014540342,0.0029246844,0.9062633,0.00543119,0.001067528,0.0011615874,0.00007143909,0.05541479],"genre_scores_gemma":[0.072657324,0.00049853715,0.01451052,0.89243007,0.0015465808,0.00004488155,0.000021268472,0.000059342427,0.018231487],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99554366,0.00031996873,0.0013490322,0.00037007072,0.0021301794,0.00028709165],"domain_scores_gemma":[0.96290964,0.033563647,0.0016705983,0.001385399,0.00044188558,0.000028800714],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015687004,0.00020781603,0.000694566,0.00039720826,0.00009506792,0.000039371593,0.001967017,0.0003398961,0.00049151876],"category_scores_gemma":[0.06416596,0.00011655264,0.0003479925,0.001666485,0.00026273067,0.000070805305,0.0003829017,0.0006588681,0.000034776396],"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":[1.9844389e-7,0.000014155734,0.01202625,0.000057240104,0.0000162297,0.000017724675,0.0001139363,0.0000030618096,0.00008411451,0.000004564495,0.9592666,0.028395893],"study_design_scores_gemma":[0.00016424729,0.000063688516,0.089705594,0.000094210816,0.000015608322,0.00005948192,0.000055306962,0.00005557999,0.0019877616,0.00607849,0.90157205,0.00014799282],"about_ca_topic_score_codex":0.00018531157,"about_ca_topic_score_gemma":0.00000404654,"teacher_disagreement_score":0.07767934,"about_ca_system_score_codex":0.00002542905,"about_ca_system_score_gemma":0.00010606475,"threshold_uncertainty_score":0.94371694},"labels":[],"label_agreement":null},{"id":"W2466829557","doi":"10.7202/1036707ar","title":"Étude de nouveaux indices de détection de la réponse au hasard et de l’inattention selon différentes valeurs de l’habileté dans le contexte de la modélisation de Rasch","year":2016,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Humanities; Philosophy; Physics","score_opus":0.15534784883987784,"score_gpt":0.46417767293588785,"score_spread":0.30882982409601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466829557","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":[0.51119953,0.00035151182,0.48031014,0.0063416716,0.00062655134,0.00032189515,0.000026125419,0.000106762156,0.00071579305],"genre_scores_gemma":[0.9275362,0.0009599478,0.06922168,0.0007014332,0.0004130971,0.00023007368,0.00005151196,0.0000643967,0.0008216607],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94046956,0.055034973,0.0011326354,0.000946315,0.0012677013,0.0011488028],"domain_scores_gemma":[0.9452274,0.051868837,0.0012463791,0.00067912607,0.0006022734,0.00037602714],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15386999,0.00044916949,0.00047723862,0.00093513046,0.00086938526,0.0006849974,0.0007215513,0.00078974996,0.00017522844],"category_scores_gemma":[0.13232887,0.00041392248,0.00027694937,0.0016032609,0.00043633257,0.0013701407,0.00010670846,0.0006824954,0.000040988467],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00017377846,0.00064094045,0.6282426,0.0000854129,0.000091997,0.00000635077,0.08091471,0.018076856,0.15182725,0.00335732,0.001804865,0.11477788],"study_design_scores_gemma":[0.0015280839,0.00017802426,0.86113334,0.00037677193,0.00018511733,0.00023149613,0.0073559373,0.049979992,0.014943445,0.06274578,0.0009418872,0.00040013762],"about_ca_topic_score_codex":0.005396782,"about_ca_topic_score_gemma":0.0011588109,"teacher_disagreement_score":0.41633663,"about_ca_system_score_codex":0.0047523417,"about_ca_system_score_gemma":0.0069592036,"threshold_uncertainty_score":0.99983126},"labels":[],"label_agreement":null},{"id":"W2468688964","doi":"10.1177/2158244016653791","title":"Differential Performance on National Exams","year":2016,"lang":"en","type":"article","venue":"SAGE Open","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differential item functioning; Test (biology); Psychology; Certificate; Item response theory; Subject (documents); Social psychology; Psychometrics; Clinical psychology; Mathematics; Computer science","score_opus":0.6708101331326844,"score_gpt":0.5210443421341487,"score_spread":0.1497657909985357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468688964","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":[0.7385551,0.000010929402,0.008434835,0.00075756287,0.00071768824,0.00014423851,0.000010346307,0.000020495314,0.25134882],"genre_scores_gemma":[0.97843224,0.000012396529,0.0023183306,0.00023178101,0.00013456239,0.0000069453495,4.5938654e-7,0.0000044450935,0.01885885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99810404,0.0001877535,0.0002600303,0.00032669384,0.0009530457,0.00016845434],"domain_scores_gemma":[0.9893924,0.010013321,0.00012607711,0.00032118987,0.00009106365,0.00005597211],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002987803,0.00007195434,0.00014453314,0.00016987394,0.00013543016,0.00026056764,0.0013935845,0.000033930646,0.0057246163],"category_scores_gemma":[0.027203659,0.000033804245,0.000036618174,0.0005554705,0.000041661613,0.0003170511,0.00040254268,0.00005333638,0.0010676705],"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":[0.000031401367,0.000020474925,0.02898327,4.0351387e-7,0.0000035800967,0.0000010071999,0.000020070614,0.0000019839654,0.00087328407,0.0011505409,0.006330232,0.9625837],"study_design_scores_gemma":[0.0008574148,0.00017351322,0.9112151,0.00005847009,0.0000017395176,0.0000044021062,0.000041614472,0.00018808078,0.0030431366,0.041148357,0.043109372,0.00015874894],"about_ca_topic_score_codex":0.000006596218,"about_ca_topic_score_gemma":0.000002194938,"teacher_disagreement_score":0.962425,"about_ca_system_score_codex":0.000026731088,"about_ca_system_score_gemma":0.000034919325,"threshold_uncertainty_score":0.99971014},"labels":[],"label_agreement":null},{"id":"W2477465698","doi":"10.1017/cbo9781139150972.010","title":"Testing the Hypotheses","year":2012,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","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":"Trent University","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; Data science; Mathematics","score_opus":0.5327778780935389,"score_gpt":0.35097158848636034,"score_spread":0.1818062896071786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2477465698","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027670476,0.0007835466,0.0012400328,0.00003602758,0.0007090363,0.00028794724,0.00008198645,0.00014332603,0.99644136],"genre_scores_gemma":[0.0033419705,0.000034050485,0.0021466422,0.00011897884,0.0004211604,4.9650447e-7,0.0000020335783,0.00003489984,0.99389976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701864,0.00029574858,0.0004359478,0.000670746,0.0011180993,0.00046082996],"domain_scores_gemma":[0.9619045,0.0352449,0.0007658157,0.0014073772,0.00048118609,0.00019618764],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003052968,0.00036688283,0.0005381766,0.00043402714,0.00056525256,0.000218657,0.0024024302,0.0003093766,0.00003419585],"category_scores_gemma":[0.016202334,0.00025043153,0.00029212557,0.00009027913,0.00045344458,0.00013743449,0.0010713965,0.0006573076,0.00010819073],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027945847,0.00000664137,0.00023459709,0.000011291432,0.00007578296,0.000072638635,0.00005175374,0.0000039007914,0.000052503005,0.7191678,0.083345845,0.19694926],"study_design_scores_gemma":[0.00014574266,0.000028764616,0.0016710225,0.00005723005,0.00009688277,0.000035398043,0.00011582469,0.000047096357,0.000032497104,0.0004799055,0.9969736,0.00031606547],"about_ca_topic_score_codex":0.000098927965,"about_ca_topic_score_gemma":5.974466e-7,"teacher_disagreement_score":0.91362774,"about_ca_system_score_codex":0.000091612106,"about_ca_system_score_gemma":0.000091474154,"threshold_uncertainty_score":0.9999948},"labels":[],"label_agreement":null},{"id":"W2502761478","doi":"","title":"The International Test and Evaluation Program","year":2003,"lang":"en","type":"article","venue":"JMU Scholoraly Commons (James Madison University)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Mine action; Test (biology); Operations research; Reliability engineering; Computer science; Engineering; Political science; Biology; Law; Ecology","score_opus":0.3339966853448025,"score_gpt":0.4401005827019881,"score_spread":0.10610389735718562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2502761478","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":[0.67515355,0.0006827897,0.0010753473,0.00513912,0.00097232097,0.0005453302,0.000011857052,0.00014970815,0.31626996],"genre_scores_gemma":[0.9830193,0.00013364383,0.009980344,0.00009897138,0.000042932166,0.0000041548515,0.000003310067,0.0000079496585,0.0067094225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973361,0.0007975232,0.00026876593,0.0004155948,0.00093176216,0.00025025327],"domain_scores_gemma":[0.98483706,0.013768983,0.00025898992,0.00056264515,0.00045161592,0.00012073391],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006066027,0.00012385723,0.00016563499,0.00057626027,0.00064039184,0.0006318533,0.0010891119,0.000074609954,0.00012752894],"category_scores_gemma":[0.052810322,0.00008608739,0.00008090902,0.0022919255,0.00022737334,0.00043645233,0.00023253611,0.00025071928,0.000040234045],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020734566,0.00008867306,0.31212953,5.525515e-7,0.000021303713,0.000008460492,0.00008295301,0.000027131893,0.000030427997,0.010667888,0.013209833,0.6637125],"study_design_scores_gemma":[0.00055419514,0.00011252198,0.13460821,0.0000058382925,0.000021729631,0.0000124971,0.0026333686,0.0022954452,0.000029521128,0.008696676,0.85090655,0.00012341724],"about_ca_topic_score_codex":0.00002304784,"about_ca_topic_score_gemma":0.000067521745,"teacher_disagreement_score":0.83769673,"about_ca_system_score_codex":0.00009039281,"about_ca_system_score_gemma":0.000074916024,"threshold_uncertainty_score":0.95516825},"labels":[],"label_agreement":null},{"id":"W2510270066","doi":"10.1186/s12874-016-0211-6","title":"Rasch modelling to deal with changes in the questionnaires used during long-term follow-up of cohort studies: a simulation study","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Université du Québec à Montréal; Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Rasch model; Raw score; Latent variable; Statistics; Raw data; Cohort; Term (time); Latent class model; Variable (mathematics); Computation; Computer science; Medicine; Mathematics; Algorithm","score_opus":0.894932611749861,"score_gpt":0.6602056242677833,"score_spread":0.23472698748207776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510270066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.5778363,0.00022175051,0.42000857,0.0010025473,0.00012949947,0.00075724407,0.0000011195502,0.000016939686,0.000026039525],"genre_scores_gemma":[0.92828524,0.00015827078,0.0709204,0.000050991533,0.0001771617,0.00023423808,3.2088073e-7,0.000015117591,0.00015825457],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9322214,0.056447838,0.0013929249,0.0012180896,0.007660384,0.0010593754],"domain_scores_gemma":[0.25521725,0.7412634,0.0003572316,0.0011789474,0.0016006822,0.00038249936],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21693848,0.00020062148,0.0009588072,0.001776901,0.00025920718,0.000054378954,0.0018080047,0.00018739754,0.00013561652],"category_scores_gemma":[0.6410719,0.00008672346,0.00007993244,0.0043152734,0.0006443909,0.00012951533,0.0006083602,0.0005342676,0.000014238551],"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":[0.0010247038,0.00016767759,0.9152924,0.00004363329,0.00009068865,0.00007458709,0.005384112,0.0038499183,0.00020212932,0.00015669456,0.000035962494,0.07367749],"study_design_scores_gemma":[0.0033308563,0.0017920936,0.968586,0.00057827897,0.000030439243,0.000024430496,0.012403421,0.0052216407,0.00027632472,0.0075212303,0.000035868386,0.00019938493],"about_ca_topic_score_codex":0.0003335273,"about_ca_topic_score_gemma":0.004917231,"teacher_disagreement_score":0.6848155,"about_ca_system_score_codex":0.000117272626,"about_ca_system_score_gemma":0.00042783932,"threshold_uncertainty_score":0.8063266},"labels":[],"label_agreement":null},{"id":"W2519326811","doi":"10.1016/j.jclinepi.2016.09.001","title":"Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":42,"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 Victoria","funders":"National Institute on Aging","keywords":"Operationalization; Covariate; Variance (accounting); Latent growth modeling; Econometrics; Computer science; Dynamics (music); Cognition; Longitudinal data; Cognitive psychology; Psychology; Mathematics; Machine learning; Data mining","score_opus":0.9338809644119007,"score_gpt":0.6854216619163461,"score_spread":0.2484593024955546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519326811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.6063259,0.000586224,0.3278804,0.06296217,0.0014706946,0.000370239,0.000036732778,0.00001274377,0.00035485128],"genre_scores_gemma":[0.8463116,0.0010471373,0.15049574,0.0015229974,0.00042318803,0.000026932277,4.1407642e-7,0.000010820849,0.00016112509],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97968656,0.011417116,0.006782605,0.00056234753,0.00091928465,0.000632117],"domain_scores_gemma":[0.45117024,0.53930604,0.0026137275,0.00069599244,0.0054175677,0.00079645065],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1484984,0.00014956051,0.0021133884,0.0017677245,0.0000770111,0.000018314695,0.0013365793,0.00033883817,0.00006801199],"category_scores_gemma":[0.9169235,0.000079971236,0.00030615248,0.0032929282,0.0003293036,0.00033080133,0.0003444925,0.00075793476,0.000039613984],"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":[0.00030314375,0.00030771468,0.83189154,0.000015896601,0.000017588693,0.000008743482,0.00014326883,0.00087022205,0.000027970058,0.013439004,0.0023323733,0.15064254],"study_design_scores_gemma":[0.00044975837,0.0008617224,0.6066653,0.00046053334,0.000006358957,0.000019365332,0.00011476952,0.0028234664,0.000005597844,0.3874862,0.0010179669,0.00008894875],"about_ca_topic_score_codex":0.00064256805,"about_ca_topic_score_gemma":0.0009957063,"teacher_disagreement_score":0.7684251,"about_ca_system_score_codex":0.00010311298,"about_ca_system_score_gemma":0.0005348201,"threshold_uncertainty_score":0.87680006},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2527744760","doi":"10.1192/pb.bp.115.052290","title":"The application of Rasch measurement theory to psychiatric clinical outcomes research","year":2016,"lang":"en","type":"article","venue":"BJPsych Bulletin","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"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":"Rasch model; Classical test theory; Item response theory; Outcome (game theory); Polytomous Rasch model; Test (biology); Test theory; Psychology; Psychiatry; Psychometrics; Computer science; Medicine; Clinical psychology; Mathematics; Developmental psychology","score_opus":0.7232814820498744,"score_gpt":0.6098927788575289,"score_spread":0.11338870319234551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527744760","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":[0.09594389,0.0016668764,0.728989,0.12451901,0.0037543185,0.0022200842,0.00001298689,0.0001173276,0.0427765],"genre_scores_gemma":[0.95918906,0.00017295782,0.035033107,0.00058967015,0.00036138183,0.00017194005,1.4468242e-7,0.00002107598,0.004460677],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98802614,0.004957948,0.0017002057,0.0008145799,0.003943063,0.0005580698],"domain_scores_gemma":[0.8663713,0.12900047,0.00050579786,0.0020774459,0.0018215909,0.00022342404],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15015519,0.00013900718,0.00038810069,0.0005135741,0.00039089425,0.000099002056,0.002161631,0.000111337766,0.00035064458],"category_scores_gemma":[0.2995182,0.000057602672,0.00024359445,0.0025275708,0.00030608388,0.00002702679,0.00031358592,0.00024248043,0.0019634343],"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":[0.00014684249,0.00007860281,0.17360604,0.0000013743461,0.000017219269,1.8569337e-7,0.000024485844,7.780041e-7,0.00013750595,0.009827645,0.116694525,0.6994648],"study_design_scores_gemma":[0.00038421425,0.0001426129,0.36266014,0.000008942967,0.0000042412466,8.1671817e-7,0.00022692051,0.0000025116094,0.000037611975,0.081718616,0.55474097,0.000072416435],"about_ca_topic_score_codex":0.000031598145,"about_ca_topic_score_gemma":0.00001474892,"teacher_disagreement_score":0.8632451,"about_ca_system_score_codex":0.000047047943,"about_ca_system_score_gemma":0.00009142517,"threshold_uncertainty_score":0.9988136},"labels":[],"label_agreement":null},{"id":"W2557592775","doi":"10.1007/978-981-10-2594-5_9","title":"Confidence Weighting Procedures for Multiple-Choice Tests","year":2016,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"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 Calgary","funders":"","keywords":"Weighting; Correctness; Multiple choice; Certainty; Computer science; Confidence interval; Statistics; Calculus (dental); Mathematics education; Mathematics; Algorithm; Medicine; Significant difference","score_opus":0.3333715532601957,"score_gpt":0.45378333477893884,"score_spread":0.12041178151874316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557592775","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033619195,0.0034033968,0.42435476,0.00055459276,0.0031477283,0.0016722656,0.0045589353,0.00019309952,0.5620816],"genre_scores_gemma":[0.0007925564,0.0010234378,0.2731635,0.000435063,0.00064565154,0.000086832566,0.000031754415,0.00011210674,0.7237091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948351,0.00011864954,0.001845702,0.0011844856,0.0013514141,0.0006646677],"domain_scores_gemma":[0.82009584,0.17645404,0.0013735302,0.0008956869,0.0010258211,0.00015506386],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031945393,0.00057467143,0.0010703729,0.0007382794,0.0002669591,0.0003068846,0.0013833658,0.00046290547,0.0008209479],"category_scores_gemma":[0.41746277,0.00042559725,0.00014565981,0.00022639697,0.0005730305,0.00049739867,0.0003585535,0.00046207866,0.000096338896],"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":[0.0001112203,0.000014076929,0.003948832,0.00017142654,0.000035615074,0.000054160202,0.00018327465,0.000010572478,0.00004356673,0.8773081,0.048437923,0.06968128],"study_design_scores_gemma":[0.0003359714,0.00012727667,0.000872521,0.00038392728,0.000016974882,0.000019191799,0.00004445627,0.0001246882,0.000021705815,0.5102088,0.4874589,0.0003856252],"about_ca_topic_score_codex":0.000017067927,"about_ca_topic_score_gemma":0.00050232024,"teacher_disagreement_score":0.439021,"about_ca_system_score_codex":0.00014275387,"about_ca_system_score_gemma":0.0004070072,"threshold_uncertainty_score":0.9998196},"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":"W2558952171","doi":"10.1037/met0000097","title":"Type I error rates and power of several versions of scaled chi-square difference tests in investigations of measurement invariance.","year":2016,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision 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":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Type I and type II errors; Mathematics; Measurement invariance; Sample size determination; Goodness of fit; Monte Carlo method; Confirmatory factor analysis; Population; Statistical power; Chi-square test; Econometrics; Structural equation modeling; Demography","score_opus":0.679952449318081,"score_gpt":0.5593365285098917,"score_spread":0.12061592080818928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558952171","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":[0.8983172,0.00034737182,0.09849953,0.00059256726,0.00036623416,0.00019727109,0.00001473866,0.000013531934,0.0016515179],"genre_scores_gemma":[0.64255726,0.000030750118,0.35731894,0.000045163913,0.000006512357,0.000005259279,1.6373674e-7,0.000003321392,0.00003260657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99507314,0.0023829371,0.0010678214,0.00050504674,0.00073818787,0.00023286855],"domain_scores_gemma":[0.97442764,0.02357387,0.0006461958,0.0006023569,0.0006179008,0.00013204069],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011008177,0.00015097586,0.00065339514,0.00044296327,0.00004136631,0.000011520079,0.00057971216,0.00015397197,0.00035450514],"category_scores_gemma":[0.1933334,0.00007945688,0.000088226436,0.0023978152,0.00056657026,0.00009144445,0.00017696386,0.00014643797,0.000003021747],"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":[0.00021301994,0.00038793834,0.673287,0.000021224381,0.00002480731,0.0000017972511,0.0004032346,0.00001606419,0.1871465,0.0027457864,0.0002603309,0.13549235],"study_design_scores_gemma":[0.0006512096,0.00046437577,0.9055998,0.00014862418,0.0000081499,0.0000033037022,0.00019192281,0.0000841603,0.004589336,0.08809432,0.00006667061,0.000098169876],"about_ca_topic_score_codex":0.000019448871,"about_ca_topic_score_gemma":0.000005278924,"teacher_disagreement_score":0.2588194,"about_ca_system_score_codex":0.000020022204,"about_ca_system_score_gemma":0.000037199286,"threshold_uncertainty_score":0.8134615},"labels":[],"label_agreement":null},{"id":"W2566941704","doi":"10.1007/s40037-016-0322-0","title":"Ensuring the quality of multiple-choice exams administered to small cohorts: A&amp;nbsp;cautionary tale","year":2017,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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; Université de Sherbrooke; McGill University Health Centre","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Medical education; Quality (philosophy); Medicine; Medical physics; Data science; Computer science","score_opus":0.5824138672067543,"score_gpt":0.5656129978868703,"score_spread":0.016800869319884004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566941704","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":[0.9665952,0.0003411476,0.004537075,0.013727408,0.0016616079,0.00033496888,0.000009183571,0.000031853408,0.012761578],"genre_scores_gemma":[0.9927461,0.00003953331,0.004860581,0.0005859921,0.00047989367,0.000048794103,0.0000030267413,0.000009063212,0.0012270258],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99557954,0.0009242023,0.00075232284,0.0006566487,0.0018370325,0.00025025092],"domain_scores_gemma":[0.92330384,0.071466014,0.0012288113,0.002607324,0.0008869931,0.0005070355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011257407,0.00014893895,0.000362337,0.00026246955,0.0006324288,0.00018926752,0.001702037,0.00011402551,0.000633729],"category_scores_gemma":[0.7593633,0.000093424,0.000134558,0.00051916373,0.0004487066,0.00014625206,0.00026522073,0.00031303178,0.0000668897],"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":[0.00018934003,0.0011809671,0.55909646,0.000022922903,0.000048603335,0.0000012316599,0.015871696,0.000026546222,0.0005122281,0.006157173,0.0054464005,0.41144642],"study_design_scores_gemma":[0.00026040289,0.000084152576,0.9682247,0.000067472654,0.0000070333926,0.0000049367613,0.019269148,0.000111392306,0.00008228817,0.004296648,0.007471504,0.00012031581],"about_ca_topic_score_codex":0.000980953,"about_ca_topic_score_gemma":0.00024961215,"teacher_disagreement_score":0.7481059,"about_ca_system_score_codex":0.000104388935,"about_ca_system_score_gemma":0.00047943136,"threshold_uncertainty_score":0.6938888},"labels":[],"label_agreement":null},{"id":"W2568498297","doi":"10.1177/0013164416685599","title":"Retrofitting Diagnostic Classification Models to Responses From IRT-Based Assessment Forms","year":2017,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of Alberta","funders":"","keywords":"Retrofitting; Item response theory; Computer science; Process (computing); Test (biology); Data mining; Engineering; Psychometrics; Mathematics; Statistics","score_opus":0.8783454710157835,"score_gpt":0.5694813197426731,"score_spread":0.3088641512731104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568498297","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":[0.86764574,0.00025236793,0.07320807,0.039226193,0.0014848049,0.00039822143,0.000031739626,0.00003583509,0.017717028],"genre_scores_gemma":[0.9380841,0.000015451546,0.060038634,0.0012141044,0.00030008695,0.00013956142,0.000006445977,0.0000069805533,0.00019460451],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957938,0.00049650716,0.0006600329,0.0008731709,0.0018827635,0.00029368428],"domain_scores_gemma":[0.97738063,0.020171879,0.0004968618,0.0010541525,0.00061107066,0.0002853962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008993718,0.00018131237,0.0002833432,0.00022468477,0.000899116,0.00066762883,0.0009590128,0.000101481375,0.00042725386],"category_scores_gemma":[0.12659203,0.00011709404,0.000084957865,0.0003042845,0.00012449107,0.00023981175,0.000116172385,0.00019974861,0.00006889915],"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":[0.00023515623,0.0008246595,0.6559843,0.0000054352085,0.000031657633,0.0000027948975,0.0002034041,0.00018193609,0.0029831678,0.021024294,0.011818968,0.30670422],"study_design_scores_gemma":[0.0002782426,0.00016624843,0.79165953,0.000037541915,0.0000073885835,0.0000012310269,0.00017754298,0.000883112,0.00003165029,0.2050371,0.0015834254,0.00013697294],"about_ca_topic_score_codex":0.00006475648,"about_ca_topic_score_gemma":0.0000111033505,"teacher_disagreement_score":0.30656725,"about_ca_system_score_codex":0.00011523829,"about_ca_system_score_gemma":0.00011241763,"threshold_uncertainty_score":0.8807651},"labels":[],"label_agreement":null},{"id":"W2569145478","doi":"10.5539/ijps.v9n1p71","title":"Accuracy of Measurement in the Classical and the Modern Test Theory: An Empirical Study on a Children Intelligence Test","year":2017,"lang":"en","type":"article","venue":"International Journal of Psychological Studies","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University","keywords":"Test (biology); Item response theory; Psychology; Standard error; Statistics; Classical test theory; Sample (material); Statistical hypothesis testing; Descriptive statistics; IBM; Computer science; Psychometrics; Mathematics; Developmental psychology","score_opus":0.7675113121022065,"score_gpt":0.6166518025269109,"score_spread":0.1508595095752956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569145478","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":[0.97383267,0.0012279763,0.0033833992,0.019549867,0.00062989665,0.00029439805,0.0000066498465,0.000004710376,0.0010704113],"genre_scores_gemma":[0.9982919,0.00027813707,0.00055214076,0.0005956863,0.00025818904,0.000007833627,6.482843e-8,0.0000033951026,0.000012618995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943213,0.0015402435,0.0010950627,0.0003266511,0.0025557799,0.00016096323],"domain_scores_gemma":[0.92950577,0.06742401,0.0013996641,0.0005551923,0.0010646668,0.00005072367],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025689553,0.00015322382,0.00048984605,0.00021273244,0.00026836715,0.00034005273,0.0035927047,0.000049576698,0.000016313395],"category_scores_gemma":[0.40174672,0.00005541871,0.0001445064,0.00024017516,0.0009860847,0.00020887864,0.00037026813,0.00049881206,0.000002622527],"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":[0.0006256668,0.0020931382,0.74575096,4.5059775e-7,0.00015007326,0.000048371858,0.004145852,0.000036045796,0.00002367802,0.0010813061,0.0007165103,0.24532795],"study_design_scores_gemma":[0.0010066503,0.0013561198,0.7974323,0.000034546036,0.000017082866,0.00009479608,0.0037686925,0.000099235076,0.000007916899,0.19607998,0.0000482694,0.000054409906],"about_ca_topic_score_codex":0.000008475662,"about_ca_topic_score_gemma":0.00001523429,"teacher_disagreement_score":0.37605718,"about_ca_system_score_codex":0.000035574838,"about_ca_system_score_gemma":0.000016599155,"threshold_uncertainty_score":0.8903538},"labels":[],"label_agreement":null},{"id":"W2572663707","doi":"","title":"Predictive performance of prevailing approaches to skills assessment techniques: Insights from real vs. synthetic data sets.","year":2014,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Data mining; Artificial intelligence; Machine learning","score_opus":0.19663171698819648,"score_gpt":0.3636479345042992,"score_spread":0.16701621751610274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572663707","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":[0.42892128,0.00019015447,0.5628542,0.00051062665,0.00018029958,0.00088150846,0.00016390394,0.00042880396,0.0058692135],"genre_scores_gemma":[0.5924266,0.00012160146,0.40673533,0.00026530123,0.00010157805,0.00018082387,0.0000354135,0.00003366302,0.000099664016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99314183,0.0011880987,0.001591793,0.001590949,0.001771416,0.0007159397],"domain_scores_gemma":[0.9819166,0.011714646,0.0009939566,0.0046145013,0.00033242741,0.0004278719],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009225665,0.00045649803,0.0010192535,0.0013599739,0.00029732997,0.00032038672,0.00403278,0.00035470346,0.000052477622],"category_scores_gemma":[0.024994984,0.0003591681,0.00016325076,0.0025774909,0.0001975092,0.00087483315,0.0018917752,0.00056920026,0.000016433924],"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":[0.00030534522,0.00067782536,0.284214,0.000064516855,0.00012622448,0.000008266512,0.0011835161,0.0040767277,0.00562719,0.0046977946,0.003362094,0.69565654],"study_design_scores_gemma":[0.00032334452,0.0007969025,0.34085646,0.0002562294,0.00006243114,0.00001644373,0.00042738652,0.62440443,0.016331414,0.013846823,0.0021494254,0.0005287221],"about_ca_topic_score_codex":0.0031403874,"about_ca_topic_score_gemma":0.00026962173,"teacher_disagreement_score":0.6951278,"about_ca_system_score_codex":0.0002715998,"about_ca_system_score_gemma":0.00025969825,"threshold_uncertainty_score":0.99988604},"labels":[],"label_agreement":null},{"id":"W2579971484","doi":"10.1007/s11192-017-2283-4","title":"How to reduce the number of rating scale items without predictability loss?","year":2017,"lang":"en","type":"article","venue":"Scientometrics","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":"Laurentian University","funders":"European Social Fund","keywords":"Predictability; Rating scale; Receiver operating characteristic; Statistics; Scale (ratio); Reliability (semiconductor); Confirmatory factor analysis; Computer science; Econometrics; Mathematics; Structural equation modeling","score_opus":0.5004341825675646,"score_gpt":0.5355242632854347,"score_spread":0.03509008071787012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579971484","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":[0.95333606,0.000104457424,0.022722062,0.0029715262,0.0025115188,0.00033775292,0.00002391916,0.000036421432,0.017956272],"genre_scores_gemma":[0.95590013,0.000008592112,0.039979696,0.00008058698,0.00019194199,0.000010241706,3.4033266e-7,0.00000873036,0.0038197304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934588,0.00045503792,0.0007144988,0.00082636724,0.0040115616,0.0005337535],"domain_scores_gemma":[0.9710071,0.021828309,0.0013367828,0.0036873696,0.0017885411,0.00035190553],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038198587,0.00016531229,0.00043389184,0.001670183,0.0011507277,0.0023658401,0.004555833,0.00008918661,0.00009284819],"category_scores_gemma":[0.62063795,0.00009242002,0.00016081956,0.018928913,0.0007552415,0.0006426634,0.0011694068,0.00023960149,0.000060132388],"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":[0.000010060326,0.000033671095,0.9044705,0.000005542201,0.000004271328,7.003969e-7,0.0003743768,0.000020765396,0.0004377992,0.00014495988,0.0021094012,0.09238795],"study_design_scores_gemma":[0.0002543657,0.0000527118,0.9816327,0.000019374298,0.000008819454,0.0000114808445,0.0010234884,0.0011439697,0.002310631,0.004919627,0.008476413,0.00014643758],"about_ca_topic_score_codex":0.00009263085,"about_ca_topic_score_gemma":0.000010622051,"teacher_disagreement_score":0.58243936,"about_ca_system_score_codex":0.00005571187,"about_ca_system_score_gemma":0.00009943529,"threshold_uncertainty_score":0.9986698},"labels":[],"label_agreement":null},{"id":"W2586268994","doi":"10.1016/j.paid.2017.01.051","title":"Item properties and the convergent validity of personality assessment: A peer rating study","year":2017,"lang":"en","type":"article","venue":"Personality and Individual Differences","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Psychology; Convergent validity; Test validity; Personality; Rating scale; Psychometrics; Personality Assessment Inventory; Clinical psychology; Developmental psychology; Social psychology; Internal consistency","score_opus":0.7684053045649344,"score_gpt":0.4843070787743096,"score_spread":0.28409822579062477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586268994","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":[0.99357235,0.0004498111,0.00014958081,0.002581634,0.00028381887,0.00042165394,0.00006651511,0.0000151951135,0.0024594658],"genre_scores_gemma":[0.9988357,0.000050038558,0.0005812456,0.00007202022,0.00008524875,0.000028141218,0.0000012605846,0.0000041718936,0.00034221268],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940212,0.0022439244,0.0006873879,0.00059552235,0.0021867852,0.00026521902],"domain_scores_gemma":[0.98278964,0.015082211,0.0009287826,0.0006498617,0.0004319611,0.000117526564],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0244832,0.00021109094,0.00068360544,0.00009592721,0.001785117,0.0013180911,0.0011245061,0.00007055232,0.00018966071],"category_scores_gemma":[0.064417556,0.00010210009,0.00011538426,0.00019772245,0.0017540145,0.0004024777,0.0007388274,0.00028250983,0.0000011484723],"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":[0.000057071862,0.00011493305,0.9728789,0.0000253172,0.00007964534,7.6893235e-7,0.013693657,1.3731068e-7,0.00001648341,0.0016657138,0.00007225893,0.011395143],"study_design_scores_gemma":[0.0011324838,0.00019439621,0.9569485,0.000027806582,0.000068150715,0.000004584215,0.030159857,0.0009015473,0.000019862375,0.010335888,0.00006977517,0.00013714074],"about_ca_topic_score_codex":0.0018209759,"about_ca_topic_score_gemma":0.00014324559,"teacher_disagreement_score":0.039934352,"about_ca_system_score_codex":0.000009608982,"about_ca_system_score_gemma":0.00006837355,"threshold_uncertainty_score":0.99971867},"labels":[],"label_agreement":null},{"id":"W2589097440","doi":"10.1186/s40536-017-0042-x","title":"A structural equation modeling approach for examining position effects in large-scale assessments","year":2017,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Psychometric Methodologies and Testing","field":"Decision 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":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Structural equation modeling; Position (finance); Equivalence (formal languages); Item response theory; Scale (ratio); Multilevel model; Context (archaeology); Computer science; Econometrics; Position paper; Psychometrics; Statistics; Mathematics; Machine learning","score_opus":0.34450591978879197,"score_gpt":0.5186875194954802,"score_spread":0.17418159970668823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589097440","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":[0.5305983,0.00006447565,0.46426615,0.00006488831,0.0016207225,0.00076209457,0.000014758581,0.000025849668,0.002582789],"genre_scores_gemma":[0.69211864,0.000008768279,0.30684033,0.0001024708,0.00020011775,0.00036618923,0.0001338015,0.000023497529,0.00020620337],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99503636,0.00074218976,0.0011583888,0.0011453113,0.0011422146,0.00077555876],"domain_scores_gemma":[0.99399525,0.0033365183,0.0009694097,0.0012131805,0.00035343994,0.00013220457],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009607917,0.0003111528,0.0005721632,0.0009971969,0.0007515107,0.0009065805,0.0011741315,0.00025693234,0.000028597602],"category_scores_gemma":[0.010536568,0.0002846973,0.00011170534,0.0009741644,0.000038718932,0.0018704183,0.0002772745,0.00039069657,0.0000059610134],"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":[0.00007775569,0.00078011904,0.8626212,0.00008078671,0.000016838825,0.0000011968041,0.0013130978,0.010171282,0.00046721095,0.0008644145,0.00012947166,0.123476654],"study_design_scores_gemma":[0.0011739118,0.000089118534,0.38934442,0.00008713156,0.000013254442,0.0000021771039,0.00431423,0.58610415,0.000043147164,0.01859403,0.000033499673,0.00020092123],"about_ca_topic_score_codex":0.00016620728,"about_ca_topic_score_gemma":0.00012574097,"teacher_disagreement_score":0.57593286,"about_ca_system_score_codex":0.00046068645,"about_ca_system_score_gemma":0.0003419928,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W2590036920","doi":"","title":"Relationships between Missing Response and Skill Mastery Profiles of Cognitive Diagnostic Assessment","year":2013,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Office of International Science and Engineering; Tsinghua University; University of Toronto","keywords":"Psychology; Missing data; Item response theory; Cognition; Cognitive skill; Literacy; Scale (ratio); Test (biology); Graduation (instrument); Developmental psychology; Psychometrics; Statistics; Pedagogy","score_opus":0.2621658766893456,"score_gpt":0.42738493465031474,"score_spread":0.16521905796096914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590036920","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":[0.96963394,0.0010951787,0.003266497,0.00020228514,0.00020563127,0.0003810371,0.000067181674,0.000021192807,0.02512708],"genre_scores_gemma":[0.9670303,0.00016153273,0.022601238,0.0000024275416,0.000025371273,7.215473e-7,0.000063207466,0.000011506888,0.010103734],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965963,0.0015795293,0.00036625945,0.00047129285,0.0007950151,0.000191643],"domain_scores_gemma":[0.9019917,0.095574416,0.0013007856,0.00034058245,0.0006563106,0.00013618526],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0042151446,0.00019199273,0.0006546914,0.00034111185,0.00027303322,0.000050037674,0.00044542903,0.00030083096,0.003352075],"category_scores_gemma":[0.070255466,0.00019324411,0.00012649118,0.00034501232,0.00016127476,0.00050179265,0.00012824398,0.00028781613,0.000009786931],"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":[0.0007010533,0.00010389061,0.41831926,0.00018844787,0.00023237232,0.000017519886,0.041854203,0.000004374992,0.0005870129,0.00017802122,0.0010374464,0.5367764],"study_design_scores_gemma":[0.00033045505,0.00015673574,0.8521722,0.0004542279,0.00012706766,9.1863893e-7,0.14582452,0.00007207226,0.000053768556,0.000615885,0.000040170595,0.00015197814],"about_ca_topic_score_codex":0.0074111987,"about_ca_topic_score_gemma":0.0015400017,"teacher_disagreement_score":0.53662443,"about_ca_system_score_codex":0.00010317157,"about_ca_system_score_gemma":0.00018537039,"threshold_uncertainty_score":0.99919856},"labels":[],"label_agreement":null},{"id":"W2590325518","doi":"10.1177/0146621617692079","title":"Plausible-Value Imputation Statistics for Detecting Item Misfit","year":2017,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Statistics; Statistic; Item response theory; Trait; Imputation (statistics); Econometrics; Parametric statistics; Test statistic; Mathematics; Statistical hypothesis testing; Differential item functioning; Latent variable model; Item analysis; Null hypothesis; Latent variable; Computer science; Psychometrics; Missing data","score_opus":0.72207883373125,"score_gpt":0.5322352636234017,"score_spread":0.18984357010784836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590325518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10147127,0.00007272288,0.87050205,0.00051090267,0.0013802287,0.0008912444,0.000032281623,0.00011476107,0.02502454],"genre_scores_gemma":[0.727478,0.000004541742,0.27173436,0.00033702137,0.00022376052,0.00013736579,0.0000018900017,0.000014323236,0.00006871617],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950816,0.00021704278,0.0009786108,0.0010469654,0.0020982097,0.0005775632],"domain_scores_gemma":[0.98522496,0.011755716,0.0010677215,0.0011181935,0.00063147664,0.00020192581],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016107928,0.00026006994,0.00047548488,0.00021007111,0.0012410905,0.0007584816,0.0015413291,0.00018938714,0.00019504878],"category_scores_gemma":[0.12904336,0.00018091715,0.00013488105,0.00036239848,0.00014861794,0.00010946947,0.00017010396,0.00025430133,0.00011126624],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023551084,0.00018297693,0.007813961,0.000012567591,0.000037818423,0.0000036570648,0.00007877905,0.0002076964,0.0073911105,0.02795454,0.007716538,0.94836485],"study_design_scores_gemma":[0.0025797356,0.0006044953,0.5173778,0.00003169721,0.000046119636,0.000012817579,0.00040239366,0.0040681437,0.001857552,0.45918143,0.01328402,0.00055377913],"about_ca_topic_score_codex":0.0000131764955,"about_ca_topic_score_gemma":0.0000090986405,"teacher_disagreement_score":0.94781107,"about_ca_system_score_codex":0.00009325043,"about_ca_system_score_gemma":0.000026992057,"threshold_uncertainty_score":0.95455897},"labels":[],"label_agreement":null},{"id":"W2590915444","doi":"10.2196/mental.6545","title":"Applying Computerized Adaptive Testing to the Four-Dimensional Symptom Questionnaire (4DSQ): A Simulation Study","year":2017,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computerized adaptive testing; Psychology; Medicine; Computer science; Medical physics; Artificial intelligence; Clinical psychology; Psychometrics","score_opus":0.5552826323121655,"score_gpt":0.5414749915067238,"score_spread":0.013807640805441612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590915444","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":[0.9582966,0.00008133957,0.030225446,0.0045301183,0.0017001854,0.004432333,0.000017810913,0.00013099439,0.0005851483],"genre_scores_gemma":[0.96770066,5.412931e-7,0.030543758,0.0011016697,0.0002688874,0.00023796991,0.000001642432,0.00001323453,0.00013165364],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956571,0.0010328724,0.00077226723,0.000665135,0.001440586,0.00043207823],"domain_scores_gemma":[0.988948,0.00867214,0.0008862963,0.0009970758,0.00025309282,0.0002433788],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008892362,0.000194463,0.00039507245,0.00024613173,0.0034530654,0.00052944274,0.00110379,0.000042758435,0.00002061049],"category_scores_gemma":[0.009948016,0.00012133955,0.000072340146,0.00079063856,0.000071034905,0.00029465053,0.00067667576,0.00022260664,0.00009239385],"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":[0.00013705913,0.00021691357,0.17318821,0.000005897698,0.000015810223,0.0000062399463,0.0020936355,0.008146347,0.000030272158,0.00010375124,0.0013852539,0.8146706],"study_design_scores_gemma":[0.00080590195,0.00076133024,0.83666104,0.00012579434,0.0000027267195,0.000012838139,0.0015697987,0.15780467,0.0000022838838,0.0010197343,0.0010889403,0.00014496261],"about_ca_topic_score_codex":0.00068509876,"about_ca_topic_score_gemma":0.000122061574,"teacher_disagreement_score":0.81452566,"about_ca_system_score_codex":0.00018904809,"about_ca_system_score_gemma":0.00013258973,"threshold_uncertainty_score":0.9983916},"labels":[],"label_agreement":null},{"id":"W2591813305","doi":"10.1037/pas0000458","title":"Factor analytic replication and model comparison of the BASC-2 Behavioral and Emotional Screening System.","year":2017,"lang":"en","type":"article","venue":"Psychological Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Psychology; PsycINFO; Replication (statistics); Factorial; Variance (accounting); Factor analysis; Construct (python library); Developmental psychology; Factor (programming language); Psychometrics; Statistics; Test validity; Clinical psychology; MEDLINE; Mathematics","score_opus":0.7686593430545826,"score_gpt":0.6260005032553175,"score_spread":0.14265883979926508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591813305","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":[0.8872945,0.00006231819,0.10812863,0.0008364348,0.0001789975,0.00017672834,0.00001665544,0.000018849638,0.003286904],"genre_scores_gemma":[0.94384027,0.0000058903915,0.055995543,0.000034725017,0.0000249522,0.000009125524,7.788678e-7,0.000003388003,0.00008533479],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975806,0.00029352016,0.0005829264,0.00061636005,0.00076496275,0.00016162879],"domain_scores_gemma":[0.99571264,0.0019942054,0.0007863484,0.0012763493,0.00014613978,0.000084326144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029776853,0.00011374394,0.00034749598,0.00009250367,0.00053152157,0.0002734278,0.00077389023,0.00008749352,0.00003605368],"category_scores_gemma":[0.005104231,0.000059923415,0.00007740575,0.0002093524,0.0002635469,0.00014041217,0.0003731929,0.00019342953,0.0000010798625],"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":[0.000009497531,0.00010359621,0.89085174,0.000005339019,0.000006657962,3.6888446e-7,0.000040433777,0.00009566942,0.0004775663,0.0027725042,0.00016167683,0.10547494],"study_design_scores_gemma":[0.00023263981,0.0000951507,0.8921208,0.000028912087,0.000011526053,0.0000068711033,0.00028101227,0.103484064,0.000027569271,0.00361026,0.000035206423,0.00006603094],"about_ca_topic_score_codex":0.000021300068,"about_ca_topic_score_gemma":0.0000024260082,"teacher_disagreement_score":0.10540891,"about_ca_system_score_codex":0.000021664646,"about_ca_system_score_gemma":0.000010470107,"threshold_uncertainty_score":0.61106104},"labels":[],"label_agreement":null},{"id":"W2594513694","doi":"10.1186/s12874-017-0309-5","title":"Why sample selection matters in exploratory factor analysis: implications for the 12-item World Health Organization Disability Assessment Schedule 2.0","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":69,"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 Aging","keywords":"Exploratory factor analysis; Stratified sampling; International Classification of Functioning, Disability and Health; Schedule; Sample (material); Psychology; Affect (linguistics); Gerontology; Sampling (signal processing); Statistics; Medicine; Mathematics; Clinical psychology; Psychometrics; Physical therapy; Computer science","score_opus":0.8952002098229414,"score_gpt":0.6886173406428713,"score_spread":0.20658286918007007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594513694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.043928497,0.0001221278,0.86229,0.09236051,0.0004085026,0.0007767281,0.00003298229,0.000037315167,0.000043291784],"genre_scores_gemma":[0.39885545,0.00014289391,0.59731805,0.0027035302,0.00032702956,0.00049504085,0.000025433246,0.000024625573,0.000107915854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96756524,0.02697399,0.0012786805,0.0010549278,0.002231528,0.000895653],"domain_scores_gemma":[0.3242561,0.6713426,0.0007274147,0.0020344001,0.0011380413,0.000501398],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16672559,0.0001662518,0.00080007105,0.0012604949,0.0019192988,0.000441861,0.0026915872,0.0001908134,0.0012199141],"category_scores_gemma":[0.8623073,0.00010366888,0.0001883624,0.0063565844,0.001116478,0.00029472538,0.00068316894,0.00088043645,0.000009187157],"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":[0.000035686546,0.000099276775,0.8854572,0.000021616414,0.000057563175,1.879251e-7,0.00014737825,0.00009489119,0.0000799058,0.0035401555,0.00602971,0.10443642],"study_design_scores_gemma":[0.0003733531,0.00009651769,0.9470139,0.0000142116705,0.000017458266,0.0000014458669,0.0010898067,0.010241698,0.000037250382,0.035193786,0.0058271005,0.000093481154],"about_ca_topic_score_codex":0.002696781,"about_ca_topic_score_gemma":0.036941618,"teacher_disagreement_score":0.69558173,"about_ca_system_score_codex":0.00044936535,"about_ca_system_score_gemma":0.0014027251,"threshold_uncertainty_score":0.9996931},"labels":[],"label_agreement":null},{"id":"W2597906635","doi":"10.1027/1614-2241/a000159","title":"Validity","year":2018,"lang":"en","type":"article","venue":"Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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":"Citation; Library science; Psychology; Delphi method; Computer science; Artificial intelligence","score_opus":0.941291787059819,"score_gpt":0.6278904871636637,"score_spread":0.3134012998961553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597906635","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":[0.24729338,0.000055222754,0.68427277,0.00083832117,0.0033150457,0.000059471764,0.0000020873895,0.000091846116,0.06407186],"genre_scores_gemma":[0.24803297,0.0000044947355,0.7476125,0.00095264317,0.0007933952,0.0000044534663,3.6540558e-7,0.000007812525,0.0025914165],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9902833,0.007542993,0.00058222585,0.0006052071,0.000585832,0.00040044068],"domain_scores_gemma":[0.8135408,0.18417749,0.00035123897,0.0012043912,0.00057606713,0.0001500151],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.047557164,0.00011815835,0.00042780835,0.00048461877,0.00020353113,0.000071329356,0.0010476322,0.00013806761,0.0037846447],"category_scores_gemma":[0.49363807,0.000079475154,0.00011596294,0.0021180736,0.0004049923,0.000099155885,0.00028732434,0.00016727118,0.0014899308],"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":[0.00007346075,0.000034180757,0.15074131,0.0000017210364,0.000013547497,0.000012881717,0.0004608099,0.0000029434887,0.004947691,0.015563669,0.05446554,0.77368224],"study_design_scores_gemma":[0.00018335445,0.00028985937,0.16030207,0.0000014696974,0.0000065935724,0.00005797685,0.0002361149,0.00022981368,0.004700651,0.62413085,0.20972833,0.00013291326],"about_ca_topic_score_codex":0.000037216636,"about_ca_topic_score_gemma":0.000011831826,"teacher_disagreement_score":0.7735493,"about_ca_system_score_codex":0.00001553558,"about_ca_system_score_gemma":0.00003466592,"threshold_uncertainty_score":0.99928755},"labels":[],"label_agreement":null},{"id":"W2612009109","doi":"","title":"WORKSHOP: Keeping up with The Standards: How to Design and Evaluate Reliability and Validity Studies","year":2015,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Facilitator; Context (archaeology); Psychology; Reliability (semiconductor); Internal validity; Validity; Standards for Educational and Psychological Testing; External validity; Construct validity; Applied psychology; Presentation (obstetrics); Quality (philosophy); Psychometrics; Social psychology; Clinical psychology; Medicine; Higher education; Education theory; Political science","score_opus":0.8179560533686604,"score_gpt":0.5321420139146238,"score_spread":0.2858140394540366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612009109","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":[0.49653202,0.0015022913,0.4876419,0.012664554,0.00041177,0.00047072503,0.000009304247,0.000044877463,0.0007225571],"genre_scores_gemma":[0.95658046,0.0001881148,0.04183149,0.00027876796,0.00005153591,0.000027546934,1.0098402e-7,0.000006471372,0.0010355383],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99581313,0.001634576,0.0002732321,0.0006472954,0.0013360751,0.0002956933],"domain_scores_gemma":[0.9415124,0.053522065,0.00032579713,0.0010379427,0.0032543647,0.0003474494],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033442546,0.0001720968,0.0004076062,0.00012484139,0.0002578949,0.0005455052,0.0005007699,0.000051488103,0.000018674067],"category_scores_gemma":[0.20047598,0.000079351346,0.000021831846,0.0007834493,0.00042553034,0.00026309988,0.00039745405,0.00016312169,0.000007800534],"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":[0.0008649618,0.00003518998,0.06090876,0.000031400912,0.000097430326,0.00001455367,0.013390371,0.0007208069,0.0002061473,0.0008619975,0.16517875,0.75768965],"study_design_scores_gemma":[0.006195587,0.0041373237,0.1689964,0.0012127141,0.00030193056,0.00014734258,0.14593473,0.03297914,0.0015090209,0.4797201,0.1564362,0.0024295386],"about_ca_topic_score_codex":0.000027035785,"about_ca_topic_score_gemma":0.00002619643,"teacher_disagreement_score":0.7552601,"about_ca_system_score_codex":0.000049738115,"about_ca_system_score_gemma":0.00028881477,"threshold_uncertainty_score":0.9952743},"labels":[],"label_agreement":null},{"id":"W2612259620","doi":"10.22237/jmasm/1177992180","title":"Ordinal Versions of Coefficients Alpha and Theta for Likert Rating Scales","year":2007,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1013,"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":"Ordinal data; Mathematics; Statistics; Likert scale; Ordinal Scale; Skewness; Ordinal regression; Reliability (semiconductor); Econometrics","score_opus":0.3690266326624584,"score_gpt":0.5562911121253126,"score_spread":0.18726447946285418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612259620","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":[0.02387316,0.0003478346,0.97262776,0.00009126041,0.00038377565,0.00016407446,0.00003425503,0.0000069408907,0.0024709534],"genre_scores_gemma":[0.39957666,0.000007761013,0.60028416,0.000038224014,0.00006185078,0.0000010035891,3.9417992e-7,0.0000073716733,0.00002259807],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99622506,0.00053205923,0.001565585,0.00030326116,0.0010290374,0.00034502026],"domain_scores_gemma":[0.8615126,0.13629773,0.0010965841,0.00024098624,0.0005852264,0.00026688707],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034538165,0.00015096582,0.0007193896,0.0004916315,0.00017550417,0.000076031894,0.0004870922,0.0001007224,0.00004569739],"category_scores_gemma":[0.08774735,0.00009916865,0.00012370604,0.0006970453,0.00025398657,0.00007772589,0.0001369516,0.00027815808,9.200718e-7],"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":[0.0004621102,0.00008526143,0.0011303078,0.000016484715,0.0000362434,0.00000551959,0.00019091644,0.00012833261,0.016685575,0.019752376,0.0005158798,0.96099097],"study_design_scores_gemma":[0.0020544813,0.00070970954,0.033262555,0.000054308006,0.000117799886,0.00010912341,0.0016239735,0.04818296,0.004983963,0.9060911,0.0025612237,0.00024881974],"about_ca_topic_score_codex":0.000002112499,"about_ca_topic_score_gemma":8.176644e-7,"teacher_disagreement_score":0.9607422,"about_ca_system_score_codex":0.000027336497,"about_ca_system_score_gemma":0.00006143885,"threshold_uncertainty_score":0.9941461},"labels":[],"label_agreement":null},{"id":"W2612271425","doi":"10.7202/1040137ar","title":"Évaluateurs évalués : évaluation diagnostique des compétences en évaluation des correcteurs d’une épreuve d’expression écrite à forts enjeux","year":2017,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","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":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Valuation (finance); Mathematics; Art; Economics","score_opus":0.5793917652197416,"score_gpt":0.527240377785965,"score_spread":0.052151387433776564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612271425","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":[0.7571529,0.0062005245,0.19193368,0.016457988,0.017650008,0.0025314523,0.00008859128,0.0002762298,0.0077085835],"genre_scores_gemma":[0.8321702,0.0066599455,0.15094905,0.00032699885,0.0013019608,0.0004371368,0.00041386607,0.00013943117,0.007601425],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9385826,0.047659334,0.003408085,0.0027159178,0.0060456074,0.0015884619],"domain_scores_gemma":[0.91298765,0.07288583,0.0043117045,0.0033923183,0.0058500515,0.00057241257],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17979106,0.0012111826,0.0014646344,0.0016934387,0.004438883,0.0030669637,0.002782635,0.0012795172,0.0018427636],"category_scores_gemma":[0.4369418,0.0011379384,0.0006412638,0.0027787122,0.0015615757,0.005501316,0.00069641037,0.0013888867,0.00059815485],"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":[0.00011629768,0.0004929483,0.13694234,0.00016674506,0.000095203526,0.00000925751,0.11943092,0.008427281,0.0030356718,0.00050863577,0.007618758,0.7231559],"study_design_scores_gemma":[0.001450002,0.0004510893,0.73413026,0.0015695725,0.0004331553,0.000079111276,0.00963157,0.046414193,0.0032955364,0.19927914,0.0023148274,0.0009515036],"about_ca_topic_score_codex":0.0046995385,"about_ca_topic_score_gemma":0.0028264883,"teacher_disagreement_score":0.72220445,"about_ca_system_score_codex":0.001375287,"about_ca_system_score_gemma":0.0034016168,"threshold_uncertainty_score":0.99910706},"labels":[],"label_agreement":null},{"id":"W2612742774","doi":"10.3389/fpsyg.2017.00777","title":"An Overview of Interrater Agreement on Likert Scales for Researchers and Practitioners","year":2017,"lang":"en","type":"review","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Statistic; Likert scale; Psychology; Statistics; Strengths and weaknesses; Inter-rater reliability; Rating scale; Computer science; Data science; Social psychology; Mathematics","score_opus":0.8995262328801251,"score_gpt":0.6840196393163346,"score_spread":0.21550659356379054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612742774","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013911143,0.97683334,0.014193608,0.0002920546,0.003785852,0.0008768901,0.00006190672,0.000009914974,0.003932504],"genre_scores_gemma":[0.000010900646,0.9351324,0.06410425,0.00016348745,0.0001049234,0.00014185112,0.000019876346,0.000023328683,0.0002990103],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945468,0.0020262816,0.0013202084,0.0011149973,0.0005598521,0.00043190274],"domain_scores_gemma":[0.98930633,0.0073017026,0.0014164676,0.0016707217,0.00016730317,0.00013747814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012791864,0.00030794306,0.0020989792,0.0020742156,0.00011627155,0.00012934947,0.0017661812,0.00045913638,0.000068301495],"category_scores_gemma":[0.027983038,0.00021028932,0.0003033066,0.00073568616,0.00048023715,0.00019572912,0.00014900079,0.0004910068,0.000011685101],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007303162,0.00008168356,0.00054862973,0.0006438762,0.00005874861,0.00000504262,0.000053879503,1.902809e-7,1.6618645e-7,0.00011990806,0.068289146,0.9301257],"study_design_scores_gemma":[0.00041843057,0.00059031317,0.0006221267,0.0020217425,0.000041001655,0.0000136262715,0.00021473352,0.000023894987,1.8218391e-7,0.028537216,0.9673213,0.00019544692],"about_ca_topic_score_codex":0.000012366944,"about_ca_topic_score_gemma":0.000011320582,"teacher_disagreement_score":0.92993027,"about_ca_system_score_codex":0.00006621122,"about_ca_system_score_gemma":0.000085059764,"threshold_uncertainty_score":0.9802047},"labels":[],"label_agreement":null},{"id":"W2612770846","doi":"","title":"PAPER: Examining Position Effects in Large-Scale Assessments Using an SEM Approach","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Rasch model; Position (finance); Reading (process); Test (biology); Structural equation modeling; Scale (ratio); Psychology; Item response theory; Sample (material); Computer science; Statistics; Econometrics; Psychometrics; Social psychology; Cognitive psychology; Artificial intelligence; Natural language processing; Mathematics; Developmental psychology; Linguistics","score_opus":0.5208722029508508,"score_gpt":0.4857174030503449,"score_spread":0.035154799900505906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612770846","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":[0.5533232,0.000044817294,0.43886203,0.000043073418,0.00029833496,0.0001344717,0.0000070255346,0.00003918216,0.007247882],"genre_scores_gemma":[0.9056558,0.000013043511,0.09369549,0.00011982871,0.00007727382,0.000014115393,0.000002023892,0.000011482873,0.00041091096],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99628264,0.001097265,0.00054591533,0.00076796446,0.0008068817,0.00049931096],"domain_scores_gemma":[0.9901865,0.008464304,0.00029885623,0.0006846544,0.00021502405,0.00015064314],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058084074,0.00018647233,0.0003757898,0.00045168924,0.00013718006,0.00023844,0.00074153877,0.00013679526,0.0002713588],"category_scores_gemma":[0.009192256,0.00010997777,0.00004584712,0.0009916147,0.00006886846,0.0010176696,0.00020184058,0.00014592934,0.00006615875],"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":[0.000039889102,0.0002664862,0.39375198,0.000014697493,0.000010661427,0.0000206189,0.0004008595,0.00003911964,0.08100749,0.0012987583,0.00018086011,0.5229686],"study_design_scores_gemma":[0.002051625,0.00039416313,0.9253656,0.00045337493,0.000015924312,0.000037021604,0.0015444871,0.039032042,0.001930774,0.0280202,0.00060062244,0.00055411656],"about_ca_topic_score_codex":0.00007791627,"about_ca_topic_score_gemma":0.000022032134,"teacher_disagreement_score":0.53161365,"about_ca_system_score_codex":0.000076061224,"about_ca_system_score_gemma":0.0001232979,"threshold_uncertainty_score":0.99915373},"labels":[],"label_agreement":null},{"id":"W2614874454","doi":"10.1186/s12955-017-0674-0","title":"Latent variable mixture models to test for differential item functioning: a population-based analysis","year":2017,"lang":"en","type":"article","venue":"Health and Quality of Life Outcomes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Western University; University of Toronto; University of British Columbia; University of Calgary; McGill University Health Centre; McMaster University; Trinity Western University; Queen's University; University of Alberta; Providence Health Care; University of Victoria; University of Saskatchewan","funders":"Canadian Institutes of Health Research; Merck Canada; Eli Lilly Canada; Dairy Farmers of Canada; Research Manitoba; Eli Lilly and Company; Amgen Canada; Amgen","keywords":"Differential item functioning; Latent class model; Logistic regression; Population; Psychology; Statistics; Demography; Cohort; Item response theory; Medicine; Psychometrics; Mathematics; Environmental health","score_opus":0.6671479108948155,"score_gpt":0.5335537194909674,"score_spread":0.1335941914038481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614874454","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":[0.55581856,0.000103606835,0.43631482,0.00692367,0.0003368636,0.0002911738,0.000089743444,0.000022455677,0.000099087934],"genre_scores_gemma":[0.9404568,0.000004738161,0.05699165,0.0020135914,0.00005704079,0.000017481878,0.00001810678,0.000005468303,0.00043513475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970895,0.00033311686,0.001161448,0.0004441693,0.0006763938,0.0002953566],"domain_scores_gemma":[0.9644531,0.032574236,0.0013270999,0.00084708136,0.00031697538,0.00048151612],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006844774,0.00013347666,0.0009535546,0.00045851266,0.00078570755,0.00024047842,0.00038464906,0.0000792211,0.000043789532],"category_scores_gemma":[0.13577352,0.000091298025,0.0002292314,0.0006093523,0.000029470883,0.00014144964,0.00007928369,0.00007626554,0.0000010453707],"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":[0.0000704101,0.00006184442,0.99082655,0.00006622941,0.000053303964,2.6414384e-8,0.00011691422,0.001385585,0.0000033132278,0.0021553105,0.0003016573,0.0049588513],"study_design_scores_gemma":[0.00058466906,0.00013592103,0.9631434,0.000012675751,0.000031407046,5.16209e-8,0.00013483138,0.028160933,0.0000013395947,0.0073912214,0.00030390196,0.00009961173],"about_ca_topic_score_codex":0.003516183,"about_ca_topic_score_gemma":0.0003498326,"teacher_disagreement_score":0.38463822,"about_ca_system_score_codex":0.000023656752,"about_ca_system_score_gemma":0.00014872875,"threshold_uncertainty_score":0.8715062},"labels":[],"label_agreement":null},{"id":"W2615407454","doi":"10.1016/j.jml.2017.05.002","title":"A Bayesian approach to the mixed-effects analysis of accuracy data in repeated-measures designs","year":2017,"lang":"en","type":"article","venue":"Journal of Memory and Language","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Akaike information criterion; Bayesian information criterion; Bayes factor; Bayesian probability; Mixed model; Statistics; Model selection; Random effects model; Deviance information criterion; Econometrics; Selection (genetic algorithm); Probit model; Logistic regression; Information Criteria; Feature selection; Computer science; Bayes' theorem; Artificial intelligence; Bayesian inference; Mathematics; Meta-analysis","score_opus":0.4535470538212062,"score_gpt":0.48974263828780545,"score_spread":0.03619558446659926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615407454","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":[0.93099785,0.0019864005,0.06336792,0.00035975903,0.00023262958,0.00011517403,0.000011548957,0.000003085431,0.0029256118],"genre_scores_gemma":[0.984026,0.00003816867,0.015650488,0.00009710428,0.00009225761,8.3241565e-7,7.617305e-7,0.0000033812364,0.00009098338],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99738777,0.000844855,0.00064901914,0.00023983112,0.0007308391,0.00014766696],"domain_scores_gemma":[0.98457825,0.012581186,0.0010954383,0.001518142,0.00013084638,0.00009614371],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02107189,0.00008697551,0.0005082143,0.0008253414,0.00016826823,0.00023102497,0.0022733966,0.000046831632,0.000018912047],"category_scores_gemma":[0.17660305,0.00004336895,0.00011201691,0.0011953412,0.00006992876,0.00033144117,0.00034626116,0.00021232206,7.264287e-7],"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":[0.00015928756,0.00013665858,0.10967562,0.000021425076,0.00040991633,0.00015610458,0.0062225712,0.0012497284,0.0031124426,0.000043621556,0.0025715334,0.8762411],"study_design_scores_gemma":[0.0005015796,0.000112620866,0.9828774,0.00005796151,0.00029814563,0.000064575506,0.008616886,0.005655837,0.00083332666,0.0003772315,0.00049989746,0.000104584855],"about_ca_topic_score_codex":0.00014076136,"about_ca_topic_score_gemma":0.000093271134,"teacher_disagreement_score":0.8761365,"about_ca_system_score_codex":0.000008163228,"about_ca_system_score_gemma":0.00003306163,"threshold_uncertainty_score":0.83033276},"labels":[],"label_agreement":null},{"id":"W2616955109","doi":"10.1007/978-3-319-56129-5_16","title":"Understanding Test-Taking Strategies for a Reading Comprehension Test via Latent Variable Regression with Pratt’s Importance Measures","year":2017,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"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":"Latent variable; Test (biology); Structural equation modeling; Latent variable model; Regression analysis; Outcome (game theory); Computer science; Comprehension; Psychology; Econometrics; Statistics; Machine learning; Mathematics","score_opus":0.7740088458811123,"score_gpt":0.5228031383082894,"score_spread":0.2512057075728229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616955109","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016782295,0.0026411733,0.08132611,0.0029981,0.0017335055,0.004813045,0.00059464574,0.0006196927,0.9035955],"genre_scores_gemma":[0.7263413,0.0009947618,0.035742916,0.00011485891,0.0026116807,0.00036754445,0.00012653529,0.000445014,0.23325537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99057424,0.00045445675,0.0012165396,0.0015604626,0.0049029426,0.0012913481],"domain_scores_gemma":[0.9525235,0.04111124,0.0032053113,0.0013100187,0.001516,0.000333884],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.016776819,0.00065577345,0.0013466972,0.0022415742,0.006219063,0.0026127277,0.0021252572,0.00089039543,0.00025544845],"category_scores_gemma":[0.071250245,0.0004480559,0.0002668644,0.0009391338,0.0021225084,0.00112333,0.0006946498,0.001757245,0.000015248042],"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":[0.0017663129,0.00025697303,0.08055966,0.0008320981,0.0006760544,0.0003759581,0.0068760687,0.00004658728,0.0037067505,0.7775958,0.071404286,0.05590346],"study_design_scores_gemma":[0.00068387215,0.001134406,0.0025290616,0.0014671672,0.00006745566,0.000034131088,0.0067093177,0.00014771402,0.00013765947,0.9177381,0.06847299,0.00087811676],"about_ca_topic_score_codex":0.000096021206,"about_ca_topic_score_gemma":0.00021516383,"teacher_disagreement_score":0.7246631,"about_ca_system_score_codex":0.0007260114,"about_ca_system_score_gemma":0.0015211899,"threshold_uncertainty_score":0.9997971},"labels":[],"label_agreement":null},{"id":"W2617677951","doi":"10.3389/fpsyg.2017.00767","title":"Normal Theory GLS Estimator for Missing Data: An Application to Item-Level Missing Data and a Comparison to Two-Stage ML","year":2017,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Missing data; Extension (predicate logic); Structural equation modeling; Statistics; Raw data; Computer science; Mathematics; Data mining; Econometrics","score_opus":0.6396154550074058,"score_gpt":0.5863758442384542,"score_spread":0.05323961076895156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617677951","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":[0.02697476,0.0004687047,0.9641633,0.0033293513,0.0025203307,0.00066838204,0.00040941796,0.000040415198,0.0014253611],"genre_scores_gemma":[0.092885114,0.0000075215457,0.90537673,0.0012129113,0.0002249765,0.000033323395,0.00008529123,0.000024209961,0.00014989826],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99576765,0.0005567202,0.0008745045,0.0018438093,0.00040201523,0.00055528653],"domain_scores_gemma":[0.9878592,0.0050491556,0.0005949173,0.0060344753,0.000118903285,0.00034337494],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.015563071,0.0002241303,0.00065195106,0.00072664686,0.00068315084,0.00067280116,0.0057112454,0.0001556591,0.000017968534],"category_scores_gemma":[0.06750814,0.000195928,0.000028700108,0.0005959097,0.00022355231,0.00096415257,0.0013957042,0.00022289823,0.000012681654],"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":[0.0002840554,0.00006301915,0.14075662,0.000007318604,0.000011236344,0.0000031352042,0.0002586047,0.0000345572,0.00041135706,0.00020508296,0.05196259,0.80600244],"study_design_scores_gemma":[0.0024902157,0.00033192543,0.34822658,0.00007214497,0.00003832835,0.00003218017,0.0022472467,0.28639865,0.00007288356,0.09518226,0.26425907,0.00064854446],"about_ca_topic_score_codex":0.00006515427,"about_ca_topic_score_gemma":0.000058269037,"teacher_disagreement_score":0.8053539,"about_ca_system_score_codex":0.000029504103,"about_ca_system_score_gemma":0.00005228225,"threshold_uncertainty_score":0.99966836},"labels":[],"label_agreement":null},{"id":"W2617719848","doi":"10.1007/978-3-319-56129-5_1","title":"Response Processes in the Context of Validity: Setting the Stage","year":2017,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":55,"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; External validity; Test (biology); Context (archaeology); Set (abstract data type); Cognitive psychology; Social psychology; Computer science; History","score_opus":0.7199056330468293,"score_gpt":0.5706609896341709,"score_spread":0.14924464341265842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617719848","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10157554,0.002787225,0.000036958438,0.037982278,0.0008575457,0.0025194567,0.00072957954,0.00007369803,0.8534377],"genre_scores_gemma":[0.67195076,0.00070311694,0.00021642719,0.00025893596,0.00061725447,0.00010436087,0.000009047172,0.00005830239,0.32608178],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865281,0.005676919,0.0010710219,0.00067224755,0.0053724097,0.0006792917],"domain_scores_gemma":[0.8602233,0.13567634,0.0015253064,0.0014176171,0.0010802544,0.000077160345],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.10543144,0.00027457013,0.0007149225,0.001658016,0.0024397539,0.0008889074,0.0053807376,0.00043933323,0.00034875577],"category_scores_gemma":[0.3881331,0.00013938326,0.00021845942,0.0012464228,0.004154051,0.00031395038,0.00096754765,0.0019354376,0.00004678075],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003535397,0.0001564082,0.026282981,0.00054857304,0.0002796127,0.00026046805,0.17720327,0.0000010243036,0.00011465602,0.2850519,0.1390336,0.36753213],"study_design_scores_gemma":[0.00016491706,0.00022001451,0.011483221,0.00012333844,0.000008628224,0.0000038533876,0.04084565,5.707003e-7,0.00012744535,0.15777025,0.7890622,0.00018991667],"about_ca_topic_score_codex":0.00015457821,"about_ca_topic_score_gemma":0.00035082304,"teacher_disagreement_score":0.6500286,"about_ca_system_score_codex":0.00009445387,"about_ca_system_score_gemma":0.0015699996,"threshold_uncertainty_score":0.9998839},"labels":[],"label_agreement":null},{"id":"W2619991132","doi":"10.1007/978-3-319-56129-5_5","title":"Putting Flesh on the Psychometric Bone: Making Sense of IRT Parameters in Non-cognitive Measures by Investigating the Social-Cognitive Aspects of the Items","year":2017,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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; Item response theory; Cognition; CLARITY; Cognitive psychology; Scale (ratio); Sample (material); Developmental psychology; Psychometrics; Social psychology","score_opus":0.5543906980281975,"score_gpt":0.515399920885707,"score_spread":0.03899077714249055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619991132","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39432538,0.0016849184,0.00008710084,0.006226783,0.0009649483,0.0031953473,0.0006626923,0.00004820155,0.5928046],"genre_scores_gemma":[0.9936681,0.00014699018,0.00012770847,0.0001815035,0.00033413174,0.00008976295,0.0000065851605,0.00007347389,0.005371741],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9855174,0.004105674,0.0016921315,0.0010535753,0.0066281357,0.0010030731],"domain_scores_gemma":[0.8999401,0.09286643,0.0044027134,0.0009994428,0.0016677195,0.00012360365],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.03841544,0.00054202904,0.0012990944,0.0028846525,0.0039657294,0.00062664883,0.002826679,0.0006905676,0.00005718191],"category_scores_gemma":[0.28249058,0.00028766794,0.0006377299,0.00439164,0.00839141,0.00026603145,0.0012034986,0.0034401962,0.000017116432],"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":[0.00062774133,0.00023803957,0.037710603,0.00029926348,0.0012196837,0.000055285178,0.07070966,0.0000054964094,0.0006528874,0.092163116,0.015846001,0.7804722],"study_design_scores_gemma":[0.0010977515,0.00056563166,0.11357378,0.0034395203,0.00015359223,0.000016737262,0.07350672,0.000024256906,0.0058805,0.7965027,0.0042549223,0.0009838946],"about_ca_topic_score_codex":0.0003077698,"about_ca_topic_score_gemma":0.00017496657,"teacher_disagreement_score":0.7794883,"about_ca_system_score_codex":0.00019721773,"about_ca_system_score_gemma":0.0006822602,"threshold_uncertainty_score":0.99995756},"labels":[],"label_agreement":null},{"id":"W2625675150","doi":"10.5539/jel.v6n4p113","title":"Examination of Different Item Response Theory Models on Tests Composed of Testlets","year":2017,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Statistics; Item response theory; Sample size determination; Psychology; Mathematics; Sample (material); Psychometrics","score_opus":0.4463604006241616,"score_gpt":0.5023882591824396,"score_spread":0.056027858558277965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625675150","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":[0.99232876,0.00019136872,0.0032099977,0.00032236133,0.00042608927,0.000038692906,3.5917842e-7,0.0000021813048,0.0034802037],"genre_scores_gemma":[0.99579775,0.000028276778,0.0031253935,0.000024376886,0.000058525202,4.2130776e-7,1.5025662e-7,0.0000037242794,0.00096139085],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99709237,0.0016085816,0.0005965447,0.00010582322,0.0005260224,0.00007063719],"domain_scores_gemma":[0.9623167,0.034414105,0.002358017,0.0002356326,0.0006149648,0.000060583716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013663013,0.00006395211,0.0002595096,0.0005742817,0.00018960642,0.00008692681,0.00033086143,0.000040116633,0.00004369672],"category_scores_gemma":[0.1803129,0.00004125679,0.000061052226,0.00017419613,0.00007953151,0.0002238227,0.000038004408,0.0002287355,7.0050896e-7],"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":[0.0005050296,0.00031278332,0.09364677,0.000014724094,0.000017640388,8.289461e-7,0.0036291205,0.0010008591,0.014371757,0.0028153963,0.0001668786,0.8835182],"study_design_scores_gemma":[0.00027723706,0.00044971096,0.9798874,0.00015364595,0.000008910814,0.000015162775,0.0034598869,0.001575165,0.0008399406,0.013063916,0.00022689388,0.000042096006],"about_ca_topic_score_codex":0.0000028164743,"about_ca_topic_score_gemma":2.2402169e-7,"teacher_disagreement_score":0.88624066,"about_ca_system_score_codex":0.000017824577,"about_ca_system_score_gemma":0.000086738364,"threshold_uncertainty_score":0.8265917},"labels":[],"label_agreement":null},{"id":"W2732670277","doi":"","title":"Applying computerized adaptive testing to the four-dimensional symptom questionnaire (4DSQ)","year":2017,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computerized adaptive testing; Psychology; Computer science; Medicine; Medical physics; Psychometrics; Clinical psychology","score_opus":0.6095508962487788,"score_gpt":0.5238081712452387,"score_spread":0.08574272500354008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732670277","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":[0.9265372,0.0008911554,0.04170289,0.022590445,0.002534057,0.0020476643,0.000024908719,0.00019184958,0.0034798079],"genre_scores_gemma":[0.9298517,0.000021497643,0.06525209,0.0039377776,0.00060222147,0.00016703222,9.769516e-7,0.00001525264,0.00015141042],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99585474,0.00072927383,0.00083133247,0.00079541694,0.0010627845,0.000726471],"domain_scores_gemma":[0.984257,0.0125042135,0.00096222403,0.0011700548,0.00042040006,0.0006861223],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.010112058,0.00023016319,0.0005056207,0.00029878024,0.0038871446,0.00059916236,0.0011547571,0.00010011408,0.00001637897],"category_scores_gemma":[0.024667574,0.00013842774,0.00006544188,0.00079553464,0.00017439219,0.00025206764,0.00055889494,0.00040303753,0.0000685317],"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":[0.000108011016,0.000029699202,0.09253344,0.0000408645,0.0000068545546,0.000009028467,0.00038324512,0.00013681747,0.000015379928,0.0020061748,0.0046925507,0.90003794],"study_design_scores_gemma":[0.0005652262,0.00033143684,0.96482706,0.0001524844,0.000010372155,0.000068034584,0.00023655314,0.018800903,0.0000023649484,0.0077576526,0.0070579797,0.000189939],"about_ca_topic_score_codex":0.00064094015,"about_ca_topic_score_gemma":0.00007020658,"teacher_disagreement_score":0.899848,"about_ca_system_score_codex":0.00007343937,"about_ca_system_score_gemma":0.00034889719,"threshold_uncertainty_score":0.99740964},"labels":[],"label_agreement":null},{"id":"W2736540189","doi":"10.7160/eriesj.2017.100202","title":"BAYESIAN DIAGNOSTICS FOR TEST DESIGN AND ANALYSIS","year":2017,"lang":"en","type":"article","venue":"Journal on Efficiency and Responsibility in Education and Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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; AXYS Technologies (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Computer science; Bayesian statistics; Test (biology); Bridge (graph theory); Item response theory; Bayesian experimental design; Artificial intelligence; Machine learning; Posterior probability; Test theory; Bayesian inference; Econometrics; Natural language processing; Statistics; Mathematics; Psychometrics","score_opus":0.26805131552357936,"score_gpt":0.5076812887630598,"score_spread":0.2396299732394805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736540189","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":[0.90320677,0.00056760747,0.092415735,0.0026337916,0.0005849242,0.0002093539,0.0000031529987,0.000004547271,0.00037413824],"genre_scores_gemma":[0.97166914,0.00037870256,0.027545601,0.00019132298,0.0000414726,0.0000051229335,7.896925e-8,0.0000019080337,0.00016667342],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977096,0.0003425419,0.000510469,0.00055875664,0.00061693235,0.00026174498],"domain_scores_gemma":[0.94957155,0.048455477,0.0005341702,0.0006400634,0.00048097776,0.000317739],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033804342,0.00010265312,0.00026000012,0.0014082423,0.0020520187,0.0014797506,0.00061771105,0.000052119874,0.00001008053],"category_scores_gemma":[0.40338215,0.00006555505,0.000047080764,0.001759464,0.0010691669,0.00043935285,0.000099950346,0.00018232428,5.658845e-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":[0.00008969965,0.0003334896,0.70951873,0.0000044253056,0.0000040721047,0.0000018229406,0.0009254692,0.00035389714,0.00023810261,0.00108111,0.00011102724,0.2873382],"study_design_scores_gemma":[0.00020282867,0.00028993777,0.9247082,0.000019908559,0.000015119927,0.00003096392,0.0009935262,0.04429124,0.0000552482,0.028973367,0.00032795957,0.00009168788],"about_ca_topic_score_codex":0.000010234792,"about_ca_topic_score_gemma":0.000007130334,"teacher_disagreement_score":0.3695778,"about_ca_system_score_codex":0.00004163815,"about_ca_system_score_gemma":0.0005123317,"threshold_uncertainty_score":0.9995568},"labels":[],"label_agreement":null},{"id":"W2738355693","doi":"10.1057/978-1-137-38523-9_4","title":"Construct Validity: Developments and Debates","year":2017,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","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":"Simon Fraser University","funders":"","keywords":"Construct (python library); Construct validity; Epistemology; Psychology; Management science; Computer science; Psychometrics; Engineering; Philosophy; Developmental psychology","score_opus":0.3960640724091895,"score_gpt":0.406571611676446,"score_spread":0.010507539267256505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738355693","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016902351,0.0011700471,0.00035994584,0.000040409326,0.0013857773,0.00035385438,0.00009444134,0.00008752555,0.9948178],"genre_scores_gemma":[0.948996,0.00021035188,0.011575842,0.00014590866,0.0002460459,0.000009792228,0.000010551984,0.000059477392,0.03874603],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955252,0.00016318884,0.0010810395,0.001250029,0.0014407845,0.00053976185],"domain_scores_gemma":[0.98536885,0.01102884,0.001335141,0.0015542877,0.0003903226,0.00032258936],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038532414,0.00062514655,0.0011592077,0.0008662131,0.0006151227,0.0006509021,0.0015587931,0.00048525663,0.0004452705],"category_scores_gemma":[0.0194791,0.00046757766,0.00023602553,0.00003780139,0.0006955668,0.0000018432453,0.00094346853,0.0004434122,0.00025375493],"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":[0.000024442334,1.6949328e-7,0.0144820195,0.000021958043,0.00012491406,0.00012506526,0.00015209614,6.535569e-8,0.000051793766,0.3494193,0.00018124896,0.6354169],"study_design_scores_gemma":[0.00034061278,0.0000575115,0.013182203,0.00013231824,0.00004363227,0.00015121516,0.000038162216,0.000007992835,0.00008029125,0.9666431,0.018750114,0.0005728591],"about_ca_topic_score_codex":0.00003158091,"about_ca_topic_score_gemma":0.00003331617,"teacher_disagreement_score":0.95607173,"about_ca_system_score_codex":0.000045323777,"about_ca_system_score_gemma":0.00016893326,"threshold_uncertainty_score":0.9997776},"labels":[],"label_agreement":null},{"id":"W2739364617","doi":"10.1057/978-1-137-38523-9_9","title":"Construct Validation: View from the “Trenches”","year":2017,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Construct (python library); Construct validity; Scholarship; Psychology; Data science; Computer science; Management science; Political science; Engineering; Psychometrics","score_opus":0.35758824086922564,"score_gpt":0.4024956285165835,"score_spread":0.044907387647357855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739364617","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019149663,0.004481604,0.00097416167,0.00032461312,0.002552767,0.0004758766,0.0003732037,0.000092485236,0.99053377],"genre_scores_gemma":[0.95573574,0.00032421743,0.0058794054,0.0005493021,0.0015020244,0.00002114876,0.000055670756,0.00007136851,0.035861097],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945922,0.00037981084,0.0013245539,0.0012750651,0.0019501995,0.00047815978],"domain_scores_gemma":[0.9627161,0.03089771,0.0019491678,0.003776785,0.0004513808,0.00020884487],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046400554,0.0006425739,0.001156183,0.0003390785,0.0007966937,0.0009909027,0.0037945367,0.0004813457,0.004936183],"category_scores_gemma":[0.022388931,0.00037466898,0.0005632333,0.000060525996,0.0008027119,0.000001949912,0.00080432394,0.00067646423,0.0011442606],"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":[0.000011842106,1.3093319e-7,0.002403581,0.000004841396,0.000118641794,0.00004113978,0.0001663934,4.1993943e-7,0.000012235202,0.42552325,0.0009371125,0.5707804],"study_design_scores_gemma":[0.00024280003,0.000034323373,0.004203647,0.00015898635,0.00008422345,0.00003631298,0.000060679584,0.000011730792,0.000047842816,0.9076827,0.086998455,0.00043827473],"about_ca_topic_score_codex":0.00017001592,"about_ca_topic_score_gemma":0.000076699376,"teacher_disagreement_score":0.9555443,"about_ca_system_score_codex":0.000048481532,"about_ca_system_score_gemma":0.00017950282,"threshold_uncertainty_score":0.99987054},"labels":[],"label_agreement":null},{"id":"W27459002","doi":"10.1139/bcb-2016-0022","title":"Detection of Differential Item Functioning in the Generalized Full-Information Item Bifactor Analysis Model","year":2012,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Canadian Institutes of Health Research","keywords":"Differential item functioning; Item response theory; Curse of dimensionality; Psychometrics; Computer science; A priori and a posteriori; Psychology; Item analysis; Statistics; Rasch model; Artificial intelligence; Econometrics; Mathematics","score_opus":0.36548229359737683,"score_gpt":0.420291226824581,"score_spread":0.05480893322720415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27459002","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":[0.5175983,0.00002420764,0.48074472,0.000026608119,0.00020269658,0.000054618617,0.0000017185037,0.000014012423,0.0013331462],"genre_scores_gemma":[0.990958,0.000005819102,0.008798589,0.00006263742,0.000059057624,0.000009323423,0.0000040214313,0.0000022166714,0.00010036201],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975529,0.00044875272,0.000769517,0.00013878748,0.00086700177,0.00022305078],"domain_scores_gemma":[0.99074095,0.008262271,0.0004185513,0.00037241433,0.0001606406,0.00004518668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005101578,0.000094871466,0.00027044126,0.0013662326,0.00011284664,0.0001385552,0.0003398041,0.00007085052,0.00026552274],"category_scores_gemma":[0.017281003,0.000050054263,0.00018782323,0.004995486,0.000023544439,0.0008774267,0.000054144723,0.000106378546,0.000016519385],"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":[0.00013901977,0.000099789475,0.5633502,0.000007011376,0.00012229219,1.01902714e-7,0.0030722967,0.02775892,0.012746736,0.0015357534,0.00023761627,0.39093027],"study_design_scores_gemma":[0.00020988217,0.000022077547,0.39019763,0.0000013067576,0.00005464825,0.0000012972602,0.0013793304,0.6063263,0.000783532,0.00078622415,0.00017083735,0.00006692798],"about_ca_topic_score_codex":0.00012343387,"about_ca_topic_score_gemma":0.00004315245,"teacher_disagreement_score":0.5785674,"about_ca_system_score_codex":0.000026938927,"about_ca_system_score_gemma":0.000010066774,"threshold_uncertainty_score":0.99099684},"labels":[],"label_agreement":null},{"id":"W2745969301","doi":"10.1007/s11136-017-1680-8","title":"The use of latent variable mixture models to identify invariant items in test construction","year":2017,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary; Research Canada; University of Manitoba; Providence Health Care; Trinity Western University; Centre for Advancing Health Outcomes; Western University","funders":"Canadian Institutes of Health Research; Canada Excellence Research Chairs, Government of Canada","keywords":"Differential item functioning; Bivariate analysis; Item response theory; Latent class model; Latent variable; Psychology; Logistic regression; Statistics; Latent variable model; Invariant (physics); Econometrics; Measurement invariance; Context (archaeology); Rasch model; Prom; Population; Mathematics; Psychometrics; Structural equation modeling; Confirmatory factor analysis; Medicine; Geography","score_opus":0.9371213187924718,"score_gpt":0.6330638612998148,"score_spread":0.304057457492657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745969301","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":[0.9744033,0.00018379571,0.017791029,0.0041195415,0.00041220986,0.0004495963,0.000046886187,0.0000091613065,0.002584464],"genre_scores_gemma":[0.9676324,0.000107608015,0.03162622,0.000035459416,0.00005662233,0.000012009862,5.9085386e-7,0.0000057486704,0.0005233462],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99190813,0.0031088828,0.0013497877,0.00042614999,0.0027864655,0.00042060867],"domain_scores_gemma":[0.72958034,0.26268744,0.0012638308,0.0033567443,0.0028005159,0.000311089],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07921305,0.000084439154,0.00043394713,0.0005686292,0.000600368,0.00066646934,0.0018780143,0.000116975076,0.000043387157],"category_scores_gemma":[0.6385847,0.000052092873,0.000074489384,0.001695592,0.0006316921,0.00047560313,0.0007595785,0.00040058032,0.000013791025],"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":[0.0002863056,0.00020126067,0.84821904,0.00006542602,0.000032202293,0.0000032094595,0.0009919782,0.0026881285,0.010067985,0.057257626,0.007839276,0.07234759],"study_design_scores_gemma":[0.0004257578,0.00011953526,0.775651,0.00009761003,0.0000018486968,0.0000019324161,0.0013719774,0.009325682,0.00043648703,0.20977837,0.0026842467,0.00010558104],"about_ca_topic_score_codex":0.010161218,"about_ca_topic_score_gemma":0.00032019202,"teacher_disagreement_score":0.5593716,"about_ca_system_score_codex":0.000037713802,"about_ca_system_score_gemma":0.00028038843,"threshold_uncertainty_score":0.9964302},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2751852067","doi":"10.3758/s13428-020-01355-x","title":"Two-stage maximum likelihood approach for item-level missing data in regression","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Imputation (statistics); Statistics; Univariate; Regression; Scale (ratio); Regression analysis; Context (archaeology); Econometrics; Restricted maximum likelihood; Mathematics; Computer science; Maximum likelihood; Multivariate statistics","score_opus":0.9595380073134077,"score_gpt":0.7275446994992708,"score_spread":0.23199330781413685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751852067","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":[0.0265774,0.00096375664,0.9646374,0.0018696976,0.00032861572,0.0015846721,0.00023412808,0.00009380941,0.0037105056],"genre_scores_gemma":[0.012105732,0.00003096982,0.9864144,0.0001453905,0.00026207167,0.00021503629,0.00006127898,0.000048940667,0.00071619416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98094076,0.011098019,0.0013577897,0.002188683,0.0030497676,0.00136498],"domain_scores_gemma":[0.89657444,0.09796237,0.00042417462,0.0033491284,0.00087633147,0.0008135633],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12227027,0.00028806084,0.0007930764,0.0013690565,0.00048762115,0.00070967985,0.0051424666,0.00021956582,0.00026448545],"category_scores_gemma":[0.4432789,0.0002041742,0.00016073456,0.0073746247,0.0002646999,0.0006203628,0.0029645844,0.0012145751,0.00002447553],"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":[0.000119533775,0.0002203957,0.03142401,0.0000394466,0.000005145443,0.0000347684,0.0003449152,0.000008992409,0.01323352,0.000084538515,0.0043081045,0.95017666],"study_design_scores_gemma":[0.0113331815,0.001878168,0.27888548,0.00040578766,0.000104847444,0.000085127656,0.02860781,0.34655696,0.026232122,0.07311597,0.230161,0.002633531],"about_ca_topic_score_codex":0.00018530033,"about_ca_topic_score_gemma":0.0000063997713,"teacher_disagreement_score":0.9475431,"about_ca_system_score_codex":0.000094712304,"about_ca_system_score_gemma":0.00039566797,"threshold_uncertainty_score":0.9556068},"labels":[],"label_agreement":null},{"id":"W2753556883","doi":"10.3102/1076998617694880","title":"Normal Theory Two-Stage ML Estimator When Data Are Missing at the Item Level","year":2017,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Missing data; Imputation (statistics); Computer science; Estimator; Item response theory; Statistics; Structural equation modeling; Scale (ratio); Data mining; Mathematics; Psychometrics","score_opus":0.7867101434106125,"score_gpt":0.5828149761437459,"score_spread":0.20389516726686663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753556883","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":[0.9081619,0.0011025803,0.07265793,0.011534536,0.0029927094,0.0001225413,0.0025643804,0.000004346618,0.00085907284],"genre_scores_gemma":[0.59981513,0.00004100451,0.38739324,0.00023163095,0.0008218321,0.0000016754138,0.00003350991,0.0000146272905,0.011647366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977374,0.00025950573,0.00068677467,0.00022838534,0.00090530067,0.00018263965],"domain_scores_gemma":[0.9781928,0.018461866,0.0018556779,0.00075215433,0.0005722467,0.000165235],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055657076,0.000118587435,0.00025555887,0.00012284034,0.0012628421,0.0008040674,0.0016192683,0.00003795007,0.0013140609],"category_scores_gemma":[0.0567458,0.00006534572,0.000044216336,0.00010304786,0.00033192438,0.0005333728,0.0005340251,0.0002366546,0.000013926992],"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":[0.00006372855,0.00015022316,0.66263354,0.0000063024336,0.000017347998,0.000023904273,0.00023593535,0.000012935005,0.00008602172,0.0062020128,0.070501864,0.26006615],"study_design_scores_gemma":[0.00029006167,0.000059135866,0.90140474,0.000034375927,0.00006231626,0.00020228724,0.00075726776,0.00043566988,0.00001549665,0.08568881,0.01094288,0.000106984895],"about_ca_topic_score_codex":0.00009462033,"about_ca_topic_score_gemma":0.00006990803,"teacher_disagreement_score":0.3147353,"about_ca_system_score_codex":0.000041061892,"about_ca_system_score_gemma":0.00024945123,"threshold_uncertainty_score":0.99959886},"labels":[],"label_agreement":null},{"id":"W2755323618","doi":"10.1155/2017/7571901","title":"Assessment of Differential Item Functioning in Health-Related Outcomes: A Simulation and Empirical Analysis with Hierarchical Polytomous Data","year":2017,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Shiraz University; Shiraz University of Medical Sciences","keywords":"Polytomous Rasch model; Differential item functioning; Multilevel model; Statistics; Ordinal data; Intraclass correlation; Logistic regression; Ordinal regression; Ordinal Scale; Ordered logit; Hierarchical database model; Hierarchical clustering; Type I and type II errors; Item response theory; Psychology; Scale (ratio); Psychometrics; Mathematics; Data mining; Computer science; Cluster analysis","score_opus":0.6258725610629365,"score_gpt":0.6430005545962104,"score_spread":0.017127993533273878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755323618","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":[0.28928858,0.0000756247,0.70798314,0.0022103821,0.00005041123,0.000120242614,0.0000034601255,0.0000068102613,0.00026133494],"genre_scores_gemma":[0.5360316,0.0000029669322,0.4638762,0.000052758045,0.000010523513,0.0000023789432,0.0000057610996,0.0000027136905,0.0000150969945],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99602515,0.0011994201,0.0013170564,0.0005006164,0.0007877068,0.00017005966],"domain_scores_gemma":[0.9276406,0.07101561,0.0006225644,0.0005067886,0.00009842091,0.000115984716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013341305,0.00013036869,0.0010133402,0.00083366054,0.00015765904,0.00006641178,0.00039219408,0.00006457764,0.00009763899],"category_scores_gemma":[0.07328707,0.00007305878,0.000032361968,0.0009961727,0.00042746816,0.00014297353,0.00033720516,0.00025484126,2.1365021e-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":[0.000039422466,0.00012698863,0.82683116,0.00006820991,0.00010880713,0.0000068925806,0.00048152797,0.01694586,0.000006239781,0.007103099,0.000007552028,0.14827423],"study_design_scores_gemma":[0.00048972975,0.000070418995,0.4445699,0.000058747642,0.000025291514,0.0000044487215,0.00011574588,0.4299196,7.298447e-8,0.12470958,0.0000031980576,0.000033306267],"about_ca_topic_score_codex":0.000053353837,"about_ca_topic_score_gemma":0.000012414842,"teacher_disagreement_score":0.41297373,"about_ca_system_score_codex":0.000020430454,"about_ca_system_score_gemma":0.00005350303,"threshold_uncertainty_score":0.93451905},"labels":[],"label_agreement":null},{"id":"W2756052618","doi":"10.1016/j.jclinepi.2017.09.005","title":"Decision making about healthcare-related tests and diagnostic test strategies. Paper 5: a qualitative study with experts suggests that test accuracy data alone is rarely sufficient for decision making","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Health Sciences Centre; Impact","funders":"","keywords":"Test (biology); Health care; Process (computing); Qualitative research; Preference; Developing country; Medicine; Psychology; Management science; Applied psychology; Computer science","score_opus":0.8959780327898161,"score_gpt":0.7278816273887818,"score_spread":0.16809640540103432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756052618","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006233358,0.9465888,0.039319098,0.0011369212,0.0035690626,0.0026503776,0.00039952467,0.000037146772,0.00006567855],"genre_scores_gemma":[0.06797622,0.8363155,0.09382274,0.00091497076,0.00076835346,0.0000621522,0.000017286118,0.00009849384,0.000024253555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9485786,0.023066461,0.021203432,0.0032571286,0.0024468615,0.0014475492],"domain_scores_gemma":[0.013697932,0.941627,0.03770015,0.004120278,0.0020957065,0.00075890525],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.24743752,0.0012155955,0.016150882,0.0014885842,0.000875219,0.00073041336,0.006574778,0.0015561017,0.00009938938],"category_scores_gemma":[0.98712784,0.0006514023,0.0015000093,0.0015288682,0.0010503961,0.0014168203,0.002159369,0.0031028192,0.00001923974],"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":[0.00046669864,0.00081403926,0.056226045,0.00040600233,0.0003064335,0.0002797356,0.0009587038,0.000016871827,1.5445389e-8,0.000055671353,0.0074702823,0.9329995],"study_design_scores_gemma":[0.0070965555,0.023841538,0.21660204,0.13930866,0.0026993924,0.0035856327,0.018468065,0.0013219186,1.86742e-8,0.0821955,0.502501,0.002379661],"about_ca_topic_score_codex":0.00005735136,"about_ca_topic_score_gemma":0.00016004851,"teacher_disagreement_score":0.9348806,"about_ca_system_score_codex":0.00015805774,"about_ca_system_score_gemma":0.0020191579,"threshold_uncertainty_score":0.99974006},"labels":[],"label_agreement":null},{"id":"W2756376863","doi":"10.7202/1041006ar","title":"La méthode de notation d’un questionnaire importe-t-elle ?","year":2017,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mathematics; Humanities; Notation; Philosophy; Arithmetic","score_opus":0.508183188442973,"score_gpt":0.540809858269047,"score_spread":0.032626669826073984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756376863","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":[0.3682274,0.0025028293,0.56034994,0.04220854,0.008504418,0.000503105,0.000018276141,0.0001075917,0.017577924],"genre_scores_gemma":[0.8932947,0.0006697095,0.098415375,0.00031925944,0.0006035999,0.000059064972,0.000037404345,0.00003319142,0.006567724],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97607857,0.01985948,0.0011313172,0.00085830915,0.0015714418,0.0005009061],"domain_scores_gemma":[0.97460073,0.020759722,0.0018469491,0.0015410878,0.0010556048,0.00019588071],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13088869,0.00031073706,0.00040228505,0.0005017027,0.0012699607,0.0013181525,0.0010394951,0.0005026359,0.001006899],"category_scores_gemma":[0.2921674,0.0003037282,0.00018745217,0.0007405182,0.00024960542,0.0016339596,0.0001619251,0.00053644524,0.00037447753],"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":[0.000022064129,0.00018759149,0.15864065,0.000041487074,0.000034618894,0.0000057244106,0.025548771,0.001069129,0.0004193875,0.010152484,0.0044103293,0.79946774],"study_design_scores_gemma":[0.0005499315,0.00006613902,0.8254007,0.00021757367,0.000093399685,0.000060111415,0.0019710164,0.026617952,0.0003744543,0.13627727,0.008087318,0.00028412708],"about_ca_topic_score_codex":0.00071857177,"about_ca_topic_score_gemma":0.0001977512,"teacher_disagreement_score":0.7991836,"about_ca_system_score_codex":0.00049908494,"about_ca_system_score_gemma":0.0017050795,"threshold_uncertainty_score":0.99994147},"labels":[],"label_agreement":null},{"id":"W2758732947","doi":"10.1016/j.cptl.2017.09.015","title":"Measuring social science concepts in pharmacy education research: From definition to item analysis of self-report instruments","year":2017,"lang":"en","type":"review","venue":"Currents in Pharmacy Teaching and Learning","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Pharmacy; Pharmacy education; Medical education; Psychology; Engineering ethics; Medicine; Pharmacy practice; Engineering; Nursing","score_opus":0.8786372339149293,"score_gpt":0.68157236660446,"score_spread":0.19706486731046935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758732947","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40653512,0.58229053,0.00018437754,0.000039225753,0.0022672475,0.0007388804,0.000027777787,0.000058679158,0.007858132],"genre_scores_gemma":[0.5010305,0.49326113,0.0050481423,0.000017366665,0.00034494023,0.00009955959,0.00007645479,0.000034266726,0.00008763396],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853545,0.008023508,0.002000422,0.0014541224,0.002504875,0.0006625702],"domain_scores_gemma":[0.9802352,0.01656631,0.0019769415,0.0005736248,0.00041558317,0.00023229778],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06406344,0.00035257626,0.001840607,0.009268862,0.00154576,0.00068736396,0.001874279,0.000093927716,0.00005096203],"category_scores_gemma":[0.16805214,0.00030698787,0.0002829504,0.0073559466,0.00027482669,0.000712016,0.00086643995,0.003629389,0.000011825451],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075553385,0.00012916967,0.1264278,0.00021551571,0.00009729075,0.000006353692,0.0031740547,0.000015578247,0.000005149301,0.000031238036,0.00003065186,0.86985964],"study_design_scores_gemma":[0.00089774106,0.000026850152,0.029831516,0.007357669,0.00078117475,0.000015190907,0.0021973012,0.0028035752,0.0000043723676,0.00061695697,0.95483637,0.00063130463],"about_ca_topic_score_codex":0.0016390656,"about_ca_topic_score_gemma":0.0000132263585,"teacher_disagreement_score":0.9548057,"about_ca_system_score_codex":0.00045271064,"about_ca_system_score_gemma":0.0011887514,"threshold_uncertainty_score":0.99993825},"labels":[],"label_agreement":null},{"id":"W2760364374","doi":"10.3102/0034654317726529","title":"Developing, Analyzing, and Using Distractors for Multiple-Choice Tests in Education: A Comprehensive Review","year":2017,"lang":"en","type":"review","venue":"Review of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":217,"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":"Task (project management); Quality (philosophy); Process (computing); Psychology; Cognitive psychology; Multiple choice; Computer science; Applied psychology; Medicine","score_opus":0.9466681700442642,"score_gpt":0.7483343693634743,"score_spread":0.19833380068078987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760364374","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020145191,0.9935573,0.000028116898,0.001664191,0.0005952428,0.0035296986,0.00007355806,0.000002952251,0.0005288105],"genre_scores_gemma":[0.0000020390814,0.98023176,0.01797561,0.0001514336,0.00032831423,0.00062431884,0.000106161264,0.00002995994,0.00055042526],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99114335,0.00263995,0.0028296285,0.0011111938,0.001743468,0.000532414],"domain_scores_gemma":[0.5552396,0.43390074,0.0034049985,0.00199499,0.0051662624,0.00029337872],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02083228,0.00039523016,0.0033668077,0.0016669554,0.00037387255,0.00019143397,0.002159496,0.00018904636,0.0003463821],"category_scores_gemma":[0.78403956,0.0002798506,0.0005490006,0.0039779297,0.0003703116,0.00025390607,0.00045636293,0.00068737264,0.000027440357],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[8.310841e-7,0.00006277508,0.0028203207,0.244022,0.000025027834,1.7849852e-7,0.000004707653,2.9296146e-8,5.34082e-8,0.00050740386,0.009549277,0.7430074],"study_design_scores_gemma":[0.000042947926,0.000016204589,0.0043173805,0.35302356,0.000083297935,0.0000227355,0.000012481445,0.0000023386513,2.4645377e-8,0.0012176462,0.6410951,0.00016630856],"about_ca_topic_score_codex":0.00019519655,"about_ca_topic_score_gemma":0.000026840708,"teacher_disagreement_score":0.76320726,"about_ca_system_score_codex":0.00043690013,"about_ca_system_score_gemma":0.010256217,"threshold_uncertainty_score":0.99996537},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2765291517","doi":"10.1080/10705511.2017.1374187","title":"An Investigation of the Alignment Method With Polytomous Indicators Under Conditions of Partial Measurement Invariance","year":2017,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"University of Connecticut; U.S. Department of Education","keywords":"Polytomous Rasch model; Measurement invariance; Skew; Econometrics; Computer science; Factor analysis; Statistical power; Statistics; Mathematics; Structural equation modeling; Confirmatory factor analysis; Item response theory; Psychometrics","score_opus":0.42639576723060524,"score_gpt":0.4729737817399195,"score_spread":0.04657801450931426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765291517","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":[0.6108527,0.000026150217,0.38801077,0.0005940769,0.00033683088,0.00013766464,0.000010238818,0.0000064029105,0.000025136174],"genre_scores_gemma":[0.89443874,0.0000030860604,0.1054244,0.000014764077,0.000097038996,0.0000050466783,0.000001953047,0.000009266612,0.0000056960052],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99485886,0.0010662246,0.001133913,0.0003427507,0.0023722246,0.00022603663],"domain_scores_gemma":[0.99412197,0.0010577367,0.0027990243,0.00093030155,0.00093255186,0.00015839741],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008608704,0.00016713861,0.00033760644,0.00037000154,0.00160311,0.00023854712,0.0012564263,0.00008054807,0.00003871814],"category_scores_gemma":[0.006355347,0.00009083461,0.0001293785,0.0005452839,0.00030035744,0.00077356934,0.0001832357,0.00029913982,6.183084e-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":[0.00010466969,0.000020412528,0.20995595,0.0000068961676,0.00005541437,0.0000011644737,0.002070059,0.7548319,0.022311645,0.0017064712,0.0000043217005,0.008931091],"study_design_scores_gemma":[0.0005099477,0.0001334255,0.33496645,0.000070801565,0.000034359673,0.000037062546,0.0015349975,0.56120634,0.0038458302,0.097567566,1.9330436e-7,0.0000930532],"about_ca_topic_score_codex":0.00011921348,"about_ca_topic_score_gemma":0.000024667006,"teacher_disagreement_score":0.28358603,"about_ca_system_score_codex":0.00010270797,"about_ca_system_score_gemma":0.0003464874,"threshold_uncertainty_score":0.9996967},"labels":[],"label_agreement":null},{"id":"W2766572348","doi":"10.7334/psicothema2017.178","title":"The maximum likelihood alignment approach to testing for approximate measurement invariance: A paradigmatic cross-cultural application","year":2017,"lang":"en","type":"article","venue":"Psicothema","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":106,"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":"Division of Mathematical Sciences","keywords":"Measurement invariance; Confirmatory factor analysis; Range (aeronautics); Trustworthiness; Scale (ratio); Econometrics; Scale invariance; Computer science; Statistics; Mathematics; Test (biology); Psychology; Structural equation modeling; Social psychology; Physics","score_opus":0.5309592073977307,"score_gpt":0.47890247616681014,"score_spread":0.05205673123092058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766572348","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":[0.029235104,0.00024084268,0.91311145,0.0019639034,0.0006545138,0.0022961057,0.000014245794,0.00010798979,0.05237587],"genre_scores_gemma":[0.734682,0.0000037381033,0.26342908,0.0002080931,0.00027203295,0.0011919048,0.0000012945357,0.000021381393,0.00019042505],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960711,0.00015852798,0.00080276903,0.00077243295,0.0015739703,0.00062118954],"domain_scores_gemma":[0.98872477,0.0072788973,0.0009461019,0.0019783855,0.00088677084,0.00018508581],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.015744215,0.0002294655,0.00035896152,0.00009746643,0.0024976826,0.003056624,0.0024784484,0.00007223579,0.0000043230857],"category_scores_gemma":[0.12873733,0.00012704628,0.00013533869,0.00053976633,0.00018885838,0.00034330843,0.0003233549,0.000113446484,0.00006109615],"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":[0.00007911711,0.00017957937,0.020476118,0.000055662164,0.00005243448,4.0949462e-7,0.00078050734,0.00023145408,0.0037867017,0.017960506,0.0041648936,0.9522326],"study_design_scores_gemma":[0.0013087862,0.00020688576,0.057010792,0.000078963916,0.000037358728,0.000022949342,0.0013783844,0.05030885,0.0021764636,0.8618892,0.025044272,0.00053710624],"about_ca_topic_score_codex":0.000044681437,"about_ca_topic_score_gemma":0.00000593849,"teacher_disagreement_score":0.9516955,"about_ca_system_score_codex":0.00011371567,"about_ca_system_score_gemma":0.00005537259,"threshold_uncertainty_score":0.99880093},"labels":[],"label_agreement":null},{"id":"W2768881033","doi":"10.1037/ipp0000042","title":"Adaptation of Assessment Scales in Cross-National Research: Issues, Guidelines, and Caveats","year":2015,"lang":"en","type":"article","venue":"International Perspectives in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":183,"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":"Equivalence (formal languages); Criticism; Scale (ratio); Set (abstract data type); Adaptation (eye); Psychology; Computer science; Management science; Data science; Political science; Mathematics; Geography; Engineering","score_opus":0.9019762010793025,"score_gpt":0.722889276717478,"score_spread":0.1790869243618245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768881033","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":[0.8647325,0.004300357,0.011318502,0.0147406915,0.0015732916,0.00024127691,0.000030243276,0.000018691866,0.10304445],"genre_scores_gemma":[0.9411087,0.0005013461,0.057855684,0.00010916835,0.00016282807,0.000017771594,0.0000031595828,0.0000061727014,0.00023518794],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951218,0.0008838924,0.00089896546,0.0006038076,0.0022842097,0.00020734996],"domain_scores_gemma":[0.98845637,0.00640429,0.00023306634,0.00023968669,0.0046025366,0.00006402277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01904705,0.00009566304,0.00024264531,0.0021443763,0.00003200044,0.00007930789,0.00067264395,0.000104671555,0.000085964726],"category_scores_gemma":[0.124767154,0.000081624676,0.00003465733,0.0015109214,0.0004535771,0.00028542808,0.00018450605,0.00030231403,0.000011380108],"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":[0.00017348734,0.00028359127,0.84169114,0.0000016442046,0.00001783198,0.000017924931,0.0027004632,0.0027134246,0.00015950878,0.08269278,0.007728415,0.0618198],"study_design_scores_gemma":[0.00080393424,0.00008198371,0.62826926,0.0000142718245,3.322325e-7,0.000018436813,0.0066079027,0.0074872826,0.0000047441736,0.35194033,0.0047153556,0.000056189016],"about_ca_topic_score_codex":0.0005339621,"about_ca_topic_score_gemma":0.00041139335,"teacher_disagreement_score":0.26924756,"about_ca_system_score_codex":0.00030079615,"about_ca_system_score_gemma":0.00015479898,"threshold_uncertainty_score":0.8826053},"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":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2768934567","doi":"10.1111/ijsa.12187","title":"Are assessment center behaviors' meanings consistent across exercises? A measurement invariance approach","year":2017,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Psychology; Dimension (graph theory); Consistency (knowledge bases); Rating scale; Measurement invariance; Sample (material); Factor analysis; Construct validity; Trait; Construct (python library); Social psychology; Statistics; Applied psychology; Confirmatory factor analysis; Psychometrics; Developmental psychology; Structural equation modeling; Mathematics; Artificial intelligence; Computer science","score_opus":0.5001267709211625,"score_gpt":0.5373745756699646,"score_spread":0.03724780474880207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768934567","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":[0.7726577,0.00017822294,0.2057787,0.0046423213,0.00529659,0.00027152163,0.000024196424,0.00002597,0.011124758],"genre_scores_gemma":[0.94920987,0.00011342894,0.04996121,0.00023139072,0.00030770106,0.000009367118,8.313279e-7,0.000009049268,0.00015718144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99479383,0.00027355272,0.0010413625,0.0003719279,0.0032764045,0.0002429399],"domain_scores_gemma":[0.9922167,0.00063732185,0.003586466,0.00029172358,0.0030971135,0.00017067824],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00891108,0.0001767579,0.0004177217,0.00032639963,0.00056493207,0.0018482992,0.0011516993,0.00007284236,0.000117026444],"category_scores_gemma":[0.0069609084,0.0001281177,0.00018276328,0.00018535562,0.000103905964,0.00072496716,0.00029586372,0.00045000503,0.000002454763],"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":[0.00008866471,0.000536571,0.87354654,0.0000063002685,0.00019913497,0.00004492416,0.00019350111,0.000121536075,0.001584941,0.00074408524,0.0021302884,0.12080351],"study_design_scores_gemma":[0.0015657765,0.00014221162,0.9821706,0.000114046496,0.000030228854,0.0004224723,0.0016703686,0.0018524996,0.00024033673,0.001979908,0.009655713,0.0001558597],"about_ca_topic_score_codex":0.00004397694,"about_ca_topic_score_gemma":0.000025749498,"teacher_disagreement_score":0.17655213,"about_ca_system_score_codex":0.00039840955,"about_ca_system_score_gemma":0.00017730334,"threshold_uncertainty_score":0.9991879},"labels":[],"label_agreement":null},{"id":"W2769536523","doi":"10.1002/pfi.21727","title":"Evidence-Based Survey Design: The Use of a Midpoint on the Likert Scale","year":2017,"lang":"en","type":"article","venue":"Performance Improvement Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":823,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Alberta","funders":"","keywords":"Likert scale; Midpoint; Scale (ratio); Computer science; Survey research; Psychology; Management science; Applied psychology; Mathematics; Engineering; Geography","score_opus":0.9048798418730529,"score_gpt":0.4941430133169829,"score_spread":0.41073682855607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769536523","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":[0.9642161,0.0001370248,0.028735254,0.005249165,0.001130445,0.0003196174,0.000004073352,0.000007711878,0.00020056634],"genre_scores_gemma":[0.9906796,0.00037955068,0.0073535275,0.0010613984,0.0001596495,0.000013180931,1.2542515e-7,0.000008274697,0.00034465856],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955772,0.0010868097,0.00086990336,0.00026927172,0.0017894567,0.00040736786],"domain_scores_gemma":[0.9526426,0.043359112,0.0016846332,0.0015529883,0.00065805623,0.0001026204],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043723352,0.00016209502,0.000275631,0.00020439141,0.0018734758,0.001546578,0.0027096553,0.000046153727,0.00024376951],"category_scores_gemma":[0.1346142,0.0000636112,0.00015861109,0.00046238204,0.0003151665,0.0008813184,0.00023723661,0.0004743438,0.000032431635],"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":[0.00031143083,0.00006021393,0.3922879,0.0000045013076,0.000021825543,0.0000015258606,0.00010872755,0.002198944,0.0014733645,0.000010692563,0.009090503,0.5944304],"study_design_scores_gemma":[0.00035212116,0.00087423756,0.9387509,0.00023314732,0.000011234194,0.000009616132,0.000110676265,0.047883846,0.009561236,0.00060653855,0.0014943844,0.00011206212],"about_ca_topic_score_codex":0.00010804255,"about_ca_topic_score_gemma":0.000019314328,"teacher_disagreement_score":0.5943183,"about_ca_system_score_codex":0.00005337825,"about_ca_system_score_gemma":0.00019087591,"threshold_uncertainty_score":0.9994899},"labels":[],"label_agreement":null},{"id":"W2770364986","doi":"10.1007/s11136-017-1746-7","title":"An evaluation of the structural validity of the shoulder pain and disability index (SPADI) using the Rasch model","year":2017,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; London Health Sciences Centre; McMaster University; Canadian Physiotherapy Association","funders":"Research Trainees Coordinating Centre; National Institute for Health and Care Research","keywords":"Rasch model; Quality of Life Research; Polytomous Rasch model; Index (typography); Psychometrics; Physical therapy; Physical medicine and rehabilitation; Psychology; Construct validity; Item response theory; Public health; Medicine; Clinical psychology; Computer science; Nursing; Developmental psychology","score_opus":0.959663442598602,"score_gpt":0.707273620668431,"score_spread":0.252389821930171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770364986","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":[0.992464,0.00007512072,0.0046924213,0.001871046,0.00012806656,0.00050823635,0.000024750572,0.0000027689746,0.00023357547],"genre_scores_gemma":[0.99870807,0.000003011697,0.0011977118,0.000022245396,0.000046050583,0.0000040048153,1.8773017e-7,0.0000041388594,0.000014598362],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9583337,0.03357946,0.0010073319,0.0004127853,0.006382379,0.0002843867],"domain_scores_gemma":[0.8840838,0.103487216,0.0020114419,0.0062778573,0.003982128,0.0001575596],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28444073,0.00008934043,0.00035645138,0.00007873193,0.0010488075,0.00016156428,0.0027789744,0.00009845348,0.00004753218],"category_scores_gemma":[0.5430649,0.00003687877,0.0001432974,0.00078641623,0.0029859918,0.0002439303,0.00090652064,0.0004115293,8.959917e-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":[0.000039238745,0.000033150092,0.9627513,0.000027933718,0.000009776743,6.168765e-9,0.0007628981,0.00379556,0.0013193354,0.0004870968,0.000041805535,0.030731875],"study_design_scores_gemma":[0.00014520282,0.000020860003,0.58065623,0.000011621134,0.000005023841,1.4448051e-7,0.0015478363,0.33417845,0.00035102371,0.08305532,0.0000016140077,0.000026662517],"about_ca_topic_score_codex":0.0028630488,"about_ca_topic_score_gemma":0.0002831205,"teacher_disagreement_score":0.38209507,"about_ca_system_score_codex":0.000050185485,"about_ca_system_score_gemma":0.00041174528,"threshold_uncertainty_score":0.9997273},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2782384206","doi":"10.1177/0265532217750692","title":"Examining sources of variability in repeaters’ L2 writing scores: The case of the PTE Academic writing section","year":2018,"lang":"en","type":"article","venue":"Language Testing","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":"York University","funders":"","keywords":"Test (biology); Psychology; Context (archaeology); Boston Naming Test; Language assessment; Language proficiency; Mathematics education; Cognition","score_opus":0.3740090240133829,"score_gpt":0.4424069973241175,"score_spread":0.0683979733107346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782384206","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":[0.9916693,0.00021102178,0.0027101394,0.00006900854,0.0003475023,0.00020038287,0.000004981368,0.000054004988,0.004733643],"genre_scores_gemma":[0.984133,0.000001063758,0.015330731,0.000072022165,0.00040918696,0.0000061222877,2.0222414e-7,0.000012224996,0.00003543585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947868,0.0023896098,0.0014007796,0.00050588616,0.00054803735,0.00036889093],"domain_scores_gemma":[0.8812267,0.115811735,0.0014950268,0.0010132339,0.00040486336,0.000048406004],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043951046,0.00015094098,0.00035407374,0.0002827357,0.00038389812,0.00007337797,0.0009004445,0.0001184916,0.00003911367],"category_scores_gemma":[0.42799452,0.000083968676,0.00007881052,0.003934137,0.0004176251,0.00018757799,0.00050096004,0.0005721146,0.0000015653378],"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":[0.000006502964,0.000009143778,0.77992404,0.000023682047,0.000004543639,0.000037589292,0.008377585,0.00011393139,0.012902584,0.000048908325,0.000008312566,0.19854316],"study_design_scores_gemma":[0.00047771228,0.00015430538,0.8202249,0.0009758305,0.000033075605,0.0014294875,0.121755175,0.032621305,0.01640105,0.0056412965,0.00001124032,0.00027466007],"about_ca_topic_score_codex":0.0018823608,"about_ca_topic_score_gemma":0.00012432784,"teacher_disagreement_score":0.38404348,"about_ca_system_score_codex":0.0000366806,"about_ca_system_score_gemma":0.000048936563,"threshold_uncertainty_score":0.98445356},"labels":[],"label_agreement":null},{"id":"W2789737102","doi":"10.1111/jcpp.12876","title":"Research Review: Test–retest reliability of standardized diagnostic interviews to assess child and adolescent psychiatric disorders: a systematic review and meta‐analysis","year":2018,"lang":"en","type":"review","venue":"Journal of Child Psychology and Psychiatry","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Meta-analysis; Psychology; Reliability (semiconductor); Clinical psychology; Systematic review; Kappa; Sample size determination; Test (biology); Psychiatry; MEDLINE; Medicine; Statistics","score_opus":0.430132906855796,"score_gpt":0.5557593511374938,"score_spread":0.12562644428169772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789737102","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000058229402,0.97327536,0.0011833657,0.019339157,0.0012448573,0.003624347,0.0001641051,0.000014156224,0.0011488216],"genre_scores_gemma":[0.000031060274,0.9869717,0.0063303607,0.0061623105,0.00028077464,0.00012619203,0.0000045772454,0.000047347516,0.000045691457],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9752317,0.012650056,0.0077748094,0.0016649852,0.0019842323,0.00069421186],"domain_scores_gemma":[0.94201756,0.04562027,0.0075442055,0.0024497877,0.0016649817,0.0007032142],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07084216,0.0009284241,0.015172749,0.003868609,0.00042437986,0.0001888962,0.0021843663,0.0005703803,0.0002564942],"category_scores_gemma":[0.11877006,0.00052297185,0.0030698362,0.0108335605,0.0007117587,0.00024901528,0.00051926187,0.0024372707,0.000014910949],"study_design_candidate":"systematic_review","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":[0.00005536271,0.00065584015,0.0020923507,0.8336317,0.018810272,0.000005368941,0.00006135158,2.4744875e-7,8.423653e-9,0.00006369325,0.1169052,0.027718637],"study_design_scores_gemma":[0.0005916544,0.0016234431,0.0021061306,0.27558607,0.35328963,0.00090591627,0.0000689787,6.1049457e-7,1.5251587e-8,0.004543388,0.36063406,0.0006501064],"about_ca_topic_score_codex":0.0000036302483,"about_ca_topic_score_gemma":0.00001599733,"teacher_disagreement_score":0.5580456,"about_ca_system_score_codex":0.00003731674,"about_ca_system_score_gemma":0.0002347406,"threshold_uncertainty_score":0.99986416},"labels":[],"label_agreement":null},{"id":"W2792554342","doi":"10.1080/00313831.2017.1420687","title":"PISA Country Rankings Valid? Results for Canada and Finland","year":2018,"lang":"en","type":"article","venue":"Scandinavian Journal of Educational Research","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":true,"ca_institutions":"Concordia University","funders":"","keywords":"Item response theory; Normalization (sociology); Contrast (vision); Econometrics; Mathematics education; Mathematics; Statistics; Psychology; Psychometrics; Computer science; Sociology; Social science; Artificial intelligence","score_opus":0.5919838220888495,"score_gpt":0.574699651340387,"score_spread":0.017284170748462446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792554342","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":[0.9700267,0.0009327077,0.0005759,0.013088598,0.0020349259,0.00019133276,0.0000894661,0.0000010833674,0.0130592985],"genre_scores_gemma":[0.9801551,0.00004256595,0.009715707,0.00014891756,0.001661493,0.0000048726124,0.00000250377,0.0000073479127,0.008261486],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9959332,0.00047260552,0.00075086294,0.00026872542,0.002193736,0.00038089082],"domain_scores_gemma":[0.853502,0.1402593,0.0005619987,0.00032538862,0.004975795,0.00037555082],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022081543,0.00008299651,0.00023992194,0.00070388406,0.00049396174,0.00026821828,0.0007097055,0.000048487575,0.00047262845],"category_scores_gemma":[0.33449885,0.000056690318,0.000048419122,0.0016163491,0.00034176835,0.00018006226,0.00007281687,0.00028597482,0.000008414539],"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":[0.00065429957,0.000041351548,0.33552173,0.000010712243,0.000027361155,0.0000033991716,0.0004053838,0.0000033417984,0.000109559245,0.0019559185,0.6396221,0.021644844],"study_design_scores_gemma":[0.0013351162,0.0006752784,0.70363194,0.00013284963,0.000007689758,0.00020624098,0.0013166975,0.000107271124,0.0001334601,0.113185324,0.17914476,0.0001233749],"about_ca_topic_score_codex":0.017616889,"about_ca_topic_score_gemma":0.017763313,"teacher_disagreement_score":0.46047735,"about_ca_system_score_codex":0.00018334438,"about_ca_system_score_gemma":0.00261913,"threshold_uncertainty_score":0.9912346},"labels":[],"label_agreement":null},{"id":"W2792702604","doi":"10.1177/0734282918760724","title":"Investigating the Theoretical Structure of the Differential Ability Scales—Second Edition Through Hierarchical Exploratory Factor Analysis","year":2018,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Psychology; Normative; Confirmatory factor analysis; Test (biology); Exploratory factor analysis; Factoring; Differential (mechanical device); Psychometrics; Developmental psychology; Cognitive psychology; Statistics; Structural equation modeling; Mathematics; Epistemology","score_opus":0.2099285397369832,"score_gpt":0.48557355500739596,"score_spread":0.27564501527041274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792702604","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":[0.93920773,0.000042033626,0.04953895,0.006826742,0.0034674355,0.00013053694,0.000059918613,0.00000392934,0.0007227403],"genre_scores_gemma":[0.97207475,0.0000034237978,0.025882661,0.0004107958,0.0015971721,0.0000030136102,0.0000023615805,0.000006277758,0.000019526384],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99383116,0.0017686932,0.0014721396,0.00031499047,0.0024039876,0.00020901613],"domain_scores_gemma":[0.98242223,0.013479087,0.0018105187,0.00068925956,0.0014743541,0.00012454682],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036869976,0.00016186392,0.00044086998,0.00029524913,0.00037329565,0.00016394853,0.0013821137,0.00009271745,0.0047228606],"category_scores_gemma":[0.014945453,0.000071597504,0.00047904826,0.002610035,0.0014354385,0.0002981855,0.00014262347,0.0006272437,0.000002248787],"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":[0.00008292491,0.0007133268,0.7984247,0.00002022297,0.0009663464,4.3382133e-7,0.0044192257,0.00016989809,0.023467235,0.13782011,0.015660282,0.018255295],"study_design_scores_gemma":[0.00015027032,0.0000864995,0.66929305,0.000013941628,0.000071717885,0.000008950994,0.0009849787,0.0002588281,0.0006155277,0.32809612,0.00036369136,0.000056422286],"about_ca_topic_score_codex":0.0000030468334,"about_ca_topic_score_gemma":0.000013971764,"teacher_disagreement_score":0.19027601,"about_ca_system_score_codex":0.00010276783,"about_ca_system_score_gemma":0.00049253704,"threshold_uncertainty_score":0.996187},"labels":[],"label_agreement":null},{"id":"W2793870071","doi":"10.1007/s40037-018-0410-4","title":"i-Assess: Evaluating the impact of electronic data capture for OSCE","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision 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 Toronto; McMaster University; Impact","funders":"","keywords":"Cronbach's alpha; Generalizability theory; Rasch model; Reliability (semiconductor); Modality (human–computer interaction); Internal consistency; Inter-rater reliability; Medicine; Repeated measures design; Post hoc; Rating scale; Post-hoc analysis; Kappa; Statistics; Physical therapy; Psychology; Clinical psychology; Psychometrics; Mathematics; Artificial intelligence; Computer science; Internal medicine","score_opus":0.60814605761424,"score_gpt":0.6509570250056883,"score_spread":0.042810967391448296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793870071","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":[0.9032808,0.0020552073,0.07663706,0.007747265,0.0012261362,0.00061665796,0.000025292458,0.000035907513,0.008375679],"genre_scores_gemma":[0.9918275,0.000037568036,0.006769528,0.00021437102,0.0008696975,0.000025072937,0.000008990737,0.000008044576,0.00023925849],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99673766,0.0006101954,0.00040208027,0.0005586389,0.0014146016,0.00027679768],"domain_scores_gemma":[0.9430906,0.051190335,0.0007981519,0.0025385057,0.0021405087,0.00024190376],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015935529,0.00010614786,0.00021299494,0.00021239603,0.00020802364,0.00007399923,0.0017401781,0.000082820065,0.0010139841],"category_scores_gemma":[0.52854437,0.000052891814,0.000100161065,0.0013249222,0.00029704982,0.00015417063,0.00012889205,0.00025369576,0.000017548544],"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":[0.0003024209,0.0009588165,0.009824225,0.000008982165,0.000105689214,1.11257876e-7,0.015961835,0.00003940667,0.0004657672,0.022251477,0.07392875,0.8761525],"study_design_scores_gemma":[0.0013891407,0.005343819,0.30695215,0.00018341771,0.0000940445,0.000035283418,0.19675948,0.18133773,0.00015656964,0.30197752,0.0053081824,0.00046267608],"about_ca_topic_score_codex":0.0002882936,"about_ca_topic_score_gemma":0.000018810179,"teacher_disagreement_score":0.87568986,"about_ca_system_score_codex":0.00014967016,"about_ca_system_score_gemma":0.002470784,"threshold_uncertainty_score":0.9998992},"labels":[],"label_agreement":null},{"id":"W2795833260","doi":"10.1177/0829573518763484","title":"Common Examiner Scoring Errors on Academic Achievement Measures","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","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 Alberta; University of Victoria","funders":"","keywords":"Psychology; Achievement test; Wechsler Adult Intelligence Scale; Academic achievement; Test (biology); Educational measurement; Measure (data warehouse); Intelligence quotient; Scoring system; Cognition; Clinical psychology; Standardized test; Developmental psychology; Mathematics education; Medicine; Curriculum; Computer science; Psychiatry; Data mining; Pedagogy","score_opus":0.6305978026502712,"score_gpt":0.5203701125482403,"score_spread":0.11022769010203093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795833260","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":[0.9577393,0.00063576986,0.0028690204,0.006417863,0.0058473228,0.000095374635,0.0000053427425,0.00000887971,0.026381107],"genre_scores_gemma":[0.9900287,0.0000320178,0.0027670925,0.005306719,0.0013445889,0.0000016808476,2.7847634e-7,0.000017282315,0.00050168193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959539,0.00080564275,0.0013313703,0.0004237419,0.00083887554,0.00064643455],"domain_scores_gemma":[0.9923944,0.0040772846,0.0008883169,0.00069803966,0.00062005536,0.0013218931],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010706305,0.00019850241,0.00050864863,0.0023630334,0.00029920976,0.00011707958,0.0018543929,0.00023835267,0.0015213429],"category_scores_gemma":[0.05718246,0.00014347698,0.00015346285,0.0016881822,0.00038389183,0.0002412558,0.000036803343,0.0011422065,0.00051897106],"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":[0.000092650065,0.000017712337,0.73493266,0.0000011587789,0.000041038915,0.00009756273,0.00019739268,0.000039473784,0.0009167307,0.0004896768,0.104454815,0.15871914],"study_design_scores_gemma":[0.000638054,0.00087067194,0.8795776,0.00006465941,0.000013032487,0.00022814983,0.00052505045,0.00001164704,0.00015775206,0.015719395,0.10202182,0.00017221512],"about_ca_topic_score_codex":0.00057652645,"about_ca_topic_score_gemma":0.0036394745,"teacher_disagreement_score":0.15854692,"about_ca_system_score_codex":0.0001573645,"about_ca_system_score_gemma":0.00045014112,"threshold_uncertainty_score":0.9993914},"labels":[],"label_agreement":null},{"id":"W2799385755","doi":"10.1007/s11136-018-1852-1","title":"Evaluation of options for presenting health-states from PROMIS® item banks for valuation exercises","year":2018,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Utilities Kingston (Canada)","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institutes of Health","keywords":"Valuation (finance); Patient-Reported Outcomes Measurement Information System; Item bank; Item response theory; Descriptive statistics; Psychology; Equating; Actuarial science; Psychometrics; Medicine; Applied psychology; Statistics; Clinical psychology; Mathematics; Finance; Economics; Developmental psychology; Computerized adaptive testing","score_opus":0.9686693684893121,"score_gpt":0.7282412574106342,"score_spread":0.2404281110786779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799385755","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":[0.8932132,0.0010241953,0.099668205,0.0026542658,0.00028377556,0.002475113,0.00025329174,0.000018808872,0.00040915125],"genre_scores_gemma":[0.8965154,0.000044611745,0.10255137,0.000024777,0.00034581457,0.000304335,0.000042654236,0.000011096267,0.00015989013],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9827011,0.008169175,0.001960589,0.0006156178,0.0060711894,0.0004823224],"domain_scores_gemma":[0.508066,0.45478877,0.0024999557,0.0016646856,0.032650378,0.00033022353],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26661447,0.000092989554,0.00053587096,0.0007035982,0.00045259428,0.00010921801,0.0006951952,0.000093633374,0.0001640324],"category_scores_gemma":[0.7051203,0.00007412891,0.0001636683,0.0017333654,0.00033892805,0.00022670678,0.00015395536,0.00012334423,0.0000066060993],"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":[0.00068034464,0.0004267695,0.07451995,0.00038466792,0.00011668618,1.8766793e-8,0.0064656124,0.00042453935,0.0061064563,0.004450684,0.018106177,0.8883181],"study_design_scores_gemma":[0.0015041955,0.00061446807,0.26789173,0.000092965514,0.000025314994,7.678915e-8,0.0056768134,0.14195998,0.004562455,0.57645,0.0011099934,0.00011198102],"about_ca_topic_score_codex":0.0013176093,"about_ca_topic_score_gemma":0.000119357755,"teacher_disagreement_score":0.8882061,"about_ca_system_score_codex":0.00009072796,"about_ca_system_score_gemma":0.0009233601,"threshold_uncertainty_score":0.75517476},"labels":[],"label_agreement":null},{"id":"W2803568088","doi":"10.1037/met0000181","title":"A comparison of several approaches for controlling measurement error in small samples.","year":2018,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":106,"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; Reliability (semiconductor); Statistics; Latent variable; Standard error; Mathematics; Inference; Observational error; Variable (mathematics); Econometrics; Computer science; Power (physics); Artificial intelligence","score_opus":0.9584692213383208,"score_gpt":0.6539327846799784,"score_spread":0.3045364366583424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803568088","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":[0.15148069,0.0005094015,0.84162205,0.00036099157,0.0008574954,0.00053449743,0.0000064955566,0.00003963605,0.004588724],"genre_scores_gemma":[0.4829129,0.0000015688464,0.51678604,0.0001171576,0.000106853746,0.000048015394,4.2179596e-7,0.000006152167,0.00002093141],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99282527,0.003305934,0.0016523595,0.00093397324,0.0007418444,0.0005406418],"domain_scores_gemma":[0.9553593,0.04235062,0.0007647714,0.0007668474,0.00061388133,0.00014458054],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051778648,0.00022423833,0.0011398235,0.0005044796,0.00011641431,0.000068806905,0.0010977829,0.00022585089,0.00016151131],"category_scores_gemma":[0.20021018,0.00014311963,0.00026944897,0.001919076,0.00034292025,0.00006531119,0.00012934428,0.00026586218,0.0000084505755],"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":[0.0006339564,0.0005436441,0.07144773,0.000012102375,0.000028234519,6.3754254e-7,0.00053756224,0.00033089705,0.0026172632,0.0029152678,0.0005056921,0.920427],"study_design_scores_gemma":[0.0036947723,0.0024248536,0.51660687,0.000059953723,0.000037012764,0.0000083285595,0.0020567204,0.08559465,0.003244027,0.3763879,0.009382405,0.0005025009],"about_ca_topic_score_codex":0.000022750495,"about_ca_topic_score_gemma":0.000021041235,"teacher_disagreement_score":0.9199245,"about_ca_system_score_codex":0.000048380934,"about_ca_system_score_gemma":0.000020998245,"threshold_uncertainty_score":0.9763934},"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":"low"}],"label_agreement":"agree"},{"id":"W2805889081","doi":"10.5539/ies.v11n6p119","title":"Comparison of Cognitive Diagnosis Models under Changing Conditions: DINA, RDINA, HODINA and HORDINA","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Hacettepe Üniversitesi","keywords":"Mathematics; Latent class model; Statistics; Class (philosophy); Fraction (chemistry); Artificial intelligence; Computer science","score_opus":0.7466842752331906,"score_gpt":0.6363099774928298,"score_spread":0.11037429774036078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805889081","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":[0.9484191,0.00430551,0.03086284,0.0023941325,0.003945139,0.00015960485,0.00003941098,0.000028420676,0.009845856],"genre_scores_gemma":[0.9936849,0.00031345492,0.0040532164,0.00028176125,0.0002875121,0.000110295136,0.000008017132,0.000006657348,0.0012541959],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980715,0.0001575376,0.00057654904,0.0003763257,0.0006560184,0.00016205877],"domain_scores_gemma":[0.9749301,0.01952848,0.00055151456,0.00018227684,0.004750681,0.000056928387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015927929,0.00012455863,0.00033728537,0.0009600599,0.00027200507,0.000091447,0.00030203853,0.000041034134,0.0001783147],"category_scores_gemma":[0.049808376,0.000099832076,0.00006123216,0.0010333009,0.00043992524,0.00039171946,0.00024241743,0.00007673392,0.000025554868],"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":[0.000048481248,0.0004898628,0.7104074,0.000015061492,0.0003937381,4.556321e-7,0.017303087,0.00009123665,0.000063121355,0.04380729,0.02693337,0.2004469],"study_design_scores_gemma":[0.00049789564,0.00027052758,0.2911304,0.00042378635,0.000072666444,0.000012762319,0.21711619,0.0037847213,0.0013426887,0.4814492,0.0036070312,0.00029215356],"about_ca_topic_score_codex":0.000040516676,"about_ca_topic_score_gemma":0.00001020892,"teacher_disagreement_score":0.4376419,"about_ca_system_score_codex":0.00007066362,"about_ca_system_score_gemma":0.00008349938,"threshold_uncertainty_score":0.9581955},"labels":[],"label_agreement":null},{"id":"W2806330276","doi":"10.1007/s11136-018-1898-0","title":"Procedures to develop a computerized adaptive test to assess patient-reported physical functioning","year":2018,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"Workers' Compensation Board – Alberta","keywords":"Computerized adaptive testing; Item response theory; Item bank; Metric (unit); Polytomous Rasch model; Test (biology); Quality of Life Research; Psychometrics; Measure (data warehouse); Confirmatory factor analysis; Computer science; Psychology; Statistics; Data mining; Machine learning; Clinical psychology; Structural equation modeling; Medicine; Mathematics; Public health; Operations management; Engineering","score_opus":0.8983227755453376,"score_gpt":0.631323527548639,"score_spread":0.2669992479966986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806330276","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":[0.9074364,0.000012753104,0.086762436,0.0014997636,0.00025613006,0.00052091497,0.000011408135,0.000054458433,0.003445782],"genre_scores_gemma":[0.89433277,5.896633e-7,0.10475056,0.0003048271,0.00033362958,0.000040974683,0.000001086262,0.00001077911,0.0002247832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902864,0.0028445045,0.0012581631,0.000837115,0.004148029,0.0006258037],"domain_scores_gemma":[0.70632416,0.26970357,0.0009982788,0.0019793175,0.01968226,0.0013124208],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030835774,0.0001496453,0.0006234253,0.0010523084,0.00042837736,0.00024685083,0.0009914432,0.00007424471,0.000114648436],"category_scores_gemma":[0.76955366,0.000111468915,0.000079824895,0.011315437,0.00031334566,0.00016541839,0.0009292818,0.00030404967,0.00025080246],"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":[0.002180007,0.0012313501,0.44806564,0.00009282275,0.00015641109,0.000012023782,0.01561615,0.00012924956,0.046356883,0.002778567,0.07253204,0.41084883],"study_design_scores_gemma":[0.00053403026,0.0024566224,0.97172755,0.00010642419,0.000003336925,0.0000038065089,0.0069863796,0.0014315791,0.003994123,0.008491257,0.003993563,0.00027130946],"about_ca_topic_score_codex":0.00045853245,"about_ca_topic_score_gemma":0.0000653537,"teacher_disagreement_score":0.73871785,"about_ca_system_score_codex":0.00007136331,"about_ca_system_score_gemma":0.00086886925,"threshold_uncertainty_score":0.99795854},"labels":[],"label_agreement":null},{"id":"W2806733544","doi":"10.1111/bjep.12230","title":"Construct validity of the Wechsler Intelligence Scale For Children – Fifth <scp>UK</scp> Edition: Exploratory and confirmatory factor analyses of the 16 primary and secondary subtests","year":2018,"lang":"en","type":"article","venue":"British Journal of Educational Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":44,"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":"Wechsler Adult Intelligence Scale; Wechsler Intelligence Scale for Children; Psychology; Wechsler Preschool and Primary Scale of Intelligence; Exploratory factor analysis; Construct validity; Confirmatory factor analysis; Intelligence quotient; Psychometrics; Developmental psychology; Clinical psychology; Statistics; Cognition; Structural equation modeling; Psychiatry","score_opus":0.3273250792765807,"score_gpt":0.4681939770483808,"score_spread":0.14086889777180006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806733544","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":[0.9904941,0.0026754914,0.0023175557,0.0006528571,0.0026592559,0.00017796908,0.0001643491,0.000001947978,0.0008565174],"genre_scores_gemma":[0.9938215,0.00021000167,0.004757482,0.00057587645,0.00056385325,0.0000041342896,0.0000020150064,0.0000067408096,0.000058402416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974493,0.0006362205,0.00096735253,0.00026885467,0.0005140762,0.00016423155],"domain_scores_gemma":[0.98248124,0.0145167215,0.0014569936,0.000296255,0.0011559931,0.000092825074],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026708846,0.00011128699,0.00039248803,0.00022290119,0.0002165794,0.00005949044,0.0007139971,0.000100787016,0.00032687667],"category_scores_gemma":[0.021126596,0.000075349875,0.00016130735,0.0006309549,0.0013940036,0.00020945702,0.00012012635,0.0002610319,9.618092e-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":[0.000022513732,0.00013508821,0.90496975,0.000020571426,0.00006426946,4.6212898e-7,0.00036749587,0.0000011722985,0.0016750585,0.00021791819,0.051937103,0.040588614],"study_design_scores_gemma":[0.00031733175,0.00013586634,0.95232743,0.00008242924,0.000025519545,0.0013021872,0.0004400145,0.000002061416,0.001854317,0.042505007,0.00096660026,0.000041221567],"about_ca_topic_score_codex":0.000015722891,"about_ca_topic_score_gemma":0.0000135810915,"teacher_disagreement_score":0.050970502,"about_ca_system_score_codex":0.0000189818,"about_ca_system_score_gemma":0.000396573,"threshold_uncertainty_score":0.9871189},"labels":[],"label_agreement":null},{"id":"W2811232920","doi":"10.1177/0272989x18776637","title":"Estimation of a Preference-Based Summary Score for the Patient-Reported Outcomes Measurement Information System: The PROMIS <sup>®</sup> -Preference (PROPr) Scoring System","year":2018,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institutes of Health; National Cancer Institute; Social Sciences and Humanities Research Council of Canada; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Riksbankens Jubileumsfond","keywords":"Patient-Reported Outcomes Measurement Information System; Preference; Quality of life (healthcare); Medicine; Applied psychology; Physical therapy; Psychology; Statistics; Psychometrics; Clinical psychology; Computerized adaptive testing; Mathematics","score_opus":0.4962130764892222,"score_gpt":0.4115047991206986,"score_spread":0.0847082773685236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811232920","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":[0.24227144,0.00012312867,0.7539767,0.0002486494,0.0011062952,0.0014384729,0.000011718025,0.00011060956,0.0007129926],"genre_scores_gemma":[0.96440214,0.0000026564983,0.035108503,0.00017201717,0.00011500944,0.0001760967,0.000003108422,0.000013269215,0.0000071864038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98797584,0.0007443507,0.0027510158,0.0005412316,0.0075272885,0.0004602872],"domain_scores_gemma":[0.9512224,0.042038865,0.0022747053,0.0016750629,0.0026037479,0.00018520639],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027672037,0.00028888395,0.00064665644,0.0005532342,0.0008138057,0.0004066258,0.0018731271,0.00020715094,0.0000797924],"category_scores_gemma":[0.26256475,0.00012858881,0.00024317353,0.0020525542,0.00028656996,0.00046839242,0.00039005812,0.00030969715,0.000030850264],"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":[0.000246273,0.00002632223,0.010259819,0.00015028493,0.000046136014,0.000002053033,0.0007493252,0.0046922145,0.0000062870704,0.0007295905,0.00097295974,0.9821187],"study_design_scores_gemma":[0.0010109851,0.00031627584,0.033711586,0.0034614622,0.00007808475,0.000022088585,0.0044419714,0.95405316,0.00015453086,0.0019530174,0.0006077415,0.0001891124],"about_ca_topic_score_codex":0.000048284543,"about_ca_topic_score_gemma":0.000009583979,"teacher_disagreement_score":0.9819296,"about_ca_system_score_codex":0.00023712085,"about_ca_system_score_gemma":0.000438075,"threshold_uncertainty_score":0.9590631},"labels":[],"label_agreement":null},{"id":"W2883355895","doi":"10.3102/1076998618787478","title":"An Information Matrix Test for the Collapsing of Categories Under the Partial Credit Model","year":2018,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"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":"Goodness of fit; Econometrics; Test statistic; Set (abstract data type); Statistic; Test (biology); Polytomous Rasch model; Computer science; Statistics; Data set; Ordinal data; Mathematics; Data mining; Statistical hypothesis testing; Item response theory; Psychometrics","score_opus":0.4011186254261651,"score_gpt":0.5242410804061896,"score_spread":0.12312245498002444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883355895","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":[0.37881464,0.00012531219,0.61678547,0.0026530102,0.0011838598,0.000119117925,0.00027593327,0.0000014804052,0.000041163603],"genre_scores_gemma":[0.8819512,0.000013979592,0.117407955,0.000074784686,0.00043513166,0.0000030610877,0.0000047129333,0.0000024145756,0.0001067224],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861485,0.000060846607,0.00063749775,0.00005933132,0.000530905,0.000096590906],"domain_scores_gemma":[0.98133343,0.01600912,0.0007910629,0.00012676837,0.0016866832,0.000052948504],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022830588,0.00006016031,0.00013188098,0.00010521112,0.00034029988,0.00020581254,0.00031678955,0.000028836388,0.00007550743],"category_scores_gemma":[0.009459394,0.000027972112,0.000034346634,0.00032348593,0.00026915254,0.00036579857,0.000024090397,0.00007930985,0.0000011748167],"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":[0.0005549354,0.0010758808,0.22047916,0.000035230543,0.000074422016,7.20317e-7,0.009509777,0.0114648715,0.0015004064,0.24520731,0.16602002,0.34407726],"study_design_scores_gemma":[0.00065831066,0.001702499,0.3072648,0.00002110649,0.00022986504,0.00012172928,0.014141835,0.1149724,0.00028669037,0.554245,0.0061782715,0.00017750611],"about_ca_topic_score_codex":0.000034468718,"about_ca_topic_score_gemma":0.000011216085,"teacher_disagreement_score":0.50313663,"about_ca_system_score_codex":0.00001734176,"about_ca_system_score_gemma":0.00030078753,"threshold_uncertainty_score":0.9988843},"labels":[],"label_agreement":null},{"id":"W2886534478","doi":"10.1186/s12913-018-3381-6","title":"The factor structure of the general health questionnaire (GHQ12) in Saudi Arabia","year":2018,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":63,"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 Northern British Columbia","funders":"Prince Sattam bin Abdulaziz University","keywords":"General Health Questionnaire; Exploratory factor analysis; Medicine; Population; Anxiety; Cross-sectional study; Clinical psychology; Psychometrics; Psychiatry; Environmental health","score_opus":0.4617434501061359,"score_gpt":0.5860727401693875,"score_spread":0.12432929006325161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886534478","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":[0.98829263,0.0035074465,0.00028547505,0.005776615,0.0010430561,0.000747992,0.00003594958,0.000021373718,0.00028945328],"genre_scores_gemma":[0.9947891,0.00028661874,0.0030225576,0.0011106967,0.00039664237,0.000010068223,0.0000010355676,0.000012502306,0.00037077346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9861639,0.007715038,0.001282155,0.0006069292,0.0031070982,0.0011248364],"domain_scores_gemma":[0.97492635,0.021281952,0.00071411114,0.0016379793,0.0011372026,0.00030242102],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.023961555,0.00014775453,0.00041901707,0.0005279577,0.0015417913,0.0002321797,0.0028665983,0.00011325909,0.000112062684],"category_scores_gemma":[0.017617894,0.00006900913,0.00008488445,0.006632288,0.00048528105,0.00014768074,0.00066911144,0.00072392565,0.000027324986],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068367845,0.000028677014,0.8824568,0.00020808575,0.0000038241146,2.758372e-7,0.0029056526,0.000037774695,0.00012512649,0.0009905363,0.0010567746,0.11211814],"study_design_scores_gemma":[0.00021624938,0.000235066,0.97124594,0.00019997591,2.5231137e-7,0.0000032712871,0.0019411565,0.0027472514,0.00008921546,0.016991492,0.006268951,0.000061173036],"about_ca_topic_score_codex":0.006978167,"about_ca_topic_score_gemma":0.028863568,"teacher_disagreement_score":0.11205697,"about_ca_system_score_codex":0.0002382976,"about_ca_system_score_gemma":0.001674044,"threshold_uncertainty_score":0.99975806},"labels":[],"label_agreement":null},{"id":"W2887118571","doi":"10.7202/1048912ar","title":"Une théorie des seuils psychométriques à double contrôle d’erreur – Partie III : les applications illustrées","year":2018,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Philosophy; Physics","score_opus":0.4890915348900396,"score_gpt":0.5261305867246465,"score_spread":0.03703905183460693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887118571","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":[0.17279483,0.0074547357,0.6837908,0.051027138,0.0072487174,0.0019872647,0.00005367899,0.00031959734,0.075323254],"genre_scores_gemma":[0.9206758,0.0011392618,0.050121747,0.00040613647,0.0020222166,0.0004410294,0.00010108751,0.000049885395,0.025042815],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98857147,0.00635993,0.001574284,0.001173856,0.0016184374,0.000702055],"domain_scores_gemma":[0.9768686,0.01745092,0.0011509595,0.0013093252,0.0029647846,0.00025536705],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045998815,0.0004443895,0.00059910485,0.00068893743,0.0011388316,0.0006561779,0.00093934423,0.00046523445,0.002689815],"category_scores_gemma":[0.025177266,0.0004028904,0.00021598992,0.0050359187,0.00084314286,0.0012004209,0.0001334587,0.0004419568,0.000764289],"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":[0.00012727543,0.00047909588,0.019532219,0.000051724775,0.00009563573,6.649023e-7,0.034621418,0.00041910546,0.00079733547,0.027110318,0.044929273,0.87183595],"study_design_scores_gemma":[0.0023900198,0.00044746886,0.25935128,0.00023053741,0.00023110809,0.000031081356,0.01099984,0.006396093,0.0026686073,0.3889942,0.32748127,0.0007785114],"about_ca_topic_score_codex":0.002035587,"about_ca_topic_score_gemma":0.0015118194,"teacher_disagreement_score":0.87105745,"about_ca_system_score_codex":0.0003855411,"about_ca_system_score_gemma":0.0010337111,"threshold_uncertainty_score":0.9998423},"labels":[],"label_agreement":null},{"id":"W2888226965","doi":"10.1177/0962280218795187","title":"Methods for shortening patient-reported outcome measures","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"Canadian Arthritis Network; Canadian Institutes of Health Research; Dr. Fooke Laboratorien","keywords":"Outcome (game theory); Observational study; Medicine; Patient-reported outcome; Clinical trial; Scale (ratio); Test (biology); Physical therapy; Computer science; Quality of life (healthcare); Nursing; Mathematics","score_opus":0.8985570285078743,"score_gpt":0.7640029906638991,"score_spread":0.13455403784397524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888226965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.0020928404,0.00035314896,0.97986263,0.0011691077,0.0017653868,0.0007323119,0.000020159545,0.00006865517,0.013935788],"genre_scores_gemma":[0.016873172,0.000021535663,0.9816599,0.00042004586,0.00042369694,0.00021467308,0.0000035403139,0.000036928603,0.00034654545],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94885397,0.036030002,0.0034519536,0.0018003222,0.007858512,0.0020052395],"domain_scores_gemma":[0.14406781,0.84874594,0.0004109763,0.0016308691,0.003645804,0.0014985864],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32825193,0.00028602633,0.001169978,0.0019171911,0.00053358544,0.00030291808,0.0021462305,0.0004716288,0.0049690767],"category_scores_gemma":[0.96920043,0.00019259013,0.00018062095,0.0066023236,0.0023593027,0.00014178432,0.00095781806,0.0018387709,0.00006134739],"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":[0.0001910056,0.00009392485,0.013021754,0.000015291651,0.000025751819,0.000065267675,0.00020132777,7.63793e-7,0.0004984044,0.015123013,0.003951239,0.96681225],"study_design_scores_gemma":[0.0008773163,0.0010505043,0.026300084,0.00006933623,0.000015545022,0.00004393475,0.0012549591,0.06631203,0.0011010166,0.7799944,0.122650385,0.00033048607],"about_ca_topic_score_codex":0.00015250932,"about_ca_topic_score_gemma":0.000031408283,"teacher_disagreement_score":0.96648175,"about_ca_system_score_codex":0.00015644051,"about_ca_system_score_gemma":0.0005487871,"threshold_uncertainty_score":0.9959405},"labels":[],"label_agreement":null},{"id":"W2889064949","doi":"10.3899/jrheum.180264","title":"Is Occam’s Razor Meaningful for Selecting Significant Outcome Items and to Narrow Down Question Numbers in a Psychometric Scale?","year":2018,"lang":"en","type":"letter","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Occam's razor; Medicine; occam; Scale (ratio); Outcome (game theory); Psychometrics; Clinical psychology; Statistics; Programming language; Computer science","score_opus":0.2795535393614303,"score_gpt":0.45715536899450365,"score_spread":0.17760182963307336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889064949","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":[0.69435555,0.0009040598,0.029600414,0.26989758,0.004278109,0.0006398824,0.000019937166,0.00002649681,0.00027795124],"genre_scores_gemma":[0.6807256,0.0006420743,0.11405822,0.20085175,0.0015362529,0.00005527082,0.000006126557,0.00019037987,0.0019343323],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99186414,0.0023685487,0.0030227448,0.0006246211,0.001326004,0.00079392066],"domain_scores_gemma":[0.93507624,0.059582066,0.0034594005,0.0006463902,0.0010713349,0.00016454775],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032093003,0.0004174143,0.0018178019,0.00448423,0.00027041146,0.00023330755,0.0019018349,0.0006969634,0.00010666265],"category_scores_gemma":[0.11912382,0.00024617222,0.0002972752,0.0048866183,0.00024547536,0.00019647476,0.00017861798,0.0018720806,0.000033326585],"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":[0.00021034121,0.000018433879,0.3786838,0.000053197273,0.000056333778,0.000008575484,0.0015289498,0.000019751045,0.00004421381,0.000011813455,0.6106992,0.0086654015],"study_design_scores_gemma":[0.006242123,0.0046197483,0.08631396,0.0017922181,0.00046975428,0.025306111,0.004427617,0.0017430721,0.00013824746,0.07490815,0.7917791,0.002259904],"about_ca_topic_score_codex":0.0003696552,"about_ca_topic_score_gemma":0.000081677485,"teacher_disagreement_score":0.29236984,"about_ca_system_score_codex":0.00013808675,"about_ca_system_score_gemma":0.00013857867,"threshold_uncertainty_score":0.99999905},"labels":[],"label_agreement":null},{"id":"W2890327729","doi":"10.1002/da.22841","title":"Shortening self-report mental health symptom measures through optimal test assembly methods: Development and validation of the Patient Health Questionnaire-Depression-4","year":2018,"lang":"en","type":"article","venue":"Depression and Anxiety","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"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 Health Centre; McGill University; University of Calgary; Concordia University; Hotchkiss Brain Institute; Jewish General Hospital","funders":"National Center for Research Resources; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; National Institute of Mental Health; Programme Grants for Applied Research; Health Research Council of New Zealand; Medical Research Council; National Institute on Disability and Rehabilitation Research; Agency for Healthcare Research and Quality; Canadian Arthritis Network; Health Resources and Services Administration; Centers for Disease Control and Prevention; Canadian Institutes of Health Research; National Heart, Lung, and Blood Institute; Ischemia Research and Education Foundation; National Institutes of Health; Robert Wood Johnson Foundation; Health Services Research and Development; Scleroderma Society of Ontario; University of Washington; Hunter Medical Research Institute; Jewish General Hospital; Alberta Health Services; University of Michigan; National Institute for Health and Care Research; Fonds de Recherche du Québec - Santé; Baylor College of Medicine; U.S. Department of Veterans Affairs; National Health and Medical Research Council; American Federation for Aging Research; Safe Work Australia; U.S. Department of Health and Human Services","keywords":"Patient Health Questionnaire; Cronbach's alpha; Clinical psychology; Confirmatory factor analysis; Test (biology); Medicine; Depression (economics); Reliability (semiconductor); Psychometrics; Mental health; Depressive symptoms; Psychology; Psychiatry; Structural equation modeling; Anxiety; Computer science; Machine learning","score_opus":0.16623035315597082,"score_gpt":0.4516214455416743,"score_spread":0.2853910923857035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890327729","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":[0.86206955,0.003550166,0.13117497,0.0011148864,0.00090984587,0.0005281557,0.0000095802125,0.0001089998,0.00053387164],"genre_scores_gemma":[0.7071412,0.00031801843,0.2920436,0.00038055077,0.00005489923,0.000012875187,0.0000035391097,0.000010986908,0.000034338038],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952379,0.0012797973,0.0012033414,0.00075219135,0.001177684,0.00034911744],"domain_scores_gemma":[0.99551165,0.00222548,0.0011961373,0.00053774734,0.00031918832,0.00020981937],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008775694,0.00022119925,0.00046296616,0.00014316113,0.0011427716,0.00014323652,0.00033277288,0.00009846728,0.000015250425],"category_scores_gemma":[0.009217454,0.00012483321,0.00007606647,0.00078926136,0.00016068832,0.0002863709,0.00051375077,0.00019301898,0.0000014398872],"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":[0.000014143505,0.000074283496,0.42503762,0.000015051696,0.000014899419,5.113739e-7,0.0041891094,0.00001135939,0.0007733301,0.000017332502,0.0019500722,0.56790227],"study_design_scores_gemma":[0.00075651944,0.00030493716,0.8731664,0.00082764786,0.000017107997,0.0004175477,0.0027594748,0.0036891953,0.06148881,0.00077353086,0.055399768,0.00039904955],"about_ca_topic_score_codex":0.000121883495,"about_ca_topic_score_gemma":0.000011562708,"teacher_disagreement_score":0.5675032,"about_ca_system_score_codex":0.00006501603,"about_ca_system_score_gemma":0.00026236166,"threshold_uncertainty_score":0.99912834},"labels":[],"label_agreement":null},{"id":"W2895969780","doi":"10.20982/tqmp.14.3.p180","title":"Impact of simple substitution methods for missing data on Classical test theory difficulty and discrimination","year":2018,"lang":"en","type":"article","venue":"The Quantitative Methods for Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval; Université TÉLUQ; Université de Montréal","funders":"","keywords":"Simple (philosophy); Substitution (logic); Test (biology); Substitution method; Computer science; Econometrics; Mathematics; Epistemology; Philosophy; Geology; Programming language","score_opus":0.7918287099739518,"score_gpt":0.7093568357431685,"score_spread":0.08247187423078328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895969780","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":[0.043838695,0.000474527,0.9521061,0.001090445,0.00078144093,0.0007310437,0.00022273912,0.00003060243,0.0007244094],"genre_scores_gemma":[0.07544844,0.000021482389,0.92404425,0.00016667355,0.00014862762,0.000041681014,0.000035835536,0.00001991016,0.000073092626],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98991334,0.007570091,0.0008841743,0.0009697993,0.0002484386,0.0004141692],"domain_scores_gemma":[0.65121627,0.34559363,0.0008705267,0.001472738,0.0007508744,0.00009595008],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055593777,0.00024671384,0.0006763492,0.000444433,0.00050219276,0.0000912427,0.0013238135,0.00015685277,0.00004644941],"category_scores_gemma":[0.43119645,0.00012856224,0.00021633928,0.0011899893,0.0015511735,0.00023364731,0.00021811802,0.00019386677,0.0000038358326],"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":[0.0009440537,0.00015694617,0.0009669172,0.0000109432085,0.000073896634,1.0314357e-7,0.0007287687,0.000004442422,0.03601898,0.09080126,0.0016363101,0.86865735],"study_design_scores_gemma":[0.0009727491,0.00392815,0.11560787,0.000021499485,0.00009518899,0.000012228347,0.0007547834,0.03635198,0.0019054711,0.83334315,0.006821003,0.00018593456],"about_ca_topic_score_codex":0.000012412796,"about_ca_topic_score_gemma":0.000004762265,"teacher_disagreement_score":0.86847144,"about_ca_system_score_codex":0.00003355595,"about_ca_system_score_gemma":0.000052690986,"threshold_uncertainty_score":0.9724649},"labels":[],"label_agreement":null},{"id":"W2896763700","doi":"10.1007/s11336-018-9639-4","title":"Optimal Scores: An Alternative to Parametric Item Response Theory and Sum Scores","year":2018,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"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":"Vetenskapsrådet","keywords":"Item response theory; Nonparametric statistics; Parametric statistics; Test theory; Mathematics; Statistics; Econometrics; Psychometrics; Classical test theory; Test (biology); Computer science","score_opus":0.3554798528631857,"score_gpt":0.49499468349719333,"score_spread":0.13951483063400766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896763700","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":[0.9363317,0.00095650775,0.05726595,0.00041282142,0.0020106116,0.00042839375,0.0000381209,0.00014300538,0.0024129164],"genre_scores_gemma":[0.9283056,0.000068019464,0.068743,0.00089084276,0.0006006051,0.000030060955,0.0000015353463,0.00003786016,0.0013224649],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99104846,0.0035527851,0.0010236888,0.0016327456,0.0019146778,0.00082762155],"domain_scores_gemma":[0.8328592,0.16302665,0.00051538314,0.0018208572,0.000930744,0.00084714283],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03639999,0.00038396814,0.0006766973,0.008647184,0.00044560115,0.00084262225,0.00196906,0.00016747868,0.0007237399],"category_scores_gemma":[0.50332975,0.00028002865,0.00014023142,0.023209544,0.0005536353,0.0006054035,0.0004385756,0.00032084592,0.00054209074],"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":[0.009223661,0.00032852407,0.3259622,0.000007850977,0.00009479896,0.000032368895,0.0028282767,0.00007772292,0.0014450549,0.0040948503,0.01079436,0.6451103],"study_design_scores_gemma":[0.001222978,0.0035114014,0.9312977,0.000052537187,0.00002154664,0.00005569799,0.0021765183,0.00086081185,0.0016953534,0.03680999,0.021675505,0.0006199535],"about_ca_topic_score_codex":0.000059462,"about_ca_topic_score_gemma":0.000011174455,"teacher_disagreement_score":0.64449036,"about_ca_system_score_codex":0.000069741865,"about_ca_system_score_gemma":0.00007097983,"threshold_uncertainty_score":0.9999652},"labels":[],"label_agreement":null},{"id":"W2899176712","doi":"10.1111/bjep.12254","title":"Significant predictors of mathematical literacy for top‐tiered countries/economies, Canada, and the United States on PISA 2012: Case for the sparse regression model","year":2018,"lang":"en","type":"article","venue":"British Journal of Educational Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"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":"Lasso (programming language); Literacy; Multilevel model; Covariate; Ranking (information retrieval); Imputation (statistics); Econometrics; Regression analysis; Regression; Statistics; Missing data; Geography; Computer science; Economics; Mathematics; Economic growth; Artificial intelligence","score_opus":0.2208634906861403,"score_gpt":0.4596055414950691,"score_spread":0.2387420508089288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899176712","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":[0.938729,0.0015228685,0.035450287,0.020932255,0.0021262204,0.000510979,0.0003834715,0.0000023006467,0.0003426441],"genre_scores_gemma":[0.97356063,0.00045917314,0.021330927,0.002807822,0.0008067992,0.0000442428,0.000011108253,0.000014604319,0.0009646902],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978753,0.00030501428,0.0010376633,0.0002198628,0.0003582423,0.00020396448],"domain_scores_gemma":[0.93057853,0.066671796,0.0009857373,0.00025620713,0.0014109577,0.000096759606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005887493,0.00010399077,0.00035805383,0.0002187591,0.00032115716,0.00012973332,0.00051476137,0.000062241576,0.00019655094],"category_scores_gemma":[0.037029944,0.0000578478,0.000095654636,0.000322106,0.00063226046,0.00013600344,0.00003039147,0.00015648837,7.6732834e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026310924,0.00029086505,0.0056867576,0.00003499569,0.00020748189,0.000020970632,0.001365393,0.0010585513,0.0000147615565,0.019973876,0.9296721,0.039043106],"study_design_scores_gemma":[0.0065119155,0.0010899955,0.048362963,0.0003698587,0.00015569368,0.009896654,0.0028600239,0.045820322,0.000044739823,0.80368775,0.08090523,0.0002948457],"about_ca_topic_score_codex":0.004177053,"about_ca_topic_score_gemma":0.0027596503,"teacher_disagreement_score":0.8487669,"about_ca_system_score_codex":0.000037690814,"about_ca_system_score_gemma":0.0004851273,"threshold_uncertainty_score":0.97108155},"labels":[],"label_agreement":null},{"id":"W2902135892","doi":"10.1027/1614-2241/a000156","title":"Examining Validity Evidence of Self-Report Measures Using Differential Item Functioning","year":2018,"lang":"en","type":"article","venue":"Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"Centre for Advancing Health Outcomes; Learning Partnership; University of British Columbia; Providence Health Care Research Institute; Providence Health Care","funders":"","keywords":"Differential item functioning; Item response theory; Psychology; Nonparametric statistics; Ordinal data; Scale (ratio); Ordinal Scale; Multilevel model; Logistic regression; Latent variable; Statistics; Econometrics; Psychometrics; Clinical psychology; Mathematics","score_opus":0.9393714709572591,"score_gpt":0.5778324970126306,"score_spread":0.36153897394462853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902135892","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":[0.5052119,0.0001647395,0.49109304,0.000028901826,0.0026788383,0.000071768845,7.065198e-7,0.00006462595,0.00068549445],"genre_scores_gemma":[0.55630916,0.000007816942,0.44303918,0.000034272427,0.00048411754,0.000003038115,2.8301392e-7,0.000010253796,0.000111886104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9859024,0.009768643,0.0015378471,0.00095642137,0.0013218446,0.00051284296],"domain_scores_gemma":[0.775876,0.21885365,0.0019134328,0.0015061462,0.0016721619,0.00017862978],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051561493,0.0002279295,0.0009014422,0.0008195868,0.00034800218,0.00009529106,0.000900591,0.00022716983,0.0006947915],"category_scores_gemma":[0.50437605,0.00017187302,0.00017548003,0.002282435,0.00039971116,0.0002990212,0.00045422814,0.00027581476,0.000023959481],"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":[0.0001911295,0.000058640944,0.7453701,0.000023869135,0.00009969637,0.00004224344,0.0010170942,0.00009423086,0.13643691,0.00030077057,0.00039637927,0.115968965],"study_design_scores_gemma":[0.00069440185,0.0013809922,0.8828159,0.00019670928,0.0002653912,0.0012744006,0.0019938473,0.010935729,0.059949297,0.037186414,0.0026600305,0.0006468682],"about_ca_topic_score_codex":0.00018582692,"about_ca_topic_score_gemma":0.000013928266,"teacher_disagreement_score":0.45281455,"about_ca_system_score_codex":0.0000569484,"about_ca_system_score_gemma":0.00013976329,"threshold_uncertainty_score":0.97661704},"labels":[],"label_agreement":null},{"id":"W2905628759","doi":"10.20982/tqmp.14.4.p242","title":"A review of effect sizes and their confidence intervals, Part I: The Cohen's d family","year":2018,"lang":"en","type":"review","venue":"The Quantitative Methods for Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":365,"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":"Confidence interval; Statistics; Mathematics; Psychology","score_opus":0.7976858719762024,"score_gpt":0.6853861465175152,"score_spread":0.11229972545868727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905628759","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003359402,0.68992853,0.30423203,0.00052900077,0.0019634916,0.0021993187,0.00008983632,0.000023167035,0.001031252],"genre_scores_gemma":[4.2658436e-7,0.83752924,0.16000108,0.0016383423,0.00014334971,0.0004974744,0.00000562866,0.000040039842,0.00014442594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9504936,0.044486135,0.0027264524,0.0013261543,0.0004058858,0.00056176924],"domain_scores_gemma":[0.5077233,0.48556197,0.0035141916,0.0023151548,0.0007986527,0.00008678369],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12838781,0.0007022314,0.0049248645,0.00044285186,0.0003443943,0.000098564924,0.0037294894,0.00031096954,0.000104758896],"category_scores_gemma":[0.33510315,0.00025213702,0.0013361082,0.002811679,0.0026884822,0.000087758955,0.0005182004,0.00067732204,0.00004373954],"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":[0.000050150826,0.000017444387,0.0000022545169,0.008573228,0.00029065573,3.4682242e-7,0.00025816695,1.500205e-8,0.0000052878554,0.005044318,0.02435795,0.9614002],"study_design_scores_gemma":[0.00019257361,0.001356764,0.000019972696,0.024027996,0.00049053243,0.00006980604,0.00029774618,0.000017248754,0.000005021177,0.07495292,0.898321,0.000248453],"about_ca_topic_score_codex":0.000012597176,"about_ca_topic_score_gemma":0.0000015280332,"teacher_disagreement_score":0.9611517,"about_ca_system_score_codex":0.000019375555,"about_ca_system_score_gemma":0.000110474626,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W2907558524","doi":"10.2196/10880","title":"AO Patient Outcomes Center: Design, Implementation, and Evaluation of a Software Application for the Collection of Patient-Reported Outcome Measures in Orthopedic Outpatient Clinics","year":2018,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; AO Foundation; National Cancer Institute; AO North America","keywords":"Usability; Medicine; Orthopedic surgery; Test (biology); Computerized adaptive testing; Data collection; Medical physics; Medical emergency; Computer science; Human–computer interaction; Psychometrics; Surgery","score_opus":0.7026752885714471,"score_gpt":0.6222257822168674,"score_spread":0.0804495063545797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907558524","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":[0.9016473,0.00011469852,0.09395622,0.00017503487,0.00021767576,0.0037847224,0.000034391865,0.000009979409,0.000059944072],"genre_scores_gemma":[0.99415815,0.000024155861,0.004712078,0.000024116207,0.000012942821,0.0010435743,0.00000961026,0.000008156501,0.000007206637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99177444,0.002367883,0.001962323,0.00034630427,0.0032350144,0.0003140342],"domain_scores_gemma":[0.96235317,0.029374175,0.001355787,0.0005000557,0.006355135,0.00006167915],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034146085,0.00012192173,0.00035644413,0.0009987752,0.00033688053,0.00004957724,0.00031768827,0.00007787268,0.0000324209],"category_scores_gemma":[0.053353727,0.0000726535,0.000090280606,0.0026918792,0.00028926303,0.00028300314,0.00018818474,0.00017875609,0.0000022667725],"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":[0.00014688536,0.00012711986,0.53027517,0.00001335876,0.000024146417,3.582289e-8,0.0074686166,0.00006317576,0.000025218647,0.000037450005,0.0004776865,0.46134117],"study_design_scores_gemma":[0.0023069442,0.0025840218,0.935042,0.000033622455,0.000023179928,0.0000018848843,0.029935645,0.01800242,0.0012823907,0.009580611,0.001090798,0.00011646677],"about_ca_topic_score_codex":0.0001587483,"about_ca_topic_score_gemma":0.00016285056,"teacher_disagreement_score":0.4612247,"about_ca_system_score_codex":0.00015387339,"about_ca_system_score_gemma":0.00022048713,"threshold_uncertainty_score":0.9945499},"labels":[],"label_agreement":null},{"id":"W2911244996","doi":"10.1016/j.jcomdis.2019.01.002","title":"Data-driven item selection for the Shirts and Shoes Test","year":2019,"lang":"en","type":"article","venue":"Journal of Communication Disorders","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ambrose University; University of Connecticut","keywords":"Item response theory; Psychology; Test (biology); Item analysis; Reliability (semiconductor); Item bank; Differential item functioning; Classical test theory; Population; Selection (genetic algorithm); Psychometrics; Statistics; Applied psychology; Social psychology; Developmental psychology; Artificial intelligence; Computer science; Mathematics; Demography","score_opus":0.4113550839938006,"score_gpt":0.48312622553802914,"score_spread":0.07177114154422853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911244996","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":[0.80973166,0.013611022,0.13147734,0.037561916,0.0010544168,0.0009003115,0.000036681362,0.00003607843,0.0055905683],"genre_scores_gemma":[0.9734615,0.0017798204,0.024380911,0.00014357673,0.000034436787,0.0000023827718,0.0000019765337,0.000005288138,0.00019008819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985699,0.00029418286,0.0005277216,0.00011970413,0.0003956265,0.00009283567],"domain_scores_gemma":[0.9113795,0.086407304,0.00084647513,0.0009750472,0.00035529744,0.00003633186],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006921158,0.000060150433,0.0001732024,0.00019478415,0.00020907016,0.00018679789,0.0018262048,0.000035100427,0.00006097751],"category_scores_gemma":[0.057342548,0.000033141492,0.000054849854,0.0006202444,0.000067146924,0.0004562301,0.00025113134,0.00017984836,0.000004565802],"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":[0.00004636789,0.00006244665,0.5720531,0.0000046280493,0.000039346483,2.6314188e-8,0.00031789968,0.0011608391,0.00014739539,0.00062113936,0.017999303,0.40754753],"study_design_scores_gemma":[0.0008424198,0.0002832951,0.53991616,0.00003590767,0.00003995701,0.000028294602,0.0042911377,0.117720544,0.000013149633,0.034547642,0.3021664,0.000115077935],"about_ca_topic_score_codex":0.000011251615,"about_ca_topic_score_gemma":0.00007421448,"teacher_disagreement_score":0.40743244,"about_ca_system_score_codex":0.000011550641,"about_ca_system_score_gemma":0.00003878525,"threshold_uncertainty_score":0.9505979},"labels":[],"label_agreement":null},{"id":"W2912835846","doi":"10.1002/0470013192.bsa654","title":"Structural Equation Modeling and Test Validation","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistics in Behavioral Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structural equation modeling; Confirmatory factor analysis; Construct validity; Context (archaeology); Psychology; Predictive validity; Test validity; Test (biology); Scale (ratio); Econometrics; Psychometrics; Computer science; Statistics; Mathematics; Clinical psychology","score_opus":0.3269988878342432,"score_gpt":0.47317956147027695,"score_spread":0.14618067363603376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912835846","genre_codex":"other","genre_gemma":"methods","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":[0.29302216,0.0012241871,0.22390087,0.00010831717,0.0039947885,0.0013025998,0.0014225388,0.00017616489,0.4748484],"genre_scores_gemma":[0.2669636,0.0007701161,0.68679905,0.000012882241,0.00027054086,0.000013653192,0.000027855733,0.00009479241,0.04504752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962102,0.00010709551,0.00084185036,0.0006936348,0.0018190818,0.00032813713],"domain_scores_gemma":[0.9933879,0.0051210593,0.0006994988,0.0004350536,0.00024428417,0.00011224299],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003894491,0.00020134081,0.00039873735,0.0015091611,0.00009557038,0.00014082984,0.0008445342,0.00013978416,0.0008158983],"category_scores_gemma":[0.0421925,0.00016337275,0.00002310169,0.0022720092,0.0005147949,0.0002568171,0.00022873365,0.0002240008,0.0000113157275],"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":[0.000005083441,0.00007046056,0.23942266,0.000019921867,0.0000013828079,0.000008349834,0.00056545547,0.0012393052,0.00012623791,0.0030610838,0.0070635257,0.74841654],"study_design_scores_gemma":[0.0016664059,0.00075282715,0.2930183,0.0006477113,0.00012998983,0.00003224601,0.0022816642,0.5893663,0.00011232128,0.08982912,0.019841652,0.0023214233],"about_ca_topic_score_codex":0.00083545083,"about_ca_topic_score_gemma":0.0001975148,"teacher_disagreement_score":0.7460951,"about_ca_system_score_codex":0.00007323593,"about_ca_system_score_gemma":0.00017425514,"threshold_uncertainty_score":0.9658755},"labels":[],"label_agreement":null},{"id":"W2912880345","doi":"10.1177/0013164419829855","title":"Item Response Tree Models to Investigate Acquiescence and Extreme Response Styles in Likert-Type Rating Scales","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Acquiescence; Psychology; Likert scale; Rating scale; Item response theory; Social psychology; Explanatory model; Scale (ratio); Psychometrics; Statistics; Developmental psychology; Mathematics","score_opus":0.7658315465227954,"score_gpt":0.4754891438004715,"score_spread":0.29034240272232387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912880345","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":[0.9806734,0.001268786,0.00048745607,0.015228469,0.0005318762,0.00037954934,0.0000036968634,0.000023802188,0.0014029617],"genre_scores_gemma":[0.97766954,0.00003598116,0.020057576,0.0014590727,0.00007116534,0.000034373865,7.394071e-7,0.0000075883386,0.00066395395],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99459946,0.0020998768,0.00070328,0.00092365936,0.0013216933,0.00035203845],"domain_scores_gemma":[0.9777385,0.020907745,0.00018337913,0.00044445347,0.00041189004,0.0003140045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020367742,0.00020834063,0.00034326,0.0005136818,0.00014896784,0.00020200684,0.00043640914,0.00010592473,0.00019676384],"category_scores_gemma":[0.07539219,0.00014229825,0.000041515777,0.0015436438,0.00014544431,0.00021254118,0.00014607381,0.00020493782,0.000071364244],"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":[0.012252368,0.0007334612,0.7199343,0.000022084116,0.000024270359,0.000009036084,0.002987203,0.0004888008,0.12055857,0.0044619157,0.0080885375,0.13043948],"study_design_scores_gemma":[0.00042959917,0.00052879023,0.95204425,0.000092418275,0.000002373401,0.000017339034,0.001022192,0.0004757549,0.000088696965,0.04367717,0.0014187994,0.00020264281],"about_ca_topic_score_codex":0.000017110107,"about_ca_topic_score_gemma":0.000018075165,"teacher_disagreement_score":0.23210993,"about_ca_system_score_codex":0.00007438178,"about_ca_system_score_gemma":0.00009923058,"threshold_uncertainty_score":0.9323962},"labels":[],"label_agreement":null},{"id":"W2914645669","doi":"10.1080/00949655.2019.1577858","title":"A comparison of the type I error rates of three assessment methods for indirect effects","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Statistics; Mathematics; Type I and type II errors; Sobel test; Sample size determination; Monte Carlo method; Econometrics; Statistical hypothesis testing; Standard error; Mediation; Variable (mathematics)","score_opus":0.5210559970260837,"score_gpt":0.6338973903667614,"score_spread":0.11284139334067766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914645669","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":[0.3745585,0.00007081535,0.6247724,0.000039320534,0.00035258912,0.00014481903,0.0000028221561,0.0000012410177,0.00005745526],"genre_scores_gemma":[0.6019065,6.499571e-7,0.39806458,0.00001036003,0.000010918846,2.5489024e-7,5.960513e-7,0.0000019737658,0.000004201107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780977,0.000676129,0.0008700955,0.00010109063,0.00047389496,0.000068995054],"domain_scores_gemma":[0.91660964,0.08128665,0.0011632855,0.00007827015,0.0008281701,0.00003397721],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047644405,0.000060433027,0.00042698794,0.00019357607,0.000045892648,0.000033796252,0.00013433995,0.00003999163,0.000022191669],"category_scores_gemma":[0.03306309,0.00003391234,0.00006405059,0.00055479066,0.00004982548,0.000084534746,0.000031852447,0.00010091465,3.6336965e-7],"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":[0.00015104185,0.00006335907,0.3259609,0.00006425006,0.000032017837,1.1984152e-7,0.00021167712,0.27568477,0.001146886,0.002492205,0.0000772004,0.3941156],"study_design_scores_gemma":[0.0003369031,0.00035705662,0.41996014,0.000022410175,0.000017457522,7.129405e-7,0.000072253,0.526204,0.00019646375,0.052778218,0.000033295855,0.000021077414],"about_ca_topic_score_codex":0.0000018429355,"about_ca_topic_score_gemma":5.2844683e-7,"teacher_disagreement_score":0.3940945,"about_ca_system_score_codex":0.000014347606,"about_ca_system_score_gemma":0.000054620756,"threshold_uncertainty_score":0.9750818},"labels":[],"label_agreement":null},{"id":"W2920811067","doi":"10.1111/jedm.12205","title":"Modeling Response Styles in Cross‐Country Self‐Reports: An Application of a Multilevel Multidimensional Nominal Response Model","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"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":"Comparability; Psychology; Multilevel model; Structural equation modeling; Econometrics; Social psychology; Cross-cultural; Computer science; Statistics; Mathematics; Political science","score_opus":0.35009938784928696,"score_gpt":0.4756613456886337,"score_spread":0.12556195783934676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920811067","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":[0.96532524,0.0003350355,0.032799017,0.00066940626,0.0005237919,0.00026770603,0.000008876688,0.0000050118915,0.00006589627],"genre_scores_gemma":[0.8661616,0.000003777808,0.13358127,0.00007178998,0.00009883042,0.000011758476,0.0000012270335,0.000011832301,0.00005790061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917957,0.0013652701,0.002431893,0.00045007328,0.0036973439,0.00025971507],"domain_scores_gemma":[0.9824462,0.011022172,0.0017489906,0.00061004487,0.0039848983,0.00018772545],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05578407,0.00018072293,0.00047675113,0.0012839555,0.00008681726,0.00007395583,0.00053969305,0.00010524938,0.00008853376],"category_scores_gemma":[0.07638445,0.00014131359,0.00015217128,0.0008572129,0.00004928675,0.00058881845,0.00006782785,0.00029561095,0.000009865677],"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":[0.0068257265,0.0010838874,0.18047534,0.000013995444,0.00003551924,0.000003553484,0.0008742341,0.6942161,0.11379981,0.0002955133,0.000094665134,0.0022816923],"study_design_scores_gemma":[0.00077282265,0.00020452579,0.4788581,0.00008810813,0.000012193091,0.00009770285,0.00071105803,0.5131901,0.0004598898,0.0053445483,0.00012921756,0.00013172675],"about_ca_topic_score_codex":0.00005891902,"about_ca_topic_score_gemma":0.000011961621,"teacher_disagreement_score":0.29838276,"about_ca_system_score_codex":0.0005170518,"about_ca_system_score_gemma":0.002325693,"threshold_uncertainty_score":0.972269},"labels":[],"label_agreement":null},{"id":"W2921135034","doi":"10.1111/bjep.12271","title":"The risk–return trade‐off: Performance assessments and cognitive validation of inferences","year":2019,"lang":"en","type":"article","venue":"British Journal of Educational Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Advanced Education; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; American Institute of Certified Public Accountants","keywords":"Cognition; Psychology; Process (computing); Cognitive interview; Argument (complex analysis); Test (biology); Cognitive psychology; Task (project management); Applied psychology; Think aloud protocol; Cognitive test; Empirical evidence; Social psychology; Computer science; Usability","score_opus":0.24871111791843975,"score_gpt":0.5083836971060273,"score_spread":0.2596725791875875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921135034","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":[0.9881376,0.0032208858,0.00040592405,0.0013790147,0.0017889732,0.00009102002,0.000012561424,0.0000014283844,0.0049626012],"genre_scores_gemma":[0.99510485,0.0022891823,0.0020987517,0.00012570176,0.00014704687,0.0000021448006,0.0000018228525,0.0000039838365,0.00022652971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99745494,0.00070538,0.0008586392,0.0001983902,0.0006338668,0.00014876979],"domain_scores_gemma":[0.9712426,0.026482917,0.0014822385,0.0001304122,0.0005980413,0.00006377848],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062838597,0.00007389243,0.00025209252,0.00023400573,0.00016737173,0.00014204494,0.000469804,0.00006373532,0.0004333173],"category_scores_gemma":[0.026885591,0.00005323796,0.00007164826,0.0006167457,0.0002074879,0.00032190653,0.000034220026,0.0003041873,0.000010339],"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":[0.00003799229,0.000052986972,0.6523326,0.000001957086,0.00002885275,4.755571e-7,0.000056852634,0.0000058859023,0.000039391274,0.00009126294,0.0014327888,0.34591895],"study_design_scores_gemma":[0.00046852697,0.0003090209,0.97197133,0.000073928735,0.000017153594,0.0006057375,0.00063151796,0.000057498084,0.000042455027,0.024460206,0.0013060801,0.000056542518],"about_ca_topic_score_codex":0.000011103501,"about_ca_topic_score_gemma":0.0000034064028,"teacher_disagreement_score":0.34586242,"about_ca_system_score_codex":0.000010053373,"about_ca_system_score_gemma":0.00016160325,"threshold_uncertainty_score":0.9813114},"labels":[],"label_agreement":null},{"id":"W2921710211","doi":"10.1186/s12874-019-0680-5","title":"A comparison of the polytomous Rasch analysis output of RUMM2030 and R (ltm/eRm/TAM/lordif)","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St Joseph's Health Centre; Western University","funders":"Canadian Institutes of Health Research","keywords":"Rasch model; Polytomous Rasch model; Likert scale; Computer science; Differential item functioning; Item response theory; Rating scale; Reliability (semiconductor); Consistency (knowledge bases); Ordinal data; Software; Statistics; Scale (ratio); Psychometrics; Psychology; Econometrics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.9064755610915639,"score_gpt":0.6992995594836466,"score_spread":0.20717600160791727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921710211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.8439105,0.001625037,0.1483466,0.001147522,0.000554735,0.00035173362,0.00000852014,0.000014883495,0.0040404326],"genre_scores_gemma":[0.894804,0.00008831879,0.103385985,0.00008189271,0.00009253022,0.00001145903,0.0000010993678,0.000010783993,0.0015239156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.944759,0.04443556,0.0019891,0.0009617411,0.006986684,0.0008678876],"domain_scores_gemma":[0.40404478,0.59136593,0.0008780507,0.0019812381,0.0012242224,0.00050577306],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16925737,0.00018647769,0.0019843774,0.0022397474,0.00016292694,0.000045722478,0.002913674,0.0004334073,0.001955254],"category_scores_gemma":[0.7406399,0.00010169143,0.0004651567,0.010617425,0.0018997674,0.000074537755,0.0018681247,0.0011338054,0.00004026009],"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":[0.00016665134,0.00009399831,0.8534713,0.000051772193,0.00015074943,0.0000022903885,0.00044935336,0.0000618959,0.0010979071,0.0019796074,0.0012619828,0.14121252],"study_design_scores_gemma":[0.0009650953,0.00053579774,0.94951826,0.000062447405,0.00011242405,0.000018386605,0.0045271064,0.015800426,0.0023493129,0.022811713,0.0031397108,0.00015934369],"about_ca_topic_score_codex":0.0006328039,"about_ca_topic_score_gemma":0.00027907937,"teacher_disagreement_score":0.5713825,"about_ca_system_score_codex":0.000032259555,"about_ca_system_score_gemma":0.0006497951,"threshold_uncertainty_score":0.9989571},"labels":[],"label_agreement":null},{"id":"W2942931432","doi":"10.1097/acm.0000000000002782","title":"Implicit Bias and the Feedback Paradox: Exploring How Health Professionals Engage With Feedback While Questioning Its Credibility","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Registered Nurses' Association of Ontario; Western University","funders":"Children's Health Foundation; Associated Medical Services; London Health Sciences Centre","keywords":"Credibility; Psychology; Implicit-association test; Conversation; Grounded theory; Social psychology; Identity (music); Mental health; Implicit attitude; Applied psychology; Qualitative research; Psychotherapist","score_opus":0.6390951318775491,"score_gpt":0.47882089678902195,"score_spread":0.16027423508852712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942931432","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":[0.90667033,0.0071224663,0.0030987638,0.07899968,0.0011193221,0.0010899128,0.0000052946907,0.00010198857,0.0017922063],"genre_scores_gemma":[0.9904128,0.0012434871,0.0014753337,0.0035978216,0.0005761661,0.00007609713,0.000003844832,0.000022007765,0.0025924502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924869,0.002812727,0.0011107909,0.0009931832,0.0019449886,0.0006514344],"domain_scores_gemma":[0.9370509,0.060351048,0.001048611,0.00089349435,0.00032270796,0.00033327108],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046571024,0.00030477272,0.0010368085,0.00035867546,0.0005287905,0.00007726558,0.0009964829,0.00017691968,0.0003121934],"category_scores_gemma":[0.10834071,0.00013570405,0.00005615989,0.0021956977,0.00045738972,0.00060571905,0.0003396811,0.0016575912,0.00005981357],"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":[0.0011018565,0.00003947855,0.69823945,0.00030262308,0.00012664545,0.000010470269,0.033631127,0.00016488503,0.0011214112,0.019702796,0.071645364,0.17391388],"study_design_scores_gemma":[0.014126346,0.0014846891,0.78350407,0.0041058776,0.00008325492,0.00032731358,0.10599756,0.0066246395,0.00042655182,0.047575027,0.03480447,0.00094021886],"about_ca_topic_score_codex":0.0001073148,"about_ca_topic_score_gemma":0.000004645771,"teacher_disagreement_score":0.17297366,"about_ca_system_score_codex":0.00006515944,"about_ca_system_score_gemma":0.00016162907,"threshold_uncertainty_score":0.9817558},"labels":[],"label_agreement":null},{"id":"W2945378006","doi":"10.21449/ijate.515085","title":"Explanatory Item Response Models for Polytomous Item Responses","year":2019,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of Alberta","funders":"","keywords":"Polytomous Rasch model; Item response theory; Rating scale; Psychology; Econometrics; Psychometrics; Scale (ratio); Statistics; Clinical psychology; Mathematics; Developmental psychology","score_opus":0.41021247149057005,"score_gpt":0.560403145971193,"score_spread":0.15019067448062295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945378006","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":[0.9596146,0.00028887947,0.025928121,0.0032080098,0.008268993,0.00025453675,0.0000193284,0.000009500668,0.0024080295],"genre_scores_gemma":[0.9488794,0.000049375307,0.048786163,0.0004271049,0.00035036705,0.000018747753,0.000004207101,0.0000111640675,0.0014734351],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957319,0.0008536553,0.0012945876,0.00027897858,0.0016556674,0.0001852478],"domain_scores_gemma":[0.9390366,0.057617124,0.001243131,0.00029896514,0.0017210912,0.00008308731],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01428318,0.00012532585,0.00030732062,0.0019452102,0.000039047263,0.00038917054,0.0012442077,0.00008060416,0.00017023402],"category_scores_gemma":[0.060425255,0.00009976969,0.00017186013,0.00060243125,0.00002597383,0.0013111933,0.00007715668,0.00023740307,0.000012485327],"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":[0.0059539992,0.0008894622,0.42506132,0.00001200646,0.00012957538,0.000022869659,0.0011532597,0.005783636,0.007133816,0.013196617,0.013670032,0.5269934],"study_design_scores_gemma":[0.0017316401,0.0005559199,0.8536826,0.00022610836,0.000013258382,0.00019269658,0.0077574034,0.010863916,0.0006158293,0.09712924,0.026983475,0.00024793425],"about_ca_topic_score_codex":0.000009939391,"about_ca_topic_score_gemma":0.0000020660086,"teacher_disagreement_score":0.5267455,"about_ca_system_score_codex":0.0005061216,"about_ca_system_score_gemma":0.001361358,"threshold_uncertainty_score":0.9474892},"labels":[],"label_agreement":null},{"id":"W2946534982","doi":"10.1007/s12630-019-01405-9","title":"Sample size calculations for educational interventions: principles and methods","year":2019,"lang":"en","type":"editorial","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Ottawa Hospital; Impact; University of Ottawa","funders":"","keywords":"Sample size determination; Psychological intervention; Sample (material); Psychology; Statistics; Mathematics; Physics; Thermodynamics","score_opus":0.1941156249487501,"score_gpt":0.44047155312832853,"score_spread":0.24635592817957844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946534982","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024741001,0.019337159,0.023106609,0.016847964,0.91295856,0.001326882,0.00076691684,0.000021652557,0.0008932757],"genre_scores_gemma":[0.00393585,0.00046031643,0.45409748,0.000111167814,0.5299871,0.000031868985,0.000077400015,0.00020559477,0.011093249],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99173707,0.001458262,0.0032723648,0.00067997776,0.0017846555,0.0010676881],"domain_scores_gemma":[0.5973761,0.3698701,0.011154696,0.0017045536,0.013568578,0.0063259676],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.027284777,0.00057417934,0.0016944848,0.0032026684,0.0010573564,0.0017767227,0.002377737,0.0008724469,0.0007305806],"category_scores_gemma":[0.48092228,0.00046583705,0.0012098913,0.0015092057,0.00035645138,0.00065986026,0.00004603145,0.0018808102,0.00001073434],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007226704,0.00003388583,0.0024919326,0.00012737373,0.00024054664,0.005491006,0.0005376583,0.0003790037,0.0000019006053,0.0014153568,0.9663881,0.02282095],"study_design_scores_gemma":[0.00067770435,0.0006683695,0.003795987,0.000581535,0.00024540842,0.18985924,0.00055914395,0.00012348355,0.0000012660286,0.029965982,0.77304536,0.00047652956],"about_ca_topic_score_codex":0.0061952737,"about_ca_topic_score_gemma":0.008759,"teacher_disagreement_score":0.4536375,"about_ca_system_score_codex":0.0011097582,"about_ca_system_score_gemma":0.01764382,"threshold_uncertainty_score":0.99977934},"labels":[],"label_agreement":null},{"id":"W2947494553","doi":"10.1111/jebm.12343","title":"Evaluating people's ability to assess treatment claims: Validating a test in Mandarin from Claim Evaluation Tools database","year":2019,"lang":"en","type":"article","venue":"Journal of Evidence-Based Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision 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":false,"ca_institutions":"McMaster University; Hamilton Health Sciences; Impact","funders":"Ministry of Science and Technology of the People's Republic of China","keywords":"Mandarin Chinese; Test (biology); Database; Computer science; Psychology; Linguistics","score_opus":0.9102972500589558,"score_gpt":0.6288915867040393,"score_spread":0.28140566335491646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947494553","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":[0.9718843,0.0011023126,0.016203426,0.007995904,0.0014744992,0.0010015434,0.000021611246,0.000015062252,0.00030133678],"genre_scores_gemma":[0.9336103,0.0000689669,0.06496891,0.00060853857,0.0006462821,0.000027849776,0.000009195249,0.000014816835,0.000045128378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98650205,0.0034891495,0.0030779722,0.0008008554,0.005674278,0.000455705],"domain_scores_gemma":[0.70325613,0.2884846,0.0030136716,0.0015788499,0.0031751385,0.00049162295],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.091621354,0.00031180336,0.0012788471,0.0014332952,0.00012188428,0.00023885896,0.0010638079,0.00011235818,0.0031343112],"category_scores_gemma":[0.6151812,0.00017170301,0.0001939765,0.0036337494,0.00007639664,0.0012480809,0.0001352852,0.0004733135,0.00005403132],"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":[0.00035026902,0.00016238035,0.6041794,0.000023045282,0.000016046455,0.000022239368,0.00064054807,0.008866451,0.028929505,0.0000061478227,0.00040382496,0.35640016],"study_design_scores_gemma":[0.0068546142,0.006841865,0.8889723,0.005872721,0.00024542608,0.000033298642,0.0045773047,0.079286836,0.002605677,0.003968144,0.00040395293,0.0003378676],"about_ca_topic_score_codex":0.0007511951,"about_ca_topic_score_gemma":0.00020597293,"teacher_disagreement_score":0.52355987,"about_ca_system_score_codex":0.0009480509,"about_ca_system_score_gemma":0.001313654,"threshold_uncertainty_score":0.997777},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2955358615","doi":"10.1177/0734282919861269","title":"Linking Test-Taking Process to Performance Through Mixed-Effects Regression Models: A Response Process–Based Validation Study","year":2019,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Test (biology); Process (computing); Logistic regression; Sample (material); Comprehension; Outcome (game theory); Active listening; Statistics; Machine learning; Computer science; Mathematics","score_opus":0.3323818155501208,"score_gpt":0.5538929842036837,"score_spread":0.2215111686535629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955358615","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":[0.9499188,0.00008336778,0.042925555,0.0020453345,0.0026212297,0.0008496195,0.0000024096496,0.000022637745,0.0015310362],"genre_scores_gemma":[0.9268071,0.0000058203464,0.07221579,0.0004065545,0.0003115965,0.00006326043,0.0000019065994,0.000022027958,0.00016593971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99270576,0.0010727551,0.0015961202,0.0006137198,0.0036596581,0.00035195952],"domain_scores_gemma":[0.97228926,0.02173495,0.002818595,0.0005829648,0.002385316,0.00018890701],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015764918,0.0002744548,0.0005572762,0.0011303513,0.00027384848,0.00037304746,0.0012029407,0.00008803803,0.00014512699],"category_scores_gemma":[0.02338597,0.0001849622,0.0001558533,0.0031241223,0.00002563083,0.0013530605,0.000064827815,0.00049646426,0.00002765205],"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":[0.000935072,0.002479262,0.8438839,0.000108283624,0.000049582522,0.000006683594,0.004454777,0.1033142,0.001539088,0.00009624954,0.00087629596,0.042256616],"study_design_scores_gemma":[0.0016718486,0.0028623294,0.9503776,0.0010195129,0.0000406047,0.00005131283,0.008187062,0.014678258,0.0011786958,0.01914258,0.00046492176,0.00032526875],"about_ca_topic_score_codex":0.0000022659872,"about_ca_topic_score_gemma":4.7203278e-7,"teacher_disagreement_score":0.10649372,"about_ca_system_score_codex":0.00030241034,"about_ca_system_score_gemma":0.0012269225,"threshold_uncertainty_score":0.98484045},"labels":[],"label_agreement":null},{"id":"W2956271099","doi":"10.1111/jedm.12207","title":"Performance of Person‐Fit Statistics Under Model Misspecification","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"McGill University","funders":"","keywords":"Statistic; Econometrics; Item response theory; Inference; Latent variable; Latent variable model; Parametric statistics; Statistics; Statistical inference; Goodness of fit; Parametric model; Computer science; Variable (mathematics); Specification; Empirical research; Aggregate (composite); Mathematics; Psychometrics; Artificial intelligence","score_opus":0.7529540980675968,"score_gpt":0.4796196803409436,"score_spread":0.27333441772665323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956271099","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":[0.9530818,0.000552744,0.03478964,0.0029922256,0.0014455643,0.00011209803,0.000008475073,0.0000017488962,0.007015693],"genre_scores_gemma":[0.90675807,0.00003277836,0.09219344,0.00007008282,0.00013383149,0.0000010867408,5.1143786e-7,0.0000047496906,0.0008054746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99600834,0.00015356211,0.00085299194,0.00014702242,0.0027174964,0.00012058696],"domain_scores_gemma":[0.9914179,0.0036609431,0.001275297,0.00026221623,0.003299369,0.00008428025],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008058826,0.00007989928,0.00024157955,0.00040239102,0.000048202946,0.000039623457,0.000471546,0.000032350476,0.0011776886],"category_scores_gemma":[0.016669834,0.00005668306,0.00008133424,0.00054197956,0.000033620563,0.00019478399,0.000015641932,0.00012854207,0.000049220496],"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":[0.0003259794,0.0010364715,0.6190682,0.00008985038,0.00018429542,3.7224518e-7,0.0014164136,0.1701382,0.028135547,0.021664172,0.0733558,0.08458471],"study_design_scores_gemma":[0.0004109372,0.00025561973,0.94477993,0.000066402834,0.000023823966,0.0000204139,0.0011409904,0.029842919,0.00065970805,0.021701397,0.0009865317,0.00011130413],"about_ca_topic_score_codex":0.000002589893,"about_ca_topic_score_gemma":5.970788e-7,"teacher_disagreement_score":0.32571176,"about_ca_system_score_codex":0.00016864992,"about_ca_system_score_gemma":0.00065041176,"threshold_uncertainty_score":0.99973536},"labels":[],"label_agreement":null},{"id":"W2962737799","doi":"10.1097/acm.0000000000002888","title":"Examinee Cohort Size and Item Analysis Guidelines for Health Professions Education Programs: A Monte Carlo Simulation Study","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; McGill University; Office of the Chief Medical Examiner; Université du Québec à Montréal; Université de Sherbrooke","funders":"","keywords":"Cohort; Reliability (semiconductor); Medicine; Cohort study; Monte Carlo method; Control (management); Medical education; Statistics; Family medicine; Psychology; Computer science; Mathematics; Internal medicine","score_opus":0.6505779948723512,"score_gpt":0.6261768352554835,"score_spread":0.02440115961686773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962737799","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":[0.9738386,0.002162973,0.009830921,0.010107681,0.0008533625,0.0030042415,0.0000032234336,0.000065771055,0.00013321821],"genre_scores_gemma":[0.988255,0.00012848631,0.0047064438,0.0015476847,0.00041412708,0.00017917147,0.000007870963,0.000012111393,0.004749074],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956262,0.0005960075,0.0015909456,0.000745785,0.0011265788,0.00031448653],"domain_scores_gemma":[0.9546409,0.04254633,0.0008993667,0.0005990874,0.0011003716,0.0002139472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017947474,0.00018497728,0.0008356856,0.0008104284,0.00017225447,0.000027320008,0.00043427988,0.00013880077,0.00007049614],"category_scores_gemma":[0.28052694,0.000110951805,0.00006770627,0.0039981925,0.00006321575,0.00017707636,0.00010226314,0.00029204378,0.0000043461287],"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":[0.000023464336,0.000030298394,0.90370816,0.000016579037,0.0000905216,1.11940686e-7,0.0026788972,0.00066409825,0.000017964632,0.000023233863,0.004267483,0.0884792],"study_design_scores_gemma":[0.0009348918,0.00069802394,0.8613013,0.00013378919,0.0002635316,0.0000019788056,0.035337716,0.09458928,6.125411e-7,0.0018237978,0.004773611,0.00014147349],"about_ca_topic_score_codex":0.00036530595,"about_ca_topic_score_gemma":0.000032960128,"teacher_disagreement_score":0.26257947,"about_ca_system_score_codex":0.000054893448,"about_ca_system_score_gemma":0.00020502323,"threshold_uncertainty_score":0.7255335},"labels":[],"label_agreement":null},{"id":"W2964007568","doi":"10.1016/j.jneb.2019.05.287","title":"Satter Eating Competence Inventory Subscale Restructure After Confirmatory Factor Analysis","year":2019,"lang":"en","type":"article","venue":"Journal of Nutrition Education and Behavior","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Food and Agriculture; Pennsylvania State University; Pennsylvania Department of Public Welfare; U.S. Department of Agriculture","keywords":"Confirmatory factor analysis; Psychology; Competence (human resources); Confidence interval; Clinical psychology; Residual; Structural equation modeling; Statistics; Social psychology; Mathematics; Algorithm","score_opus":0.1455850739043927,"score_gpt":0.42680109059317906,"score_spread":0.2812160166887864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964007568","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":[0.9966094,0.0008536642,0.0002762835,0.00034088062,0.0016288068,0.00012811512,0.000008421027,0.000006546063,0.00014788448],"genre_scores_gemma":[0.98960614,0.000044647542,0.009448459,0.00035427915,0.00021974753,0.000012866076,0.0000021919745,0.0000046962227,0.00030699733],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99801874,0.00027460646,0.0007381499,0.00019772707,0.000648139,0.00012266298],"domain_scores_gemma":[0.9968716,0.0014076716,0.00076258666,0.00022223279,0.0005965042,0.000139431],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001109042,0.00009813084,0.00032532983,0.0010538977,0.00006446242,0.00017523729,0.00023366381,0.000077543096,0.0018290922],"category_scores_gemma":[0.001308837,0.00007073662,0.00018086373,0.0011774644,0.000051552164,0.00038349038,0.000027074297,0.0002169862,0.00001702934],"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":[0.000013938964,0.0005279088,0.9796209,0.000011633874,0.000025606036,0.000002615995,0.0002815959,0.000001208563,0.0013515904,0.000012586391,0.000808208,0.017342223],"study_design_scores_gemma":[0.00034814744,0.00007068653,0.99169344,0.000051441522,0.0001643519,0.0000745621,0.0030053318,0.000027192553,0.000109173605,0.0004996132,0.0038684558,0.00008763364],"about_ca_topic_score_codex":0.000006924431,"about_ca_topic_score_gemma":0.0000031189152,"teacher_disagreement_score":0.01725459,"about_ca_system_score_codex":0.00004021647,"about_ca_system_score_gemma":0.000083980914,"threshold_uncertainty_score":0.9990834},"labels":[],"label_agreement":null},{"id":"W2965061113","doi":"10.5539/ijsp.v8n5p1","title":"On the Contextual Conditions Driving a Difficulty Factor","year":2019,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Uncorrelated; Confirmatory factor analysis; Factor (programming language); Factor analysis; Statistics; Range (aeronautics); Psychology; Econometrics; Cognitive psychology; Mathematics; Computer science; Structural equation modeling","score_opus":0.24893958629824312,"score_gpt":0.44278548750254854,"score_spread":0.19384590120430542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965061113","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":[0.9450642,0.000021341197,0.05069503,0.0016952724,0.0011514355,0.00009701401,0.0002510895,0.0000033427664,0.0010213045],"genre_scores_gemma":[0.9916764,0.000011015657,0.007894251,0.00021955796,0.00007073162,9.555855e-7,0.0000014237414,0.0000024681617,0.00012323537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99791825,0.00026781435,0.00058411027,0.00014733437,0.0009929744,0.00008949823],"domain_scores_gemma":[0.95728284,0.04091272,0.0005244014,0.00015156902,0.0010700217,0.000058452108],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027964865,0.00007135166,0.00017612573,0.00012414307,0.0000690003,0.00022636258,0.00052199786,0.000027307311,0.0011225836],"category_scores_gemma":[0.06996308,0.000035764308,0.000060383965,0.00015002719,0.000106311425,0.000103010156,0.000076758326,0.00020278404,0.000021119105],"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":[0.00014616988,0.0001996438,0.38409668,0.000005259025,0.00014575887,0.000020177458,0.0006745509,0.00038297905,0.0005672651,0.4997491,0.011782382,0.102230035],"study_design_scores_gemma":[0.00026060164,0.00015153199,0.4837021,0.000021086138,0.0000035598457,0.0000315768,0.00019855108,0.0011690799,0.000020584934,0.5125032,0.0018914476,0.000046664332],"about_ca_topic_score_codex":0.000006743544,"about_ca_topic_score_gemma":0.0000053331773,"teacher_disagreement_score":0.102183364,"about_ca_system_score_codex":0.000036047884,"about_ca_system_score_gemma":0.000048135396,"threshold_uncertainty_score":0.99979055},"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":"W2966096503","doi":"10.1186/s41687-019-0131-4","title":"Psychometric performance of the PROMIS® depression item bank: a comparison of the 28- and 51-item versions using Rasch measurement theory","year":2019,"lang":"en","type":"article","venue":"Journal of Patient-Reported Outcomes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"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":"Rasch model; Item response theory; Item bank; Polytomous Rasch model; Psychology; Psychometrics; Clinical psychology; Short Forms; Differential item functioning; Developmental psychology","score_opus":0.3203688270700454,"score_gpt":0.42393774292675335,"score_spread":0.10356891585670797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966096503","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":[0.99511725,0.0010678576,0.0004130622,0.00010410529,0.0024915393,0.00039192944,0.0000020522639,0.0000051343673,0.00040708156],"genre_scores_gemma":[0.99755067,0.000018253128,0.0022816365,0.000040490893,0.000022243905,0.0000010542474,7.2796375e-8,0.000009874965,0.0000756852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9929648,0.00081890007,0.002400966,0.0002694443,0.0033076715,0.00023823763],"domain_scores_gemma":[0.9829377,0.008285493,0.0064876354,0.0008690825,0.00132307,0.00009705456],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00894926,0.00018940869,0.0008237809,0.00080652797,0.00022074266,0.00005027461,0.000924739,0.000098219585,0.00006271475],"category_scores_gemma":[0.056330863,0.000081116705,0.00040798713,0.0031133653,0.00013268771,0.00026885804,0.00032962952,0.0004019047,8.539154e-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":[0.00012172474,0.00013595271,0.9664486,0.000026469712,0.000103147024,5.962074e-7,0.00050508976,0.0004985698,0.0047658077,0.000010790574,0.00013984065,0.027243419],"study_design_scores_gemma":[0.0010237548,0.00023464482,0.9869852,0.00033489466,0.000109242006,0.000057545687,0.0017349526,0.001596853,0.007201299,0.0003724363,0.00025090127,0.000098280645],"about_ca_topic_score_codex":0.000009886646,"about_ca_topic_score_gemma":0.0000013954417,"teacher_disagreement_score":0.047381602,"about_ca_system_score_codex":0.000083411156,"about_ca_system_score_gemma":0.00017852582,"threshold_uncertainty_score":0.9516181},"labels":[],"label_agreement":null},{"id":"W2970279362","doi":"10.5539/ijps.v11n3p83","title":"An Evaluation of Common Method Variance-Bias in Psychology","year":2019,"lang":"en","type":"article","venue":"International Journal of Psychological Studies","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Cosmic microwave background; Psychology; Covariate; Variance (accounting); Statistics; Econometrics; Common-method variance; Variable (mathematics); Social psychology; Cognitive psychology; Mathematics; Physics; Thermodynamics; Optics","score_opus":0.8603077168663666,"score_gpt":0.6976733872193087,"score_spread":0.16263432964705793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970279362","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":[0.9720581,0.0019282756,0.011969115,0.0017050232,0.00473189,0.00014488635,0.0000046786017,0.000007047615,0.00745099],"genre_scores_gemma":[0.9535166,0.00037429665,0.045373403,0.00053191284,0.00016902207,0.0000036926072,5.718479e-7,0.000004771105,0.000025718475],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99183387,0.002961576,0.0018433116,0.00039387032,0.0027788854,0.00018849463],"domain_scores_gemma":[0.98037386,0.0142068835,0.0017385852,0.00038210145,0.0032354097,0.000063178806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037295256,0.00013875029,0.00072572695,0.0008843122,0.00002524652,0.000048721966,0.0017141538,0.000116884694,0.0007399451],"category_scores_gemma":[0.050085723,0.000084370484,0.00019141301,0.0010046284,0.00012345429,0.0003134098,0.000119370685,0.00033837708,0.000028440169],"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":[0.00038167334,0.0006388192,0.43010843,0.0000019843858,0.00015615814,0.000025237752,0.00044071773,0.0019958864,0.0016538618,0.0012653989,0.0011940293,0.5621378],"study_design_scores_gemma":[0.0018711502,0.0008378034,0.7432732,0.00005079199,0.000019736724,0.00013227307,0.001010395,0.0010480678,0.000102858365,0.2503722,0.0011893604,0.00009215074],"about_ca_topic_score_codex":0.000011937357,"about_ca_topic_score_gemma":0.000010570888,"teacher_disagreement_score":0.56204563,"about_ca_system_score_codex":0.00007868647,"about_ca_system_score_gemma":0.000027476317,"threshold_uncertainty_score":0.99130714},"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":"W2974598948","doi":"10.1007/s11136-019-02276-9","title":"Relating response shift and cognitive appraisal to measurement validation","year":2019,"lang":"en","type":"letter","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity Western University; Centre for Advancing Health Outcomes; Western University","funders":"","keywords":"Quality of Life Research; Public health; Cognition; Psychology; Psychometrics; Applied psychology; Clinical psychology; Medicine; Psychiatry; Nursing","score_opus":0.9153689328582775,"score_gpt":0.6471130934034154,"score_spread":0.2682558394548621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974598948","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.41775715,0.00062405464,0.006821684,0.5669835,0.00074857794,0.0012386593,0.00010898005,0.000042232736,0.0056751263],"genre_scores_gemma":[0.9066558,0.000028247925,0.009416023,0.07708993,0.00262174,0.00010803209,0.000042012645,0.000091219794,0.0039470107],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.939971,0.040488686,0.0022650561,0.001546725,0.014829972,0.0008985557],"domain_scores_gemma":[0.17621863,0.8142679,0.0014168796,0.0018638987,0.005899598,0.0003331012],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29521015,0.0002484303,0.0010165746,0.0023733536,0.00027701724,0.00040013375,0.0014122836,0.00061832526,0.00021259907],"category_scores_gemma":[0.9221554,0.00019794477,0.00016383536,0.0031542827,0.00034520528,0.00017427818,0.0010194513,0.0024675785,0.000266103],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001767352,0.000051221126,0.06060171,0.00032818658,0.000116019655,0.000014361103,0.0023119755,0.000007644468,0.00066665764,0.00009890086,0.9046961,0.029339842],"study_design_scores_gemma":[0.0018550259,0.0016049164,0.5969939,0.0012708406,0.000037917358,0.0000054630955,0.0068080383,0.00013310119,0.0005039764,0.016818766,0.37298355,0.0009844858],"about_ca_topic_score_codex":0.00049000664,"about_ca_topic_score_gemma":0.000007194184,"teacher_disagreement_score":0.7737792,"about_ca_system_score_codex":0.00010996935,"about_ca_system_score_gemma":0.000739674,"threshold_uncertainty_score":0.99983376},"labels":[],"label_agreement":null},{"id":"W2978741138","doi":"10.1177/0013164419878861","title":"A Propensity Score Method for Investigating Differential Item Functioning in Performance Assessment","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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":"Propensity score matching; Differential item functioning; Matching (statistics); Context (archaeology); Psychology; Proxy (statistics); Language proficiency; Aptitude; Set (abstract data type); Test (biology); Computer science; Psychometrics; Statistics; Natural language processing; Cognitive psychology; Item response theory; Machine learning; Developmental psychology; Mathematics; Mathematics education","score_opus":0.7918302834411759,"score_gpt":0.5152538123684256,"score_spread":0.2765764710727503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978741138","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":[0.96294296,0.00009228509,0.028875984,0.002306052,0.0014334372,0.0006194682,0.0000023359232,0.0000162645,0.0037111999],"genre_scores_gemma":[0.91398185,0.000005432166,0.08498016,0.000394821,0.0001832243,0.00012794166,0.0000035587364,0.000005118826,0.00031790035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996895,0.00045508705,0.00059889053,0.000694811,0.0010831986,0.0002730183],"domain_scores_gemma":[0.9924827,0.006486253,0.00025280457,0.00026402014,0.0003992723,0.00011491624],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008982325,0.00014854893,0.00031122615,0.00022672406,0.00018812247,0.00015195916,0.00028145185,0.000077231074,0.0005146002],"category_scores_gemma":[0.015745478,0.00009559405,0.00006526914,0.00069003506,0.00004837473,0.0001399267,0.00007072685,0.00022765719,0.000017786266],"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":[0.00004068296,0.00019853181,0.89448565,0.00001800246,0.000008313528,8.898317e-8,0.000080550664,0.0000769228,0.0022882249,0.0016939376,0.00058374554,0.10052537],"study_design_scores_gemma":[0.00056374364,0.0003063206,0.9732747,0.00006251464,0.000004813251,0.000007357346,0.0001216014,0.003625702,0.000045814108,0.02100385,0.0008487372,0.00013481437],"about_ca_topic_score_codex":0.000013064756,"about_ca_topic_score_gemma":0.0000044994613,"teacher_disagreement_score":0.10039056,"about_ca_system_score_codex":0.000086678985,"about_ca_system_score_gemma":0.00007842275,"threshold_uncertainty_score":0.9925453},"labels":[],"label_agreement":null},{"id":"W2979505351","doi":"10.1177/1069072719879910","title":"We Can Do That? Technological Advances in Interest Assessment","year":2019,"lang":"en","type":"article","venue":"Journal of Career Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data science; Computer science; Psychology","score_opus":0.44442279293672926,"score_gpt":0.5173520996052661,"score_spread":0.07292930666853681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979505351","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":[0.9289981,0.0035961322,0.024894573,0.007399426,0.0036685038,0.00034202062,0.000008125772,0.000033929024,0.03105917],"genre_scores_gemma":[0.95412296,0.000707301,0.044784255,0.00012079107,0.00008728638,0.0000051501024,3.4091084e-7,0.00000940274,0.0001624847],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9950328,0.0006520659,0.0013250904,0.00039193116,0.0022136904,0.00038441375],"domain_scores_gemma":[0.98775107,0.009845814,0.0012639688,0.0005581254,0.0004372326,0.00014377179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011397101,0.00020274502,0.0007571132,0.0012699324,0.000049143142,0.00030601944,0.0015478807,0.0001395787,0.00056444167],"category_scores_gemma":[0.0065611107,0.00012145167,0.00023893303,0.0016532671,0.000091524715,0.000543161,0.0003242098,0.00090191886,0.000012109265],"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":[0.000024996929,0.00011196905,0.670049,0.000008814143,0.000020442549,0.000089455905,0.00008844821,0.00028009227,0.00037193822,0.0039292225,0.0008273753,0.32419822],"study_design_scores_gemma":[0.0015972888,0.0011441562,0.8249298,0.00035717338,0.000021451571,0.000223101,0.017783022,0.0005094869,0.0002621109,0.07685888,0.07596944,0.00034413094],"about_ca_topic_score_codex":0.000004727542,"about_ca_topic_score_gemma":0.000024882554,"teacher_disagreement_score":0.3238541,"about_ca_system_score_codex":0.00036486052,"about_ca_system_score_gemma":0.00027903047,"threshold_uncertainty_score":0.78547364},"labels":[],"label_agreement":null},{"id":"W2984476219","doi":"10.3102/1076998619885636","title":"Full Information Optimal Scoring","year":2019,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Statistics; Binary number; Scoring rule; Mathematics; Binary data; Scoring system; Computer science; Point (geometry); Test (biology); Mean squared error; Arithmetic; Medicine","score_opus":0.35222512895115965,"score_gpt":0.4970637307263445,"score_spread":0.14483860177518487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984476219","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":[0.9616501,0.00010093979,0.03583035,0.00048175693,0.0014312841,0.00004471975,0.000036479527,0.000001578022,0.00042283937],"genre_scores_gemma":[0.6829764,0.00002265435,0.31636962,0.00006559618,0.00016621327,6.4294255e-7,0.000004977717,0.0000025173974,0.00039132615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984284,0.000058916197,0.0006568306,0.000073576026,0.00067862944,0.00010362489],"domain_scores_gemma":[0.9938056,0.0046472303,0.00064886676,0.000090407455,0.00071332476,0.00009459937],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014825235,0.00006296616,0.00016791219,0.00030589695,0.00006239818,0.00019263054,0.00020509385,0.00002996433,0.0009874334],"category_scores_gemma":[0.006850415,0.000043038362,0.000035253775,0.00035271997,0.000032960605,0.00061834406,0.000039429313,0.00013469407,0.000065160646],"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":[0.00010397286,0.00014510387,0.6293312,0.000011061851,0.0000102350095,0.000002287975,0.00048193184,0.00025763598,0.00036547953,0.0144381765,0.014682062,0.34017086],"study_design_scores_gemma":[0.00048127113,0.00082361844,0.92581695,0.000030964515,0.000029529798,0.00026895865,0.0015639905,0.0005898121,0.000026122569,0.051628947,0.01859435,0.00014549248],"about_ca_topic_score_codex":0.000011740422,"about_ca_topic_score_gemma":7.0301604e-7,"teacher_disagreement_score":0.34002537,"about_ca_system_score_codex":0.000026369384,"about_ca_system_score_gemma":0.0001379572,"threshold_uncertainty_score":0.9999258},"labels":[],"label_agreement":null},{"id":"W2986493832","doi":"10.1002/jrsm.1385","title":"Construct validity of the Physiotherapy Evidence Database (PEDro) quality scale for randomized trials: Item response theory and factor analyses","year":2019,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Physiotherapy Foundation of Canada; National Science Foundation","keywords":"Item response theory; Construct (python library); Scale (ratio); Construct validity; Psychology; Randomized controlled trial; Clinical psychology; Quality (philosophy); Psychometrics; Physical therapy; Applied psychology; Medicine; Computer science","score_opus":0.942994865986386,"score_gpt":0.7599710097067921,"score_spread":0.18302385627959394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986493832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73163605,0.002011356,0.2629606,0.0005489071,0.00036704112,0.0021156555,0.00018178014,0.000022876142,0.00015571229],"genre_scores_gemma":[0.5596728,0.0005860564,0.4388112,0.00004623538,0.00009025429,0.00020543515,3.8959485e-7,0.00002254929,0.00056512794],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.50680315,0.48572102,0.0025300968,0.0011894222,0.0030896699,0.0006666644],"domain_scores_gemma":[0.03266813,0.9621036,0.0013989665,0.0023544165,0.001289653,0.00018521365],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7405687,0.00025668045,0.0029899129,0.00094171154,0.00040625595,0.00029114285,0.0019968448,0.00015967006,0.000805069],"category_scores_gemma":[0.9807892,0.00012375992,0.0010197462,0.0031520573,0.0015797925,0.0003849678,0.00059427967,0.0003985416,0.000006612944],"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":[0.12082169,0.000066242894,0.0103404,0.00013188749,0.00017419612,3.2010766e-7,0.00038339008,0.0000060790576,0.5309297,0.0010466649,0.00022523405,0.3358742],"study_design_scores_gemma":[0.018386386,0.00023245573,0.079511024,0.0006406538,0.00015177825,0.0000057669254,0.0041218605,0.0027416057,0.7144586,0.17829923,0.0010254619,0.00042517626],"about_ca_topic_score_codex":0.00014370593,"about_ca_topic_score_gemma":0.000003159986,"teacher_disagreement_score":0.4763826,"about_ca_system_score_codex":0.000059412814,"about_ca_system_score_gemma":0.0003893722,"threshold_uncertainty_score":0.88149405},"labels":[],"label_agreement":null},{"id":"W2990367555","doi":"10.1016/j.cptl.2019.10.001","title":"Guidance for high-stakes testing within pharmacy educational assessment","year":2019,"lang":"en","type":"article","venue":"Currents in Pharmacy Teaching and Learning","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalizability theory; Pharmacy; Reliability (semiconductor); Item response theory; Psychology; Standardized test; Medical education; Engineering ethics; Medicine; Psychometrics; Mathematics education; Clinical psychology; Engineering; Family medicine","score_opus":0.43039504960538527,"score_gpt":0.5504070374077461,"score_spread":0.12001198780236083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990367555","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":[0.98016006,0.00073075586,0.010531467,0.00063953456,0.0029067,0.0003539324,0.0000064530154,0.00007348544,0.004597595],"genre_scores_gemma":[0.8856263,0.0000131111665,0.11258637,0.0001319016,0.0002970964,0.000039600418,0.000008926114,0.0000191187,0.0012775415],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954864,0.0017506037,0.00085927395,0.00076515955,0.0007069104,0.0004316736],"domain_scores_gemma":[0.95615685,0.042683914,0.00061023835,0.00024619157,0.00017702069,0.00012580786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01971838,0.00022060458,0.0003699174,0.0005291524,0.0006496189,0.00034724158,0.00056694663,0.00002880742,0.00019910355],"category_scores_gemma":[0.092195675,0.00018338556,0.000060914706,0.00078381173,0.00004907444,0.00047977635,0.00016562494,0.0015299076,0.000023040018],"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":[0.000016416732,0.000058056237,0.6353139,0.000026348209,0.000008117803,4.7808703e-7,0.0006478714,0.0035082551,0.00074221386,0.00075432827,0.00042023213,0.35850376],"study_design_scores_gemma":[0.0059662876,0.00015761815,0.3979483,0.0005586366,0.000034287736,0.000029216213,0.0033693009,0.48688164,0.00017275156,0.017090527,0.086982496,0.00080894795],"about_ca_topic_score_codex":0.00021829095,"about_ca_topic_score_gemma":0.0000013966899,"teacher_disagreement_score":0.48337337,"about_ca_system_score_codex":0.00007467904,"about_ca_system_score_gemma":0.00014777838,"threshold_uncertainty_score":0.91545117},"labels":[],"label_agreement":null},{"id":"W2994056206","doi":"10.1097/phm.0000000000001359","title":"Evaluation of Longitudinal Assessment for Use in Maintenance of Certification","year":2019,"lang":"en","type":"article","venue":"American Journal of Physical Medicine & Rehabilitation","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":"Sunnybrook Health Science Centre","funders":"","keywords":"Certification; Maintenance of Certification; Medicine; Rehabilitation; Physical therapy; Physical examination; Internal medicine; Management","score_opus":0.3580259271085565,"score_gpt":0.5333457614917764,"score_spread":0.17531983438321985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994056206","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":[0.9662744,0.000033072993,0.03220092,0.0007973981,0.00022682967,0.00035144345,0.00000245042,0.0000017007166,0.00011179965],"genre_scores_gemma":[0.94670004,8.833363e-7,0.053191315,0.000012842011,0.000076362485,0.000008397184,8.1521216e-7,0.000004640241,0.000004703056],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99495745,0.001130164,0.001308157,0.00021420867,0.0022710424,0.00011898565],"domain_scores_gemma":[0.93732446,0.055908024,0.0024032188,0.00028736945,0.0040305625,0.0000463829],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022032592,0.00008222913,0.00066046865,0.00063809287,0.000012826623,0.0000074539125,0.0002633019,0.000017422713,0.000024864266],"category_scores_gemma":[0.15854158,0.000051780724,0.00015053371,0.0018047637,0.00034166625,0.00030895634,0.0000160533,0.00011656195,7.182432e-7],"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":[0.00013976287,0.00016117613,0.21560597,0.00001645419,0.000014404699,7.010923e-8,0.0008598686,0.0027495793,0.0074844994,0.00093220006,0.000044898643,0.77199113],"study_design_scores_gemma":[0.0011512871,0.017661916,0.8956682,0.00023081366,0.00005944542,0.0000014911664,0.0056243557,0.039406348,0.00009909079,0.040013127,0.000035758534,0.000048181133],"about_ca_topic_score_codex":0.00008973618,"about_ca_topic_score_gemma":0.000005000796,"teacher_disagreement_score":0.7719429,"about_ca_system_score_codex":0.0001276764,"about_ca_system_score_gemma":0.00015323017,"threshold_uncertainty_score":0.8485464},"labels":[],"label_agreement":null},{"id":"W2994407421","doi":"10.1016/j.dadm.2019.08.003","title":"Nonlinear Z‐score modeling for improved detection of cognitive abnormality","year":2019,"lang":"en","type":"article","venue":"Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Cancer Institute; National Institute on Aging; Avid Radiopharmaceuticals; National Institutes of Health; Rainwater Charitable Foundation; Biogen; Centers for Disease Control and Prevention; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Association for Frontotemporal Degeneration; National Heart, Lung, and Blood Institute; Pfizer; U.S. Department of Defense","keywords":"Normative; Standard deviation; Cognition; Residual; Nonlinear system; Mathematics; Statistics; Abnormality; Variance (accounting); Standard score; Psychology; Econometrics; Developmental psychology; Algorithm; Social psychology","score_opus":0.2880534394599593,"score_gpt":0.458652965280045,"score_spread":0.1705995258200857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994407421","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":[0.899368,0.007097061,0.08922386,0.00008590977,0.0025414894,0.0013473317,0.00013114004,0.00007512376,0.00013006655],"genre_scores_gemma":[0.9778157,0.00018299292,0.020926831,0.000040301573,0.00036895825,0.00059821154,0.000025411293,0.00003627115,0.0000053118715],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957152,0.0003595351,0.0012651795,0.00097546994,0.0011213251,0.0005632981],"domain_scores_gemma":[0.98453945,0.012695065,0.0007831331,0.00072735234,0.00095915707,0.00029585834],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00391965,0.00032747915,0.0005972759,0.00046139842,0.0002668503,0.00025987692,0.0006626821,0.00009663369,0.00011367128],"category_scores_gemma":[0.0072157984,0.00028697643,0.00043557218,0.0010695362,0.00004918175,0.0006916235,0.00030829257,0.00020162291,0.000015100361],"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":[0.00013653937,0.0003639364,0.8414612,0.000022889382,0.0012441333,0.0000016278199,0.000054694927,0.0011866731,0.001316695,0.000025351626,0.000018647324,0.1541676],"study_design_scores_gemma":[0.0024616984,0.0005034844,0.671098,0.00035782534,0.0046605733,8.82523e-7,0.0016501019,0.28466746,0.029808166,0.003723009,0.0003105911,0.00075824367],"about_ca_topic_score_codex":0.00012736622,"about_ca_topic_score_gemma":0.0000034311065,"teacher_disagreement_score":0.2834808,"about_ca_system_score_codex":0.000037440906,"about_ca_system_score_gemma":0.00013744032,"threshold_uncertainty_score":0.9999582},"labels":[],"label_agreement":null},{"id":"W3004991600","doi":"10.3389/fpsyg.2020.00072","title":"Estimation of Response Styles Using the Multidimensional Nominal Response Model: A Tutorial and Comparison With Sum Scores","year":2020,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Michigan State University","keywords":"Item response theory; Likert scale; Context (archaeology); Computer science; Contrast (vision); Psychology; Interpretation (philosophy); Focus (optics); Machine learning; Scale (ratio); Artificial intelligence; Natural language processing; Statistics; Econometrics; Psychometrics; Mathematics; Clinical psychology","score_opus":0.33986422920009207,"score_gpt":0.47532466831978776,"score_spread":0.13546043911969569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004991600","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":[0.57675856,0.00029018844,0.42097285,0.0013548178,0.0004638407,0.00012042644,0.00000676989,0.000010113445,0.000022429405],"genre_scores_gemma":[0.6096408,0.0000038638386,0.39009324,0.00021118567,0.000034981338,0.0000034317777,4.896825e-7,0.0000065870613,0.0000054701745],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955806,0.0023874643,0.0007009461,0.0005327464,0.0005553562,0.00024288215],"domain_scores_gemma":[0.98709565,0.011889684,0.00042765314,0.0003896277,0.00011151832,0.00008584701],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00791125,0.0001459808,0.00047837154,0.00047628314,0.00011343201,0.000037883136,0.0004249092,0.000114817056,0.000009383927],"category_scores_gemma":[0.03384621,0.00008992946,0.000044536122,0.0012915502,0.0004978036,0.00012779879,0.00011029542,0.0002517547,0.0000010923566],"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":[0.15385647,0.00017991738,0.52718073,0.000012416774,0.00006196185,0.00003602911,0.005733187,0.16367455,0.013662614,0.00027842776,0.020806627,0.11451707],"study_design_scores_gemma":[0.0016882072,0.00054384174,0.12983,0.000022246499,0.000014693573,0.000024005969,0.0018098538,0.86122406,0.00018196805,0.004024152,0.00051408116,0.00012286943],"about_ca_topic_score_codex":0.00002027074,"about_ca_topic_score_gemma":0.0000034090788,"teacher_disagreement_score":0.6975495,"about_ca_system_score_codex":0.000024179235,"about_ca_system_score_gemma":0.000104332,"threshold_uncertainty_score":0.9742921},"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":"W3008373672","doi":"10.1016/j.apmr.2020.01.019","title":"Measurement Properties of the Multiple Errands Test: A Systematic Review","year":2020,"lang":"en","type":"review","venue":"Archives of Physical Medicine and Rehabilitation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":29,"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 Toronto; Baycrest Hospital","funders":"","keywords":"Test (biology); Rehabilitation; Physical medicine and rehabilitation; Medicine; Psychology; Physical therapy","score_opus":0.5166261453542399,"score_gpt":0.4533718645360037,"score_spread":0.0632542808182362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008373672","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031413456,0.99641204,0.00015537693,0.001250109,0.00009057355,0.0018122887,0.000004999752,0.0000078209305,0.00023537883],"genre_scores_gemma":[0.012771561,0.9862487,0.0007008296,0.0000409323,0.000097072,0.0001151125,5.213576e-7,0.00001038054,0.000014896531],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99493897,0.0017674372,0.0016399841,0.00036108875,0.0011856639,0.000106872605],"domain_scores_gemma":[0.8920238,0.10523673,0.0017357223,0.0006877517,0.00024408066,0.00007194378],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003431621,0.00020821828,0.0031061007,0.000231942,0.00005213386,0.0000065699414,0.0005985575,0.00003446277,0.000001448647],"category_scores_gemma":[0.5770321,0.00007672352,0.0006351874,0.0012339469,0.00068457593,0.00004018373,0.00015253415,0.00019131758,0.0000012073848],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028731488,0.000046761164,0.00003777781,0.6887219,0.000040064187,8.965474e-8,0.0015147809,1.8235983e-7,0.000051077204,0.00010640707,0.00005735555,0.30942076],"study_design_scores_gemma":[0.00015775202,0.0007734363,0.00018469521,0.9862629,0.0010030651,0.0000030158733,0.0004932947,0.00022156257,0.0000026824257,0.004318376,0.006485491,0.00009372835],"about_ca_topic_score_codex":0.000009341905,"about_ca_topic_score_gemma":8.2950373e-7,"teacher_disagreement_score":0.5736005,"about_ca_system_score_codex":0.000010125298,"about_ca_system_score_gemma":0.00007907342,"threshold_uncertainty_score":0.42653072},"labels":[],"label_agreement":null},{"id":"W3010790150","doi":"10.1177/0962280220907625","title":"A study of alternative approaches to non-normal latent trait distributions in item response theory models used for health outcome measurement","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Polytomous Rasch model; Item response theory; Skewness; Normality; Statistics; Econometrics; Outcome (game theory); Mathematics; Psychology; Psychometrics","score_opus":0.957603297598445,"score_gpt":0.7042964429288336,"score_spread":0.25330685466961134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010790150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.068435,0.000051434185,0.9172918,0.011764688,0.00011541341,0.0019577371,0.00022323162,0.000012211078,0.00014845286],"genre_scores_gemma":[0.5834897,0.0000027074195,0.41599372,0.00016373272,0.000031261196,0.00029650042,0.0000019446386,0.000010239793,0.000010198729],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9282534,0.052906547,0.0038516475,0.0016938945,0.01164318,0.0016513104],"domain_scores_gemma":[0.47987115,0.5169968,0.00027313776,0.0006529298,0.00074367126,0.00146229],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31745926,0.00019089157,0.0010829605,0.0010575486,0.00015248558,0.00007389828,0.0015402328,0.00012940614,0.00019891468],"category_scores_gemma":[0.86797816,0.00013398346,0.00008963202,0.0050521223,0.0003889065,0.000089207235,0.0006560164,0.001197323,0.0000039921597],"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":[0.0071817287,0.0020450258,0.014538727,0.00012334008,0.000059160076,0.00013234283,0.016235009,0.0017607966,0.000117890035,0.061393183,0.00081341824,0.89559937],"study_design_scores_gemma":[0.004151815,0.0060408683,0.20518817,0.00014116883,0.000008672263,0.0000025933919,0.017131863,0.2947284,0.00013434156,0.47200325,0.00020644692,0.0002624025],"about_ca_topic_score_codex":0.0002193422,"about_ca_topic_score_gemma":0.00011625922,"teacher_disagreement_score":0.895337,"about_ca_system_score_codex":0.00034744036,"about_ca_system_score_gemma":0.00077525794,"threshold_uncertainty_score":0.70281935},"labels":[],"label_agreement":null},{"id":"W3011072191","doi":"10.7202/1067534ar","title":"L’alpha de Cronbach est l’un des pires estimateurs de la consistance interne : une étude de simulation","year":2020,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Vitalité Health Network; Université de Moncton","funders":"","keywords":"Mathematics; Humanities; Philosophy","score_opus":0.7982502984047913,"score_gpt":0.5683613788970864,"score_spread":0.22988891950770496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011072191","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":[0.5972048,0.0055148676,0.3882347,0.0034802689,0.00051556097,0.00014221054,0.000008765978,0.00008041528,0.004818368],"genre_scores_gemma":[0.703039,0.0005689358,0.29535213,0.00053754123,0.00023644073,0.000014265233,0.0000020192335,0.000015736567,0.00023394047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944261,0.0022742546,0.0007967428,0.0008863374,0.00061105733,0.0010055244],"domain_scores_gemma":[0.97211576,0.025840638,0.00066512066,0.0004253231,0.00038607474,0.0005670588],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013805882,0.00029228439,0.000404113,0.0003574454,0.00112805,0.0011754753,0.001357229,0.00023497362,0.00024238607],"category_scores_gemma":[0.11087574,0.00028546195,0.00014716975,0.0052527636,0.0035926457,0.00092685234,0.00017425315,0.00036097397,0.00007184585],"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":[0.00004578051,0.00017618485,0.30818376,0.00023878102,0.000021746511,0.000036820882,0.04373407,0.23783098,0.0027410195,0.00718208,0.00056541443,0.39924335],"study_design_scores_gemma":[0.00022082879,0.00024083325,0.267057,0.00034822273,0.000052071213,0.00022567822,0.0072644358,0.5910915,0.0010310002,0.1307089,0.0014687814,0.00029073085],"about_ca_topic_score_codex":0.0013293156,"about_ca_topic_score_gemma":0.00025580867,"teacher_disagreement_score":0.3989526,"about_ca_system_score_codex":0.0011069357,"about_ca_system_score_gemma":0.0012366696,"threshold_uncertainty_score":0.99995977},"labels":[],"label_agreement":null},{"id":"W3011484504","doi":"10.1177/0013164420911136","title":"Evaluating the Performances of Missing Data Handling Methods in Ability Estimation From Sparse Data","year":2020,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":79,"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":"Missing data; Imputation (statistics); Statistics; Cart; Data set; Regression; Mean squared error; Mathematics; Computer science; Regression analysis; Data mining; Engineering","score_opus":0.9728668887097844,"score_gpt":0.6848813766788585,"score_spread":0.2879855120309259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011484504","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":[0.77417326,0.0038595607,0.18871535,0.031227242,0.0007960083,0.00031966218,0.0000668081,0.000014520455,0.0008275712],"genre_scores_gemma":[0.58206,0.000018802491,0.41742325,0.00032239588,0.00014105071,0.0000051265974,0.000025828524,0.0000019239465,0.0000016321445],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995159,0.0016832638,0.0008591573,0.00085482793,0.0012891844,0.00015458126],"domain_scores_gemma":[0.9725879,0.025044374,0.00048813707,0.0014783576,0.00028937042,0.000111886424],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034227863,0.00010897554,0.00027378552,0.000068505775,0.00016486029,0.000117738804,0.0017610884,0.000049172486,0.00038912054],"category_scores_gemma":[0.19343059,0.00005919431,0.000023899705,0.000880895,0.00014556624,0.00029063175,0.0004866393,0.00020808633,0.0000062951767],"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":[0.00006719087,0.00014168471,0.055705838,0.000007987333,0.000010923625,1.3980345e-7,0.0004956385,0.00039277933,0.0021936726,0.00007479744,0.0007508764,0.9401585],"study_design_scores_gemma":[0.00024494663,0.00012189699,0.7066829,0.00003916008,0.00001452093,0.0000018449863,0.00049203116,0.23140287,0.000055214532,0.06028666,0.0005731066,0.0000848261],"about_ca_topic_score_codex":0.00007103551,"about_ca_topic_score_gemma":0.000005508873,"teacher_disagreement_score":0.94007367,"about_ca_system_score_codex":0.000018250435,"about_ca_system_score_gemma":0.0000888725,"threshold_uncertainty_score":0.99446565},"labels":[],"label_agreement":null},{"id":"W3013409274","doi":"10.5539/hes.v10n2p107","title":"Should Items and Answer Keys of Small-Scale Exams Be Published?","year":2020,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Statistics; Reliability (semiconductor); Item analysis; Descriptive statistics; Internal consistency; Item response theory; Mathematics education; Psychometrics; Clinical psychology; Mathematics","score_opus":0.7685150406017406,"score_gpt":0.5240299162515087,"score_spread":0.24448512435023184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013409274","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":[0.92349535,0.014414015,0.00056140654,0.040592816,0.0036592034,0.000165129,0.000007227959,0.00006367991,0.01704116],"genre_scores_gemma":[0.9729886,0.00032587972,0.015432692,0.0037676035,0.00051954266,0.00003125965,0.0000020207244,0.000011162727,0.0069212588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979934,0.00022008353,0.00057569105,0.0004788408,0.0005610447,0.00017094416],"domain_scores_gemma":[0.9905728,0.007866879,0.0003398742,0.0003553542,0.00073815236,0.00012695814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017810303,0.00012997344,0.00040897142,0.00022975932,0.00012015983,0.00013695036,0.00035688042,0.00005681313,0.00040079723],"category_scores_gemma":[0.012134427,0.000088548666,0.000058768605,0.0018752831,0.00018349226,0.00024169308,0.00021757215,0.00011147559,0.000014863992],"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":[0.000018353085,0.00011239058,0.56919885,0.00004765618,0.000077774275,4.969586e-7,0.0044646407,0.00000774581,0.00040717798,0.0027033726,0.36565337,0.05730817],"study_design_scores_gemma":[0.00019115375,0.000091451,0.6540422,0.000018684965,0.000023593066,0.000001551675,0.016452473,0.000016704353,0.00026298832,0.0075861663,0.321159,0.00015401532],"about_ca_topic_score_codex":0.000045334935,"about_ca_topic_score_gemma":0.000004370905,"teacher_disagreement_score":0.084843345,"about_ca_system_score_codex":0.000013639099,"about_ca_system_score_gemma":0.000058639853,"threshold_uncertainty_score":0.9961868},"labels":[],"label_agreement":null},{"id":"W3016806524","doi":"10.3352/jeehp.2020.17.12","title":"Performance of the Ebel standard-setting method for the spring 2019 Royal College of Physicians and Surgeons of Canada internal medicine certification examination consisting of multiple-choice questions","year":2020,"lang":"en","type":"article","venue":"Journal of Educational Evaluation for Health Professions","topic":"Psychometric Methodologies and Testing","field":"Decision 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 Manitoba; University of Calgary; Royal College of Physicians and Surgeons of Canada","funders":"","keywords":"Specialty; Certification; Nuclear medicine; Medicine; Statistics; Psychology; Mathematics; Family medicine; Management","score_opus":0.3982188306808459,"score_gpt":0.5391948166882257,"score_spread":0.14097598600737976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016806524","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":[0.7749726,0.0010787024,0.104317345,0.11517453,0.0019432988,0.0018189522,0.0005860908,0.0000023880307,0.00010609802],"genre_scores_gemma":[0.96559715,0.000020421754,0.03390514,0.00021663931,0.00013359624,0.000028438659,0.0000040864925,0.000006358589,0.00008817913],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951599,0.00122444,0.001987487,0.00015598415,0.0013312445,0.00014092507],"domain_scores_gemma":[0.87720054,0.111592956,0.0057058763,0.00020405445,0.0052264617,0.00007008405],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022159556,0.00008677334,0.00042761286,0.0002019808,0.0004353609,0.000004641288,0.0003573154,0.000038935796,0.000029106748],"category_scores_gemma":[0.26133877,0.000050650924,0.00009280076,0.0007777116,0.00013933814,0.00011244763,0.0000482555,0.00017551715,2.0570264e-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":[0.00069173885,0.00030046437,0.699519,0.001231465,0.00023479463,2.676518e-8,0.010288335,0.03501034,0.009224675,0.0066541214,0.04833601,0.18850905],"study_design_scores_gemma":[0.0007857529,0.00026077725,0.79780483,0.0007800138,0.00008201546,0.000001973346,0.0064199246,0.19125499,0.0007301784,0.0012663248,0.0005688247,0.00004438232],"about_ca_topic_score_codex":0.004487721,"about_ca_topic_score_gemma":0.0032177833,"teacher_disagreement_score":0.23917922,"about_ca_system_score_codex":0.00013763133,"about_ca_system_score_gemma":0.0041158907,"threshold_uncertainty_score":0.76801044},"labels":[],"label_agreement":null},{"id":"W3016903275","doi":"10.1177/0146621620909897","title":"The Monotonic Polynomial Graded Response Model: Implementation and a Comparative Study","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Monotonic function; Mathematics; Categorical variable; Probit; Probit model; Heteroscedasticity; Polynomial; Applied mathematics; Logistic regression; Function (biology); Statistics; Econometrics","score_opus":0.8339036917039917,"score_gpt":0.5454023379535109,"score_spread":0.2885013537504808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016903275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97972864,0.00020697202,0.010385547,0.0043679313,0.00016793233,0.0015022585,0.0000036750123,0.00008625208,0.003550816],"genre_scores_gemma":[0.99588794,0.000010874297,0.0027766954,0.0010356396,0.00006185197,0.00020764559,3.456161e-7,0.0000064765,0.000012511682],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945073,0.0014419673,0.0008622382,0.0009071004,0.0018934486,0.0003879262],"domain_scores_gemma":[0.99165344,0.0071010767,0.00033422493,0.00049781625,0.00018394772,0.00022946812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0146900425,0.00021912725,0.0003991887,0.00009310507,0.0005340399,0.00031169446,0.00077104993,0.00006276514,0.000053729676],"category_scores_gemma":[0.0069329287,0.000117553565,0.00007242752,0.0010748924,0.00015310041,0.00005797681,0.00019977946,0.00027926103,0.000045903394],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028103948,0.0018695503,0.030448586,0.0000060629127,0.0004191737,0.000023625424,0.024394546,0.00166861,0.075832844,0.0099963145,0.073522635,0.7537141],"study_design_scores_gemma":[0.008778771,0.0049229655,0.8567132,0.0000052463906,0.00008270348,0.000008095958,0.07796169,0.0054039806,0.0013651015,0.03361682,0.010368468,0.00077299617],"about_ca_topic_score_codex":0.000005048678,"about_ca_topic_score_gemma":0.000009585676,"teacher_disagreement_score":0.82626456,"about_ca_system_score_codex":0.00005512619,"about_ca_system_score_gemma":0.000029374325,"threshold_uncertainty_score":0.8299864},"labels":[],"label_agreement":null},{"id":"W3019656051","doi":"10.1007/s40271-020-00419-6","title":"Agreement Among Paper and Electronic Modes of the EQ-5D-5L","year":2020,"lang":"en","type":"article","venue":"Patient","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":"Fluidigm (Canada)","funders":"U.S. Food and Drug Administration; EuroQol Research Foundation","keywords":"Psychology; Computer science","score_opus":0.3528374730957486,"score_gpt":0.37311269890934984,"score_spread":0.02027522581360125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019656051","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":[0.9919203,0.00052360154,0.0017040703,0.0009969111,0.000104248866,0.00013593085,0.0000026584123,0.000008754697,0.004603543],"genre_scores_gemma":[0.9982918,0.000024516326,0.0011004593,0.0005062052,0.000019017258,0.000004803979,1.383584e-7,0.0000028545114,0.00005023432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99843204,0.00020835652,0.0003323634,0.00023617144,0.00061684736,0.00017421333],"domain_scores_gemma":[0.99690646,0.002482375,0.00021101329,0.00026670808,0.00007499131,0.000058475543],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008887327,0.00006633608,0.0001503112,0.000045939432,0.000070340386,0.00003165542,0.00032539637,0.000022757342,0.00016423504],"category_scores_gemma":[0.012967779,0.000034162094,0.00005638664,0.000714827,0.0000716261,0.00006487554,0.00023958461,0.00008826312,0.0000076800525],"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":[0.0000260797,0.000041444608,0.59248537,0.00000872358,0.000021296062,7.235358e-7,0.0022143307,0.00058547704,0.0032480583,0.0020788447,0.0028899738,0.3963997],"study_design_scores_gemma":[0.0005174829,0.0008043206,0.920785,0.000030381108,0.000021344495,0.0000018563233,0.0032762757,0.014266964,0.0077260435,0.03412004,0.018231,0.00021928952],"about_ca_topic_score_codex":0.000045725752,"about_ca_topic_score_gemma":0.000012278353,"teacher_disagreement_score":0.3961804,"about_ca_system_score_codex":0.000012369007,"about_ca_system_score_gemma":0.000020376307,"threshold_uncertainty_score":0.9953464},"labels":[],"label_agreement":null},{"id":"W3022866891","doi":"10.1177/0146621620909898","title":"Partially and Fully Noncompensatory Response Models for Dichotomous and Polytomous Items","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Polytomous Rasch model; Item response theory; Econometrics; Set (abstract data type); Statistics; Computer science; Psychometrics; Mathematics","score_opus":0.700374042316265,"score_gpt":0.4526023993021298,"score_spread":0.24777164301413518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022866891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7341497,0.0016916197,0.24618748,0.0075490745,0.00043306203,0.0017270081,0.000034264416,0.00024333423,0.007984468],"genre_scores_gemma":[0.97389287,0.000035389945,0.021335898,0.0043983073,0.00013609574,0.00016807183,9.238002e-7,0.000014532491,0.000017885222],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953348,0.00055453094,0.00084651326,0.0012747257,0.0014885899,0.0005008237],"domain_scores_gemma":[0.98979443,0.008641582,0.00029877538,0.00048569535,0.00026002678,0.00051949103],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012647056,0.00028581807,0.00058850483,0.00016194387,0.0002496805,0.00024136323,0.0005669784,0.00018308584,0.000059877097],"category_scores_gemma":[0.019224513,0.00019570644,0.000095978896,0.00072468875,0.00022062428,0.0000889208,0.00018047703,0.00024677324,0.000028556911],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01745035,0.00054702617,0.005096177,0.00004965548,0.00013920983,0.00004904042,0.0020529423,0.00053517544,0.1383571,0.011575821,0.024975674,0.7991718],"study_design_scores_gemma":[0.018933827,0.010153491,0.34850484,0.00007917081,0.00021985154,0.00016967452,0.0038125324,0.019731374,0.0042892676,0.4486026,0.1423895,0.0031138863],"about_ca_topic_score_codex":0.0000027847648,"about_ca_topic_score_gemma":0.0000016608276,"teacher_disagreement_score":0.79605794,"about_ca_system_score_codex":0.000031911768,"about_ca_system_score_gemma":0.000029312936,"threshold_uncertainty_score":0.989037},"labels":[],"label_agreement":null},{"id":"W3023909498","doi":"10.1002/9781118445112.stat06389","title":"Maximum Likelihood Item Response Theory Estimation","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Maximum likelihood sequence estimation; Maximum likelihood; Marginal likelihood; Restricted maximum likelihood; Estimation; Estimation theory; Expectation–maximization algorithm; Mathematics; Statistics; Likelihood principle; Maximum a posteriori estimation; Likelihood function; Bayes estimator; Bayesian probability; Computer science; Quasi-maximum likelihood; Econometrics; Engineering","score_opus":0.2424780445390895,"score_gpt":0.45288457973443613,"score_spread":0.21040653519534663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023909498","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":[0.00013187694,0.0012372653,0.911787,0.00017882549,0.0016028967,0.0004947449,0.014725962,0.00046461087,0.069376856],"genre_scores_gemma":[0.00040553548,0.0007184691,0.75799984,0.00036479012,0.00041285297,0.000029551995,0.0014249434,0.00045763946,0.23818637],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888018,0.0039850413,0.0018637808,0.0016402904,0.0027320187,0.0009770974],"domain_scores_gemma":[0.9201935,0.0739797,0.00233901,0.002326072,0.00069325574,0.0004684666],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012199442,0.0008222841,0.001498779,0.0022315355,0.00021499716,0.0004452798,0.0021178802,0.00068917294,0.009843985],"category_scores_gemma":[0.2155048,0.0006232583,0.00014205142,0.0019838496,0.0003981023,0.00011886453,0.00044745175,0.00096514134,0.0018104556],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029815617,0.00011562054,0.00018787176,0.00004387023,0.000052855205,0.000034066772,0.000057822945,0.000031362266,0.000013924625,0.008122192,0.49378905,0.4972532],"study_design_scores_gemma":[0.00058954826,0.00037793204,0.0021508597,0.00039792238,0.00007322007,0.00001705299,0.00022372247,0.0073661166,0.0000031387178,0.43148148,0.5566142,0.0007047873],"about_ca_topic_score_codex":0.00012078258,"about_ca_topic_score_gemma":0.0001894695,"teacher_disagreement_score":0.49654844,"about_ca_system_score_codex":0.00013364293,"about_ca_system_score_gemma":0.00047537166,"threshold_uncertainty_score":0.99962187},"labels":[],"label_agreement":null},{"id":"W3024642039","doi":"10.12973/ijem.6.1.207","title":"Somers' D as an Alternative for the Item–Test and Item-Rest Correlation Coefficients in the Educational Measurement Settings","year":2020,"lang":"en","type":"article","venue":"International Journal of Educational Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":32,"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":"Imperial College London; York University","keywords":"Statistics; Correlation; Estimator; Statistic; Item response theory; Pearson product-moment correlation coefficient; Psychology; Econometrics; Mathematics; Correlation coefficient; Scale (ratio); Psychometrics","score_opus":0.6055639871038005,"score_gpt":0.5439933675142452,"score_spread":0.06157061958955534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024642039","genre_codex":"commentary","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":[0.36145675,0.0014776035,0.15680014,0.4710924,0.007705262,0.0006330623,0.00005019522,0.000005878556,0.0007787037],"genre_scores_gemma":[0.93805563,0.00006706892,0.051378183,0.007831262,0.0024865393,0.00004498876,0.000011837734,0.000012796354,0.000111715606],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939408,0.0020773518,0.0012411772,0.0003985142,0.0021226113,0.00021959626],"domain_scores_gemma":[0.6293838,0.3638207,0.0020245856,0.00030200896,0.004269451,0.00019944912],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02130249,0.00016969096,0.00032049432,0.0005429005,0.00021326545,0.00026962513,0.0019455479,0.000079635174,0.00031844885],"category_scores_gemma":[0.48419744,0.00009871527,0.00014445871,0.0007722025,0.00021644884,0.00041942534,0.00010570731,0.00039985636,0.000015026778],"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":[0.0014747094,0.0015542875,0.5700931,0.000023634922,0.00055063743,0.000012557785,0.02867857,0.010172603,0.0021014032,0.15156285,0.033803415,0.19997224],"study_design_scores_gemma":[0.0014113535,0.00063849404,0.68466806,0.000056205095,0.00006160326,0.0004808742,0.009250812,0.0118607255,0.000102666425,0.26610145,0.025163509,0.000204265],"about_ca_topic_score_codex":0.000057036745,"about_ca_topic_score_gemma":0.000020289124,"teacher_disagreement_score":0.5765988,"about_ca_system_score_codex":0.00013566174,"about_ca_system_score_gemma":0.0006173228,"threshold_uncertainty_score":0.73830605},"labels":[],"label_agreement":null},{"id":"W3032360828","doi":"10.1007/978-3-319-28099-8_483-1","title":"Structural Equation Modeling","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Structural equation modeling; Mathematics; Statistics","score_opus":0.8058461991614304,"score_gpt":0.48777530763838456,"score_spread":0.31807089152304585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032360828","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005751567,0.00026493694,0.15638795,0.00010231101,0.0014725111,0.0001367944,0.0000061276364,0.00006404883,0.8409902],"genre_scores_gemma":[0.031131988,0.0000213576,0.028189078,0.00016217584,0.0002586207,6.278913e-7,0.000008093676,0.00002325928,0.9402048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968717,0.00005464007,0.00077256333,0.0006383354,0.0014660665,0.00019667117],"domain_scores_gemma":[0.98648745,0.011868082,0.00042000625,0.0008002458,0.00036091232,0.0000632933],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00316576,0.00022011039,0.0004641486,0.0006480767,0.000082336286,0.00022163913,0.00077209907,0.00028116227,0.0071347905],"category_scores_gemma":[0.020385113,0.00014029614,0.00019639112,0.00015992805,0.000026230071,0.00015365482,0.00020786494,0.00028147988,0.001240123],"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":[0.000013263078,0.0000012181148,0.0004306939,0.0000071321533,0.000029987963,0.0000034863908,0.000059522055,0.015926514,0.000010608714,0.54000026,0.004954292,0.43856302],"study_design_scores_gemma":[0.00006772985,0.000020481599,0.000033230594,0.000015337499,0.0000067567366,0.0000038195362,0.00002999914,0.40148494,7.432712e-7,0.58406776,0.014103884,0.00016529829],"about_ca_topic_score_codex":0.00001797867,"about_ca_topic_score_gemma":0.0000035205267,"teacher_disagreement_score":0.4383977,"about_ca_system_score_codex":0.000037907845,"about_ca_system_score_gemma":0.00007659831,"threshold_uncertainty_score":0.9995375},"labels":[],"label_agreement":null},{"id":"W3035107461","doi":"10.1177/0146621620929431","title":"OpenMx: A Modular Research Environment for Item Response Theory Method Development","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse; National Institutes of Health","keywords":"Modular design; Computer science; Implementation; Item response theory; Source code; Code (set theory); Selection (genetic algorithm); Software; Software engineering; Theoretical computer science; Programming language; Machine learning; Statistics; Mathematics; Psychometrics","score_opus":0.9218223146811826,"score_gpt":0.5923631288612036,"score_spread":0.329459185819979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035107461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058314368,0.00045996395,0.92320925,0.006693102,0.00027567756,0.0022647576,0.000008164497,0.0001369433,0.008637769],"genre_scores_gemma":[0.5871417,0.0000104019955,0.40956843,0.0021774836,0.00014166888,0.0007867218,0.0000017178423,0.000025697625,0.00014621233],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98507893,0.005110349,0.0014356287,0.0020916988,0.0052606645,0.0010227036],"domain_scores_gemma":[0.95124596,0.046180584,0.000340191,0.0011616688,0.00048000872,0.0005915749],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13675483,0.0003539798,0.0006984674,0.00038827147,0.0005998886,0.00025722818,0.002182934,0.0002477593,0.0009966706],"category_scores_gemma":[0.11555357,0.00023517567,0.00020214717,0.0018535473,0.00020328368,0.00006869371,0.0005525107,0.0005993436,0.00076755893],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008510056,0.00053916307,0.00033804277,0.000015301039,0.00010178025,0.000014594546,0.0012996718,0.00028533526,0.07766089,0.014852761,0.015061834,0.8813206],"study_design_scores_gemma":[0.002729097,0.0014035067,0.054489605,0.000022196362,0.000022396142,0.000007519898,0.0025047339,0.00041483037,0.010207494,0.13103774,0.796499,0.00066186645],"about_ca_topic_score_codex":7.316912e-7,"about_ca_topic_score_gemma":2.3053896e-7,"teacher_disagreement_score":0.8806587,"about_ca_system_score_codex":0.00024695974,"about_ca_system_score_gemma":0.00008169239,"threshold_uncertainty_score":0.99991655},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3036745105","doi":"10.5539/ijsp.v9n4p62","title":"Overcoming Limitations of the Independent Clusters Model for CFA by Means of Bayes-Estimation and Buffered Simple Structure","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bayes' theorem; Population; Mathematics; Statistics; Simple (philosophy); Bayes factor; Factor analysis; Sampling (signal processing); Sample size determination; Bayesian probability; Computer science","score_opus":0.33186528992804704,"score_gpt":0.4143898785245977,"score_spread":0.08252458859655065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036745105","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":[0.3424173,0.000049081773,0.6554383,0.000978148,0.00011215926,0.00009525186,0.00089492043,8.621226e-7,0.000013962681],"genre_scores_gemma":[0.7780163,0.000022304961,0.22186379,0.00007298221,0.000015411599,5.9192996e-7,0.000003353797,0.000002207824,0.0000030181166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982844,0.00012526664,0.0007393652,0.00012725269,0.0006642647,0.000059429018],"domain_scores_gemma":[0.9879679,0.009958683,0.0008912173,0.00008401323,0.0010439728,0.00005418849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014667613,0.00006282775,0.00020651314,0.000067411704,0.0000472337,0.000054066222,0.00032071257,0.000034074874,0.000009424786],"category_scores_gemma":[0.050364736,0.00003927585,0.000049898732,0.0001389965,0.00010279815,0.000118408,0.00009069468,0.00010013173,1.8348103e-8],"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":[0.0009475723,0.00016622352,0.14107011,0.00017413778,0.00031396208,0.0000013924597,0.0073386068,0.15654325,0.007286322,0.03221576,0.006414188,0.64752847],"study_design_scores_gemma":[0.00038582366,0.00008689215,0.023970634,0.000012396973,0.000017678527,0.000004704742,0.0001536539,0.5756793,0.00019797885,0.39938152,0.00007776679,0.000031653148],"about_ca_topic_score_codex":0.000011134754,"about_ca_topic_score_gemma":0.000015813986,"teacher_disagreement_score":0.6474968,"about_ca_system_score_codex":0.000020188838,"about_ca_system_score_gemma":0.00006598787,"threshold_uncertainty_score":0.95763445},"labels":[],"label_agreement":null},{"id":"W3047129708","doi":"10.1111/bmsp.12207","title":"A note on computing Louis’ observed information matrix identity for IRT and cognitive diagnostic models","year":2020,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"York University","funders":"National Taiwan Normal University","keywords":"Latent variable; Latent variable model; Computer science; Representation (politics); Variable (mathematics); Identity matrix; Monte Carlo method; Flexibility (engineering); Algorithm; Matrix (chemical analysis); Mathematics; Algebraic number; Maximization; Applied mathematics; Theoretical computer science; Artificial intelligence; Mathematical optimization; Statistics; Eigenvalues and eigenvectors","score_opus":0.42078208780786935,"score_gpt":0.49142747486818933,"score_spread":0.07064538706031998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047129708","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":[0.11332132,0.00034531535,0.88384926,0.0014086826,0.00015871668,0.0002022232,0.00012562977,0.000010840639,0.0005779823],"genre_scores_gemma":[0.8197263,0.00009780025,0.1782214,0.0018262859,0.0001100666,0.0000028821996,0.0000030641968,0.0000071404156,0.000005045849],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99728036,0.0003556787,0.0012733367,0.00025132022,0.00058815855,0.000251155],"domain_scores_gemma":[0.92699105,0.07170064,0.0004933927,0.00007191662,0.00043290804,0.0003101235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036395448,0.00012772247,0.0006104057,0.00013301907,0.000145674,0.00041597622,0.0002556983,0.000105535546,0.000095196374],"category_scores_gemma":[0.2360558,0.00010479221,0.00007812697,0.00032291716,0.00023465196,0.0004985028,0.000092309,0.00033202468,0.000017489494],"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":[0.0005252109,0.00019406242,0.0007469518,0.00018440216,0.00005940609,0.00019709925,0.0007724484,0.000065849395,0.000014373895,0.1337892,0.00565555,0.8577954],"study_design_scores_gemma":[0.0018868494,0.0010594608,0.03649589,0.00021831694,0.000060655817,0.0012011804,0.00035704495,0.045299932,0.0000018735241,0.91305155,0.00022312229,0.00014413676],"about_ca_topic_score_codex":0.0000026460534,"about_ca_topic_score_gemma":7.102096e-7,"teacher_disagreement_score":0.8576513,"about_ca_system_score_codex":0.000006843668,"about_ca_system_score_gemma":0.000020776954,"threshold_uncertainty_score":0.77037925},"labels":[],"label_agreement":null},{"id":"W3085277111","doi":"10.1119/perc.2020.pr.ives","title":"Exploratory Factor Analysis of a survey on group-exam experiences and subsequent investigation of the role of group familiarity","year":2020,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Group (periodic table); Exploratory factor analysis; Factor (programming language); Computer science; Psychology; Clinical psychology; Chemistry; Psychometrics; Programming language","score_opus":0.5408185976839321,"score_gpt":0.40712147356833706,"score_spread":0.1336971241155951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085277111","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":[0.9971269,0.00019588092,0.0020783553,0.000059923605,0.00008147224,0.00010860675,0.000039529314,0.000009973162,0.00029938293],"genre_scores_gemma":[0.9981194,0.00001998527,0.0017417041,0.000096946525,0.0000072281705,0.000005007036,0.000002424872,0.000002691271,0.0000045834117],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964791,0.0013045879,0.00076778,0.00035386416,0.0009859465,0.00010875428],"domain_scores_gemma":[0.9862952,0.012316614,0.00066025154,0.00040181875,0.00023819858,0.00008788399],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004056614,0.00010023428,0.0004998242,0.0003470403,0.00005005576,0.000024069914,0.000569476,0.00005679347,0.0001003518],"category_scores_gemma":[0.034919944,0.00005444819,0.00013631866,0.0063578063,0.00034053432,0.00014546783,0.00017039262,0.00008079777,4.944371e-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":[0.000025009855,0.00002032943,0.97840416,0.000003982447,0.000050836326,6.5895414e-8,0.005843681,0.000035392317,0.009975545,0.00032565196,0.00003531648,0.0052800435],"study_design_scores_gemma":[0.00008780121,0.00014090429,0.9636517,0.0000056484578,0.000027517335,4.3545246e-8,0.014831833,0.0034494686,0.01614006,0.0015908869,0.000018385033,0.000055723696],"about_ca_topic_score_codex":0.0011739038,"about_ca_topic_score_gemma":0.00030270443,"teacher_disagreement_score":0.03086333,"about_ca_system_score_codex":0.000008286837,"about_ca_system_score_gemma":0.000026317764,"threshold_uncertainty_score":0.9732093},"labels":[],"label_agreement":null},{"id":"W3087153552","doi":"10.1177/0265532220957298","title":"Hanyu Shuiping Kaoshi (HSK): A multi-level, multi-purpose proficiency test","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Language proficiency; Test (biology); Psychology; Argument (complex analysis); Language assessment; Scale (ratio); Mathematics education; Linguistics; Geography","score_opus":0.8227491867455936,"score_gpt":0.5099737195301289,"score_spread":0.3127754672154647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087153552","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":[0.6171786,0.0030291248,0.36631793,0.0012476112,0.0008284577,0.00097530236,0.00008678201,0.0014841938,0.008851971],"genre_scores_gemma":[0.55950004,0.0000022654522,0.4384884,0.0010543712,0.000295155,0.000020140556,0.0000030020208,0.000034220993,0.0006024119],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948754,0.0004547962,0.0012147677,0.0012781551,0.0012733941,0.00090349314],"domain_scores_gemma":[0.9553905,0.041881032,0.0008040175,0.0009346224,0.0004909616,0.0004988471],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0050352854,0.00038864595,0.0006416252,0.00042248293,0.0005002351,0.0005397485,0.0017285668,0.00015021299,0.00032279262],"category_scores_gemma":[0.58667415,0.00029838667,0.0001700977,0.0061946306,0.00014165154,0.00041478517,0.00067698554,0.0005704049,0.00047430748],"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":[0.000012024313,0.00020564096,0.36005777,0.000054807497,0.000012762554,0.00034692872,0.0077433777,0.00023384902,0.059637427,0.000036578098,0.00071235024,0.5709465],"study_design_scores_gemma":[0.0034309558,0.0007012363,0.4814237,0.00038517584,0.000060250317,0.00021360845,0.023980051,0.47916046,0.006773615,0.00045781696,0.001710408,0.0017027049],"about_ca_topic_score_codex":0.00018105634,"about_ca_topic_score_gemma":0.000021959377,"teacher_disagreement_score":0.5816389,"about_ca_system_score_codex":0.000050778563,"about_ca_system_score_gemma":0.00011980023,"threshold_uncertainty_score":0.99994683},"labels":[],"label_agreement":null},{"id":"W3095583164","doi":"10.1177/2515245920951747","title":"Your Coefficient Alpha Is Probably Wrong, but Which Coefficient Omega Is Right? A Tutorial on Using R to Obtain Better Reliability Estimates","year":2020,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":542,"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":"Omega; Confusion; Reliability (semiconductor); Construct (python library); Alpha (finance); Variety (cybernetics); Quality (philosophy); Confirmatory factor analysis; Cronbach's alpha; Computer science; Correlation coefficient; Statistics; Mathematics; Psychology; Epistemology; Physics; Psychometrics; Structural equation modeling; Philosophy; Programming language; Thermodynamics","score_opus":0.3780115946846152,"score_gpt":0.6190029165631815,"score_spread":0.2409913218785663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095583164","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":[0.75933415,0.000978811,0.2191463,0.011393683,0.002469201,0.00083744136,0.000015910051,0.00006396168,0.005760574],"genre_scores_gemma":[0.38598767,0.0001793424,0.60754013,0.006074179,0.00016425419,0.00003064337,2.8420058e-7,0.000009185737,0.000014315594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98922014,0.0027031286,0.0015407805,0.003175521,0.002264244,0.0010961802],"domain_scores_gemma":[0.9518736,0.044305973,0.0014195857,0.0011989517,0.00055171334,0.0006502033],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044286266,0.00043270778,0.0008644495,0.0007120636,0.000520473,0.0007844348,0.0023812116,0.00022226025,0.00026580875],"category_scores_gemma":[0.3259605,0.00027865043,0.00009341305,0.013410035,0.0009888133,0.0015644581,0.0007774964,0.0009493185,0.000032281438],"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":[0.0013862476,0.0010980425,0.14088027,0.000044981964,0.000008154156,0.00007985701,0.00446268,0.025019674,0.0091656055,0.0019767457,0.000563462,0.8153143],"study_design_scores_gemma":[0.00357061,0.006478912,0.18416445,0.0003400315,0.000054673652,0.00012488857,0.004947643,0.34213609,0.0071778097,0.2160769,0.23251313,0.0024148684],"about_ca_topic_score_codex":0.00006929998,"about_ca_topic_score_gemma":0.000009375878,"teacher_disagreement_score":0.8128994,"about_ca_system_score_codex":0.00016159147,"about_ca_system_score_gemma":0.00010365687,"threshold_uncertainty_score":0.99996656},"labels":[],"label_agreement":null},{"id":"W3099333586","doi":"10.3390/educsci10110324","title":"The Effect of Person Misfit on Item Parameter Estimation and Classification Accuracy: A Simulation Study","year":2020,"lang":"en","type":"article","venue":"Education Sciences","topic":"Psychometric Methodologies and Testing","field":"Decision 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 Alberta; University of Saskatchewan","funders":"","keywords":"Test (biology); Psychology; Statistics; Estimation; Item response theory; Computer science; Social psychology; Econometrics; Cognitive psychology; Psychometrics; Clinical psychology; Mathematics; Engineering","score_opus":0.6689828634516667,"score_gpt":0.5662955670270043,"score_spread":0.10268729642466234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099333586","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":[0.9894332,0.00017245155,0.004358374,0.003951939,0.00045874852,0.0005281686,9.1102663e-7,0.000022678707,0.0010734787],"genre_scores_gemma":[0.9974755,0.0000042061506,0.0022658575,0.00011141985,0.0000558948,0.000029700317,5.871992e-7,0.000002949705,0.000053891737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969527,0.0009716599,0.00043530192,0.00046001206,0.0010510591,0.00012925292],"domain_scores_gemma":[0.85689604,0.14185362,0.00064143405,0.00031701312,0.00020454565,0.000087331944],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067408984,0.00009932807,0.00017546768,0.000219955,0.00051734335,0.00043326564,0.0005085192,0.00003167852,0.00002199743],"category_scores_gemma":[0.29857805,0.000052110274,0.000040368708,0.0023172642,0.00021787273,0.0003594327,0.00003490511,0.000084755644,0.000021817506],"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":[0.00003462051,0.000038061342,0.21688788,0.0000042440265,0.0000037898114,4.172173e-8,0.0023155187,0.0027123538,0.00016127077,0.00023250894,0.00041234837,0.77719736],"study_design_scores_gemma":[0.0001684128,0.001247725,0.60490537,0.000014709736,0.000010788482,5.264783e-7,0.010375212,0.38113332,0.00022562132,0.0014303878,0.00041561405,0.00007232526],"about_ca_topic_score_codex":0.000017636905,"about_ca_topic_score_gemma":0.0000016218006,"teacher_disagreement_score":0.77712506,"about_ca_system_score_codex":0.000016424592,"about_ca_system_score_gemma":0.00008809756,"threshold_uncertainty_score":0.70733035},"labels":[],"label_agreement":null},{"id":"W3112823139","doi":"10.3390/psych2040026","title":"Better Rating Scale Scores with Information–Based Psychometrics","year":2020,"lang":"en","type":"article","venue":"Psych","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":"Ottawa Hospital; McGill University","funders":"","keywords":"Metric (unit); A priori and a posteriori; Psychometrics; Scale (ratio); Computer science; Item response theory; Rating scale; Data science; Statistics; Test (biology); Data mining; Econometrics; Psychology; Machine learning; Mathematics","score_opus":0.43089612382639825,"score_gpt":0.4354774462568831,"score_spread":0.004581322430484869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112823139","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":[0.24485658,0.0001432056,0.66888356,0.01945445,0.0007110815,0.0004622875,0.000022370486,0.00018662201,0.06527986],"genre_scores_gemma":[0.6467254,0.000003426823,0.33769873,0.015291055,0.00018005433,0.000021566684,0.000005554328,0.000011923561,0.00006227969],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99696136,0.00021025249,0.0007204629,0.00043118454,0.0013560805,0.0003206353],"domain_scores_gemma":[0.9901405,0.008209491,0.00045893533,0.0005753701,0.00038600035,0.00022971198],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028829325,0.00016581017,0.0003225479,0.00065749517,0.00022680983,0.0010339754,0.0015633618,0.0000672381,0.0005444611],"category_scores_gemma":[0.03229691,0.000106386884,0.00007030194,0.00918785,0.000075397234,0.00095195335,0.00015438718,0.00022682326,0.00042066234],"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":[0.00013218822,0.000040228442,0.55713236,0.000017155493,0.000014102617,0.0000022152988,0.0005478618,0.00039920397,0.000053760996,0.00016251211,0.06806613,0.37343225],"study_design_scores_gemma":[0.0058235847,0.0014772987,0.60507476,0.00010525916,0.000046627323,0.000021900838,0.0027093303,0.04717113,0.0012985726,0.015878055,0.31917924,0.0012142198],"about_ca_topic_score_codex":0.000016131706,"about_ca_topic_score_gemma":0.0000034142142,"teacher_disagreement_score":0.40186882,"about_ca_system_score_codex":0.000013592215,"about_ca_system_score_gemma":0.00006075424,"threshold_uncertainty_score":0.9970649},"labels":[],"label_agreement":null},{"id":"W3113194203","doi":"10.1016/j.bjps.2020.12.029","title":"Optimising the computerised adaptive test to reliably reduce the burden of administering the CLEFT-Q: A Monte Carlo simulation study","year":2020,"lang":"en","type":"letter","venue":"Journal of Plastic Reconstructive & Aesthetic Surgery","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto; McMaster University","funders":"Canadian Institutes of Health Research; National Institute for Health and Care Research","keywords":"Monte Carlo method; Test (biology); Computer science; Computerized adaptive testing; Reliability engineering; Statistics; Engineering; Mathematics; Psychometrics","score_opus":0.3333822597090917,"score_gpt":0.3995747554086898,"score_spread":0.06619249569959812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113194203","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":[0.7849124,0.0003019642,0.022165684,0.18138559,0.009507583,0.0013927646,0.00006249915,0.000029952396,0.00024157832],"genre_scores_gemma":[0.983302,0.000020325286,0.004835468,0.009092784,0.0026226847,0.00001505093,4.6973676e-7,0.000056204943,0.000055025448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9887016,0.0037714115,0.0033242065,0.0006889346,0.00295176,0.0005621198],"domain_scores_gemma":[0.6985071,0.2925666,0.00584312,0.0010397907,0.0018868789,0.00015654073],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0127939405,0.00052390737,0.0017374649,0.0009566478,0.00057253055,0.0006086056,0.0024947012,0.0002285029,0.000045722165],"category_scores_gemma":[0.12082566,0.00023595667,0.0009293253,0.002764373,0.000628782,0.0002336322,0.00048702498,0.002390349,0.00001072709],"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":[0.00089458894,0.00012519442,0.012443068,0.000028520953,0.0006021764,0.00089942646,0.011805051,0.38833526,0.000025794145,0.0000028362772,0.30057934,0.28425875],"study_design_scores_gemma":[0.004120221,0.010820456,0.13060588,0.007206561,0.0033336685,0.020209812,0.21072489,0.40283498,0.00006225161,0.007240695,0.19903655,0.0038040378],"about_ca_topic_score_codex":0.00006389597,"about_ca_topic_score_gemma":0.0000011758311,"teacher_disagreement_score":0.29019448,"about_ca_system_score_codex":0.00014132526,"about_ca_system_score_gemma":0.0006047726,"threshold_uncertainty_score":0.9999112},"labels":[],"label_agreement":null},{"id":"W3118574895","doi":"10.1186/s13643-020-01565-6","title":"A methodological review protocol of the use of Bayesian factor analysis in primary care research","year":2021,"lang":"en","type":"review","venue":"Systematic Reviews","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; McGill University","keywords":"Medicine; Protocol (science); Primary care; Research design; Bayesian probability; Family medicine; Alternative medicine; Statistics; Pathology","score_opus":0.9632415826864709,"score_gpt":0.6949322796442678,"score_spread":0.268309303042203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118574895","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.303091e-7,0.7184039,0.001822035,0.000011972225,0.00010786242,0.27919495,0.00003552088,0.000005471811,0.00041818016],"genre_scores_gemma":[1.2381582e-7,0.8013514,0.031289015,0.000031716612,0.00002306145,0.1670328,0.0000075645207,0.000019397103,0.0002448902],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.77707654,0.20251091,0.014440168,0.0013000323,0.0041636694,0.0005087073],"domain_scores_gemma":[0.7539778,0.22738504,0.01131385,0.005538725,0.0016663412,0.00011825623],"candidate_categories":["metaresearch","metaepi_broad","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16306503,0.00063079974,0.025574718,0.0023090187,0.0000918363,0.00014216556,0.004140521,0.00043468951,0.0003999682],"category_scores_gemma":[0.7141467,0.00023534214,0.006230398,0.04019565,0.00024098637,0.00013053951,0.0012019114,0.0010591681,0.000026375832],"study_design_candidate":"systematic_review","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":[6.943643e-7,0.000025230687,0.00015901735,0.6319426,0.00015289045,0.000003113889,0.000059312224,5.192984e-7,7.1158986e-8,0.000022954915,0.00056672044,0.36706692],"study_design_scores_gemma":[0.000041604562,0.000025489773,0.000068847774,0.4646946,0.0010830202,0.000010842553,0.000055859644,0.0000036226797,1.1746722e-7,0.000042193748,0.53383625,0.00013759082],"about_ca_topic_score_codex":0.0000384443,"about_ca_topic_score_gemma":0.000016579077,"teacher_disagreement_score":0.55108166,"about_ca_system_score_codex":0.00030156664,"about_ca_system_score_gemma":0.00075079506,"threshold_uncertainty_score":0.98889166},"labels":[],"label_agreement":null},{"id":"W3118829027","doi":"10.3389/feduc.2020.607260","title":"Bayesian Mixed Effects Model and Data Visualization for Understanding Item Response Time and Response Order in Open Online Assessment","year":2021,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Response time; Item response theory; Computer science; Visualization; Generalized linear mixed model; Formative assessment; Bayesian probability; Machine learning; Data mining; Artificial intelligence; Statistics; Psychometrics; Mathematics","score_opus":0.4163450157324386,"score_gpt":0.5446325208250691,"score_spread":0.12828750509263048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118829027","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":[0.4213528,0.00042169858,0.5760282,0.0010729657,0.00063013966,0.00039998992,0.000025865891,0.0000071654117,0.00006111756],"genre_scores_gemma":[0.3501588,0.00006444461,0.64866865,0.00017938952,0.000026514375,0.000032119002,0.00012834376,0.000012793103,0.00072891003],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636745,0.0020500382,0.0004458067,0.00067095424,0.00028553387,0.00018023734],"domain_scores_gemma":[0.97943723,0.01951513,0.00020303472,0.0006187695,0.00015140224,0.00007442768],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014257558,0.00010641241,0.00028372987,0.0007750098,0.00011297372,0.00037049313,0.0004630008,0.00008420011,0.000007495719],"category_scores_gemma":[0.110606596,0.00009877569,0.000011444942,0.0019026457,0.000041453102,0.00058217184,0.00038388342,0.00009041468,2.3700447e-7],"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":[0.0074743805,0.0012743411,0.48566684,0.000120514174,0.00004998915,0.000012386406,0.005528659,0.0032163206,0.0047853687,0.0028538457,0.092953295,0.39606404],"study_design_scores_gemma":[0.0009320128,0.000069288944,0.18557446,0.0000997442,0.000009653553,0.0000040562413,0.011356194,0.73944384,0.000028878749,0.061771914,0.0005766423,0.00013334071],"about_ca_topic_score_codex":0.00001944364,"about_ca_topic_score_gemma":0.000047428308,"teacher_disagreement_score":0.7362275,"about_ca_system_score_codex":0.00029379933,"about_ca_system_score_gemma":0.0007824948,"threshold_uncertainty_score":0.89688516},"labels":[],"label_agreement":null},{"id":"W3121031673","doi":"10.21449/ijate.705426","title":"Examining the Measurement Invariance of TIMSS 2015 Mathematics Liking Scale through Different Methods","year":2021,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Rasch model; Measurement invariance; Mathematics; Statistics; Metric (unit); Homogeneity (statistics); Scale (ratio); Level of measurement; Descriptive statistics; Polytomous Rasch model; Scale invariance; Econometrics; Psychology; Structural equation modeling; Mathematics education; Social psychology; Item response theory; Confirmatory factor analysis; Psychometrics; Geography; Engineering","score_opus":0.6714988377706251,"score_gpt":0.597784172952272,"score_spread":0.07371466481835309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121031673","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":[0.47132543,0.00084897515,0.50868154,0.0037468185,0.0067747,0.0001153877,0.0000023370217,0.0000043139858,0.008500516],"genre_scores_gemma":[0.5875616,0.00013582583,0.41189492,0.00012657813,0.00021398066,0.0000053773247,0.0000010047634,0.000004818962,0.000055908047],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99466753,0.00093826855,0.00153472,0.00020293501,0.0025251296,0.00013140503],"domain_scores_gemma":[0.98264,0.012059889,0.0018358849,0.00034294333,0.0030812914,0.000039939623],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014422799,0.00010983237,0.0003433503,0.00031808825,0.0000483165,0.00030278077,0.0010973971,0.000047842303,0.00017592228],"category_scores_gemma":[0.037111863,0.000068408095,0.00011401016,0.0007532737,0.00004763619,0.00053426955,0.00017299465,0.00028995052,0.0000014420008],"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":[0.000027022064,0.0011863293,0.11740626,0.000016405795,0.00015567403,0.000008258029,0.0036932933,0.0015565936,0.01422622,0.0074429153,0.0024011997,0.85187984],"study_design_scores_gemma":[0.000676987,0.00012273055,0.73414475,0.0009177495,0.00004705096,0.00015302969,0.028425716,0.0028674407,0.013437243,0.21420504,0.004822533,0.00017974747],"about_ca_topic_score_codex":0.000008941636,"about_ca_topic_score_gemma":0.000009260283,"teacher_disagreement_score":0.85170007,"about_ca_system_score_codex":0.00034833432,"about_ca_system_score_gemma":0.0007300253,"threshold_uncertainty_score":0.97099894},"labels":[],"label_agreement":null},{"id":"W3124813312","doi":"","title":"Predicting Intentions to Return to the Web Site: Extending the Dual Mediation Hypothesis","year":2004,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dual (grammatical number); Mediation; Computer science; Business; Econometrics; World Wide Web; Economics; Political science; Art; Law","score_opus":0.1819401861165566,"score_gpt":0.39563078364597554,"score_spread":0.21369059752941894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124813312","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":[0.8341005,0.0009883886,0.12152206,0.040519208,0.0012627953,0.00027095331,0.0000039418173,0.00004858249,0.001283565],"genre_scores_gemma":[0.99396926,0.0004385072,0.0032302756,0.0007785972,0.0009674201,0.000015087949,3.1391866e-7,0.000015045316,0.00058548246],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99482214,0.00078675355,0.0007094406,0.00035697792,0.0016828856,0.0016417841],"domain_scores_gemma":[0.9843697,0.01402913,0.00045543586,0.00057374773,0.0003892462,0.00018271971],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04034423,0.00015025168,0.00021152118,0.0005461997,0.0012233609,0.00051630964,0.001192649,0.00005922582,0.000046901634],"category_scores_gemma":[0.16441083,0.00007224033,0.00017775231,0.0033401318,0.000043736014,0.00024338941,0.00020246222,0.0014522285,0.00015039115],"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":[0.00019552588,0.00009935154,0.09711878,0.0000021053834,0.00021631252,0.000011533733,0.00521839,0.011430606,0.0068212827,0.038698975,0.004245803,0.8359413],"study_design_scores_gemma":[0.0008563989,0.00072532875,0.11398297,0.00006754733,0.00007093418,0.0014671766,0.030390361,0.0017636172,0.00024420186,0.83740395,0.01266868,0.00035880646],"about_ca_topic_score_codex":0.000052186202,"about_ca_topic_score_gemma":0.0017073903,"teacher_disagreement_score":0.83558255,"about_ca_system_score_codex":0.00066451094,"about_ca_system_score_gemma":0.0009435407,"threshold_uncertainty_score":0.9881676},"labels":[],"label_agreement":null},{"id":"W3125326271","doi":"10.1007/s11136-020-02750-9","title":"Using confirmatory factor analysis and Rasch analysis to examine the dimensionality of The Patient Assessment of Care for Chronic Illness Care (PACIC)","year":2021,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St Mary's Hospital Centre; McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Rasch model; Differential item functioning; Confirmatory factor analysis; Polytomous Rasch model; Item response theory; Psychometrics; Clinical psychology; Reliability (semiconductor); Psychology; Structural equation modeling; Classical test theory; Medicine; Developmental psychology; Statistics","score_opus":0.7995263564922511,"score_gpt":0.6382828395040523,"score_spread":0.16124351698819883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125326271","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":[0.9829958,0.002445431,0.013086119,0.00037680878,0.00008279529,0.00044980596,0.00042432957,0.0000032279738,0.00013569712],"genre_scores_gemma":[0.99453014,0.000024124318,0.005351961,0.000028364475,0.000020185258,0.0000145373515,0.000009178703,0.0000048868055,0.000016625643],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9878553,0.0064892625,0.0013456898,0.00053374725,0.003469507,0.0003064492],"domain_scores_gemma":[0.9383265,0.054424413,0.00068647746,0.0013902192,0.0050396887,0.00013269862],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016932564,0.00011975833,0.001024524,0.00085049105,0.00038407094,0.00006221304,0.00074678997,0.00007833737,0.00012943376],"category_scores_gemma":[0.0817205,0.00006533534,0.0005465673,0.011157622,0.0004473983,0.00005785188,0.00076978473,0.0002104436,1.6282799e-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":[0.000057490168,0.00007812756,0.9619277,0.0003560485,0.0013167388,3.7899133e-7,0.0061681867,0.0031917451,0.0065510576,0.0005398607,0.000029978813,0.019782657],"study_design_scores_gemma":[0.00023105429,0.00011029479,0.93568015,0.000027562155,0.00025257896,1.5833751e-7,0.053800978,0.0024529207,0.006868135,0.00026526392,0.00022530791,0.00008559598],"about_ca_topic_score_codex":0.0020433683,"about_ca_topic_score_gemma":0.001018822,"teacher_disagreement_score":0.06478794,"about_ca_system_score_codex":0.00014098654,"about_ca_system_score_gemma":0.0007996644,"threshold_uncertainty_score":0.92601454},"labels":[],"label_agreement":null},{"id":"W3131054533","doi":"10.1177/0013164421991211","title":"A Polytomous Scoring Approach to Handle Not-Reached Items in Low-Stakes Assessments","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"Polytomous Rasch model; Test (biology); Psychology; Item response theory; Statistics; Psychometrics; Clinical psychology; Mathematics","score_opus":0.8074745264456583,"score_gpt":0.5362121694680764,"score_spread":0.27126235697758194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131054533","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":[0.93713295,0.000837971,0.011574955,0.004665763,0.0013810436,0.00027592535,0.0000067758424,0.000024406467,0.044100188],"genre_scores_gemma":[0.9603879,0.000015673659,0.03720906,0.0011900639,0.00022839507,0.00009169724,0.000004428037,0.000006149796,0.0008666293],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99588376,0.0005463748,0.0006411288,0.00091100374,0.0016660233,0.00035171985],"domain_scores_gemma":[0.9958897,0.0028805498,0.00013734675,0.00041161253,0.00043231816,0.00024845425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062339017,0.00016906967,0.00032284716,0.0003166229,0.00014134067,0.0002513652,0.0003967074,0.00008678187,0.0003079576],"category_scores_gemma":[0.024780631,0.000119123935,0.00006979623,0.0017942928,0.00004971071,0.000100435085,0.000101123864,0.00021799983,0.000052279123],"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":[0.00026299368,0.0068651913,0.60213363,0.000039150185,0.00006509469,0.000019086287,0.0015204219,0.00034724153,0.015980277,0.009870173,0.010394881,0.35250184],"study_design_scores_gemma":[0.00047189937,0.000118640775,0.9807056,0.000050966966,0.0000041791145,0.00003056945,0.0008993396,0.00010445661,0.00026864008,0.014523715,0.0026331772,0.00018879495],"about_ca_topic_score_codex":0.000033230805,"about_ca_topic_score_gemma":0.000009581437,"teacher_disagreement_score":0.378572,"about_ca_system_score_codex":0.00009613525,"about_ca_system_score_gemma":0.00010268258,"threshold_uncertainty_score":0.9834341},"labels":[],"label_agreement":null},{"id":"W3134090036","doi":"10.24926/iip.v12i1.2925","title":"Validation Evidence from using Generalizability Theory in a Basic-Science Course","year":2021,"lang":"en","type":"article","venue":"INNOVATIONS in pharmacy","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalizability theory; Reliability (semiconductor); Psychology; Computer science; Mathematics education; Medical education; Statistics; Mathematics; Medicine","score_opus":0.740443777180831,"score_gpt":0.5876889081472201,"score_spread":0.1527548690336109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134090036","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":[0.9242785,0.0004103969,0.07240771,0.00092322193,0.00087535183,0.0001295801,0.000011302463,0.00002456906,0.00093937013],"genre_scores_gemma":[0.9309352,0.000028900846,0.06846429,0.00042696873,0.000071117596,0.000012141738,0.0000035870971,0.0000054195857,0.000052358995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957655,0.0011434485,0.0010232786,0.00073614315,0.0010316168,0.0003000118],"domain_scores_gemma":[0.9714527,0.025484491,0.0004099207,0.0010296588,0.0015568044,0.000066391345],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02123603,0.00011324383,0.00022790715,0.0010326132,0.00017432989,0.00027748477,0.0008316327,0.00003360503,0.00096441404],"category_scores_gemma":[0.15070477,0.0001013862,0.000036297584,0.023447087,0.0002453315,0.001277251,0.0002915729,0.0002594258,0.00002552918],"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":[0.000016482196,0.00012905944,0.7997226,0.0000021485641,0.0000031788893,0.000025564275,0.00050861674,0.0049352474,0.108498394,0.0036059455,0.00019320776,0.08235954],"study_design_scores_gemma":[0.00079946767,0.000008006245,0.5881037,0.00010139845,0.000009438347,0.000016786971,0.0010454402,0.09427695,0.067502744,0.24686335,0.0010048712,0.00026787],"about_ca_topic_score_codex":0.00039262255,"about_ca_topic_score_gemma":0.00001818667,"teacher_disagreement_score":0.2432574,"about_ca_system_score_codex":0.0001992148,"about_ca_system_score_gemma":0.00080595625,"threshold_uncertainty_score":0.99994886},"labels":[],"label_agreement":null},{"id":"W3134552356","doi":"10.24926/iip.v12i1.2235","title":"Providing Validation Evidence for a Clinical-Science Module: Improving Testing Reliability with Quizzes","year":2021,"lang":"en","type":"article","venue":"INNOVATIONS in pharmacy","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 Alberta","funders":"","keywords":"Reliability (semiconductor); Syllabus; Generalizability theory; Coursework; Computer science; Mathematics education; Psychology; Medical education; Medical physics; Medicine","score_opus":0.8471072521476786,"score_gpt":0.6358239551542438,"score_spread":0.21128329699343473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134552356","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":[0.788799,0.000116264666,0.20779318,0.0013957137,0.0007114215,0.00047266018,0.000005749097,0.000075282915,0.0006307393],"genre_scores_gemma":[0.6681767,0.000010143052,0.331318,0.000218067,0.00011589775,0.000081975115,0.0000016690038,0.000008055337,0.00006948989],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99526393,0.00044534408,0.0016451655,0.0011317652,0.0010831862,0.00043060115],"domain_scores_gemma":[0.78448683,0.19730516,0.0021561007,0.002327668,0.013510119,0.00021414134],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03557128,0.00015117612,0.00032095108,0.00085241697,0.0005163065,0.00054632477,0.0009093013,0.00004051771,0.000029973724],"category_scores_gemma":[0.68423593,0.00011686341,0.00005473219,0.022377633,0.00032160286,0.0017971927,0.00031080766,0.00033002437,0.000004894969],"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":[0.00003496507,0.00008556999,0.67068154,0.000020650401,0.0000032802575,0.000004848771,0.00008834593,0.0011937198,0.012915796,0.0007442317,0.00017744944,0.31404957],"study_design_scores_gemma":[0.0031839996,0.000291753,0.562407,0.00051833584,0.000042974436,0.00008640495,0.0012871514,0.3188831,0.06009376,0.047514614,0.0049080853,0.0007828033],"about_ca_topic_score_codex":0.00009018964,"about_ca_topic_score_gemma":0.000006501179,"teacher_disagreement_score":0.64866465,"about_ca_system_score_codex":0.00014770243,"about_ca_system_score_gemma":0.001344262,"threshold_uncertainty_score":0.9984022},"labels":[],"label_agreement":null},{"id":"W3135505713","doi":"10.1186/s12955-021-01725-9","title":"Exploratory factor analysis of PROMIS-29 V1.0, PROMIS Global Health and the RAND SF-36 from chiropractic responders attending care in a practice-based research network","year":2021,"lang":"en","type":"article","venue":"Health and Quality of Life Outcomes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Chiropractic Association","funders":"","keywords":"Algorithm; Computer science; Artificial intelligence","score_opus":0.7570294681486143,"score_gpt":0.6108843337019182,"score_spread":0.14614513444669608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135505713","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":[0.9328935,0.029313903,0.00095365616,0.035592698,0.00021257729,0.00070202496,0.00013427889,0.000015804877,0.00018153955],"genre_scores_gemma":[0.977101,0.0013595482,0.016286448,0.0051138406,0.000055842484,0.00002455835,0.000020908066,0.000009302167,0.000028537434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97449887,0.019506482,0.0023838347,0.0008144831,0.0020873267,0.00070902053],"domain_scores_gemma":[0.8783848,0.11738131,0.0020496116,0.00085613556,0.0007245081,0.0006036185],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05162488,0.00020404297,0.0019754646,0.00060892326,0.00049830525,0.0001601158,0.00038061303,0.00011661127,0.000034763023],"category_scores_gemma":[0.2907239,0.00012913319,0.00021934402,0.0061722375,0.00043779775,0.0002685798,0.00023594637,0.0004960076,7.410755e-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":[0.0032789395,0.00008957765,0.96775895,0.000235843,0.00023879742,0.0000029535415,0.009180512,0.000068102505,0.0000021328372,0.00055820745,0.00029982498,0.018286165],"study_design_scores_gemma":[0.0042535644,0.00023582524,0.8931015,0.00012094825,0.000048430175,7.8914763e-7,0.09853405,0.00044946853,0.000002701795,0.0016703915,0.0014474448,0.00013487045],"about_ca_topic_score_codex":0.0048100213,"about_ca_topic_score_gemma":0.0030440765,"teacher_disagreement_score":0.239099,"about_ca_system_score_codex":0.00017438784,"about_ca_system_score_gemma":0.0032374875,"threshold_uncertainty_score":0.9765518},"labels":[],"label_agreement":null},{"id":"W3139260591","doi":"10.1016/j.cpnec.2021.100040","title":"Response to: On item response theory models in allostatic load scoring","year":2021,"lang":"en","type":"article","venue":"Comprehensive Psychoneuroendocrinology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Allostatic load; Item response theory; Psychology; Clinical psychology; Neuroscience; Psychometrics","score_opus":0.39600001500988063,"score_gpt":0.46016642447539113,"score_spread":0.0641664094655105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139260591","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":[0.9677665,0.0008623107,0.010698589,0.012789403,0.003272671,0.0003977445,0.000015514264,0.00014131793,0.004055903],"genre_scores_gemma":[0.9706166,0.00011437841,0.0136390785,0.012499882,0.00007170802,0.0000654843,0.0000013357359,0.00005415931,0.0029373767],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.97986364,0.014350668,0.0013391351,0.0019346158,0.0013521208,0.0011598108],"domain_scores_gemma":[0.8457359,0.15085927,0.00027285016,0.0019178585,0.0009393564,0.0002747843],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037321928,0.0004305102,0.00092771335,0.0019397152,0.00019675518,0.00017492293,0.0013963748,0.00009317685,0.00026286053],"category_scores_gemma":[0.200922,0.00038446445,0.00021622323,0.0046978327,0.00020215052,0.00020363652,0.0006635244,0.00073051563,0.0007751703],"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":[0.18967089,0.0018057774,0.031587765,0.000052361236,0.00023589018,0.031211974,0.006735346,0.05498449,0.32333717,0.04695887,0.045283917,0.26813555],"study_design_scores_gemma":[0.0044024494,0.0019403752,0.593207,0.0001810184,0.000017731294,0.0016831234,0.0045983144,0.0022964708,0.003583846,0.30798933,0.07916053,0.00093979336],"about_ca_topic_score_codex":0.000011208803,"about_ca_topic_score_gemma":0.000011421223,"teacher_disagreement_score":0.5616193,"about_ca_system_score_codex":0.00018164027,"about_ca_system_score_gemma":0.0002947525,"threshold_uncertainty_score":0.9998607},"labels":[],"label_agreement":null},{"id":"W3139312164","doi":"10.5555/1161734.3259805","title":"Session details: Advanced tutorials: Bayesian methods","year":2004,"lang":"en","type":"article","venue":"Winter Simulation Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Calgary","funders":"","keywords":"Session (web analytics); Computer science; Bayesian probability; Multimedia; Machine learning; Artificial intelligence; World Wide Web","score_opus":0.4780396118289245,"score_gpt":0.5514799065697306,"score_spread":0.07344029474080604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139312164","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":[0.043319944,0.0000860779,0.9443371,0.00054752995,0.0025456895,0.00019624112,0.0000033863769,0.00014358178,0.008820432],"genre_scores_gemma":[0.690679,0.0000036677648,0.30857146,0.00016307447,0.00015971817,0.0000068437253,0.0000017386718,0.00000912935,0.0004053733],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99615806,0.0009788031,0.00094652484,0.0007231784,0.00086370384,0.00032971526],"domain_scores_gemma":[0.97618663,0.021365544,0.00054830214,0.0008967459,0.00082324917,0.0001795255],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060026804,0.00020993047,0.0004259793,0.00044862521,0.0001935464,0.00039784238,0.0008228234,0.000132767,0.0011045747],"category_scores_gemma":[0.0840447,0.00015216632,0.0001387198,0.0014396539,0.000081300015,0.0006703747,0.0001907474,0.00020670296,0.00016051508],"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":[0.000058507234,0.000038132777,0.0036661867,0.0000038332373,0.000010653167,0.0000039842384,0.000639764,0.11220504,0.0032985567,0.00366453,0.00007773358,0.87633306],"study_design_scores_gemma":[0.002685,0.00031190817,0.041725885,0.00022469014,0.000027644957,0.000012285741,0.001702952,0.26750815,0.008390582,0.62514937,0.051491782,0.00076974847],"about_ca_topic_score_codex":0.000015481302,"about_ca_topic_score_gemma":0.0000071632858,"teacher_disagreement_score":0.8755633,"about_ca_system_score_codex":0.0000730889,"about_ca_system_score_gemma":0.00011931714,"threshold_uncertainty_score":0.99980855},"labels":[],"label_agreement":null},{"id":"W3155215713","doi":"10.5539/elt.v14n5p23","title":"Identifying Guessing in English Language Tests via Rasch Fit Statistics: An Exploratory Study","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rasch model; Psychology; Polytomous Rasch model; Test (biology); Statistics; Item response theory; Social psychology; Psychometrics; Mathematics education; Developmental psychology; Mathematics","score_opus":0.24782592278892335,"score_gpt":0.467829404316962,"score_spread":0.22000348152803867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155215713","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":[0.9621365,0.0017075919,0.028828895,0.000010851875,0.0024790438,0.00028248018,0.00003475901,0.0004593783,0.0040604714],"genre_scores_gemma":[0.9310068,0.000004551356,0.06716595,0.0001283943,0.0011163522,0.00002605513,0.000033437747,0.00005782471,0.00046062586],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9897892,0.0050817574,0.0013065473,0.001332686,0.001716999,0.0007728252],"domain_scores_gemma":[0.9804567,0.016862374,0.0004731687,0.0015453803,0.00039959972,0.00026279708],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02009318,0.00037963106,0.00075812655,0.0010190469,0.00044352136,0.0014156492,0.0012324923,0.00015252408,0.0005353043],"category_scores_gemma":[0.2733515,0.00034426185,0.000114013055,0.0022163272,0.000062334504,0.0015983989,0.00062993047,0.0014196282,0.00003683302],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012822023,0.000471315,0.08763903,0.000018139677,0.000024740564,0.001882857,0.6946984,0.00014503025,0.0031589577,0.00007821398,0.00035130238,0.21151918],"study_design_scores_gemma":[0.001124068,0.000104498926,0.023219323,0.00010403269,0.000025915317,0.00001443509,0.9719262,0.0011867762,0.0005978714,0.00089623645,0.0002957706,0.0005048504],"about_ca_topic_score_codex":0.00034560298,"about_ca_topic_score_gemma":0.00179279,"teacher_disagreement_score":0.27722782,"about_ca_system_score_codex":0.00014902792,"about_ca_system_score_gemma":0.00012227774,"threshold_uncertainty_score":0.99990094},"labels":[],"label_agreement":null},{"id":"W3161167275","doi":"10.1093/oxfordhb/9780190092689.013.7","title":"Test Theory and Measurement in Assessment","year":2021,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","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":"McMaster University","funders":"","keywords":"Item response theory; Classical test theory; Scale (ratio); Test (biology); Psychology; Reliability (semiconductor); Construct validity; Jargon; Construct (python library); Field (mathematics); Cognitive psychology; Computer science; Data science; Social psychology; Psychometrics; Mathematics; Linguistics; Developmental psychology","score_opus":0.38068892624784034,"score_gpt":0.3734058047044967,"score_spread":0.007283121543343651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161167275","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002458837,0.00043584718,0.003885389,0.00003133526,0.00023546816,0.00021914869,0.000031092695,0.000034260273,0.9948816],"genre_scores_gemma":[0.003719252,0.00035176452,0.0047499565,0.000060212835,0.000046362125,6.4721905e-7,0.0000025376798,0.000018455356,0.99105084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99685776,0.00041385466,0.0003901168,0.0007597067,0.0013268768,0.00025168725],"domain_scores_gemma":[0.986224,0.012232875,0.00037133016,0.00068061566,0.00036327605,0.00012792042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006855515,0.0002614821,0.0005426079,0.0006003932,0.0001446567,0.0001523491,0.0007191142,0.0002564293,0.0001376085],"category_scores_gemma":[0.006999792,0.00023717509,0.00013171768,0.00005981044,0.0001642054,0.00008025044,0.00080056576,0.00048746174,5.4021825e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038765207,0.0000184194,0.0010302862,0.000017937355,0.000045678204,0.00024461624,0.00008586839,0.0000043609193,0.000024855372,0.8481604,0.0008434093,0.14948544],"study_design_scores_gemma":[0.00044094858,0.000058844744,0.0027851854,0.00015313369,0.00004177739,0.000009143289,0.00032099016,0.000037546153,0.000013066892,0.037303563,0.958571,0.00026477198],"about_ca_topic_score_codex":0.00002242394,"about_ca_topic_score_gemma":0.000036331618,"teacher_disagreement_score":0.9577276,"about_ca_system_score_codex":0.0002138915,"about_ca_system_score_gemma":0.00017485097,"threshold_uncertainty_score":0.9671719},"labels":[],"label_agreement":null},{"id":"W3162616454","doi":"10.1037/pas0000938","title":"Estimating classification consistency of screening measures and quantifying the impact of measurement bias.","year":2021,"lang":"en","type":"article","venue":"Psychological Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"Simon Fraser University","funders":"National Institute on Alcohol Abuse and Alcoholism","keywords":"PsycINFO; Consistency (knowledge bases); Respondent; Psychology; Ethnic group; Construct (python library); Measure (data warehouse); Psychometrics; MEDLINE; Clinical psychology; Statistics; Social psychology; Applied psychology; Computer science; Data mining; Artificial intelligence; Mathematics","score_opus":0.888597288137103,"score_gpt":0.6043494304083137,"score_spread":0.28424785772878935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162616454","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":[0.67659384,0.001010518,0.3148078,0.0007348212,0.0002450412,0.00016924817,0.0000062930417,0.000020993572,0.0064114495],"genre_scores_gemma":[0.81125844,0.00003369323,0.1886251,0.0000335004,0.000027363443,0.000009354604,9.023587e-7,0.0000044579056,0.0000071773693],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99477804,0.0015246191,0.0011753367,0.0005444186,0.0017383429,0.00023924989],"domain_scores_gemma":[0.9857596,0.011278631,0.0009911523,0.0007078395,0.0011788122,0.00008392593],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016525244,0.00015625414,0.0005046156,0.0001663912,0.00019051849,0.000120232085,0.00046674884,0.00008135798,0.00015774868],"category_scores_gemma":[0.06033054,0.00007759376,0.00023256632,0.0014919153,0.00030681412,0.00009201551,0.00016421144,0.0002316824,0.0000013231715],"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":[0.000027531414,0.00026763786,0.4914458,0.0000130609305,0.000083851926,0.0000040402597,0.00012842486,0.00066838873,0.029870266,0.0025588758,0.00033082647,0.4746013],"study_design_scores_gemma":[0.00030478966,0.00021610963,0.9706503,0.00006680802,0.000019843037,0.000024266801,0.0011955828,0.014844752,0.0003632794,0.012186441,0.00003569679,0.0000921269],"about_ca_topic_score_codex":0.000048263864,"about_ca_topic_score_gemma":0.000003447381,"teacher_disagreement_score":0.4792045,"about_ca_system_score_codex":0.000040215884,"about_ca_system_score_gemma":0.0000798012,"threshold_uncertainty_score":0.9475847},"labels":[],"label_agreement":null},{"id":"W3162676432","doi":"10.1177/00131644211014261","title":"On the Performance of Semi- and Nonparametric Item Response Functions in Computer Adaptive Tests","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"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":"Computerized adaptive testing; Nonparametric statistics; Item response theory; Monotonic function; Parametric statistics; Selection (genetic algorithm); Statistics; Smoothing; Polynomial; Kernel (algebra); Mathematics; Function (biology); Differential item functioning; Sample (material); Computer science; Econometrics; Psychometrics; Artificial intelligence","score_opus":0.622595515931154,"score_gpt":0.4554608671959295,"score_spread":0.16713464873522454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162676432","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":[0.9896255,0.0006333599,0.0009820742,0.006915492,0.0004413631,0.0001077567,0.000003852081,0.0000044074495,0.0012861973],"genre_scores_gemma":[0.99457425,0.00003106523,0.004560649,0.0005937269,0.0000579684,0.000020695326,5.0279283e-7,0.000001992055,0.0001591387],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997507,0.00084376225,0.0003647408,0.0003788627,0.0007762909,0.00012938354],"domain_scores_gemma":[0.96394956,0.03525796,0.00012446489,0.00023803907,0.00036997927,0.00005997715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006843746,0.00008755823,0.00016639222,0.0002377645,0.00011574148,0.000046187102,0.00015901077,0.00004705945,0.0002884709],"category_scores_gemma":[0.04094793,0.000047124497,0.00003251239,0.0017038857,0.00011478594,0.000042124477,0.000052019055,0.00016629374,0.000014020501],"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":[0.0011291389,0.0017933481,0.7719322,0.000010119425,0.00003712654,0.0000042892552,0.0004903547,0.00048765272,0.0018990113,0.0076980917,0.012308722,0.20220995],"study_design_scores_gemma":[0.0001961106,0.0004682621,0.9856955,0.0000345504,0.0000025709842,0.00001843871,0.0001719621,0.00061193964,0.000056810226,0.0122923115,0.00039156404,0.000060023915],"about_ca_topic_score_codex":0.0000030595845,"about_ca_topic_score_gemma":0.0000020803163,"teacher_disagreement_score":0.21376325,"about_ca_system_score_codex":0.000027924209,"about_ca_system_score_gemma":0.000054688324,"threshold_uncertainty_score":0.9671306},"labels":[],"label_agreement":null},{"id":"W3163249028","doi":"10.31234/osf.io/wprg8","title":"We need to change how we compute RMSEA for nested model comparisons in structural equation modeling","year":2021,"lang":"en","type":"preprint","venue":"","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":"Structural equation modeling; Nested set model; Context (archaeology); Mathematics; Square root; Index (typography); Computer science; Applied mathematics; Econometrics; Statistics; Data mining","score_opus":0.8713736100893348,"score_gpt":0.5306916632316865,"score_spread":0.3406819468576483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163249028","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":[0.14075476,0.0006667889,0.8330863,0.022116585,0.0016743614,0.0013250111,0.000044614542,0.000116705116,0.0002148454],"genre_scores_gemma":[0.53244466,0.00004404735,0.46666738,0.00028229874,0.00017005201,0.00013533099,0.000042587206,0.000018295688,0.00019532329],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99489355,0.0005232594,0.001188784,0.0014722402,0.0013069882,0.0006151975],"domain_scores_gemma":[0.98563796,0.011662048,0.00053440145,0.0011170998,0.00082236686,0.00022613509],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0050024213,0.00042844284,0.0012061084,0.0017582452,0.00017106338,0.0011949145,0.0015466552,0.0004047036,0.000037474856],"category_scores_gemma":[0.022825222,0.00033686525,0.00030910826,0.0026232775,0.000026582258,0.00033164132,0.0017826067,0.0005891625,0.0000041991575],"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":[0.00003146956,0.000018416007,0.0014803855,0.000042037747,0.000015764203,0.000001781738,0.002066685,0.92221344,0.000042659874,0.00048023253,0.0015897128,0.0720174],"study_design_scores_gemma":[0.00041866163,0.00003327184,0.0007674032,0.0001770635,0.000014445471,0.000002087895,0.0049824594,0.9509722,0.000015194525,0.042087354,0.00013957573,0.00039027465],"about_ca_topic_score_codex":0.00039516902,"about_ca_topic_score_gemma":0.0003884629,"teacher_disagreement_score":0.3916899,"about_ca_system_score_codex":0.00014890275,"about_ca_system_score_gemma":0.00019293914,"threshold_uncertainty_score":0.9999083},"labels":[],"label_agreement":null},{"id":"W3164067782","doi":"10.1007/s11136-021-02873-7","title":"More flexible response functions for the PROMIS physical functioning item bank by application of a monotonic polynomial approach","year":2021,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Item response theory; Computerized adaptive testing; Item bank; Nonparametric statistics; Patient-Reported Outcomes Measurement Information System; Monotonic function; Trait; Parametric statistics; Statistics; Computer science; Quality of Life Research; Econometrics; Mathematics; Psychometrics; Medicine; Public health","score_opus":0.7543205334325487,"score_gpt":0.5944195435939915,"score_spread":0.15990098983855716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164067782","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":[0.7043845,0.0007238074,0.28928012,0.003684787,0.00010185472,0.00070571405,0.00009013404,0.000026081634,0.0010029919],"genre_scores_gemma":[0.9875729,0.000012352219,0.009152007,0.000040497656,0.00018489097,0.0003045316,0.000013415929,0.000012123245,0.0027072688],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.991714,0.004162291,0.000937631,0.00061657274,0.0021845577,0.0003849582],"domain_scores_gemma":[0.80201256,0.19451196,0.00042674414,0.0011603388,0.0017637888,0.00012460783],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049725465,0.00010648586,0.00046373546,0.0003482293,0.00051147165,0.00011778428,0.0007794366,0.00009954108,0.000045852972],"category_scores_gemma":[0.30992693,0.00007156723,0.00025320565,0.004018704,0.00045088772,0.00012761603,0.00027091583,0.00036882795,0.0000095282485],"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":[0.013352716,0.00258023,0.06656026,0.00046141763,0.00041746418,5.0614915e-7,0.006539433,0.0024026844,0.30692363,0.0062056193,0.14370653,0.45084953],"study_design_scores_gemma":[0.0042682094,0.0013212978,0.5479046,0.00006224788,0.0000695516,0.000008663609,0.07659818,0.22538011,0.040316723,0.016995836,0.086463645,0.0006108951],"about_ca_topic_score_codex":0.00035892424,"about_ca_topic_score_gemma":0.0000045734378,"teacher_disagreement_score":0.48134437,"about_ca_system_score_codex":0.000059695485,"about_ca_system_score_gemma":0.0005728356,"threshold_uncertainty_score":0.9785076},"labels":[],"label_agreement":null},{"id":"W3172809335","doi":"10.5430/ijhe.v10n6p22","title":"The Effect of Multiple-Choice Test Items’ Difficulty Degree on the Reliability Coefficient and the Standard Error of Measurement Depending on the Item Response Theory (IRT)","year":2021,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Item response theory; Statistics; Reliability (semiconductor); Degree (music); Test (biology); Standard error; Mathematics; Function (biology); Psychometrics","score_opus":0.24375367906054937,"score_gpt":0.4476650472345339,"score_spread":0.2039113681739845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172809335","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":[0.96955407,0.0009017199,0.0005423208,0.02516842,0.0027459606,0.0002683832,0.000014577368,0.0000035643607,0.0008009798],"genre_scores_gemma":[0.99904734,0.000033291297,0.0001458239,0.00025843485,0.00019493014,0.000013082215,4.198208e-7,0.000006460677,0.0003002286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99012387,0.005623227,0.0009893937,0.000215529,0.0029176516,0.00013035847],"domain_scores_gemma":[0.5165309,0.47806162,0.0017423751,0.0006171551,0.0029957823,0.00005219564],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04634428,0.00013252629,0.00026698364,0.00016738518,0.0002944946,0.00020132534,0.0011564665,0.000041762883,0.00008447483],"category_scores_gemma":[0.45850956,0.00004414623,0.00020382671,0.00056021166,0.00033893733,0.00007898161,0.000121714314,0.0003442548,0.0000020688615],"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":[0.039273173,0.001457788,0.5935398,0.00003856967,0.0008895192,0.000012288531,0.005219263,0.0049949936,0.020898517,0.06510894,0.025266634,0.24330057],"study_design_scores_gemma":[0.0013090866,0.0005655345,0.9667915,0.0002840263,0.000048985246,0.00003418185,0.002155186,0.00032009347,0.009851221,0.009163094,0.009399825,0.00007723902],"about_ca_topic_score_codex":0.000015679252,"about_ca_topic_score_gemma":0.000007708828,"teacher_disagreement_score":0.47359297,"about_ca_system_score_codex":0.00020442413,"about_ca_system_score_gemma":0.00025379416,"threshold_uncertainty_score":0.98198926},"labels":[],"label_agreement":null},{"id":"W3174167521","doi":"10.33881/2027-1786.rip.14102","title":"Validez y Validación para Pruebas Educativas y Psicológicas: Teoría y Recomendaciones","year":2021,"lang":"es","type":"article","venue":"Revista Iberoamericana de Psicología","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":"Carleton University","funders":"","keywords":"Humanities; Philosophy; Psychology","score_opus":0.27953419530806745,"score_gpt":0.45886523749114416,"score_spread":0.17933104218307672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174167521","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":[0.8380921,0.034318008,0.018330632,0.05420562,0.005304105,0.0018946804,0.0003953047,0.00062971894,0.046829842],"genre_scores_gemma":[0.8198424,0.0072685466,0.14447957,0.0071066213,0.0016464817,0.0002968818,0.00007036031,0.00021557254,0.01907353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98278934,0.007024611,0.0028849086,0.0029234265,0.002093573,0.00228415],"domain_scores_gemma":[0.94665813,0.04510354,0.002455923,0.0032275084,0.0013287367,0.0012261755],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009123565,0.0011281115,0.002793989,0.0011254166,0.0009567233,0.0027512521,0.0025650994,0.0005738446,0.0074488106],"category_scores_gemma":[0.11237429,0.0009945886,0.0010874573,0.011866896,0.001046131,0.00052151125,0.0010933842,0.0013240094,0.0012421136],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015382489,0.0016903954,0.17257723,0.00039974082,0.00069926784,0.0009663173,0.0013248733,0.00009683807,0.008421852,0.015276926,0.114375755,0.68401694],"study_design_scores_gemma":[0.0008771741,0.00056662725,0.105812885,0.0005034887,0.0003996998,0.0006693149,0.0051649865,0.00024900932,0.0019197038,0.005734989,0.87666476,0.0014373466],"about_ca_topic_score_codex":0.00031690238,"about_ca_topic_score_gemma":0.00000936414,"teacher_disagreement_score":0.76228905,"about_ca_system_score_codex":0.00081012,"about_ca_system_score_gemma":0.0025327182,"threshold_uncertainty_score":0.99953556},"labels":[],"label_agreement":null},{"id":"W3175993016","doi":"10.21031/epod.864744","title":"The Comparison of the Equated Tests Scores by Using Various Covariates using Bayesian Nonparametric Model","year":2021,"lang":"en","type":"article","venue":"Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Covariate; Nonparametric statistics; Mathematics; Statistics; Bayesian probability; Item response theory; Econometrics; Psychometrics","score_opus":0.3307558401803789,"score_gpt":0.46108954413433995,"score_spread":0.13033370395396104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175993016","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":[0.7536779,0.006558281,0.2355397,0.0005627296,0.0017778864,0.00047984664,0.00013239642,0.00008761448,0.0011836493],"genre_scores_gemma":[0.92132854,0.00009558106,0.07765013,0.0002425715,0.000114198214,0.000013079219,0.000013150974,0.000069623915,0.00047311137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892342,0.0025355932,0.002646781,0.0014245486,0.0028365161,0.0013223791],"domain_scores_gemma":[0.9455028,0.04735411,0.0024171013,0.0027464028,0.0016505971,0.00032900213],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.007046627,0.00063290633,0.0013270564,0.0009162495,0.0016869416,0.0009272745,0.002843326,0.00038232375,0.0001645527],"category_scores_gemma":[0.109556176,0.0003909228,0.00060097704,0.011994061,0.00072259514,0.00044259962,0.0011195043,0.000899072,0.000039257597],"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":[0.0002805805,0.0010731011,0.37420014,0.00006766925,0.000656357,0.00012525648,0.0022535806,0.44172373,0.08885139,0.0033268132,0.015892377,0.07154899],"study_design_scores_gemma":[0.00078324997,0.000103672246,0.008194925,0.00012358806,0.00016711035,0.0001477386,0.0015230333,0.9451296,0.017730953,0.024504632,0.0010280987,0.0005634134],"about_ca_topic_score_codex":0.00053459895,"about_ca_topic_score_gemma":0.00012566608,"teacher_disagreement_score":0.50340587,"about_ca_system_score_codex":0.00026500353,"about_ca_system_score_gemma":0.0008032421,"threshold_uncertainty_score":0.99985427},"labels":[],"label_agreement":null},{"id":"W3184107741","doi":"10.3390/psych3030023","title":"Estimating Explanatory Extensions of Dichotomous and Polytomous Rasch Models: The eirm Package in R","year":2021,"lang":"en","type":"article","venue":"Psych","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":30,"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":"Polytomous Rasch model; Rasch model; Item response theory; Econometrics; Computer science; Scale (ratio); Logistic regression; Statistical model; Psychology; Statistics; Psychometrics; Machine learning; Mathematics","score_opus":0.4349971242673599,"score_gpt":0.45978103812481624,"score_spread":0.02478391385745632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184107741","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":[0.95311207,0.00426803,0.02853308,0.0010299517,0.00071967475,0.0001373722,0.000009904394,0.000027430186,0.012162494],"genre_scores_gemma":[0.9456021,0.00006496466,0.053766392,0.00028425513,0.00004507688,0.000009649559,7.796361e-7,0.000008934327,0.00021780467],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974515,0.00052316085,0.00063497963,0.00045372918,0.00067789346,0.00025874432],"domain_scores_gemma":[0.9821944,0.01656251,0.00024317062,0.0007209365,0.00020124712,0.00007773871],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0046451967,0.00011614432,0.00032773582,0.00029149634,0.00013652658,0.000088948764,0.00045133237,0.000068112735,0.00009445928],"category_scores_gemma":[0.030846689,0.00007175368,0.00006578761,0.002060709,0.00011635396,0.00014210261,0.00019046463,0.00022620797,0.000008468282],"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":[0.000079317,0.0003893728,0.15863284,0.000051065246,0.000056216195,0.00023827866,0.0066501717,0.0053271665,0.008572436,0.008698265,0.010824155,0.8004807],"study_design_scores_gemma":[0.0014646582,0.00010934316,0.2627529,0.00016883848,0.000027407244,0.00035536467,0.012488527,0.24693787,0.0016279732,0.4725711,0.0010537157,0.000442287],"about_ca_topic_score_codex":0.00008511511,"about_ca_topic_score_gemma":0.000045498415,"teacher_disagreement_score":0.8000384,"about_ca_system_score_codex":0.000011012362,"about_ca_system_score_gemma":0.000056709927,"threshold_uncertainty_score":0.9773169},"labels":[],"label_agreement":null},{"id":"W3185510443","doi":"10.17605/osf.io/275x9","title":"Preregistration (Study 2 and Integrative Data Analysis of Studies 1 and 2)","year":2019,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Computer science","score_opus":0.3825028245136807,"score_gpt":0.4825685019581849,"score_spread":0.10006567744450423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185510443","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":[0.9340364,0.00002959347,0.0039581605,0.00010661693,0.00015751932,0.0006434908,0.00001803832,0.00002506938,0.061025117],"genre_scores_gemma":[0.97359866,0.00014519157,0.0071158744,0.000020357187,0.000012086985,0.000018085702,0.0000050421654,0.0000064075134,0.019078266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941469,0.0015102559,0.00090016687,0.0025086142,0.00074538146,0.00018869281],"domain_scores_gemma":[0.96879727,0.023863452,0.00073628017,0.00605566,0.0004473962,0.000099927835],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.029006884,0.00019107934,0.00082998053,0.0007301454,0.00010333047,0.00016520392,0.0014788355,0.000077129305,0.025451262],"category_scores_gemma":[0.15661444,0.00013960557,0.00007898947,0.0021188888,0.00023571115,0.0004698399,0.0034880799,0.0002003465,0.010517622],"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":[0.00006137567,0.00012588919,0.90680385,0.000023999504,0.0010963057,0.000002204316,0.0053346707,0.00019134868,0.00043673936,0.0004243341,0.0011962777,0.08430301],"study_design_scores_gemma":[0.00045023052,0.000008659662,0.95429116,0.00003809198,0.0005022344,0.000005224183,0.019821962,0.009602673,0.00028646897,0.0135337245,0.0012654902,0.00019407221],"about_ca_topic_score_codex":0.00021958159,"about_ca_topic_score_gemma":0.00019821039,"teacher_disagreement_score":0.12760755,"about_ca_system_score_codex":0.000029330278,"about_ca_system_score_gemma":0.00004333521,"threshold_uncertainty_score":0.99984175},"labels":[],"label_agreement":null},{"id":"W3192789200","doi":"10.3389/fpsyg.2021.517155","title":"Binary Restrictive Threshold Method for Item Exposure Control in Cognitive Diagnostic Computerized Adaptive Testing","year":2021,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Binary number; Cognition; Control (management); Psychology; Computer science; Artificial intelligence; Mathematics","score_opus":0.3403070482027519,"score_gpt":0.4740336226893931,"score_spread":0.13372657448664116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192789200","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":[0.05014238,0.0038825646,0.93646187,0.0007442983,0.0044636438,0.0009004382,0.000084844825,0.00005574525,0.0032641992],"genre_scores_gemma":[0.2779425,0.000084378305,0.7196218,0.0018353403,0.00016330591,0.00025414303,0.0000104319415,0.000026437785,0.00006166156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99314886,0.0026629323,0.0013342861,0.0015490007,0.0005157627,0.00078915706],"domain_scores_gemma":[0.8109626,0.18683867,0.00061115396,0.00066325715,0.00077539735,0.00014889348],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007591327,0.00032499724,0.001209591,0.001553276,0.00013409399,0.000090654125,0.0007825758,0.00035525512,0.0000400541],"category_scores_gemma":[0.21620677,0.00029148353,0.0001816642,0.005852788,0.00019376806,0.00021318746,0.00017387683,0.0006125589,0.0000071811614],"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":[0.00085474935,0.00025227197,0.558885,0.000005742537,0.000060135604,0.00046199653,0.000358755,0.00029409936,0.00026883758,0.00014582848,0.011946688,0.42646593],"study_design_scores_gemma":[0.013081424,0.0012829781,0.63685614,0.00025333368,0.000047850663,0.000114419454,0.00540349,0.105287544,0.00006355492,0.2357696,0.0012946306,0.0005450287],"about_ca_topic_score_codex":0.00002426479,"about_ca_topic_score_gemma":0.000017178238,"teacher_disagreement_score":0.4259209,"about_ca_system_score_codex":0.00009286507,"about_ca_system_score_gemma":0.00015053917,"threshold_uncertainty_score":0.99995375},"labels":[],"label_agreement":null},{"id":"W3205145300","doi":"10.1111/bmsp.12255","title":"A comparative evaluation of factor‐ and component‐based structural equation modelling approaches under (in)correct construct representations","year":2021,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":51,"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":"Component (thermodynamics); Construct (python library); Structural equation modeling; Misrepresentation; Population; Principal component analysis; Factor analysis; Mathematics; Econometrics; Factor (programming language); Statistics; Computer science","score_opus":0.8016671738027995,"score_gpt":0.5424559714075778,"score_spread":0.25921120239522166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205145300","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":[0.4819427,0.000559792,0.5167004,0.0001368813,0.00008295537,0.00007078569,0.000024242354,0.0000016847538,0.00048059772],"genre_scores_gemma":[0.81859535,0.000024847928,0.18131734,0.00003400674,0.000015926118,0.0000018898857,0.0000035529274,0.000003200308,0.000003862127],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959045,0.0015809541,0.0011965373,0.00028583824,0.00087679754,0.00015534692],"domain_scores_gemma":[0.9784634,0.02019897,0.00047807983,0.00012464666,0.0006270996,0.00010777052],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004137191,0.00009592115,0.0006229411,0.00021448323,0.00006907243,0.00010196002,0.0001263294,0.00007680793,0.0003773958],"category_scores_gemma":[0.018861314,0.00008066414,0.000052919542,0.0004265096,0.00038692742,0.00012504359,0.000036553967,0.00025122342,9.838326e-7],"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":[0.0004694892,0.00091321184,0.037147656,0.00018432169,0.0002469002,0.0002906278,0.002496109,0.040748127,0.0011397259,0.17251946,0.00043906464,0.74340534],"study_design_scores_gemma":[0.0009392886,0.00006656194,0.11886338,0.00006412327,0.000031353644,0.00094802503,0.00095239736,0.37955266,0.000030520754,0.49849164,0.0000016921293,0.000058351172],"about_ca_topic_score_codex":0.000009927747,"about_ca_topic_score_gemma":0.000008598924,"teacher_disagreement_score":0.743347,"about_ca_system_score_codex":0.000016616696,"about_ca_system_score_gemma":0.000079806385,"threshold_uncertainty_score":0.98940325},"labels":[],"label_agreement":null},{"id":"W3205378930","doi":"","title":"A critical study of proposed GST in special comparison with Canada New Zealand and Singapore","year":2019,"lang":"en","type":"dissertation","venue":"INFLIBNET","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography","score_opus":0.25948062550007067,"score_gpt":0.46680332668137026,"score_spread":0.20732270118129958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205378930","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":[0.992017,0.00012950868,0.000008878639,0.0000858434,0.00097023905,0.00046554953,0.000013192536,0.000007583452,0.0063022426],"genre_scores_gemma":[0.9945303,0.0000022507434,0.0010524562,0.000023400853,0.00021394416,0.000003063045,0.000021916894,0.000014680065,0.0041379887],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967155,0.00028272148,0.00089204026,0.00051826495,0.0013494113,0.00024205478],"domain_scores_gemma":[0.9893911,0.009395442,0.00047057593,0.0003776301,0.00025255902,0.00011268262],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013009921,0.0002050301,0.00082152156,0.00045828143,0.000044355445,0.00016156647,0.00042330349,0.00013496644,0.00011918185],"category_scores_gemma":[0.019883703,0.00013880034,0.00002245937,0.0011615446,0.000040623323,0.00009295685,0.000044500946,0.00036092114,0.0000020786451],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004422798,0.00016054275,0.9385614,0.000037796748,0.00002070615,0.00004318072,0.0045435396,0.000072451534,0.000015018556,0.000051025603,0.018034028,0.03801806],"study_design_scores_gemma":[0.0013680474,0.00082908757,0.9668197,0.00014804494,0.000027952068,0.0000052380265,0.022821331,0.00013804014,0.000028319715,0.00090118014,0.006676912,0.0002361482],"about_ca_topic_score_codex":0.31406906,"about_ca_topic_score_gemma":0.8020859,"teacher_disagreement_score":0.48801684,"about_ca_system_score_codex":0.000043933454,"about_ca_system_score_gemma":0.0009817006,"threshold_uncertainty_score":0.9883722},"labels":[],"label_agreement":null},{"id":"W3213093900","doi":"10.1007/s11136-021-03037-3","title":"What difference does multiple imputation make in longitudinal modeling of EQ-5D-5L data? Empirical analyses of simulated and observed missing data patterns","year":2021,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Eberhard Karls Universität Tübingen","keywords":"Missing data; Imputation (statistics); Covariate; Statistics; Mixed model; Computer science; Econometrics; Data mining; Mathematics","score_opus":0.977871169050491,"score_gpt":0.6865777363541867,"score_spread":0.29129343269630426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213093900","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":[0.94856846,0.0014517715,0.048855297,0.0006913008,0.000081608654,0.00011888531,0.00021756899,0.000006849712,0.000008245795],"genre_scores_gemma":[0.98450536,0.00035169916,0.0149725685,0.000013391792,0.000025644264,6.5557833e-7,0.00011162249,0.00000631888,0.000012769607],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98908526,0.005125936,0.0019032983,0.0009647304,0.0025721407,0.0003486278],"domain_scores_gemma":[0.8563781,0.13761075,0.00075089815,0.0030529262,0.0020028658,0.000204496],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035969015,0.000119250675,0.00080507307,0.0006557182,0.00009381534,0.0002323557,0.001691176,0.000109820205,0.00004259778],"category_scores_gemma":[0.3853986,0.00008254447,0.00005501737,0.0028788683,0.00025034367,0.00062946364,0.0024805516,0.00033311752,4.2985312e-7],"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":[0.00011908524,0.00015872,0.9410239,0.00020191475,0.00003485041,0.000005049127,0.00048642932,0.0048943367,0.0063917334,0.000005391322,0.000009656069,0.046668928],"study_design_scores_gemma":[0.00032820276,0.000026645454,0.49011496,0.00015379142,0.000004888354,4.6734647e-7,0.0047849403,0.5014035,0.000599939,0.002527616,0.000001294843,0.0000537438],"about_ca_topic_score_codex":0.004558333,"about_ca_topic_score_gemma":0.0010770751,"teacher_disagreement_score":0.49650916,"about_ca_system_score_codex":0.00001916295,"about_ca_system_score_gemma":0.00030341107,"threshold_uncertainty_score":0.99267274},"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":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3216055993","doi":"10.31234/osf.io/qr32u","title":"Measurement Invariance Testing Using Confirmatory Factor Analysis and Alignment Optimization: A Tutorial for Transparent Analysis Planning and Reporting","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Measurement invariance; Confirmatory factor analysis; Key (lock); Field (mathematics); Data science; Plan (archaeology); Management science; Data mining; Machine learning; Structural equation modeling; Mathematics","score_opus":0.8501560226486674,"score_gpt":0.5234001879642686,"score_spread":0.32675583468439884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216055993","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":[0.17348504,0.0019629016,0.82291734,0.000062921725,0.00080785196,0.00047986108,0.00003537394,0.00006467403,0.00018404644],"genre_scores_gemma":[0.5633504,0.000017163375,0.43635705,0.000039754796,0.00015974422,0.00003566969,0.000015939804,0.000012956091,0.0000113672895],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99074405,0.00072523655,0.003872939,0.0019618298,0.002225686,0.00047025026],"domain_scores_gemma":[0.9807338,0.01066794,0.005553417,0.00096385693,0.0018078595,0.00027310953],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01825325,0.0004743816,0.002232129,0.0019888955,0.00048746867,0.0016639471,0.00044680425,0.0003043458,0.000102084276],"category_scores_gemma":[0.12095322,0.00039005067,0.00058787933,0.005631758,0.0000887375,0.00020377662,0.00060855976,0.00033333068,6.9457634e-8],"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":[0.000018461726,0.000022226257,0.36062223,0.00007001413,0.0028792366,0.00001496979,0.0005858443,0.63037026,0.00023056805,0.000008299953,0.0000074628197,0.005170391],"study_design_scores_gemma":[0.00038522293,0.00003175152,0.11464507,0.00018221632,0.0050685005,0.000009994436,0.0016781967,0.876961,0.00019261286,0.00031426043,0.000033996268,0.0004971647],"about_ca_topic_score_codex":0.0004986216,"about_ca_topic_score_gemma":0.00005972485,"teacher_disagreement_score":0.3898653,"about_ca_system_score_codex":0.00019902925,"about_ca_system_score_gemma":0.0003400699,"threshold_uncertainty_score":0.99985516},"labels":[],"label_agreement":null},{"id":"W33388808","doi":"10.55016/ojs/ajer.v49i3.54983","title":"The Jackknife and Multilevel Modeling: A New Application of an Old Trick","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Jackknife resampling; Multilevel model; Psychology; Statistics; Mathematics education; Econometrics; Mathematics; Estimator","score_opus":0.7027471767946046,"score_gpt":0.594211678522578,"score_spread":0.10853549827202669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W33388808","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":[0.97458667,0.0016509843,0.0057838256,0.00616854,0.00024454764,0.00015498085,8.514993e-7,3.2230315e-7,0.011409292],"genre_scores_gemma":[0.9783357,0.00017137155,0.01123988,0.00003632747,0.0001846156,0.0000045551456,4.0006617e-7,0.000006251778,0.010020947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99620783,0.0009445353,0.00081672403,0.00020939916,0.00158739,0.00023411331],"domain_scores_gemma":[0.7194292,0.27768126,0.0004597714,0.00041642296,0.0017328181,0.00028055656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015356546,0.00006854953,0.00018566012,0.000572131,0.00028935153,0.0001570365,0.0008116746,0.000050147966,0.0004388278],"category_scores_gemma":[0.5160499,0.00003922066,0.00006322261,0.0013121461,0.0001356171,0.00026640136,0.00005256352,0.0003062184,0.000020343463],"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":[0.0003433484,0.00066214136,0.15664351,0.000014985619,0.00009092317,4.402871e-7,0.0018915331,0.0035045212,0.0015019339,0.27602348,0.01892488,0.5403983],"study_design_scores_gemma":[0.0013828087,0.00065062573,0.15915254,0.000049301812,0.000022356322,0.00027335007,0.0043011964,0.08018582,0.0005039636,0.6868382,0.06642118,0.00021863548],"about_ca_topic_score_codex":0.00074838364,"about_ca_topic_score_gemma":0.000095068026,"teacher_disagreement_score":0.54017967,"about_ca_system_score_codex":0.000036309404,"about_ca_system_score_gemma":0.000798017,"threshold_uncertainty_score":0.5322303},"labels":[],"label_agreement":null},{"id":"W34381395","doi":"10.3389/fpsyg.2021.643823","title":"The uses of the WISC-III and the WAIS-III with people with a learning disability: Three concerns","year":2005,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"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":"Canadian Institutes of Health Research; Simon Fraser University; Canada Research Chairs","keywords":"Learning disability; Psychology; Wechsler Intelligence Scale for Children; Wechsler Adult Intelligence Scale; Developmental psychology; Cognitive psychology; Psychiatry; Cognition","score_opus":0.1459013275769954,"score_gpt":0.4080447868775073,"score_spread":0.26214345930051186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W34381395","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":[0.8852334,0.0030052909,0.08651002,0.015585305,0.001151197,0.00058525364,0.0000025584295,0.000028188508,0.00789879],"genre_scores_gemma":[0.98402494,0.0002016931,0.014923388,0.00042503854,0.000092805654,0.00003851122,2.0081328e-7,0.000012003838,0.00028143544],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99657005,0.0013082764,0.0005896738,0.0005359664,0.00061318045,0.00038288176],"domain_scores_gemma":[0.98436147,0.013917529,0.00050542556,0.0010578395,0.00011040273,0.0000473413],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.006016925,0.00017247102,0.0005074912,0.000102892416,0.00044083412,0.00009560832,0.0012976896,0.00009134508,0.00003225303],"category_scores_gemma":[0.008451607,0.00005886258,0.00007372441,0.0018340764,0.0033361306,0.00011563731,0.00019469493,0.0004933446,0.0000018523886],"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":[0.00089283555,0.000027903476,0.803222,0.0000014659612,0.000034383862,5.5988124e-7,0.0016188885,0.00016750266,0.0000032154487,0.00075369247,0.0045638597,0.18871371],"study_design_scores_gemma":[0.0055142683,0.00041992904,0.8796664,0.000037290425,0.000040256153,0.000066848734,0.01430449,0.0029555017,0.000013333304,0.053614654,0.043163113,0.00020394029],"about_ca_topic_score_codex":0.00018948846,"about_ca_topic_score_gemma":0.0021928698,"teacher_disagreement_score":0.18850976,"about_ca_system_score_codex":0.000024044422,"about_ca_system_score_gemma":0.000038807655,"threshold_uncertainty_score":0.99990064},"labels":[],"label_agreement":null},{"id":"W35347496","doi":"10.1186/s41687-022-00435-0","title":"スポーツ・コミットメント尺度の検証及びスポーツ・コミットメントのレベルとスポーツ行動診断検査によるスポーツ意識との関連について : 女子大学生を対象に","year":2013,"lang":"ja","type":"article","venue":"Journal of physical education and sport","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Merck Canada; Canadian HIV Trials Network, Canadian Institutes of Health Research","keywords":"Mathematics","score_opus":0.19097017484572829,"score_gpt":0.46403160231006924,"score_spread":0.2730614274643409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W35347496","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":[0.9704395,0.0026737151,0.00041918948,0.003846259,0.004605634,0.00030983705,0.0000043495384,0.000019687779,0.017681826],"genre_scores_gemma":[0.9823229,0.00044823298,0.006413335,0.0010051995,0.003176693,0.000009065137,0.0000020571667,0.000029935927,0.0065926095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947437,0.00030150244,0.0019943286,0.00058364513,0.0018064044,0.00057041267],"domain_scores_gemma":[0.9886509,0.0051246984,0.002490118,0.0006475069,0.0021705432,0.00091621396],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037625353,0.00042390724,0.0012536192,0.0010552267,0.0002817954,0.00075803517,0.0010316101,0.00020490287,0.0017223941],"category_scores_gemma":[0.013844387,0.00029768847,0.0005518137,0.0021826036,0.00032522995,0.0013620707,0.00018102594,0.0008844452,0.00044175368],"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":[0.00007407205,0.0026515524,0.049693756,0.000072027375,0.00014102145,0.000017364075,0.0050167544,0.000034049317,0.001974772,0.004996925,0.078724355,0.8566033],"study_design_scores_gemma":[0.0013974005,0.0015970066,0.7043561,0.00047518933,0.00027372502,0.0006128366,0.028482696,0.002373042,0.0005043382,0.05628028,0.20275909,0.0008882948],"about_ca_topic_score_codex":0.00017116759,"about_ca_topic_score_gemma":0.0000013241631,"teacher_disagreement_score":0.85571504,"about_ca_system_score_codex":0.000098949626,"about_ca_system_score_gemma":0.0010384532,"threshold_uncertainty_score":0.99994755},"labels":[],"label_agreement":null},{"id":"W4205105826","doi":"10.1037/met0000295","title":"Intermittent faking of personality profiles in high-stakes assessments: A grade of membership analysis.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision 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":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"PsycINFO; Psychology; Item response theory; Test (biology); Scale (ratio); Psychometrics; Personality; Social psychology; Big Five personality traits; Ideal (ethics); Test validity; Control (management); Statistics; Applied psychology; Computer science; Artificial intelligence; Clinical psychology; Mathematics","score_opus":0.7410462818435025,"score_gpt":0.6411131628585449,"score_spread":0.0999331189849576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205105826","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":[0.83273464,0.00036739217,0.1607822,0.0003069425,0.0005522253,0.00023175671,0.00003769686,0.000032497628,0.0049546603],"genre_scores_gemma":[0.60644686,0.0000062899076,0.3933063,0.00010640194,0.000016034717,0.000044407727,0.0000025540137,0.00000472409,0.00006642554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98254335,0.012647443,0.0018403956,0.00097151694,0.0015897155,0.0004075685],"domain_scores_gemma":[0.9606238,0.036859885,0.0013357446,0.00089797477,0.00018546784,0.00009711527],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04362603,0.00020703951,0.0012562467,0.0016068795,0.000109044406,0.000039389146,0.0016186568,0.00010523523,0.0034364269],"category_scores_gemma":[0.048772797,0.00014303808,0.0005191994,0.010717125,0.00025494338,0.00010566859,0.00052540266,0.00057691353,0.0000012102059],"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":[0.00017562995,0.0009637883,0.64135414,0.00001787459,0.00021292992,0.000016452586,0.00064354914,0.0008219282,0.0041667824,0.006093894,0.00015957968,0.34537345],"study_design_scores_gemma":[0.00050647947,0.00052288966,0.9081372,0.0000102809345,0.000089036024,0.000008099517,0.0045665368,0.0016935267,0.0006078211,0.083094,0.000586618,0.00017751468],"about_ca_topic_score_codex":0.00021426108,"about_ca_topic_score_gemma":0.000005484202,"teacher_disagreement_score":0.34519592,"about_ca_system_score_codex":0.00007407641,"about_ca_system_score_gemma":0.000021222553,"threshold_uncertainty_score":0.99747455},"labels":[],"label_agreement":null},{"id":"W4205584196","doi":"10.1016/s1701-2163(16)32694-9","title":"Summative Feedback","year":2007,"lang":"en","type":"article","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Summative assessment; Medical physics; Formative assessment; Mathematics education","score_opus":0.16743116186105023,"score_gpt":0.3796139710350999,"score_spread":0.2121828091740497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205584196","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":[0.95065403,0.0047176317,0.0048387293,0.00046059812,0.024026563,0.00005337425,0.0000049181626,0.0000031736822,0.015240983],"genre_scores_gemma":[0.9909904,0.000042751457,0.008166826,0.00037857966,0.0000421652,1.2866617e-7,1.1948646e-7,0.0000043385257,0.0003746656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974575,0.0001747099,0.000988929,0.0001606339,0.0009224752,0.00029576194],"domain_scores_gemma":[0.8215161,0.17567043,0.0012361199,0.00019796364,0.0010782777,0.00030108792],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007857106,0.00009618255,0.00039458676,0.0007574751,0.00012425632,0.00006123852,0.0004684889,0.0000893949,0.00033479425],"category_scores_gemma":[0.36092806,0.0000638636,0.00006163724,0.0020696237,0.00007591949,0.00011936974,0.00008163557,0.00030925925,0.0000015644315],"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":[0.0000029575192,0.0000156041,0.3223311,0.000001951642,0.000026380103,0.00086496037,0.000069952555,0.00002450893,0.000009217096,0.0004069104,0.009214626,0.6670318],"study_design_scores_gemma":[0.0004907332,0.00017252078,0.93229955,0.0000013285029,0.0000106195885,0.0000663331,0.0015706159,0.000037572965,0.000058379715,0.0071986676,0.058009412,0.00008426113],"about_ca_topic_score_codex":0.0037810144,"about_ca_topic_score_gemma":0.014285096,"teacher_disagreement_score":0.66694754,"about_ca_system_score_codex":0.00034788376,"about_ca_system_score_gemma":0.0006943098,"threshold_uncertainty_score":0.7971419},"labels":[],"label_agreement":null},{"id":"W4206128774","doi":"10.1016/j.respe.2021.12.001","title":"The Kessler Abbreviated Psychological Distress Scale (K6) in Canadian population surveys : Report on psychometric assessment practices and analysis of the performance of several reliability coefficients","year":2022,"lang":"en","type":"article","venue":"Revue d Épidémiologie et de Santé Publique","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec en Outaouais; Cégep de l'Outaouais","funders":"","keywords":"Respondent; Reliability (semiconductor); Cronbach's alpha; Confidence interval; Scale (ratio); Population; Psychology; Statistics; Standard error; Distress; Sample (material); Clinical psychology; Psychometrics; Medicine; Mathematics; Geography; Environmental health","score_opus":0.1931897450248653,"score_gpt":0.48120637915904374,"score_spread":0.28801663413417844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206128774","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":[0.9951328,0.00014739434,0.00091817894,0.0013844599,0.00054478995,0.00042139966,0.00012741925,0.000016044452,0.001307494],"genre_scores_gemma":[0.9982037,0.00020334934,0.0012380003,0.00015500294,0.00001494458,0.00005447316,0.000044956174,0.0000065951635,0.00007896245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9842693,0.012150283,0.0014713291,0.0007729005,0.0008489428,0.00048720464],"domain_scores_gemma":[0.96289444,0.032729577,0.0025146962,0.0013763013,0.0003582994,0.00012669124],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.078819744,0.00017614145,0.00067706505,0.0013884039,0.0003998027,0.000104296545,0.0013071011,0.00013417835,0.00006385717],"category_scores_gemma":[0.15882397,0.00009721884,0.00020234457,0.013278625,0.00019963102,0.00018330908,0.00033648318,0.0006880464,2.4398352e-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":[0.000040846935,0.00015167713,0.944504,0.000009191031,0.000036673155,0.0000039154766,0.000050708946,0.028579494,0.000009093242,0.0001311356,0.00010022782,0.026383037],"study_design_scores_gemma":[0.00016456662,0.00019917352,0.96624273,0.000014496517,0.000034433353,0.000021752783,0.00015858395,0.032070808,0.000004076718,0.00069692306,0.00028630285,0.0001061487],"about_ca_topic_score_codex":0.023918444,"about_ca_topic_score_gemma":0.008717861,"teacher_disagreement_score":0.08000422,"about_ca_system_score_codex":0.00043624153,"about_ca_system_score_gemma":0.00025814047,"threshold_uncertainty_score":0.9825814},"labels":[],"label_agreement":null},{"id":"W4206657990","doi":"10.31234/osf.io/d8tuy","title":"The Devil is Mainly in the Nuisance Parameters: Performance of Structural Fit Indices Under Misspecified Structural Models in SEM","year":2021,"lang":"en","type":"preprint","venue":"","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":"Simon Fraser University","funders":"","keywords":"Structural equation modeling; Goodness of fit; Statistics; Mathematics; Econometrics; Cutoff; Latent variable; Factor analysis; Type I and type II errors; Variable (mathematics); Component (thermodynamics); Mathematical analysis","score_opus":0.5924685084379286,"score_gpt":0.46902780513302655,"score_spread":0.12344070330490209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206657990","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":[0.9906358,0.0023377046,0.00096648466,0.0013834623,0.0009859512,0.00047428365,0.000018728564,0.000018966315,0.0031786026],"genre_scores_gemma":[0.9772358,0.00036570168,0.021409841,0.0006955959,0.000057789348,0.000026904896,0.0000041466415,0.00001368347,0.00019056894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9930651,0.001498704,0.0017731173,0.0010484585,0.0020045321,0.00061007607],"domain_scores_gemma":[0.9669496,0.030075885,0.00082609296,0.0018011372,0.00028576047,0.00006155116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008514186,0.00040808605,0.00084704615,0.0005478058,0.00022483458,0.0008934502,0.004135447,0.00031978666,0.0002500401],"category_scores_gemma":[0.00901715,0.00019229275,0.00024929966,0.00281087,0.00034958462,0.00038577834,0.0011962877,0.0012950287,0.0000033874164],"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":[0.00038950675,0.00005538056,0.3824536,0.00020803016,0.00017255738,0.00004410286,0.023287632,0.3172903,0.000107832195,0.0058244937,0.0015846187,0.268582],"study_design_scores_gemma":[0.00041625937,0.00005222489,0.61926025,0.00019460745,0.000011440102,0.000024330619,0.021353198,0.1999246,0.00034912114,0.15794691,0.00008338048,0.00038370796],"about_ca_topic_score_codex":0.00056097924,"about_ca_topic_score_gemma":0.0005690879,"teacher_disagreement_score":0.26819825,"about_ca_system_score_codex":0.000093981274,"about_ca_system_score_gemma":0.00022172401,"threshold_uncertainty_score":0.99933034},"labels":[],"label_agreement":null},{"id":"W4206987968","doi":"10.1090/mbk/139/27","title":"The probabilistic Miller-Rabin primality test","year":2021,"lang":"en","type":"book-chapter","venue":"American Mathematical Society eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Primality test; Probabilistic logic; Test (biology); Computer science; Miller; Mathematics; Prime (order theory); Combinatorics; Artificial intelligence; Biology","score_opus":0.2538631342861301,"score_gpt":0.4036595900774885,"score_spread":0.14979645579135836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206987968","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028063403,0.00042748792,0.00983365,0.0014556424,0.000292756,0.000657327,0.000046137928,0.00016356922,0.9868428],"genre_scores_gemma":[0.0020992411,0.00011801424,0.07711597,0.0012196114,0.0003906553,0.00007903306,0.000005877076,0.000107705186,0.9188639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9932639,0.00032065116,0.0018184612,0.0012303689,0.0026345497,0.0007320727],"domain_scores_gemma":[0.86455184,0.13112263,0.0013864517,0.0020551337,0.00059896393,0.0002849817],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.008530322,0.00059531495,0.0015016865,0.00006627161,0.0007594875,0.0006667375,0.0019433529,0.00029415073,0.0008537345],"category_scores_gemma":[0.108800896,0.00033730702,0.0013878047,0.0003269724,0.0033686273,0.0000359282,0.0008745469,0.0010460505,0.0003955284],"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":[0.0000105978515,0.00008057722,0.00011025504,0.00009905234,0.0002494625,0.000021615215,0.0006576301,0.000002168428,0.000033981923,0.5702335,0.042334132,0.386167],"study_design_scores_gemma":[0.00011108489,0.00012121507,0.00016011276,0.00011235662,0.00007546275,0.000029883819,0.000971101,0.00039835277,0.0000078745425,0.76903445,0.2285538,0.00042429904],"about_ca_topic_score_codex":0.000013146063,"about_ca_topic_score_gemma":0.0000056729514,"teacher_disagreement_score":0.38574266,"about_ca_system_score_codex":0.00018511305,"about_ca_system_score_gemma":0.0003243295,"threshold_uncertainty_score":0.9999079},"labels":[],"label_agreement":null},{"id":"W4210257588","doi":"10.2310/6620.2003.11597","title":"Self-Assessment","year":2003,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.28183315004902587,"score_gpt":0.45821486867683686,"score_spread":0.176381718627811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210257588","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10928016,0.0003271304,0.15319203,0.0017608851,0.0014687448,0.00014381786,0.0000045861307,0.00018519985,0.73363745],"genre_scores_gemma":[0.7071707,0.000027167182,0.29096985,0.0013813825,0.000024725692,0.0000069477082,3.9335518e-7,0.000004317658,0.00041452402],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796027,0.0005189729,0.00038188658,0.00023011917,0.00070921757,0.0001995148],"domain_scores_gemma":[0.99058044,0.008658174,0.00014164876,0.00042487396,0.00011624625,0.0000786292],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003250428,0.00007418669,0.00016740014,0.00022131763,0.00012831332,0.00018789447,0.00034630258,0.000037400947,0.0012304893],"category_scores_gemma":[0.016543351,0.000053320287,0.00006080967,0.0012246713,0.000018234172,0.00015779138,0.00003943747,0.000086113636,0.00039213212],"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":[2.375569e-7,0.00007753476,0.51048416,0.000008326431,0.000021840353,0.000040672687,0.00036098127,0.000026423219,0.000028009477,0.08664047,0.23270597,0.16960539],"study_design_scores_gemma":[0.00015375635,0.000015329524,0.36923632,0.0000026505936,0.000002656102,0.000050026258,0.00022909255,0.0006344127,0.00013858327,0.06377657,0.56567776,0.00008286879],"about_ca_topic_score_codex":0.00000594875,"about_ca_topic_score_gemma":0.0000017966744,"teacher_disagreement_score":0.7332229,"about_ca_system_score_codex":0.000031266994,"about_ca_system_score_gemma":0.000051415973,"threshold_uncertainty_score":0.99968255},"labels":[],"label_agreement":null},{"id":"W4210448219","doi":"10.1007/978-1-4419-1005-9_1152","title":"Multilevel Modeling","year":2012,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.8612226485125948,"score_gpt":0.5144808604504569,"score_spread":0.34674178806213785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210448219","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023507306,0.0014558893,0.2476861,0.00006877331,0.0009730046,0.00008774587,0.000008683302,0.00008485093,0.74961144],"genre_scores_gemma":[0.008126592,0.00011986895,0.0906136,0.00020677451,0.0005030853,0.0000020420234,0.0000024163026,0.000033170978,0.9003924],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966554,0.000054850323,0.00088454346,0.00061286526,0.0014477859,0.0003445642],"domain_scores_gemma":[0.98200303,0.016136447,0.00037101202,0.0009720184,0.0003394137,0.00017808081],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005718892,0.0002790423,0.0005674906,0.0007456532,0.00010878148,0.00014462747,0.0010148654,0.00036849285,0.015308116],"category_scores_gemma":[0.028725198,0.00017879107,0.0002648523,0.00012463055,0.000046220346,0.00014992856,0.00035337583,0.00037344723,0.00224832],"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":[0.0000038080364,0.0000051562897,0.000089884765,0.0000024773392,0.000017421491,0.000002963114,0.000033251938,0.00021628052,0.000004744954,0.1064679,0.0096105635,0.8835455],"study_design_scores_gemma":[0.00009408907,0.00001319365,0.000047581943,0.00002571545,0.000015404321,0.00001091408,0.000029877054,0.04452529,0.0000019757392,0.53460073,0.420324,0.000311224],"about_ca_topic_score_codex":0.000016250013,"about_ca_topic_score_gemma":0.0000023853192,"teacher_disagreement_score":0.8832343,"about_ca_system_score_codex":0.000030238094,"about_ca_system_score_gemma":0.000038354534,"threshold_uncertainty_score":0.99852854},"labels":[],"label_agreement":null},{"id":"W4210694249","doi":"10.1016/j.stueduc.2022.101126","title":"Item wording effects in self-report measures and reading achievement: Does removing careless respondents help?","year":2022,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading (process); Psychology; Mathematics education; Academic achievement; Achievement test; Standardized test; Linguistics","score_opus":0.4604167025598831,"score_gpt":0.5511538330204064,"score_spread":0.09073713046052334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210694249","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":[0.9897216,0.0035060677,0.00013737069,0.0016660425,0.0032015452,0.0005882257,0.0000023513037,0.000020174803,0.0011566016],"genre_scores_gemma":[0.99266243,0.00008767609,0.0062302784,0.00009783083,0.00015550602,0.0004476151,0.000007983026,0.00000931759,0.00030138576],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99264497,0.0027558922,0.00088868197,0.0006861688,0.002749058,0.0002752471],"domain_scores_gemma":[0.95380396,0.04461826,0.0005475607,0.00037001754,0.00061131356,0.00004891836],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04221355,0.00014581591,0.0003341896,0.0013675116,0.00055019365,0.00008563319,0.00033615396,0.00003323363,0.000054199718],"category_scores_gemma":[0.21099113,0.00011494425,0.0000402389,0.0027739739,0.000061258936,0.00025521198,0.00045894238,0.00024564948,0.000002149585],"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":[0.000046491215,0.000104547005,0.9148682,0.000028720013,0.00004054688,0.000010907817,0.010046772,0.0017078572,0.00019913109,0.0007059223,0.0004257289,0.07181523],"study_design_scores_gemma":[0.00054268265,0.000048216636,0.8817748,0.00009382405,0.000021918335,0.000027757887,0.034569856,0.0026099482,0.000029231996,0.079626925,0.00050307,0.00015179468],"about_ca_topic_score_codex":0.000087862274,"about_ca_topic_score_gemma":0.000118140866,"teacher_disagreement_score":0.16877757,"about_ca_system_score_codex":0.0010147482,"about_ca_system_score_gemma":0.00027366326,"threshold_uncertainty_score":0.9862427},"labels":[],"label_agreement":null},{"id":"W4211129752","doi":"10.1007/s41237-022-00158-y","title":"The effect of various simultaneous sources of mechanical error in the estimators of correlation causing deflation in reliability: seeking the best options of correlation for deflation-corrected reliability","year":2022,"lang":"en","type":"article","venue":"Behaviormetrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"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":"Imperial College London; York University","keywords":"Estimator; Statistics; Polychoric correlation; Mathematics; Reliability (semiconductor); Correlation; Correction for attenuation; Dimension (graph theory); Deflation; Correlation coefficient; Variance (accounting); Econometrics; Attenuation; Physics; Combinatorics; Economics","score_opus":0.13687726826461455,"score_gpt":0.416882248747622,"score_spread":0.2800049804830074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211129752","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":[0.9241795,0.00018129629,0.07338797,0.00007431662,0.00053179933,0.0015577856,0.000039260827,0.000012147636,0.000035925266],"genre_scores_gemma":[0.99387765,0.0000066007697,0.005949477,0.000003909514,0.000011642775,0.000112432,0.000014161679,0.000011997015,0.000012139097],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99196196,0.0037419766,0.0021408738,0.00041275634,0.0014907217,0.0002517142],"domain_scores_gemma":[0.7988757,0.19757238,0.0021023222,0.0008699549,0.00055183645,0.000027814196],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03196036,0.0001706374,0.0005619981,0.0008323244,0.0004884847,0.000035239747,0.00068681495,0.00013407692,0.000018056115],"category_scores_gemma":[0.18367179,0.00009667044,0.00023154145,0.0069584246,0.00025164237,0.00015820641,0.00018139143,0.0004839033,3.4732295e-7],"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":[0.00024699816,0.00010308931,0.5162713,0.000018712652,0.000004671439,6.01469e-7,0.0011834506,0.45591852,0.00056458474,0.00016442018,0.0000045387765,0.025519095],"study_design_scores_gemma":[0.000781767,0.000938233,0.3009272,0.00005164111,0.00012193233,0.000013377752,0.004290308,0.68860185,0.00075004,0.0033890295,0.000027576134,0.00010704757],"about_ca_topic_score_codex":0.0012846089,"about_ca_topic_score_gemma":0.00020377197,"teacher_disagreement_score":0.23268335,"about_ca_system_score_codex":0.00023256362,"about_ca_system_score_gemma":0.00015326423,"threshold_uncertainty_score":0.99680054},"labels":[],"label_agreement":null},{"id":"W4214576881","doi":"10.1007/978-3-030-39903-0_1152","title":"Multilevel Modeling","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.8612762847583199,"score_gpt":0.5044064050232675,"score_spread":0.35686987973505235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214576881","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000055232167,0.00025691415,0.3122931,0.00042308978,0.0005480771,0.00008429277,0.000011354691,0.000106678155,0.68627095],"genre_scores_gemma":[0.0050191297,0.00004881919,0.11372134,0.0008245221,0.00037034217,0.000001731627,0.000003171085,0.000035552683,0.8799754],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964721,0.000049478862,0.00091264554,0.00088072807,0.0014783788,0.00020666163],"domain_scores_gemma":[0.98410213,0.014338384,0.00033700414,0.0007399197,0.00030368412,0.00017887051],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025083914,0.0002735579,0.00063126517,0.0004938596,0.00009374439,0.0001952067,0.0011780679,0.00028719852,0.0066994526],"category_scores_gemma":[0.052899033,0.00018182978,0.00028435542,0.00017428343,0.00004062022,0.00008370798,0.00041868404,0.000429887,0.0019062108],"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":[0.000011947873,0.0000042236165,0.00003282552,0.0000059476088,0.000035408393,0.000032237167,0.000052519084,0.0010721227,0.000010619955,0.25860405,0.040488906,0.6996492],"study_design_scores_gemma":[0.00008188377,0.000021588006,0.0000072038174,0.000019076148,0.000008622428,0.000004770401,0.000028907589,0.19459958,0.000001401932,0.570084,0.23492758,0.00021541302],"about_ca_topic_score_codex":0.000010211509,"about_ca_topic_score_gemma":0.0000017923344,"teacher_disagreement_score":0.69943374,"about_ca_system_score_codex":0.000022592421,"about_ca_system_score_gemma":0.000059499933,"threshold_uncertainty_score":0.9988709},"labels":[],"label_agreement":null},{"id":"W4214686438","doi":"10.1111/bmsp.12269","title":"Reliability coefficients for multiple group item response theory models","year":2022,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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":"Reliability (semiconductor); Item response theory; Group (periodic table); Mathematics; Statistics; Econometrics; Reliability engineering; Psychology; Psychometrics; Engineering; Physics","score_opus":0.3057821453871747,"score_gpt":0.4634622157514617,"score_spread":0.157680070364287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214686438","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":[0.2135176,0.00038323313,0.7843809,0.00036482624,0.00046003293,0.00019110089,0.0002330067,0.000010888753,0.00045838725],"genre_scores_gemma":[0.8021678,0.000020071773,0.19700241,0.00054297334,0.00005502924,0.000021363327,0.0000020086245,0.000012876235,0.00017550636],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99334204,0.0033905245,0.0014929107,0.00043557666,0.0009813923,0.0003575357],"domain_scores_gemma":[0.84884316,0.14996025,0.00043221036,0.00023944183,0.0003045209,0.00022041921],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03522916,0.00012649049,0.0006549987,0.00024110403,0.00039083336,0.00012597411,0.00064894906,0.000075280375,0.00076648255],"category_scores_gemma":[0.27608702,0.000103200386,0.00015354066,0.00048387217,0.00038628452,0.000117615156,0.00020818877,0.00048042386,0.0000049516325],"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":[0.009728293,0.0019163209,0.0010379304,0.000060449096,0.00006645095,0.0005000552,0.00041956434,0.00059089396,0.00024918068,0.22586343,0.029725691,0.72984177],"study_design_scores_gemma":[0.0015550669,0.001125391,0.018578133,0.000019862506,0.000021085072,0.0032603375,0.00064686564,0.018622233,9.072709e-7,0.9520822,0.0039681834,0.000119739714],"about_ca_topic_score_codex":0.0000018670484,"about_ca_topic_score_gemma":3.976097e-7,"teacher_disagreement_score":0.729722,"about_ca_system_score_codex":0.000030047388,"about_ca_system_score_gemma":0.000034402878,"threshold_uncertainty_score":0.9934346},"labels":[],"label_agreement":null},{"id":"W4214760420","doi":"10.1186/s12913-022-07577-3","title":"Development of a theory-informed questionnaire to assess the acceptability of healthcare interventions","year":2022,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":538,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Psychological intervention; Medicine; Intervention (counseling); Content validity; Health care; Nursing research; Discriminant validity; Focus group; Health administration; Health informatics; Public health; Nursing; Patient satisfaction; Psychometrics; Clinical psychology","score_opus":0.7507588387515985,"score_gpt":0.6539609633253661,"score_spread":0.09679787542623242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214760420","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":[0.9726901,0.0016396841,0.018983921,0.0031855453,0.0004977373,0.0017115389,0.00006606642,0.000036754194,0.0011886362],"genre_scores_gemma":[0.9566974,0.000014701537,0.042526968,0.00031778598,0.00002454462,0.00027351678,0.0000045357933,0.000007879776,0.00013266256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98248637,0.010171911,0.0021717018,0.0005178063,0.003981265,0.0006709208],"domain_scores_gemma":[0.9298296,0.064256504,0.0011664656,0.0019320098,0.0023646844,0.00045076554],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10299055,0.000104726874,0.0004379078,0.00104083,0.0014234877,0.00007242225,0.0026696785,0.000039119754,0.001360007],"category_scores_gemma":[0.027778348,0.00006694782,0.00015542573,0.007309871,0.00013027198,0.00012996982,0.0020434896,0.0005093808,0.0000151288805],"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":[0.00024323248,0.00024339592,0.26402432,0.0023770803,0.000015725693,3.2933136e-7,0.02937244,0.00023002304,0.000015493426,0.0072533223,0.00014980318,0.69607484],"study_design_scores_gemma":[0.00015728413,0.00030952133,0.8821769,0.00012150601,0.0000010300249,0.0000020329387,0.09941006,0.0003028214,0.00007186025,0.010017934,0.0073701185,0.000058978265],"about_ca_topic_score_codex":0.0012310086,"about_ca_topic_score_gemma":0.0035530971,"teacher_disagreement_score":0.69601583,"about_ca_system_score_codex":0.00036809754,"about_ca_system_score_gemma":0.0028058721,"threshold_uncertainty_score":0.9998765},"labels":[],"label_agreement":null},{"id":"W4220679456","doi":"10.1186/s12874-022-01542-8","title":"Using linear and natural cubic splines, SITAR, and latent trajectory models to characterise nonlinear longitudinal growth trajectories in cohort studies","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; University of Saskatchewan; Children's Hospital of Eastern Ontario","funders":"H2020 European Research Council; University of Bristol; European Commission; Medical Research Council; Royal Society; Economic and Social Research Council; Dairy Farmers of Canada; National Institute of Child Health and Human Development; Canadian Institutes of Health Research; Saskatchewan Health Research Foundation; Wellcome Trust","keywords":"Trajectory; Nonlinear system; Spline (mechanical); Econometrics; Linear model; Latent variable; Statistics; Mathematics; Computer science; Physics","score_opus":0.8894941905454349,"score_gpt":0.6241866468485189,"score_spread":0.265307543696916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220679456","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":[0.9553709,0.008628069,0.03307498,0.0011937213,0.0010664609,0.0005720379,0.000019680869,0.00003732363,0.00003685551],"genre_scores_gemma":[0.5750393,0.001569243,0.42227352,0.0003269206,0.00042810678,0.0001369277,0.0000052671744,0.000030609284,0.00019008026],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.967802,0.023679266,0.0013570853,0.0015367244,0.004449349,0.0011756064],"domain_scores_gemma":[0.69758296,0.29936752,0.00028849946,0.0007437105,0.0010969468,0.00092035317],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12467855,0.0002877746,0.0013241362,0.002174239,0.0006596072,0.00008465765,0.001048007,0.00019032361,0.00022425747],"category_scores_gemma":[0.45775685,0.00021303417,0.00010375468,0.004025867,0.0010013795,0.00023547876,0.0025638153,0.0018638443,0.0000041402823],"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":[0.001664093,0.00024069764,0.91908467,0.0001822913,0.00017493853,0.00058801484,0.0047675716,0.0011938821,0.0024290434,0.0014286133,0.0005578993,0.067688294],"study_design_scores_gemma":[0.002284312,0.0013659399,0.7050354,0.00015247623,0.000054204567,0.0008120897,0.016433453,0.22668058,0.00023645512,0.045243718,0.0009702965,0.000731091],"about_ca_topic_score_codex":0.0010844264,"about_ca_topic_score_gemma":0.00063273555,"teacher_disagreement_score":0.38919854,"about_ca_system_score_codex":0.00020676186,"about_ca_system_score_gemma":0.0006676921,"threshold_uncertainty_score":0.9013276},"labels":[],"label_agreement":null},{"id":"W4220727910","doi":"10.21031/epod.1013784","title":"Analyzing the Effects of Test, Student, and School Predictors on Science Achievement: An Explanatory IRT Modeling Approach","year":2022,"lang":"en","type":"article","venue":"Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Psychology; Test (biology); Item response theory; Mathematics education; Explanatory model; Secondary education; Scale (ratio); Private school; Psychometrics; Developmental psychology; Mathematics; Statistics","score_opus":0.14305144090029645,"score_gpt":0.39980747609458583,"score_spread":0.25675603519428936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220727910","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":[0.98175883,0.001969938,0.010677822,0.00016964298,0.0010594833,0.0007933939,0.00005956077,0.00010724346,0.0034040534],"genre_scores_gemma":[0.99263203,0.000112853755,0.006341026,0.0003236621,0.00015970424,0.00016635456,0.000010435666,0.00004300413,0.00021091364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904214,0.001732525,0.0013525344,0.0017642815,0.0037335365,0.0009957012],"domain_scores_gemma":[0.9720946,0.024269493,0.0008746768,0.001876881,0.0003839998,0.00050033914],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.017570117,0.0004716816,0.00076640316,0.002419821,0.0021168913,0.0005002676,0.0034538256,0.00009781983,0.00016735347],"category_scores_gemma":[0.0549681,0.00033314782,0.00021156295,0.0061150766,0.00069007004,0.00080127234,0.001551016,0.0009705389,0.000021828666],"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":[0.00033489778,0.0023271746,0.83077466,0.0001364746,0.00032414883,0.00014782835,0.0069879806,0.08174342,0.014213664,0.0035998207,0.0033049502,0.05610496],"study_design_scores_gemma":[0.004707964,0.0068759406,0.49018976,0.00023617496,0.00037864325,0.00026717657,0.05346421,0.41594082,0.0039059813,0.018818084,0.003050065,0.002165179],"about_ca_topic_score_codex":0.000073572395,"about_ca_topic_score_gemma":0.0000038002215,"teacher_disagreement_score":0.3405849,"about_ca_system_score_codex":0.00025273557,"about_ca_system_score_gemma":0.00028861672,"threshold_uncertainty_score":0.9999121},"labels":[],"label_agreement":null},{"id":"W4220878283","doi":"10.2147/prom.s355679","title":"How to Improve Interpretability of Patient-Reported Outcome Measures for Clinical Use: A Perspective on Measuring Abilities and Feelings","year":2022,"lang":"en","type":"article","venue":"Patient Related Outcome Measures","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"University of British Columbia; Research Canada","funders":"","keywords":"Interpretability; Perspective (graphical); Feeling; Prom; Scale (ratio); Outcome (game theory); Perception","score_opus":0.5237955622645547,"score_gpt":0.4719558480127806,"score_spread":0.05183971425177408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220878283","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":[0.98882854,0.00081418816,0.0028016043,0.0016959498,0.0030013646,0.0020975627,0.00013136258,0.00014677564,0.00048265787],"genre_scores_gemma":[0.99309725,0.0000119044535,0.0059414185,0.00034736065,0.00003399744,0.00027053436,0.000002997663,0.000044974182,0.00024959282],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98777807,0.0026466656,0.0037746804,0.0017841574,0.0033465973,0.0006698283],"domain_scores_gemma":[0.95327246,0.04021156,0.0022161147,0.0016091391,0.0022937309,0.00039697232],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01837126,0.00049212814,0.0015454489,0.0011170947,0.000588913,0.00031565264,0.0008538084,0.00020643823,0.000040926294],"category_scores_gemma":[0.39174837,0.00036814806,0.0007656702,0.0018441521,0.0003118135,0.00034671315,0.00078774506,0.0009206914,0.0000029576552],"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":[0.0010161997,0.00033021736,0.8639183,0.00002825549,0.00022237762,0.000006307396,0.0044017644,0.00066365575,0.00025646618,0.0006089151,0.00018187777,0.12836568],"study_design_scores_gemma":[0.0067473687,0.01651902,0.7859479,0.00023702461,0.00056769175,0.0000795186,0.0998702,0.0025160878,0.002493328,0.059480816,0.02304605,0.002495005],"about_ca_topic_score_codex":0.0002995996,"about_ca_topic_score_gemma":0.000019785848,"teacher_disagreement_score":0.3733771,"about_ca_system_score_codex":0.0004875057,"about_ca_system_score_gemma":0.00011557614,"threshold_uncertainty_score":0.99987704},"labels":[],"label_agreement":null},{"id":"W4220879717","doi":"10.2196/28692","title":"Statistical Methods for Item Reduction in a Representative Lifestyle Questionnaire: Pilot Questionnaire Study","year":2022,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Center of Innovation Program; Japan Science and Technology Agency","keywords":"Respondent; Psychology; Exploratory factor analysis; Applied psychology; Statistics; Clinical psychology; Mathematics; Psychometrics","score_opus":0.6041755532514097,"score_gpt":0.6909037486040397,"score_spread":0.08672819535262999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220879717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.5048352,0.00087110995,0.47866374,0.010980986,0.003274205,0.0010053564,0.000012855866,0.000016431117,0.00034015143],"genre_scores_gemma":[0.9701295,0.00004350212,0.028923918,0.00006151204,0.00045750162,0.0001678294,8.8671953e-7,0.000016049766,0.00019933147],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9528945,0.034962073,0.0021281734,0.00066325354,0.008783327,0.0005686724],"domain_scores_gemma":[0.3905559,0.5974581,0.0022688007,0.0010721296,0.0074063274,0.0012387203],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1841129,0.00014761805,0.00064434967,0.0026729456,0.00046605966,0.00020975556,0.0017626041,0.00007253782,0.0012675943],"category_scores_gemma":[0.8319356,0.0001075549,0.00013863221,0.0040417775,0.0003417231,0.00046577997,0.00082006556,0.0031971568,0.000007415986],"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":[0.0052534654,0.0035625766,0.08881926,0.000016121208,0.00013629775,0.0005757844,0.0072189476,0.00020520392,0.000489057,0.0018190693,0.024358742,0.8675455],"study_design_scores_gemma":[0.006124967,0.023470705,0.5893641,0.00051878317,0.000035350393,0.0017597061,0.12926453,0.01827679,0.00026648937,0.22052354,0.010055115,0.00033988367],"about_ca_topic_score_codex":0.0005177882,"about_ca_topic_score_gemma":0.00003516899,"teacher_disagreement_score":0.8672056,"about_ca_system_score_codex":0.0007460564,"about_ca_system_score_gemma":0.001035021,"threshold_uncertainty_score":0.9996454},"labels":[],"label_agreement":null},{"id":"W4223932835","doi":"10.1016/j.apmr.2022.03.019","title":"Reporting Guideline for RULER: Rasch Reporting Guideline for Rehabilitation Research: Explanation and Elaboration","year":2022,"lang":"en","type":"letter","venue":"Archives of Physical Medicine and Rehabilitation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"U.S. Department of Defense","keywords":"Checklist; Rasch model; Guideline; Transparency (behavior); Rehabilitation; Consistency (knowledge bases); Consolidated Standards of Reporting Trials; Protocol (science); Ruler; Context (archaeology); Psychology; Medicine; Applied psychology; Medical education; Physical therapy; Nursing; Computer science; Alternative medicine; Psychological intervention","score_opus":0.5005385379172481,"score_gpt":0.5624884271670626,"score_spread":0.06194988924981448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223932835","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.033366136,0.00077126967,0.121979356,0.8385358,0.00074511714,0.003523182,0.0001362629,0.00007045979,0.0008724253],"genre_scores_gemma":[0.02326455,0.00007753841,0.94784933,0.018063724,0.0069928244,0.0012394901,0.0019832982,0.000101904574,0.00042732424],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98407066,0.001824283,0.010144542,0.0014096996,0.002076952,0.0004738779],"domain_scores_gemma":[0.47610992,0.50092185,0.018500263,0.001050557,0.0032752848,0.00014215392],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05884168,0.00032157564,0.0013802449,0.002053617,0.00059058185,0.00007217424,0.0003553748,0.00021019988,0.000022226455],"category_scores_gemma":[0.87150073,0.00023422105,0.0003371853,0.0014842931,0.00089925743,0.00031341743,0.00020949119,0.0008552871,2.90889e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002631781,0.00007105479,0.0012231751,0.0008359829,0.00004377717,0.0000030254757,0.007717744,0.00015294392,0.003217005,0.0021047841,0.70802736,0.27633998],"study_design_scores_gemma":[0.0010758135,0.006120275,0.0020680965,0.00043630015,0.00008410043,0.000007730899,0.011552259,0.029951243,0.00003614668,0.49454755,0.453865,0.0002555022],"about_ca_topic_score_codex":0.00014186579,"about_ca_topic_score_gemma":0.000007634185,"teacher_disagreement_score":0.82587,"about_ca_system_score_codex":0.000054746368,"about_ca_system_score_gemma":0.00016262548,"threshold_uncertainty_score":0.96912056},"labels":[],"label_agreement":null},{"id":"W4225620955","doi":"10.1007/s11136-022-03129-8","title":"A comparison of methods to address item non-response when testing for differential item functioning in multidimensional patient-reported outcome measures","year":2022,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Missing data; Differential item functioning; Statistics; Type I and type II errors; Imputation (statistics); Robustness (evolution); Item response theory; Mathematics; Computer science; Econometrics; Psychometrics","score_opus":0.9296003443393536,"score_gpt":0.6752551009186993,"score_spread":0.25434524342065423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225620955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.92950785,0.00015679823,0.06824808,0.00048766824,0.00046938227,0.00094205333,0.00006037934,0.000024118683,0.00010368544],"genre_scores_gemma":[0.808851,2.2028485e-7,0.19077785,0.00003691347,0.000036352605,0.00016809403,0.00000422171,0.000015187248,0.00011014441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9664059,0.02269868,0.0042264415,0.0009672233,0.00493136,0.0007703511],"domain_scores_gemma":[0.29202005,0.69997233,0.002201611,0.0014149704,0.0039365706,0.00045446717],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14130005,0.00018651047,0.0012438972,0.0024494103,0.0005088904,0.00007405452,0.0009769029,0.00009590021,0.00024053673],"category_scores_gemma":[0.8017828,0.0001579081,0.00024489025,0.004722711,0.00018221827,0.00011486578,0.0012901927,0.0007082545,0.000002270756],"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":[0.0041682506,0.00042839732,0.83981764,0.00005777838,0.00004213633,0.000001229628,0.0033502746,0.0022366836,0.06848489,0.000055693028,0.00084791187,0.080509104],"study_design_scores_gemma":[0.0013696013,0.0012104511,0.95446485,0.000053296877,0.000007528231,0.0000019655026,0.015294092,0.021942038,0.0030482667,0.001185461,0.0012230417,0.0001993943],"about_ca_topic_score_codex":0.0014950966,"about_ca_topic_score_gemma":0.000038211925,"teacher_disagreement_score":0.67727363,"about_ca_system_score_codex":0.00016404313,"about_ca_system_score_gemma":0.00041189135,"threshold_uncertainty_score":0.8842123},"labels":[],"label_agreement":null},{"id":"W4229591651","doi":"10.1007/978-94-007-0753-5_101918","title":"Illiteracy Tests","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Functional illiteracy; Philosophy; Linguistics","score_opus":0.5839757368161601,"score_gpt":0.4896221313631417,"score_spread":0.09435360545301841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229591651","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024197043,0.00052457047,0.028210247,0.00023599098,0.0012814212,0.0001072858,0.00000803043,0.00012206714,0.9694862],"genre_scores_gemma":[0.0009731719,0.00004590343,0.037666596,0.00091576844,0.00047393548,0.0000017546223,0.0000035026962,0.000028416724,0.95989096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963337,0.00009268336,0.0009867613,0.00081138243,0.0015085314,0.00026690643],"domain_scores_gemma":[0.95686287,0.040559195,0.0006343307,0.0013627675,0.00042955333,0.000151295],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005895493,0.00029308617,0.0006582223,0.00086725136,0.00009721266,0.00032987344,0.0012981932,0.00030803483,0.016827937],"category_scores_gemma":[0.08482769,0.00017993341,0.000287497,0.00024349133,0.0000940969,0.00007503348,0.0003077839,0.00034148508,0.0057416866],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022100855,0.000001820573,0.00033913972,0.0000023013001,0.000005946483,0.000006778711,0.00001129882,0.000001151514,0.0000019960257,0.2304149,0.09168194,0.6775305],"study_design_scores_gemma":[0.000049903836,0.000029719811,0.0007044268,0.000020751604,0.0000049338323,0.00001075669,0.0000032760954,0.000043226333,0.0000011180197,0.38285112,0.6161242,0.00015656304],"about_ca_topic_score_codex":0.0000072454923,"about_ca_topic_score_gemma":0.0000034651305,"teacher_disagreement_score":0.67737395,"about_ca_system_score_codex":0.000022537024,"about_ca_system_score_gemma":0.00003753117,"threshold_uncertainty_score":0.9950324},"labels":[],"label_agreement":null},{"id":"W4230351272","doi":"10.1007/978-94-007-0753-5_100774","title":"Correlation of Ordinal Variables","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Ordinal data; Statistics; Correlation; Mathematics; Ordinal regression; Psychology; Geometry","score_opus":0.45547011310252183,"score_gpt":0.43302143042520286,"score_spread":0.022448682677318976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230351272","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012642492,0.00009917858,0.37732404,0.00003428796,0.0006170592,0.000049632352,0.0000043076325,0.000020737605,0.62183815],"genre_scores_gemma":[0.0054962263,0.000022545733,0.04905286,0.00006246971,0.00016428284,7.231512e-7,0.000003969703,0.000013221097,0.9451837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99740666,0.000090007765,0.00088243256,0.0004077554,0.0010871261,0.00012600285],"domain_scores_gemma":[0.9649974,0.032982938,0.0009195301,0.0006246663,0.00042177903,0.000053654992],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00602444,0.00015973818,0.0005514021,0.0006595488,0.000048088263,0.000051313993,0.00060483196,0.00027204546,0.009616537],"category_scores_gemma":[0.042983312,0.00010360997,0.00015980742,0.00022443011,0.000085264335,0.000045532117,0.00014054545,0.00018851025,0.00034300075],"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":[0.0000083736895,0.0000025407396,0.0010420387,0.0000050390886,0.000014546561,8.414512e-7,0.000008338403,0.000100138685,0.000005739602,0.731688,0.02850715,0.23861726],"study_design_scores_gemma":[0.0000885139,0.00006677634,0.0008742433,0.000040150197,0.000016801943,0.000006160552,0.000011421427,0.0016867797,0.0000054223556,0.6068268,0.39025307,0.00012391187],"about_ca_topic_score_codex":0.000020908214,"about_ca_topic_score_gemma":0.0000024435972,"teacher_disagreement_score":0.36174592,"about_ca_system_score_codex":0.000013781216,"about_ca_system_score_gemma":0.0000440813,"threshold_uncertainty_score":0.9912888},"labels":[],"label_agreement":null},{"id":"W4230999613","doi":"10.1007/978-1-4939-7131-2_100693","title":"Multidimensional Embedding","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Calgary","funders":"","keywords":"Computer science","score_opus":0.5786772822411523,"score_gpt":0.49824571084257313,"score_spread":0.0804315713985792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230999613","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014862332,0.00027942852,0.01766042,0.00012988484,0.0019640215,0.000106179075,0.000010649585,0.00011041949,0.97959036],"genre_scores_gemma":[0.00017222558,0.000019336629,0.16075179,0.00033487353,0.0005684998,0.0000011155244,0.00000306108,0.000024708344,0.8381244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960717,0.00007243277,0.00085470104,0.00086931506,0.0018546695,0.0002772026],"domain_scores_gemma":[0.9667119,0.031123182,0.0005307563,0.00092162116,0.00056818867,0.00014438825],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0054971813,0.00028468194,0.0005596657,0.00083309977,0.0001639716,0.00013094235,0.0008056732,0.00034200732,0.094759196],"category_scores_gemma":[0.04637472,0.00018014613,0.00027270507,0.00020542499,0.00017612946,0.00009297149,0.00047355198,0.00030156114,0.0104233],"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":[0.00001624412,0.000008501659,0.00017113969,0.0000031333384,0.00004734838,0.00003042004,0.000061350074,0.000011291867,0.000025880476,0.17728962,0.6148947,0.20744038],"study_design_scores_gemma":[0.00008083991,0.000040384723,0.00008907123,0.000030276917,0.0000073241818,0.000014814778,0.000029081933,0.00071146473,0.000013178719,0.31430003,0.68448436,0.00019915795],"about_ca_topic_score_codex":0.000005002663,"about_ca_topic_score_gemma":0.0000025853699,"teacher_disagreement_score":0.20724122,"about_ca_system_score_codex":0.000033706223,"about_ca_system_score_gemma":0.00006228486,"threshold_uncertainty_score":0.9903472},"labels":[],"label_agreement":null},{"id":"W4231180700","doi":"10.1007/978-0-387-39940-9_5052","title":"Test Collection","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Waterloo","funders":"","keywords":"Test (biology); Computer science; Biology","score_opus":0.2317750746846782,"score_gpt":0.39109244276009053,"score_spread":0.15931736807541233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231180700","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005185278,0.0039964938,0.0027502712,0.00005723258,0.0040191477,0.00056633446,0.00095382717,0.00009074538,0.9875141],"genre_scores_gemma":[0.0006804194,0.0024495798,0.0056327367,0.000031042397,0.0011292119,0.000012840602,0.00013872175,0.000045570498,0.9898799],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99416167,0.00022111073,0.0020299533,0.0009702479,0.0022838293,0.00033319747],"domain_scores_gemma":[0.9671839,0.028184392,0.0019971933,0.0018391461,0.0006120937,0.00018331425],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0064683855,0.0004260538,0.0012149853,0.0014310447,0.00014515959,0.00011775658,0.0011969054,0.00036806992,0.0007298568],"category_scores_gemma":[0.0658895,0.00032725916,0.00026338018,0.00077352824,0.000113332215,0.0002500737,0.00023455804,0.00046808107,0.00045482896],"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":[0.00004051048,0.00009978125,0.0030616245,0.00016651633,0.00008312956,0.00010027888,0.00012654574,0.000042523963,0.00007183525,0.025141763,0.78825855,0.18280692],"study_design_scores_gemma":[0.00024147228,0.00020553943,0.00063566084,0.0004021873,0.000047593832,0.00005331588,0.000087598775,0.0001667527,0.000006590057,0.0076609473,0.99012303,0.00036931736],"about_ca_topic_score_codex":0.00015278366,"about_ca_topic_score_gemma":0.000019624633,"teacher_disagreement_score":0.20186447,"about_ca_system_score_codex":0.00007934638,"about_ca_system_score_gemma":0.0002221809,"threshold_uncertainty_score":0.9999179},"labels":[],"label_agreement":null},{"id":"W4232338866","doi":"10.1007/978-1-4939-7131-2_100372","title":"External Factor Analysis","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Calgary","funders":"","keywords":"Factor (programming language); Computer science; Programming language","score_opus":0.6753318278355495,"score_gpt":0.5027457807605489,"score_spread":0.17258604707500058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232338866","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051964074,0.00023932375,0.16323273,0.000044796565,0.00073787884,0.00006282488,0.000027212622,0.00006795826,0.83506763],"genre_scores_gemma":[0.0027194824,0.000037183567,0.043005366,0.00019902184,0.00048624023,9.3671787e-7,0.0000025070167,0.000016918004,0.95353234],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959514,0.00008509982,0.00091197295,0.0008951748,0.0019031031,0.0002532407],"domain_scores_gemma":[0.98000234,0.01736839,0.00069961196,0.0012917197,0.00047970767,0.00015823635],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003044707,0.00028116192,0.00085816026,0.0023707696,0.00010028332,0.0003357714,0.0014228156,0.00030579168,0.20550197],"category_scores_gemma":[0.021416277,0.0001700401,0.0007640946,0.00091970596,0.00013787954,0.0000898209,0.00031637074,0.00024959692,0.0041762227],"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":[0.00002731097,0.00001660653,0.018968094,0.0000042256825,0.0013945815,0.00004969672,0.00014229104,0.000006711168,0.000031385687,0.06806604,0.0985207,0.81277233],"study_design_scores_gemma":[0.00008113175,0.00007048491,0.016094789,0.000013785767,0.00024554116,0.0000055468972,0.00002588905,0.00023431209,0.000020328258,0.53781563,0.44503435,0.00035819205],"about_ca_topic_score_codex":0.000021982602,"about_ca_topic_score_gemma":0.000026657284,"teacher_disagreement_score":0.81241417,"about_ca_system_score_codex":0.000031250547,"about_ca_system_score_gemma":0.000038104903,"threshold_uncertainty_score":0.99659914},"labels":[],"label_agreement":null},{"id":"W4234048446","doi":"10.1093/med/9780199685219.003.0015","title":"Reporting test results","year":2014,"lang":"en","type":"book","venue":"","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":"McMaster University","funders":"","keywords":"Reliability (semiconductor); Test (biology); Flow chart; Scale (ratio); Chart; Medical physics; Psychology; Medicine; Medical education; Engineering; Statistics; Cartography; Geography","score_opus":0.7504532026062126,"score_gpt":0.5341415242884985,"score_spread":0.21631167831771414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234048446","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012961226,0.00013714122,0.010395112,0.0004982068,0.0015010799,0.00013561503,0.00003201588,0.00020403188,0.98708385],"genre_scores_gemma":[0.00018473533,0.000009031442,0.049039412,0.00037517637,0.0009359055,0.000002922076,0.000018492545,0.000025974634,0.94940835],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902193,0.0002444506,0.0057067187,0.00125962,0.0021745227,0.00039537702],"domain_scores_gemma":[0.47897434,0.4887901,0.025471587,0.0048809224,0.0014984348,0.00038461096],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.05189667,0.00029593642,0.0010621242,0.00085926935,0.0001623057,0.00037399062,0.0014615748,0.0004167197,0.00091634714],"category_scores_gemma":[0.90635586,0.00018384527,0.00032959337,0.0009110921,0.00009683804,0.00008022392,0.00042651282,0.00053946575,0.0015211472],"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":[0.000004059945,0.0000052794826,0.00092219934,0.0000037645416,0.0000053581634,0.000024194289,0.000011976419,0.0000035900814,0.0000027299072,0.0009901166,0.80881286,0.18921389],"study_design_scores_gemma":[0.00013156366,0.00006723705,0.0022466355,0.0000546469,0.00000817026,0.000041800373,0.00002005869,0.00016397287,0.000007310887,0.15787122,0.83916324,0.00022415665],"about_ca_topic_score_codex":0.000010956607,"about_ca_topic_score_gemma":0.000010323395,"teacher_disagreement_score":0.85445917,"about_ca_system_score_codex":0.000068092035,"about_ca_system_score_gemma":0.00029650916,"threshold_uncertainty_score":0.99999696},"labels":[],"label_agreement":null},{"id":"W4234538572","doi":"10.2310/6620.2005.00019","title":"Self-Assessment","year":2005,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2643819910732367,"score_gpt":0.4650700633162458,"score_spread":0.2006880722430091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234538572","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25252798,0.00056659675,0.15457904,0.024906505,0.0012393056,0.00021702913,0.000010968722,0.0004264164,0.5655262],"genre_scores_gemma":[0.6462914,0.000030074116,0.35041234,0.0026751128,0.00013883266,0.000005815103,6.210713e-7,0.000003806457,0.0004420411],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981848,0.00022528463,0.00041539432,0.0002242593,0.00075395516,0.00019630369],"domain_scores_gemma":[0.99239993,0.0068623447,0.00014515863,0.00040646485,0.000108282926,0.00007781727],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002267097,0.00007331788,0.00016261965,0.00023958307,0.00011848282,0.00019668089,0.00048412138,0.000037037764,0.0012306295],"category_scores_gemma":[0.005307587,0.00005269055,0.00006206395,0.00095250783,0.00001777023,0.00025782222,0.00009335802,0.00009023031,0.0008829108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7639904e-7,0.000035151763,0.08572191,0.0000023757364,0.000007961226,0.0000071053764,0.0002177607,0.0000476945,0.000012007181,0.0038454295,0.1938609,0.71624154],"study_design_scores_gemma":[0.000121231096,0.000010466204,0.40636688,0.0000022934194,0.0000020458979,0.000025446121,0.00009486122,0.00663043,0.00007153742,0.0077008503,0.5789098,0.000064157546],"about_ca_topic_score_codex":0.000007775549,"about_ca_topic_score_gemma":0.0000064316355,"teacher_disagreement_score":0.71617734,"about_ca_system_score_codex":0.000046647077,"about_ca_system_score_gemma":0.00003455648,"threshold_uncertainty_score":0.99989504},"labels":[],"label_agreement":null},{"id":"W4235191866","doi":"10.1093/med/9780199685219.003.0012","title":"Item response theory","year":2014,"lang":"en","type":"book","venue":"","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":"McMaster University","funders":"","keywords":"Item response theory; Classical test theory; Scale (ratio); Test (biology); Computer science; Test theory; Cognitive psychology; Psychology; Artificial intelligence; Psychometrics; Developmental psychology; Cartography; Geography","score_opus":0.5747251321570575,"score_gpt":0.5025615853033681,"score_spread":0.07216354685368931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235191866","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013188412,0.00044849355,0.06177117,0.0002768585,0.0014180226,0.00012254923,0.00000783149,0.00014923455,0.93567395],"genre_scores_gemma":[0.00016711377,0.000009667351,0.0147827035,0.0010251302,0.0004034969,0.0000041834637,0.0000022958575,0.000027308266,0.9835781],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927192,0.0034462532,0.0009291771,0.0008504157,0.0017289008,0.0003260961],"domain_scores_gemma":[0.6058665,0.39181748,0.00051936257,0.0014095723,0.00026435952,0.00012275758],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06528503,0.00026952333,0.000699277,0.0012245412,0.0001237778,0.00025970244,0.0019030736,0.0004125508,0.008557438],"category_scores_gemma":[0.51964,0.00016001255,0.00029728605,0.00072573614,0.00015123066,0.00006790443,0.00037573956,0.00042433533,0.0039501064],"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":[0.00018676293,0.0000038962075,0.00008600381,0.0000023916477,0.00001183633,0.000008500051,0.000024501867,0.0000012737975,0.0000052616774,0.054664426,0.7098096,0.23519552],"study_design_scores_gemma":[0.000063952866,0.000049556806,0.00095146155,0.000015512383,0.000005425383,0.000008351755,0.00002759942,0.000027204975,0.0000034611814,0.4338294,0.564888,0.0001300458],"about_ca_topic_score_codex":0.0000011391652,"about_ca_topic_score_gemma":0.0000011260173,"teacher_disagreement_score":0.45435497,"about_ca_system_score_codex":0.00006910084,"about_ca_system_score_gemma":0.0002889575,"threshold_uncertainty_score":0.99682546},"labels":[],"label_agreement":null},{"id":"W4236987526","doi":"10.1080/10705510709336736","title":"The Effect of the Number of Observations per Parameter in Misspecified Confirmatory Factor Analytic Models","year":2007,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":54,"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 Windsor","funders":"","keywords":"Sample size determination; Statistics; Structural equation modeling; Context (archaeology); Mathematics; Confirmatory factor analysis; Covariance; Econometrics; Sample (material); Physics; Geography","score_opus":0.4246153844163098,"score_gpt":0.4715834738566535,"score_spread":0.0469680894403437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236987526","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":[0.85196483,0.00015215945,0.14665183,0.00022177448,0.0006613735,0.00020501755,0.00000666621,0.0000069986927,0.00012934883],"genre_scores_gemma":[0.9854281,0.000012888072,0.0144208325,0.0000068830755,0.00006893211,0.0000022889872,8.771774e-7,0.000009891915,0.000049339826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99520206,0.00097531144,0.001815116,0.0002673301,0.0014064142,0.000333734],"domain_scores_gemma":[0.97355515,0.024105288,0.0011342729,0.00052815845,0.0005902588,0.000086844746],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010076598,0.00018070822,0.00040941976,0.00030372827,0.0005825092,0.00011260716,0.0009451115,0.00010104,0.000053827585],"category_scores_gemma":[0.019249542,0.0000824034,0.00030898492,0.0012695971,0.00017727113,0.00041869652,0.00017885103,0.0005165336,0.0000019562694],"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":[0.0002402762,0.000008200927,0.411939,0.00000844132,0.0000273891,0.0000015726989,0.0016669391,0.5677249,0.0023411217,0.00049990753,0.0000075779612,0.015534713],"study_design_scores_gemma":[0.00047928534,0.00003912927,0.20541182,0.000036062786,0.00001211585,0.000031895008,0.0010665136,0.7350162,0.00031232278,0.057516225,0.000001204238,0.000077184595],"about_ca_topic_score_codex":0.000038254562,"about_ca_topic_score_gemma":0.000019532374,"teacher_disagreement_score":0.20652717,"about_ca_system_score_codex":0.00008377642,"about_ca_system_score_gemma":0.000087360364,"threshold_uncertainty_score":0.98901176},"labels":[],"label_agreement":null},{"id":"W4238955974","doi":"10.1007/978-3-319-24612-3_483","title":"Structural Equation Modeling","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Structural equation modeling; Multivariate statistics; Series (stratigraphy); Computer science; Simultaneous equations model; Applied mathematics; Mathematics; Econometrics; Geology; Machine learning","score_opus":0.8464450682943275,"score_gpt":0.4882610245150216,"score_spread":0.3581840437793059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238955974","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000101558515,0.00022390793,0.23594968,0.0004747457,0.0007098597,0.00009284994,0.00000654927,0.00009236655,0.7623485],"genre_scores_gemma":[0.07964844,0.00003520665,0.097638816,0.00079497846,0.00081883615,0.000001943807,0.000016961934,0.00004433826,0.82100046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969147,0.000056212422,0.00079015293,0.0006628904,0.0014181152,0.00015793738],"domain_scores_gemma":[0.9900223,0.008710191,0.00037151726,0.0005044967,0.00027965245,0.00011185082],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019059425,0.00021641381,0.00045126004,0.00040531895,0.00010325177,0.00022855874,0.0007578715,0.00022012928,0.004578853],"category_scores_gemma":[0.035645403,0.00014234011,0.0001928962,0.00021648256,0.000029897561,0.00012526632,0.00023375006,0.00031405655,0.0005687285],"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":[0.000015620655,8.801118e-7,0.00011562792,0.0000059275358,0.00003058353,0.000011401391,0.0000894534,0.006411101,0.000012544909,0.55544055,0.0070408173,0.43082553],"study_design_scores_gemma":[0.000046820987,0.000019095018,0.000009511121,0.000008291926,0.000006631613,0.0000027988276,0.000031157135,0.39527002,8.9249284e-7,0.5922931,0.012180843,0.00013086136],"about_ca_topic_score_codex":0.000011659794,"about_ca_topic_score_gemma":0.0000022020176,"teacher_disagreement_score":0.43069467,"about_ca_system_score_codex":0.000028711247,"about_ca_system_score_gemma":0.000048119688,"threshold_uncertainty_score":0.9963311},"labels":[],"label_agreement":null},{"id":"W4239440113","doi":"10.2310/6620.2005.00011","title":"Self-Assessment","year":2005,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2643819910732367,"score_gpt":0.4650700633162458,"score_spread":0.2006880722430091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239440113","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25252798,0.00056659675,0.15457904,0.024906505,0.0012393056,0.00021702913,0.000010968722,0.0004264164,0.5655262],"genre_scores_gemma":[0.6462914,0.000030074116,0.35041234,0.0026751128,0.00013883266,0.000005815103,6.210713e-7,0.000003806457,0.0004420411],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981848,0.00022528463,0.00041539432,0.0002242593,0.00075395516,0.00019630369],"domain_scores_gemma":[0.99239993,0.0068623447,0.00014515863,0.00040646485,0.000108282926,0.00007781727],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002267097,0.00007331788,0.00016261965,0.00023958307,0.00011848282,0.00019668089,0.00048412138,0.000037037764,0.0012306295],"category_scores_gemma":[0.005307587,0.00005269055,0.00006206395,0.00095250783,0.00001777023,0.00025782222,0.00009335802,0.00009023031,0.0008829108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7639904e-7,0.000035151763,0.08572191,0.0000023757364,0.000007961226,0.0000071053764,0.0002177607,0.0000476945,0.000012007181,0.0038454295,0.1938609,0.71624154],"study_design_scores_gemma":[0.000121231096,0.000010466204,0.40636688,0.0000022934194,0.0000020458979,0.000025446121,0.00009486122,0.00663043,0.00007153742,0.0077008503,0.5789098,0.000064157546],"about_ca_topic_score_codex":0.000007775549,"about_ca_topic_score_gemma":0.0000064316355,"teacher_disagreement_score":0.71617734,"about_ca_system_score_codex":0.000046647077,"about_ca_system_score_gemma":0.00003455648,"threshold_uncertainty_score":0.99989504},"labels":[],"label_agreement":null},{"id":"W4239494675","doi":"10.2310/6620.2005.00022","title":"Self-Assessment","year":2005,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2643819910732367,"score_gpt":0.4650700633162458,"score_spread":0.2006880722430091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239494675","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25252798,0.00056659675,0.15457904,0.024906505,0.0012393056,0.00021702913,0.000010968722,0.0004264164,0.5655262],"genre_scores_gemma":[0.6462914,0.000030074116,0.35041234,0.0026751128,0.00013883266,0.000005815103,6.210713e-7,0.000003806457,0.0004420411],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981848,0.00022528463,0.00041539432,0.0002242593,0.00075395516,0.00019630369],"domain_scores_gemma":[0.99239993,0.0068623447,0.00014515863,0.00040646485,0.000108282926,0.00007781727],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002267097,0.00007331788,0.00016261965,0.00023958307,0.00011848282,0.00019668089,0.00048412138,0.000037037764,0.0012306295],"category_scores_gemma":[0.005307587,0.00005269055,0.00006206395,0.00095250783,0.00001777023,0.00025782222,0.00009335802,0.00009023031,0.0008829108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7639904e-7,0.000035151763,0.08572191,0.0000023757364,0.000007961226,0.0000071053764,0.0002177607,0.0000476945,0.000012007181,0.0038454295,0.1938609,0.71624154],"study_design_scores_gemma":[0.000121231096,0.000010466204,0.40636688,0.0000022934194,0.0000020458979,0.000025446121,0.00009486122,0.00663043,0.00007153742,0.0077008503,0.5789098,0.000064157546],"about_ca_topic_score_codex":0.000007775549,"about_ca_topic_score_gemma":0.0000064316355,"teacher_disagreement_score":0.71617734,"about_ca_system_score_codex":0.000046647077,"about_ca_system_score_gemma":0.00003455648,"threshold_uncertainty_score":0.99989504},"labels":[],"label_agreement":null},{"id":"W4240308469","doi":"10.1093/med/9780199685219.003.0010","title":"Validity","year":2014,"lang":"en","type":"book","venue":"","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":"McMaster University","funders":"","keywords":"Construct validity; External validity; Criterion validity; Concurrent validity; Psychology; Incremental validity; Scale (ratio); Validity; Construct (python library); Predictive validity; Test validity; Test (biology); Internal validity; Face validity; Sample (material); Content validity; Cognitive psychology; Social psychology; Computer science; Mathematics; Psychometrics; Statistics; Developmental psychology; Geography; Cartography; Internal consistency","score_opus":0.8200006900426946,"score_gpt":0.5315232405478808,"score_spread":0.2884774494948138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240308469","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017759914,0.000080913065,0.08040462,0.00015481879,0.0018475684,0.00007614057,0.0000054385428,0.000105878666,0.91730684],"genre_scores_gemma":[0.00009234214,0.000009775411,0.02448513,0.0005115229,0.00070675154,0.0000019042633,0.0000039213323,0.000014643418,0.974174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962941,0.00044276135,0.00070227147,0.00066612486,0.0016608747,0.0002338832],"domain_scores_gemma":[0.90159583,0.096181825,0.00052385795,0.0012863143,0.00029291149,0.00011928225],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014086377,0.00019548148,0.0006042701,0.00058001897,0.000084961954,0.00021579718,0.0015030105,0.00031323064,0.008597228],"category_scores_gemma":[0.16524293,0.00011694491,0.0002514075,0.0004766477,0.000075426186,0.000050855168,0.00029709557,0.00032339848,0.004602892],"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":[0.0000010174718,0.0000024759668,0.00033479667,0.0000020008663,0.0000029899948,0.000001917077,0.0000035004293,0.0000010550997,3.160695e-7,0.009119695,0.8718454,0.118684836],"study_design_scores_gemma":[0.00003110597,0.000024832518,0.0004908674,0.0000062377426,0.000004037421,0.0000034936916,0.000003114814,0.000050906874,0.0000016439118,0.38852295,0.6107611,0.00009970039],"about_ca_topic_score_codex":0.0000040085715,"about_ca_topic_score_gemma":0.0000037457273,"teacher_disagreement_score":0.37940326,"about_ca_system_score_codex":0.000043548076,"about_ca_system_score_gemma":0.0001439175,"threshold_uncertainty_score":0.99617213},"labels":[],"label_agreement":null},{"id":"W4241133324","doi":"10.1177/0013164408318769","title":"Invariance of the Measurement Model Underlying the Wechsler Adult Intelligence Scale—III in the United States and Canada","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":true,"ca_institutions":"University of Calgary; BC Mental Health & Substance Use Services; University of British Columbia","funders":"","keywords":"Measurement invariance; Psychology; Normative; Latent variable; Statistics; Wechsler Adult Intelligence Scale; Latent variable model; Psychometrics; Test (biology); Item response theory; Sample (material); Level of measurement; Scale (ratio); Structural equation modeling; Confirmatory factor analysis; Intelligence quotient; Set (abstract data type); Developmental psychology; Mathematics; Cognition","score_opus":0.774923581148864,"score_gpt":0.45804181837841057,"score_spread":0.3168817627704534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241133324","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":[0.96222126,0.0007389672,0.0045650764,0.029871343,0.00041380667,0.00034085818,0.000005527182,0.000004234898,0.0018388983],"genre_scores_gemma":[0.9947783,0.0003060373,0.0012929233,0.0034996686,0.00002763794,0.00004115962,6.9669665e-7,0.0000027746923,0.000050808372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958607,0.0006781541,0.0005608786,0.0003682035,0.0023231697,0.00020889378],"domain_scores_gemma":[0.9942394,0.004319829,0.00023925022,0.0004255618,0.0007146728,0.000061306026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007498812,0.00012756891,0.00017472502,0.00010612731,0.0004578927,0.00006990846,0.0008071734,0.00004294246,0.000044169556],"category_scores_gemma":[0.011314486,0.00005164614,0.00003720569,0.0012218592,0.00036664694,0.000046701243,0.000076788405,0.00025650876,9.1845874e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005817134,0.002728,0.60254395,0.000066747045,0.00017558994,0.000007137921,0.03024107,0.0353913,0.0015205914,0.05160478,0.115647614,0.15949148],"study_design_scores_gemma":[0.00018102667,0.000052931195,0.8781536,0.000045605895,0.000007049359,0.00002423589,0.003622827,0.0033897357,0.000030163477,0.11315146,0.0012346548,0.00010670043],"about_ca_topic_score_codex":0.06767186,"about_ca_topic_score_gemma":0.07233101,"teacher_disagreement_score":0.27560964,"about_ca_system_score_codex":0.000094466515,"about_ca_system_score_gemma":0.00026293856,"threshold_uncertainty_score":0.9970136},"labels":[],"label_agreement":null},{"id":"W4242208031","doi":"10.1002/9781118625392.wbecp178","title":"Content Overlap","year":2015,"lang":"en","type":"other","venue":"The Encyclopedia of Clinical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Construct (python library); Set (abstract data type); Content (measure theory); Variance (accounting); Computer science; Psychology; Mathematics","score_opus":0.8592365797054518,"score_gpt":0.6421367245892715,"score_spread":0.21709985511618024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242208031","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004737721,0.0029791533,0.001030219,0.0018532707,0.015194091,0.00034565575,0.00007182317,0.00010266371,0.9779493],"genre_scores_gemma":[0.00038428672,0.0033811848,0.00607155,0.002094132,0.0030016145,0.000012676088,0.000007645962,0.00017861305,0.9848683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905546,0.0033358345,0.00317816,0.0010006707,0.0014991682,0.00043160658],"domain_scores_gemma":[0.9234045,0.06883645,0.0037353116,0.003287685,0.00043750025,0.00029851033],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.028406156,0.00032420552,0.0019005337,0.0005142158,0.000036906462,0.000018923125,0.003331517,0.00087965815,0.005930436],"category_scores_gemma":[0.26213184,0.0001655353,0.00050015806,0.0013502752,0.0010608875,0.000032142954,0.0004031672,0.00095329224,0.0015676247],"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":[0.00006880912,0.00010184287,0.0119379945,0.0000032323767,0.000060606293,0.0000061885635,0.000023499819,3.313684e-7,4.2447672e-7,0.0003441148,0.84899956,0.13845342],"study_design_scores_gemma":[0.0007939693,0.0002912993,0.024160244,0.00002999081,0.00003872085,0.000009677936,0.000108908054,0.000003983658,1.2550244e-7,0.03623885,0.93814903,0.00017519086],"about_ca_topic_score_codex":0.00009589406,"about_ca_topic_score_gemma":0.000043326327,"teacher_disagreement_score":0.23372568,"about_ca_system_score_codex":0.000007202612,"about_ca_system_score_gemma":0.00017372212,"threshold_uncertainty_score":0.99920976},"labels":[],"label_agreement":null},{"id":"W4243043663","doi":"10.2310/6620.2003.6036","title":"Self-Assessment","year":2003,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.28183315004902587,"score_gpt":0.45821486867683686,"score_spread":0.176381718627811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243043663","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10928016,0.0003271304,0.15319203,0.0017608851,0.0014687448,0.00014381786,0.0000045861307,0.00018519985,0.73363745],"genre_scores_gemma":[0.7071707,0.000027167182,0.29096985,0.0013813825,0.000024725692,0.0000069477082,3.9335518e-7,0.000004317658,0.00041452402],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796027,0.0005189729,0.00038188658,0.00023011917,0.00070921757,0.0001995148],"domain_scores_gemma":[0.99058044,0.008658174,0.00014164876,0.00042487396,0.00011624625,0.0000786292],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003250428,0.00007418669,0.00016740014,0.00022131763,0.00012831332,0.00018789447,0.00034630258,0.000037400947,0.0012304893],"category_scores_gemma":[0.016543351,0.000053320287,0.00006080967,0.0012246713,0.000018234172,0.00015779138,0.00003943747,0.000086113636,0.00039213212],"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":[2.375569e-7,0.00007753476,0.51048416,0.000008326431,0.000021840353,0.000040672687,0.00036098127,0.000026423219,0.000028009477,0.08664047,0.23270597,0.16960539],"study_design_scores_gemma":[0.00015375635,0.000015329524,0.36923632,0.0000026505936,0.000002656102,0.000050026258,0.00022909255,0.0006344127,0.00013858327,0.06377657,0.56567776,0.00008286879],"about_ca_topic_score_codex":0.00000594875,"about_ca_topic_score_gemma":0.0000017966744,"teacher_disagreement_score":0.7332229,"about_ca_system_score_codex":0.000031266994,"about_ca_system_score_gemma":0.000051415973,"threshold_uncertainty_score":0.99968255},"labels":[],"label_agreement":null},{"id":"W4244025558","doi":"10.24124/2011/bpgub723","title":"\"Pick Me, Pick Me, I Want to Be a Counsellor\": Assessment of a MEd-Counselling Application Selection Process using Rasch Analysis and Generalizability Theory.","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Rasch model; Generalizability theory; Selection (genetic algorithm); Psychology; Rating scale; Facet (psychology); Scale (ratio); Process (computing); Item response theory; Applied psychology; Medical education; Social psychology; Clinical psychology; Computer science; Medicine; Psychometrics; Artificial intelligence; Developmental psychology","score_opus":0.2889371271362756,"score_gpt":0.5058258340243975,"score_spread":0.2168887068881219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244025558","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":[0.52204347,0.00014564254,0.47486365,0.000016800312,0.00018319923,0.00058113737,0.00001589892,0.00004609939,0.0021040798],"genre_scores_gemma":[0.8597332,0.00024754272,0.13779165,0.00011558675,0.00008806807,0.00014863435,0.00013319125,0.000041122465,0.0017009787],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927443,0.0010665007,0.0019950136,0.0016250996,0.0021376386,0.00043139228],"domain_scores_gemma":[0.98750854,0.006717479,0.0019679384,0.00091730565,0.0026759685,0.00021278004],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01647594,0.00047224213,0.0013932855,0.002420077,0.00035312856,0.00028149152,0.00082810846,0.00041154242,0.00045056938],"category_scores_gemma":[0.0057983887,0.00035427447,0.00032160757,0.0102291955,0.00008341781,0.00030448203,0.00003653471,0.0003505886,0.0000059657923],"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":[0.0012605502,0.0012695529,0.64559984,0.0011213034,0.0037969565,0.0000034722816,0.026769647,0.025735816,0.08060138,0.011511821,0.0005071981,0.20182249],"study_design_scores_gemma":[0.0010235806,0.0005866122,0.30580527,0.00016900158,0.0048091975,0.000018125027,0.023897752,0.43629715,0.028382758,0.19557855,0.0012764425,0.0021555815],"about_ca_topic_score_codex":0.0011078448,"about_ca_topic_score_gemma":0.0013875035,"teacher_disagreement_score":0.41056132,"about_ca_system_score_codex":0.0001121756,"about_ca_system_score_gemma":0.00031745882,"threshold_uncertainty_score":0.9998909},"labels":[],"label_agreement":null},{"id":"W4244056413","doi":"10.1002/9781118445112.stat06402","title":"Test Construction","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Function (biology); Construct (python library); Computer science; Item bank; Computerized adaptive testing; Key (lock); Item response theory; Process (computing); Data mining; Information retrieval; Artificial intelligence; Statistics; Mathematics; Psychometrics; Programming language","score_opus":0.353458140929248,"score_gpt":0.4677002338967999,"score_spread":0.11424209296755189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244056413","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":[0.000026760183,0.0008346245,0.622557,0.00012733573,0.0024827025,0.0003584094,0.026399093,0.0004254234,0.34678864],"genre_scores_gemma":[0.00014916237,0.0013326867,0.6708017,0.00018819098,0.00071844395,0.000012244334,0.0011966135,0.00029487873,0.32530612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937505,0.00059710426,0.0014654872,0.0013518166,0.0021445677,0.0006904881],"domain_scores_gemma":[0.96516675,0.03003197,0.002071575,0.0017175177,0.00065357273,0.00035858984],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023242324,0.00062281697,0.0012441077,0.0015153628,0.00015700833,0.00032650356,0.0015287744,0.0005443287,0.01397609],"category_scores_gemma":[0.11531381,0.0004716339,0.000098338656,0.001702297,0.0005349481,0.0000707972,0.00030423593,0.0008041757,0.0015422344],"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":[0.000007372275,0.00007793758,0.0023065743,0.000029149893,0.000025605115,0.000014978652,0.000011096312,0.000004199381,0.000009200448,0.008635619,0.66397715,0.32490113],"study_design_scores_gemma":[0.00042602277,0.00023256366,0.0015804892,0.00024703622,0.000048664737,0.00002928449,0.00016836614,0.0011072217,0.0000023629918,0.07577861,0.91980225,0.0005771102],"about_ca_topic_score_codex":0.00027933766,"about_ca_topic_score_gemma":0.0004969206,"teacher_disagreement_score":0.324324,"about_ca_system_score_codex":0.00007413329,"about_ca_system_score_gemma":0.0002636973,"threshold_uncertainty_score":0.99977356},"labels":[],"label_agreement":null},{"id":"W4244488309","doi":"10.1007/978-94-007-0753-5_103649","title":"Scale, Interval","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Scale (ratio); Interval (graph theory); Mathematics; Environmental science; Geography; Combinatorics; Cartography","score_opus":0.5733336290732757,"score_gpt":0.470363667834227,"score_spread":0.10296996123904867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244488309","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029552717,0.00010591752,0.07471266,0.00073926884,0.0015475103,0.000083432766,0.000005688648,0.0001009206,0.9226751],"genre_scores_gemma":[0.0005116364,0.000018287385,0.029061308,0.0012340521,0.00042472672,0.0000014014803,0.0000020250848,0.000024127748,0.96872246],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967906,0.00009402458,0.00085090526,0.00071030384,0.0013285636,0.00022559556],"domain_scores_gemma":[0.97362876,0.024313668,0.0004790146,0.0010671066,0.00037988924,0.00013155495],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005949692,0.0002507524,0.0006743676,0.0007286263,0.00007130203,0.00021470386,0.0013787095,0.0003092771,0.01794873],"category_scores_gemma":[0.033746123,0.00013025307,0.0002791252,0.00023498051,0.00009264258,0.00004424544,0.00041741057,0.00034747084,0.0062181517],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004189826,0.0000016293867,0.00016840131,0.0000021793414,0.000009804631,0.0000026646715,0.000010495949,7.068605e-7,0.0000015431685,0.05099956,0.15475747,0.79404134],"study_design_scores_gemma":[0.00005724344,0.00003508436,0.00028650893,0.000025339295,0.0000064146307,0.000010153297,0.000009883183,0.00007360398,0.0000046832474,0.31399992,0.6853382,0.00015295287],"about_ca_topic_score_codex":0.00001121218,"about_ca_topic_score_gemma":0.000020893363,"teacher_disagreement_score":0.7938884,"about_ca_system_score_codex":0.000021244256,"about_ca_system_score_gemma":0.000030706076,"threshold_uncertainty_score":0.99455565},"labels":[],"label_agreement":null},{"id":"W4244854269","doi":"10.2310/6620.2004.00009","title":"Self-Assessment","year":2004,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine; Family medicine","score_opus":0.2631226708143088,"score_gpt":0.459013350376797,"score_spread":0.19589067956248823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244854269","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":[0.36264253,0.00030615978,0.36403474,0.012726905,0.0016803275,0.0002102704,0.00000946511,0.00037089238,0.2580187],"genre_scores_gemma":[0.7053549,0.000024421981,0.2927654,0.0016989673,0.000053051288,0.0000059628856,6.800345e-7,0.000003882426,0.0000927205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982892,0.0001425414,0.00037900673,0.00022952312,0.00076680863,0.00019286617],"domain_scores_gemma":[0.9952355,0.004034238,0.00013949953,0.00040248793,0.00010995306,0.000078321435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018352681,0.000074146614,0.00016408556,0.00023771412,0.00012868649,0.00019550683,0.00047075996,0.00003791223,0.00034982894],"category_scores_gemma":[0.0059393463,0.000053163636,0.00006373563,0.001185129,0.000021964253,0.00019646206,0.00009023461,0.00009061801,0.00048040654],"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":[9.917359e-7,0.0002162653,0.27806926,0.000019518084,0.000046623543,0.00016247176,0.0014808237,0.0007462832,0.00009332333,0.08533864,0.09742337,0.5364024],"study_design_scores_gemma":[0.00036251312,0.00002874523,0.68248993,0.000007154354,0.0000032389978,0.000059243615,0.00023073863,0.00038675952,0.0001707143,0.18731116,0.12884943,0.00010034669],"about_ca_topic_score_codex":0.000031970863,"about_ca_topic_score_gemma":0.0000057195552,"teacher_disagreement_score":0.5363021,"about_ca_system_score_codex":0.0000653473,"about_ca_system_score_gemma":0.000069021786,"threshold_uncertainty_score":0.7110381},"labels":[],"label_agreement":null},{"id":"W4245715125","doi":"10.1002/9781118445112.stat05263","title":"Specificity","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Psychology; Medicine","score_opus":0.4404230759254655,"score_gpt":0.4819114510317137,"score_spread":0.0414883751062482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245715125","genre_codex":"methods","genre_gemma":"other","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":[0.000026543534,0.0009877575,0.5444743,0.000097253105,0.001907297,0.00030480098,0.019755514,0.00034088225,0.43210563],"genre_scores_gemma":[0.00015580631,0.0014439184,0.49308878,0.00023460855,0.00088548654,0.000009723883,0.0011115584,0.00034620235,0.50272393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99212563,0.00095970597,0.0016358792,0.0016306975,0.002789447,0.00085864734],"domain_scores_gemma":[0.97500914,0.019714408,0.001966325,0.0022748436,0.00060006266,0.00043521676],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033343574,0.0007268274,0.0015404671,0.0015788099,0.0001535123,0.00037077285,0.0023805774,0.00057713146,0.026207732],"category_scores_gemma":[0.06594346,0.00053758797,0.00013156857,0.0018209987,0.00039501695,0.00006384365,0.00046597287,0.00097244134,0.0027879896],"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":[0.00001405442,0.00009720268,0.0006555457,0.000028792245,0.000034755598,0.000027822727,0.000017797442,0.000006749421,0.0000054751804,0.012708853,0.76894623,0.2174567],"study_design_scores_gemma":[0.00033576015,0.00016406288,0.0016844367,0.00019534855,0.00003619158,0.000009061707,0.00013048218,0.00088754675,0.0000017684964,0.07584802,0.9200955,0.00061184354],"about_ca_topic_score_codex":0.00046080037,"about_ca_topic_score_gemma":0.00083521596,"teacher_disagreement_score":0.21684486,"about_ca_system_score_codex":0.000081743194,"about_ca_system_score_gemma":0.00023489115,"threshold_uncertainty_score":0.9997076},"labels":[],"label_agreement":null},{"id":"W4246233974","doi":"10.2310/6620.2005.00016","title":"Self-Assessment","year":2005,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2643819910732367,"score_gpt":0.4650700633162458,"score_spread":0.2006880722430091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246233974","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25252798,0.00056659675,0.15457904,0.024906505,0.0012393056,0.00021702913,0.000010968722,0.0004264164,0.5655262],"genre_scores_gemma":[0.6462914,0.000030074116,0.35041234,0.0026751128,0.00013883266,0.000005815103,6.210713e-7,0.000003806457,0.0004420411],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981848,0.00022528463,0.00041539432,0.0002242593,0.00075395516,0.00019630369],"domain_scores_gemma":[0.99239993,0.0068623447,0.00014515863,0.00040646485,0.000108282926,0.00007781727],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002267097,0.00007331788,0.00016261965,0.00023958307,0.00011848282,0.00019668089,0.00048412138,0.000037037764,0.0012306295],"category_scores_gemma":[0.005307587,0.00005269055,0.00006206395,0.00095250783,0.00001777023,0.00025782222,0.00009335802,0.00009023031,0.0008829108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7639904e-7,0.000035151763,0.08572191,0.0000023757364,0.000007961226,0.0000071053764,0.0002177607,0.0000476945,0.000012007181,0.0038454295,0.1938609,0.71624154],"study_design_scores_gemma":[0.000121231096,0.000010466204,0.40636688,0.0000022934194,0.0000020458979,0.000025446121,0.00009486122,0.00663043,0.00007153742,0.0077008503,0.5789098,0.000064157546],"about_ca_topic_score_codex":0.000007775549,"about_ca_topic_score_gemma":0.0000064316355,"teacher_disagreement_score":0.71617734,"about_ca_system_score_codex":0.000046647077,"about_ca_system_score_gemma":0.00003455648,"threshold_uncertainty_score":0.99989504},"labels":[],"label_agreement":null},{"id":"W4246399207","doi":"10.2310/6620.2004.00007","title":"Self-Assessment","year":2004,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2631226708143088,"score_gpt":0.459013350376797,"score_spread":0.19589067956248823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246399207","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":[0.36264253,0.00030615978,0.36403474,0.012726905,0.0016803275,0.0002102704,0.00000946511,0.00037089238,0.2580187],"genre_scores_gemma":[0.7053549,0.000024421981,0.2927654,0.0016989673,0.000053051288,0.0000059628856,6.800345e-7,0.000003882426,0.0000927205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982892,0.0001425414,0.00037900673,0.00022952312,0.00076680863,0.00019286617],"domain_scores_gemma":[0.9952355,0.004034238,0.00013949953,0.00040248793,0.00010995306,0.000078321435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018352681,0.000074146614,0.00016408556,0.00023771412,0.00012868649,0.00019550683,0.00047075996,0.00003791223,0.00034982894],"category_scores_gemma":[0.0059393463,0.000053163636,0.00006373563,0.001185129,0.000021964253,0.00019646206,0.00009023461,0.00009061801,0.00048040654],"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":[9.917359e-7,0.0002162653,0.27806926,0.000019518084,0.000046623543,0.00016247176,0.0014808237,0.0007462832,0.00009332333,0.08533864,0.09742337,0.5364024],"study_design_scores_gemma":[0.00036251312,0.00002874523,0.68248993,0.000007154354,0.0000032389978,0.000059243615,0.00023073863,0.00038675952,0.0001707143,0.18731116,0.12884943,0.00010034669],"about_ca_topic_score_codex":0.000031970863,"about_ca_topic_score_gemma":0.0000057195552,"teacher_disagreement_score":0.5363021,"about_ca_system_score_codex":0.0000653473,"about_ca_system_score_gemma":0.000069021786,"threshold_uncertainty_score":0.7110381},"labels":[],"label_agreement":null},{"id":"W4247011641","doi":"10.1348/000712609x448243","title":"Book Review","year":2009,"lang":"en","type":"article","venue":"British Journal of Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Psychology; SAGE; Structural equation modeling; Psychoanalysis; Statistics; Mathematics; Physics","score_opus":0.3643998450583174,"score_gpt":0.536101019684075,"score_spread":0.17170117462575757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247011641","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020683683,0.9340265,0.014080451,0.02076244,0.0016758136,0.000077344645,0.0000020795205,0.00001449747,0.027292538],"genre_scores_gemma":[0.012921472,0.46768954,0.04029922,0.4727166,0.0011409426,0.0000013925122,6.239365e-7,0.000015906253,0.0052143238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99669015,0.0007275534,0.001344193,0.00024286975,0.0007466988,0.0002485586],"domain_scores_gemma":[0.99450475,0.0034584322,0.0010228396,0.00032298383,0.00054486044,0.0001461628],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009836865,0.000084688225,0.0005630445,0.00032500242,0.000072395545,0.000093201794,0.001069753,0.00007755693,0.0043464485],"category_scores_gemma":[0.06155508,0.00007178497,0.00024617423,0.0011852619,0.000066862354,0.00025284954,0.000025644978,0.00038663272,0.00008797499],"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":[0.000006243085,0.00002830093,0.00016251706,0.000001928282,0.0000037952007,0.00024473088,0.0000030516019,4.3260795e-7,0.000028472386,0.000015208258,0.5463587,0.45314664],"study_design_scores_gemma":[0.00038622358,0.00035006,0.1006425,0.00043726215,0.000011751457,0.01960521,0.0000093051785,0.000001349658,0.0000051542197,0.019113705,0.85936147,0.00007603066],"about_ca_topic_score_codex":0.0000015211414,"about_ca_topic_score_gemma":3.6712748e-7,"teacher_disagreement_score":0.46633694,"about_ca_system_score_codex":0.000010850259,"about_ca_system_score_gemma":0.00003286241,"threshold_uncertainty_score":0.99656373},"labels":[],"label_agreement":null},{"id":"W4247379461","doi":"10.1002/0470013192.bsa670","title":"Test Construction","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistics in Behavioral Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Function (biology); Construct (python library); Computer science; Item bank; Computerized adaptive testing; Key (lock); Item response theory; Process (computing); Information retrieval; Data mining; Artificial intelligence; Statistics; Mathematics; Psychometrics; Programming language","score_opus":0.19599023824961725,"score_gpt":0.46840730384296747,"score_spread":0.2724170655933502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247379461","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017446377,0.00027034103,0.016084881,0.000028692568,0.002673841,0.00029751877,0.0007764439,0.00006736059,0.9780563],"genre_scores_gemma":[0.0031164472,0.00073269906,0.7721904,0.00001482979,0.00027197378,0.0000117632,0.000007612923,0.00008402456,0.22357026],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99513984,0.00011429367,0.0010236973,0.0008283549,0.002427521,0.000466294],"domain_scores_gemma":[0.9909371,0.0067839324,0.0010730509,0.00077088486,0.00027787805,0.00015713049],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004309739,0.00024137953,0.00056739844,0.0023141042,0.00007895318,0.00010123553,0.0017688745,0.00018737704,0.005600159],"category_scores_gemma":[0.04868558,0.000195648,0.000046506888,0.004809966,0.0018552048,0.00016134717,0.00028258166,0.00033418514,0.0001026236],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022095262,0.00013210374,0.15173744,0.0000071631825,7.952731e-7,0.000016712165,0.00008919308,0.000006472607,0.00004486149,0.00289009,0.110463426,0.73460954],"study_design_scores_gemma":[0.0005886693,0.0003317229,0.2399202,0.0002407019,0.000037904996,0.000032415544,0.000692888,0.0002820443,0.00005341311,0.019977152,0.73699105,0.0008518594],"about_ca_topic_score_codex":0.000684545,"about_ca_topic_score_gemma":0.00042141997,"teacher_disagreement_score":0.75610554,"about_ca_system_score_codex":0.00010322277,"about_ca_system_score_gemma":0.0003836918,"threshold_uncertainty_score":0.9953089},"labels":[],"label_agreement":null},{"id":"W4248943796","doi":"10.1007/978-1-0716-1138-8_1","title":"On Framing the Research Question and Choosing the Appropriate Research Design","year":2021,"lang":"en","type":"book-chapter","venue":"Methods in molecular biology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Memorial University of Newfoundland","funders":"","keywords":"Clinical study design; Randomized controlled trial; Psychological intervention; Internal validity; Framing (construction); Research design; Medicine; Relevance (law); Epidemiology; Clinical trial; Management science; Psychology; Intensive care medicine; Medical physics; Statistics; Surgery; Mathematics; Pathology; Engineering; Political science; Nursing","score_opus":0.7902741427521535,"score_gpt":0.6562047129254822,"score_spread":0.13406942982667125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248943796","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":[0.00023424682,0.010645189,0.903674,0.0021446997,0.00066502887,0.00073943095,0.0000027578565,0.000019220297,0.08187542],"genre_scores_gemma":[0.0004639656,0.00095405534,0.97325563,0.00039892163,0.00022081313,0.000081267404,0.0000034681932,0.00005534935,0.02456653],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92370886,0.07093185,0.0010355262,0.0016584268,0.0017595593,0.0009057786],"domain_scores_gemma":[0.72324926,0.27371508,0.00030461463,0.0017603388,0.0008895798,0.000081126964],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2746484,0.00030851236,0.0006886028,0.001822406,0.00081850606,0.0004335714,0.0019786677,0.0008202389,0.00012364113],"category_scores_gemma":[0.3708522,0.00015641675,0.00014628583,0.0018434359,0.0016524722,0.00003094843,0.0014398235,0.0042584897,0.000026025631],"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":[0.00003923127,0.000009436767,0.00003865394,0.0000064710152,0.00002670988,0.000053276104,0.00017835667,0.00008280208,0.008881117,0.41571864,0.00023946812,0.57472587],"study_design_scores_gemma":[0.00012712675,0.00022952595,0.00016405476,0.00015240679,0.000008092535,0.000031010397,0.0003078064,0.0009899404,0.0014753226,0.9660088,0.030332392,0.00017353173],"about_ca_topic_score_codex":0.00008863975,"about_ca_topic_score_gemma":0.000007676261,"teacher_disagreement_score":0.5745523,"about_ca_system_score_codex":0.00012710843,"about_ca_system_score_gemma":0.00021626432,"threshold_uncertainty_score":0.9980387},"labels":[],"label_agreement":null},{"id":"W4249400204","doi":"10.1051/pmed/2013038","title":"Affiches","year":2013,"lang":"fr","type":"article","venue":"Pédagogie médicale","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal","funders":"","keywords":"Medicine","score_opus":0.5145740517529641,"score_gpt":0.48100701912694116,"score_spread":0.03356703262602295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249400204","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3273154,0.12087134,0.0616625,0.115078725,0.019644773,0.0009906434,0.000045440596,0.0005216028,0.35386956],"genre_scores_gemma":[0.12999524,0.0019868645,0.13699748,0.003312915,0.0017911934,0.000085630694,0.0000039654337,0.000057979494,0.72576874],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994587,0.00093560887,0.0010258822,0.0009186864,0.0014503354,0.0010824986],"domain_scores_gemma":[0.9600887,0.037312742,0.00035351122,0.00119618,0.0004231564,0.0006257421],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004793684,0.00032508376,0.0006051282,0.00044596003,0.00032435183,0.0008064881,0.0016327499,0.00037234213,0.04775047],"category_scores_gemma":[0.1077899,0.00025413357,0.0002931196,0.0029487063,0.00077721133,0.00065054366,0.00056637556,0.0005417959,0.024348684],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032670328,0.00013059018,0.01352151,0.000015176795,0.000018602002,0.000014922329,0.00020951554,0.000022162596,0.00018018056,0.0011515648,0.2240976,0.7606349],"study_design_scores_gemma":[0.00038237713,0.0001576453,0.05818832,0.00007568055,0.000024936471,0.000041009644,0.0026180164,0.004150359,0.00031045955,0.081118025,0.8525177,0.00041542217],"about_ca_topic_score_codex":0.00055049214,"about_ca_topic_score_gemma":0.0000062581157,"teacher_disagreement_score":0.7602195,"about_ca_system_score_codex":0.00007823945,"about_ca_system_score_gemma":0.00019137585,"threshold_uncertainty_score":0.9999911},"labels":[],"label_agreement":null},{"id":"W4250867464","doi":"10.1007/978-3-319-69909-7_751-2","title":"Discriminant Validity","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Discriminant; Linear discriminant analysis; Psychology; Artificial intelligence; Computer science","score_opus":0.847662021513052,"score_gpt":0.5130119029156807,"score_spread":0.33465011859737137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250867464","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005543222,0.00068231585,0.019193772,0.0004320328,0.0021290865,0.000086874024,0.000018877001,0.00006778111,0.97733384],"genre_scores_gemma":[0.0005898895,0.00018059288,0.02412516,0.00027597192,0.0003199616,0.000001720249,0.0000073469537,0.000022375212,0.974477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613595,0.00015029084,0.00084495393,0.00090535573,0.0017049011,0.0002585543],"domain_scores_gemma":[0.9686828,0.028992284,0.00045153586,0.0013324948,0.00040415628,0.0001366837],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005283303,0.00027187422,0.0007195333,0.0004514681,0.00012164196,0.00030701587,0.0010178515,0.0002906563,0.026424529],"category_scores_gemma":[0.06459742,0.00016462646,0.0003970372,0.0002537978,0.00009680454,0.00007792286,0.0005632057,0.00036812254,0.0010507698],"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":[0.000003968587,0.000011193977,0.00036096858,0.000006636806,0.000021938547,0.00011836852,0.000022901451,0.0000012005964,0.0000129333885,0.49296945,0.14958866,0.35688177],"study_design_scores_gemma":[0.00004294784,0.000027117392,0.00087586395,0.000028225677,0.000015257944,0.00002119981,0.000057252208,0.000017565233,0.0000189738,0.36670527,0.63200134,0.00018897823],"about_ca_topic_score_codex":0.000016435875,"about_ca_topic_score_gemma":0.00001516816,"teacher_disagreement_score":0.4824127,"about_ca_system_score_codex":0.000033027405,"about_ca_system_score_gemma":0.00009927527,"threshold_uncertainty_score":0.999727},"labels":[],"label_agreement":null},{"id":"W4250943650","doi":"10.1007/978-94-007-0753-5_103556","title":"Response Time Approach to Identifying IER","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Computer science","score_opus":0.616890183372952,"score_gpt":0.4688774892502784,"score_spread":0.1480126941226736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250943650","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000096306954,0.00009183107,0.2359436,0.00032656532,0.0005796701,0.00022666596,0.000007715481,0.000120696546,0.762607],"genre_scores_gemma":[0.00038991915,0.000004064315,0.14384586,0.00089964585,0.00022162255,0.0000065534373,0.0000028609027,0.000042919673,0.85458654],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945011,0.00054162694,0.0010943532,0.0012910772,0.0021620516,0.00040980338],"domain_scores_gemma":[0.9534546,0.043719728,0.00048341817,0.0016840557,0.0003673169,0.0002908381],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0270421,0.00037558124,0.00086935586,0.0019630732,0.00017486505,0.00052869646,0.0018888746,0.0003986476,0.0062991665],"category_scores_gemma":[0.10521059,0.00025614316,0.00032564803,0.0005860508,0.00008109848,0.0000836972,0.00068924157,0.000385503,0.016421925],"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":[0.00033126285,0.000016378977,0.00005785612,0.000010253809,0.000058557678,0.000014254278,0.00019614153,0.00005443455,0.00031267374,0.08684347,0.6617714,0.25033334],"study_design_scores_gemma":[0.00012049898,0.00007147481,0.00046408322,0.00003886683,0.000014053588,0.000023666313,0.0000382244,0.00036703295,0.00001472654,0.095257014,0.90319407,0.0003962758],"about_ca_topic_score_codex":0.0000057837337,"about_ca_topic_score_gemma":5.0942697e-7,"teacher_disagreement_score":0.24993704,"about_ca_system_score_codex":0.00006407665,"about_ca_system_score_gemma":0.00006416101,"threshold_uncertainty_score":0.9999891},"labels":[],"label_agreement":null},{"id":"W4253164021","doi":"10.1198/016214505000000691","title":"Rejoinder","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics","score_opus":0.2224096634831433,"score_gpt":0.47857288979036566,"score_spread":0.2561632263072223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253164021","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":[0.65215784,0.000080612714,0.3108186,0.029641207,0.0012636026,0.00007238794,0.000023853652,0.0000132428595,0.0059286444],"genre_scores_gemma":[0.8923314,0.000010384606,0.10487566,0.001252179,0.00043779708,3.160873e-7,9.467879e-8,0.000004304201,0.0010878155],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99634826,0.00088284456,0.0007714445,0.0001051017,0.0017163244,0.00017602603],"domain_scores_gemma":[0.9596091,0.036451634,0.003086058,0.0001992118,0.0005740754,0.0000799349],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008251292,0.000060823066,0.00031252857,0.0001467007,0.00009787393,0.000106619205,0.00055450917,0.000022934766,0.00016352179],"category_scores_gemma":[0.26105127,0.000031056938,0.00012953817,0.0012756009,0.000071591865,0.00013972621,0.000066337896,0.0002619401,0.000051903757],"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":[0.000034281336,0.000047785587,0.30494168,4.1581438e-7,0.00003811775,0.000002201624,0.00009758853,0.00024496266,0.00018207265,0.0015929819,0.14562348,0.5471944],"study_design_scores_gemma":[0.00017272843,0.000097205964,0.9236294,0.00000430492,0.000021011845,0.000018687077,0.0002249694,0.00081326487,0.000047184945,0.036981236,0.037938405,0.00005156942],"about_ca_topic_score_codex":0.000011834767,"about_ca_topic_score_gemma":0.000004029623,"teacher_disagreement_score":0.61868775,"about_ca_system_score_codex":0.00027102776,"about_ca_system_score_gemma":0.0000633029,"threshold_uncertainty_score":0.7451732},"labels":[],"label_agreement":null},{"id":"W4253816837","doi":"10.22374/1710-6222.23.1.2","title":"20 Years of CAPT: How Far We Have Come","year":2016,"lang":"en","type":"article","venue":"Journal of Population Therapeutics and Clinical Pharmacology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"History","score_opus":0.5882365101444152,"score_gpt":0.574588751453085,"score_spread":0.01364775869133028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253816837","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":[0.9706549,0.0012229206,0.008751545,0.016478775,0.0027347833,0.00007051317,0.0000082998,0.000004978134,0.00007325466],"genre_scores_gemma":[0.9929937,0.002520135,0.0029029371,0.0008745946,0.0004252124,3.0209583e-7,1.9040291e-7,0.0000061830497,0.0002767367],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99697953,0.0008868546,0.0013376822,0.00016758667,0.0004814113,0.00014695818],"domain_scores_gemma":[0.97510445,0.02263558,0.0016217405,0.00013459676,0.0003868623,0.00011677677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006923812,0.00008034578,0.0005006784,0.00028476835,0.00003894315,0.000027909586,0.00035300225,0.00013032209,0.00020389757],"category_scores_gemma":[0.0060671135,0.00004516803,0.00020053962,0.0002845848,0.00017349093,0.00013940826,0.00006406592,0.00020831493,0.0000032190458],"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":[0.00015648936,0.00008484294,0.34398806,0.0000017151235,0.00012752967,0.000006749261,0.000042016454,0.000011075525,0.0034699354,0.0001923443,0.0014502719,0.650469],"study_design_scores_gemma":[0.0025422147,0.0008269199,0.8475575,0.000018108558,0.00014203864,0.00004004389,0.00016714621,0.0006521905,0.00018799266,0.042796396,0.104961626,0.000107856446],"about_ca_topic_score_codex":0.0000043338127,"about_ca_topic_score_gemma":0.0000031748034,"teacher_disagreement_score":0.6503611,"about_ca_system_score_codex":0.000015389833,"about_ca_system_score_gemma":0.000029264307,"threshold_uncertainty_score":0.726334},"labels":[],"label_agreement":null},{"id":"W4255033255","doi":"10.1207/s15328007sem1401_5","title":"Multiplicity Control in Structural Equation Modeling","year":2007,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Type I and type II errors; Multiplicity (mathematics); Statistical power; Sample size determination; False discovery rate; Statistics; Multiple comparisons problem; Mathematics; Structural equation modeling; Computer science; Algorithm","score_opus":0.3975708787621388,"score_gpt":0.4703581866455891,"score_spread":0.07278730788345028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255033255","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":[0.50533414,0.00017444165,0.49279124,0.00025822927,0.0010480882,0.00023683258,0.0000070687624,0.000050860843,0.00009912729],"genre_scores_gemma":[0.9000734,0.0000131476,0.099090636,0.000060703744,0.00068108505,0.0000056261906,0.000012578864,0.00003339979,0.000029433015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99107116,0.0009310659,0.003261226,0.0009741851,0.0026582207,0.0011041525],"domain_scores_gemma":[0.9883206,0.008081097,0.0012130663,0.0006411987,0.001317127,0.00042692575],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.020011362,0.00048690586,0.00078012573,0.0019853099,0.0013013772,0.0006099368,0.001146716,0.00031026066,0.00013744229],"category_scores_gemma":[0.030259835,0.00036238716,0.00035736818,0.0022478176,0.00009136886,0.0016949257,0.00025655873,0.0013479736,0.000022727394],"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":[0.00035480355,0.000012427214,0.07346478,0.000004615749,0.000017633736,0.0000260037,0.001783708,0.8793762,0.001877708,0.00027800153,0.0000028100667,0.042801306],"study_design_scores_gemma":[0.0022908445,0.000092194576,0.026932672,0.00005205679,0.000016598258,0.00018138847,0.003429923,0.8308188,0.000031146268,0.13577576,8.453771e-7,0.00037779412],"about_ca_topic_score_codex":0.00023651845,"about_ca_topic_score_gemma":0.00012494145,"teacher_disagreement_score":0.39473927,"about_ca_system_score_codex":0.00047655497,"about_ca_system_score_gemma":0.00018499502,"threshold_uncertainty_score":0.9999988},"labels":[],"label_agreement":null},{"id":"W4256415333","doi":"10.2310/6620.2004.20306","title":"Self-Assessment","year":2004,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.2631226708143088,"score_gpt":0.459013350376797,"score_spread":0.19589067956248823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256415333","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":[0.36264253,0.00030615978,0.36403474,0.012726905,0.0016803275,0.0002102704,0.00000946511,0.00037089238,0.2580187],"genre_scores_gemma":[0.7053549,0.000024421981,0.2927654,0.0016989673,0.000053051288,0.0000059628856,6.800345e-7,0.000003882426,0.0000927205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982892,0.0001425414,0.00037900673,0.00022952312,0.00076680863,0.00019286617],"domain_scores_gemma":[0.9952355,0.004034238,0.00013949953,0.00040248793,0.00010995306,0.000078321435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018352681,0.000074146614,0.00016408556,0.00023771412,0.00012868649,0.00019550683,0.00047075996,0.00003791223,0.00034982894],"category_scores_gemma":[0.0059393463,0.000053163636,0.00006373563,0.001185129,0.000021964253,0.00019646206,0.00009023461,0.00009061801,0.00048040654],"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":[9.917359e-7,0.0002162653,0.27806926,0.000019518084,0.000046623543,0.00016247176,0.0014808237,0.0007462832,0.00009332333,0.08533864,0.09742337,0.5364024],"study_design_scores_gemma":[0.00036251312,0.00002874523,0.68248993,0.000007154354,0.0000032389978,0.000059243615,0.00023073863,0.00038675952,0.0001707143,0.18731116,0.12884943,0.00010034669],"about_ca_topic_score_codex":0.000031970863,"about_ca_topic_score_gemma":0.0000057195552,"teacher_disagreement_score":0.5363021,"about_ca_system_score_codex":0.0000653473,"about_ca_system_score_gemma":0.000069021786,"threshold_uncertainty_score":0.7110381},"labels":[],"label_agreement":null},{"id":"W4280512083","doi":"10.1177/00131644221096431","title":"Investigating Confidence Intervals of Item Parameters When Some Item Parameters Take Priors in the 2PL and 3PL Models","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Prior probability; Statistics; Covariance; Mathematics; Marginal likelihood; Standard error; Maximum a posteriori estimation; Restricted maximum likelihood; Confidence interval; Maximization; Econometrics; Estimation theory; Bayesian probability; Maximum likelihood; Mathematical optimization","score_opus":0.7746316401685195,"score_gpt":0.4702359430135424,"score_spread":0.3043956971549771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280512083","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":[0.98511964,0.0018402857,0.0008312443,0.010600177,0.0005452365,0.00037517658,0.0000115426965,0.000010250942,0.0006664614],"genre_scores_gemma":[0.97977746,0.000040009527,0.017461604,0.002493347,0.000035332832,0.00014311963,0.0000019140934,0.0000047691265,0.000042419782],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946089,0.0017463363,0.0008830011,0.000637042,0.0018579947,0.00026677235],"domain_scores_gemma":[0.97878104,0.02004546,0.0004731324,0.00039338897,0.00018303085,0.00012396321],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014992902,0.00016609456,0.00033732684,0.00028774372,0.00025263015,0.00013276079,0.00076303375,0.000050983894,0.00015560084],"category_scores_gemma":[0.033697523,0.00010132279,0.0000762804,0.0008384688,0.00031142333,0.00018015526,0.00017340796,0.0003550547,0.0000019877266],"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":[0.00023467712,0.002024971,0.6112234,0.000080849124,0.00012788101,0.000009019919,0.030685198,0.003942939,0.0034168414,0.0716163,0.015133082,0.26150483],"study_design_scores_gemma":[0.0003095533,0.00035247408,0.42479387,0.000042608957,0.0000088082115,0.00003338373,0.006246823,0.0009158573,0.000027968323,0.56667495,0.0004472166,0.00014648198],"about_ca_topic_score_codex":0.00007540542,"about_ca_topic_score_gemma":0.0000047174863,"teacher_disagreement_score":0.49505866,"about_ca_system_score_codex":0.0000527837,"about_ca_system_score_gemma":0.000057721656,"threshold_uncertainty_score":0.97444206},"labels":[],"label_agreement":null},{"id":"W4283080197","doi":"10.1007/s11136-022-03169-0","title":"Accuracy of mixture item response theory models for identifying sample heterogeneity in patient-reported outcomes: a simulation study","year":2022,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Trinity Western University; Western University; University of Manitoba; University of Saskatchewan; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Quality of Life Research; Item response theory; Sample (material); Public health; Psychology; Econometrics; Medicine; Psychometrics; Clinical psychology; Economics; Nursing","score_opus":0.9013700084845456,"score_gpt":0.6644036239285863,"score_spread":0.2369663845559593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283080197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.9396953,0.00021487367,0.058188777,0.00018311397,0.00013491014,0.0014061701,0.00013314832,0.000016144044,0.000027550297],"genre_scores_gemma":[0.9944376,0.0000023055973,0.005330947,0.000035953406,0.000010939443,0.00013247975,0.000005247688,0.000011565943,0.00003301441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95488805,0.035655323,0.0029639236,0.0007802629,0.005210277,0.0005021863],"domain_scores_gemma":[0.14511478,0.84926724,0.0018502577,0.0017280354,0.0018787904,0.00016088352],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2127215,0.0001257912,0.00074313715,0.0017197124,0.00037594177,0.00007458187,0.001075176,0.00006482597,0.00010313208],"category_scores_gemma":[0.803913,0.00010101818,0.00022835395,0.004120781,0.00012720158,0.00027559884,0.0008957471,0.00041945043,6.8212114e-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":[0.0076913745,0.0013044097,0.8650081,0.00007325228,0.00008875145,0.0000046599102,0.010605768,0.08159809,0.0010342646,0.00042653832,0.00007747671,0.03208732],"study_design_scores_gemma":[0.0019073923,0.0009333311,0.73891187,0.000017055558,0.0000066918947,6.62295e-7,0.053725857,0.044969484,0.00019110044,0.15908185,0.00010020178,0.0001545164],"about_ca_topic_score_codex":0.0009998423,"about_ca_topic_score_gemma":0.00006645709,"teacher_disagreement_score":0.8136119,"about_ca_system_score_codex":0.00011295249,"about_ca_system_score_gemma":0.00031660442,"threshold_uncertainty_score":0.8106689},"labels":[],"label_agreement":null},{"id":"W4285496188","doi":"10.1080/00949655.2022.2098499","title":"Estimating longitudinal change in latent variable means: a comparison of non-negative matrix factorization and other item non-response methods","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Mathematics; Statistics; Latent variable; Item response theory; Latent variable model; Factorization; Matrix (chemical analysis); Change detection; Matrix decomposition; Longitudinal data; Econometrics; Variable (mathematics); Applied mathematics; Algorithm; Artificial intelligence; Data mining; Mathematical analysis; Computer science; Psychometrics","score_opus":0.44080481839056845,"score_gpt":0.5709859365924613,"score_spread":0.13018111820189288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285496188","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":[0.3656371,0.000050541974,0.63394105,0.00004085512,0.00018066862,0.000118011514,0.000016709808,0.0000028293196,0.000012249147],"genre_scores_gemma":[0.5658591,6.5391765e-7,0.43409005,0.000018299732,0.000022188076,0.0000018129564,0.0000013453267,0.0000039613406,0.0000026153605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618095,0.0015505933,0.0012000559,0.00020183272,0.0007423969,0.00012414421],"domain_scores_gemma":[0.9484161,0.049928386,0.0011419094,0.00006433137,0.0003756483,0.000073587915],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008926043,0.00010299794,0.00045899002,0.0006827231,0.0001542541,0.00008777644,0.00010594461,0.000040925348,0.00008085892],"category_scores_gemma":[0.028481664,0.000083371306,0.000030750172,0.0010943894,0.00005236775,0.00024662935,0.00008290363,0.00022715866,2.9178986e-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":[0.0004992705,0.000069413625,0.17477323,0.000017408163,0.0000126864525,0.0000031870775,0.003472711,0.738741,0.00026833217,0.00025799294,0.000010968285,0.08187382],"study_design_scores_gemma":[0.00056271703,0.00033177465,0.3579037,0.000022844719,0.000012017011,0.0000072324856,0.0005431337,0.6283084,0.000009863607,0.01223308,0.0000147298115,0.000050488125],"about_ca_topic_score_codex":0.000055593322,"about_ca_topic_score_gemma":0.0000015103152,"teacher_disagreement_score":0.20022199,"about_ca_system_score_codex":0.00006284689,"about_ca_system_score_gemma":0.000042409905,"threshold_uncertainty_score":0.9797019},"labels":[],"label_agreement":null},{"id":"W4292454731","doi":"10.1177/00131644221111402","title":"Comparing the Psychometric Properties of a Scale Across Three Likert and Three Alternative Formats: An Application to the Rosenberg Self-Esteem Scale","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Likert scale; Scale (ratio); Psychology; Acquiescence; Psychometrics; Computer science; Statistics; Clinical psychology; Mathematics","score_opus":0.591184351862449,"score_gpt":0.45387219246827853,"score_spread":0.13731215939417046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292454731","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":[0.9779297,0.0017751893,0.007975584,0.009972205,0.00068857084,0.00078893185,0.000014563971,0.000025375724,0.00082988775],"genre_scores_gemma":[0.9951015,0.00002672862,0.0033231962,0.00081094896,0.0001980831,0.00049852143,0.0000016809445,0.000006980927,0.000032345255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99604917,0.0005336209,0.0006255085,0.0006173582,0.0018815403,0.0002928206],"domain_scores_gemma":[0.99674594,0.0017151909,0.00034031452,0.0006231512,0.0004328222,0.0001425498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010270857,0.00016913941,0.00027794982,0.0001887728,0.0011151234,0.00020199463,0.0010873383,0.00003749097,0.0000613215],"category_scores_gemma":[0.002605751,0.00008082662,0.00006370349,0.0021125332,0.0001937653,0.00014712945,0.00036815283,0.00027278278,0.0000098052205],"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":[0.00030191784,0.0018111689,0.6910167,0.000016888824,0.000062741245,1.5629739e-7,0.007792927,0.0007335208,0.0014972468,0.0018559487,0.0024653976,0.2924454],"study_design_scores_gemma":[0.00029115545,0.00043989194,0.96248525,0.000011238328,0.000010642204,0.000029495588,0.0030856687,0.0014810095,0.000055523156,0.02649871,0.0054790545,0.00013235639],"about_ca_topic_score_codex":0.0001230757,"about_ca_topic_score_gemma":0.00022022164,"teacher_disagreement_score":0.29231304,"about_ca_system_score_codex":0.000067689616,"about_ca_system_score_gemma":0.000033088,"threshold_uncertainty_score":0.85767406},"labels":[],"label_agreement":null},{"id":"W4293408802","doi":"10.1177/01466216221124089","title":"Item Selection With Collaborative Filtering in On-The-Fly Multistage Adaptive Testing","year":2022,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Item bank; Selection (genetic algorithm); Computer science; Item response theory; Collaborative filtering; On the fly; Feature selection; Test (biology); Machine learning; Data mining; Artificial intelligence; Statistics; Recommender system; Mathematics; Psychometrics","score_opus":0.6812333426754545,"score_gpt":0.43299204654842544,"score_spread":0.2482412961270291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293408802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85351354,0.0000939414,0.033866536,0.0009608243,0.00047506654,0.0017366566,0.000018183046,0.00017978935,0.10915546],"genre_scores_gemma":[0.9688712,0.0000010616221,0.029410314,0.0008741032,0.000055607958,0.0007100754,6.415321e-7,0.000014014813,0.00006302418],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939356,0.0012060183,0.0006642339,0.0009872083,0.0027348048,0.00047212976],"domain_scores_gemma":[0.9827898,0.015838912,0.0004424195,0.000490337,0.0003467075,0.00009179107],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013283672,0.00024548717,0.00036651042,0.00036280643,0.00067800365,0.00013495829,0.0008201291,0.000056126304,0.0005516226],"category_scores_gemma":[0.016498785,0.00013980795,0.00004664822,0.006474267,0.00010609409,0.00005057476,0.0001896474,0.00072258624,0.000036792957],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005642999,0.002815352,0.08965644,0.000010137962,0.00016352945,0.000180964,0.0027914736,0.04678565,0.07099558,0.03223433,0.014103996,0.73461956],"study_design_scores_gemma":[0.005518064,0.008989912,0.88807994,0.0001008901,0.000030095205,0.00009479337,0.02435626,0.007005433,0.0034744423,0.042024504,0.018832145,0.0014935369],"about_ca_topic_score_codex":0.000019621531,"about_ca_topic_score_gemma":0.000020446869,"teacher_disagreement_score":0.79842347,"about_ca_system_score_codex":0.00033511908,"about_ca_system_score_gemma":0.00004279819,"threshold_uncertainty_score":0.99178565},"labels":[],"label_agreement":null},{"id":"W4296010629","doi":"10.1016/j.heliyon.2022.e10493","title":"Great diversity in the utilization and reporting of latent growth modeling approaches in type 2 diabetes: A literature review","year":2022,"lang":"en","type":"review","venue":"Heliyon","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Université du Québec à Trois-Rivières; Institut National de Santé Publique du Québec; Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"CINAHL; Latent growth modeling; MEDLINE; Checklist; Medicine; Latent class model; Type 2 diabetes; Clinical study design; Health care; Family medicine; Clinical trial; Diabetes mellitus; Psychology; Computer science; Internal medicine; Machine learning; Psychological intervention; Psychiatry","score_opus":0.8862902505809133,"score_gpt":0.5079650370043434,"score_spread":0.3783252135765699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296010629","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00062549714,0.99808484,0.00007724552,0.000038011553,0.00014910189,0.0005756888,0.0000071655336,0.000008801858,0.0004336724],"genre_scores_gemma":[0.00019182662,0.9989593,0.00068886357,0.000066876455,0.000020977126,0.000024376772,0.000024058656,0.00000840155,0.000015297803],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99402905,0.002063827,0.0023195287,0.0005692544,0.0008125741,0.0002057609],"domain_scores_gemma":[0.98952556,0.007253321,0.002546051,0.0005314938,0.00011432891,0.000029277482],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023947923,0.00020219517,0.0015665899,0.00071096414,0.00011963394,0.00007214876,0.0006706436,0.0001333657,0.000032938242],"category_scores_gemma":[0.10595523,0.000111842666,0.00019469923,0.0066044745,0.00002648203,0.00012036936,0.00071691506,0.0005194215,8.265819e-7],"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":[0.0000017186117,0.000017822065,0.008629425,0.028822828,0.0000073106803,0.000018488769,0.00039815018,0.00001877086,1.0697349e-8,0.000046578767,0.000029111945,0.9620098],"study_design_scores_gemma":[0.00045241776,0.00027557815,0.004671626,0.5357173,0.00067019014,0.00020155832,0.0011289768,0.008610633,2.342959e-7,0.0067420155,0.44038048,0.0011489931],"about_ca_topic_score_codex":0.00001214765,"about_ca_topic_score_gemma":0.0000056561826,"teacher_disagreement_score":0.9608608,"about_ca_system_score_codex":0.000048355792,"about_ca_system_score_gemma":0.000054953274,"threshold_uncertainty_score":0.9015757},"labels":[],"label_agreement":null},{"id":"W4296169238","doi":"10.31234/osf.io/q3djt","title":"The InterModel Vigorish as a lens for understanding (and quantifying) the value of item response models for dichotomously coded items","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Jacobs Foundation; Leverhulme Trust","keywords":"Value (mathematics); Lens (geology); Computer science; Optics; Physics; Machine learning","score_opus":0.7894785360017323,"score_gpt":0.5272314517039378,"score_spread":0.26224708429779453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296169238","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":[0.08947357,0.0010651025,0.8979254,0.0032651823,0.001964434,0.00260198,0.00024569163,0.000074915,0.0033837277],"genre_scores_gemma":[0.9545238,0.00035072575,0.040291578,0.0003727729,0.000105457235,0.0008074385,0.00000834051,0.000057209967,0.0034826873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931052,0.002029026,0.001651919,0.0011676302,0.0014792241,0.0005670294],"domain_scores_gemma":[0.6700534,0.3264472,0.0013690642,0.0015795138,0.0004666036,0.000084188374],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051628023,0.0003749113,0.0008666332,0.0005922845,0.0014382261,0.0008681284,0.002778058,0.0002475415,0.000043877142],"category_scores_gemma":[0.15741292,0.00019073112,0.000604486,0.000984287,0.000378894,0.00017284426,0.002294213,0.0006608466,7.3011716e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012474168,0.00013901954,0.00093105494,0.0002620847,0.00058513775,0.000005068742,0.010710526,0.07331079,0.0009597045,0.84809875,0.02469818,0.027825493],"study_design_scores_gemma":[0.00041049934,0.00020076681,0.0000778955,0.000043755834,0.00003988302,0.0000075869207,0.012784642,0.45423514,0.000057795965,0.5278077,0.004167982,0.00016633628],"about_ca_topic_score_codex":0.00020983307,"about_ca_topic_score_gemma":0.000048121557,"teacher_disagreement_score":0.8650502,"about_ca_system_score_codex":0.00020377735,"about_ca_system_score_gemma":0.00035179043,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W4307097012","doi":"10.31234/osf.io/2hswm","title":"The Accuracy of Bayesian Model Fit Indices in Selecting Among Multidimensional Item Response Theory Models","year":2022,"lang":"en","type":"preprint","venue":"","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":"McGill University","funders":"","keywords":"Curse of dimensionality; Nested set model; Deviance information criterion; Bayesian probability; Statistics; Bayesian information criterion; Computer science; Mathematics; Econometrics; Bayesian inference; Data mining","score_opus":0.47889339208041737,"score_gpt":0.48674954262737374,"score_spread":0.007856150546956375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307097012","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":[0.8364999,0.00071479724,0.15445636,0.00053501176,0.00059690967,0.0005609536,0.00003431002,0.00007445938,0.0065272893],"genre_scores_gemma":[0.93309927,0.00007577239,0.06407924,0.00014387957,0.000032460783,0.00009090805,0.0000030539054,0.000027711467,0.002447678],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9858357,0.0075050676,0.002165267,0.001274989,0.0026252214,0.00059375464],"domain_scores_gemma":[0.5638254,0.43163523,0.0022211182,0.0017657517,0.0004253942,0.00012710356],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08064235,0.00036917464,0.0008072144,0.0016034814,0.00058872625,0.00026333155,0.0029460022,0.00030083998,0.00042532984],"category_scores_gemma":[0.3559909,0.00022285743,0.00033246435,0.0028592665,0.00024913208,0.00031955988,0.0044523007,0.0017090708,0.00000282446],"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":[0.00096442,0.00006817231,0.024985794,0.000012633908,0.000040701398,0.000009724324,0.0018768664,0.9252487,0.00008298154,0.0058159465,0.0006041173,0.04028994],"study_design_scores_gemma":[0.00018552928,0.000027562988,0.019759485,0.00004711564,0.0000071735108,0.0000025888583,0.0033708815,0.67538524,0.000060499693,0.30088517,0.00007997403,0.00018876696],"about_ca_topic_score_codex":0.00032682385,"about_ca_topic_score_gemma":0.000090457674,"teacher_disagreement_score":0.42413017,"about_ca_system_score_codex":0.00014220814,"about_ca_system_score_gemma":0.00062859553,"threshold_uncertainty_score":0.94667214},"labels":[],"label_agreement":null},{"id":"W4308426657","doi":"10.1111/jedm.12347","title":"A Unified Comparison of IRT‐Based Effect Sizes for DIF Investigations","year":2022,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Differential item functioning; Estimator; Statistics; Item response theory; Sample size determination; Differential (mechanical device); Population; Sample (material); Monte Carlo method; Econometrics; Computer science; Mathematics; Psychometrics","score_opus":0.6842492147562678,"score_gpt":0.529819503327333,"score_spread":0.1544297114289348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308426657","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":[0.9480686,0.0017151192,0.027155632,0.017425476,0.0039496743,0.0005232892,0.00003112977,0.0000056360436,0.0011254137],"genre_scores_gemma":[0.9549753,7.2193865e-7,0.04459525,0.00013937496,0.0001703093,0.0000410286,0.000001993457,0.0000053668473,0.000070659364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99471533,0.0009318049,0.0011987125,0.00015420657,0.0028663988,0.00013353393],"domain_scores_gemma":[0.95808357,0.037666816,0.0018994329,0.00024523243,0.0019836884,0.000121276935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018950822,0.00008853992,0.00039117187,0.0006583376,0.000275096,0.00004406178,0.0006119709,0.000020026471,0.00046498032],"category_scores_gemma":[0.15057439,0.00006447136,0.00022171393,0.0012048474,0.000055577202,0.00008341571,0.00004305578,0.00017816812,0.0000015202055],"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":[0.0005644303,0.001653287,0.7779037,0.000066944944,0.00019845937,4.980901e-7,0.0009492635,0.052037563,0.021591717,0.006310406,0.11227844,0.026445301],"study_design_scores_gemma":[0.0038747406,0.0046766335,0.7382927,0.00015779196,0.00021241506,0.00003105726,0.0037685642,0.0066753486,0.01444881,0.17301524,0.054491438,0.0003552587],"about_ca_topic_score_codex":0.0000075685284,"about_ca_topic_score_gemma":0.0000027157846,"teacher_disagreement_score":0.16670482,"about_ca_system_score_codex":0.00021715576,"about_ca_system_score_gemma":0.0009982039,"threshold_uncertainty_score":0.8565807},"labels":[],"label_agreement":null},{"id":"W4308807819","doi":"10.36660/abc.20220355","title":"Avaliação Psicométrica da Prova de Título de Especialista em Cardiologia da Sociedade Brasileira de Cardiologia","year":2022,"lang":"pt","type":"article","venue":"Arquivos Brasileiros de Cardiologia","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":"Discovery Air (Canada)","funders":"","keywords":"Medicine; Certification; Cardiology; Internal medicine; Management","score_opus":0.2540396377354422,"score_gpt":0.4099368379858626,"score_spread":0.15589720025042042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308807819","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":[0.8967764,0.008683076,0.07214103,0.0006390498,0.0066894297,0.0025894295,0.0021364905,0.0012876332,0.009057478],"genre_scores_gemma":[0.9658575,0.00056306884,0.02100251,0.004205701,0.003146061,0.0011034816,0.00019200037,0.00030887852,0.0036207666],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9566261,0.024016993,0.0038711678,0.0049228873,0.0035519127,0.0070109027],"domain_scores_gemma":[0.950174,0.039156206,0.0026903765,0.0052373805,0.0008963002,0.0018457652],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.049794808,0.002380234,0.0054751285,0.0021000206,0.004065527,0.0020890506,0.009522844,0.0023450083,0.001453198],"category_scores_gemma":[0.10269917,0.002244604,0.00404021,0.009077832,0.0019718758,0.00064825726,0.005958486,0.00601099,0.00032366693],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005599648,0.00025330295,0.8128758,0.00010915528,0.001348628,0.0014567942,0.0037906254,0.020278685,0.0063258605,0.00078692473,0.13144188,0.020772379],"study_design_scores_gemma":[0.002801957,0.001898784,0.9332549,0.00010105387,0.0009398398,0.0038718276,0.02446283,0.0049081207,0.0006029199,0.005707741,0.018413993,0.0030360313],"about_ca_topic_score_codex":0.0010035576,"about_ca_topic_score_gemma":0.000020144924,"teacher_disagreement_score":0.1203791,"about_ca_system_score_codex":0.0062084896,"about_ca_system_score_gemma":0.0044965637,"threshold_uncertainty_score":0.9994596},"labels":[],"label_agreement":null},{"id":"W4309499037","doi":"10.1080/10705511.2022.2134140","title":"Structural Parameters under Partial Least Squares and Covariance-Based Structural Equation Modeling: A Comment on Yuan and Deng (2021)","year":2022,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","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":"Concordia University","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Structural equation modeling; Partial least squares regression; Covariance; Mathematics; Null hypothesis; Zero (linguistics); Null (SQL); Econometrics; Applied mathematics; Statistics; Computer science; Data mining; Philosophy","score_opus":0.4530253858465273,"score_gpt":0.4324932390906678,"score_spread":0.020532146755859515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309499037","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":[0.66695803,0.0002953537,0.3278363,0.0032809705,0.0012109398,0.00032277824,0.00004280666,0.000042312266,0.000010534829],"genre_scores_gemma":[0.94402444,0.000016885962,0.05520063,0.00033145296,0.00029617338,0.000028710663,0.000049986265,0.000038000162,0.000013689512],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920828,0.0017543975,0.0017223235,0.0011129306,0.0025727963,0.00075477595],"domain_scores_gemma":[0.9930663,0.004474393,0.0010137206,0.0005448285,0.00048384198,0.0004168763],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0050109024,0.0005349351,0.00067514007,0.0009909882,0.0040862174,0.0010474572,0.00071526156,0.000142237,0.00026212522],"category_scores_gemma":[0.005030541,0.00041318295,0.00022316288,0.0010495649,0.0001792815,0.0008368608,0.0005741422,0.0012612758,0.0000027904837],"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":[0.0006393957,0.0000113661235,0.008199241,0.000008598612,0.0000417881,0.000012561258,0.0016300804,0.9614215,0.00029107893,0.0009255157,0.000017327455,0.02680154],"study_design_scores_gemma":[0.0020850578,0.0005196358,0.004513669,0.000040980947,0.000046531604,0.0002322706,0.0074218204,0.8767023,0.000021912829,0.10795543,0.0000036919362,0.00045671136],"about_ca_topic_score_codex":0.00017089599,"about_ca_topic_score_gemma":0.000009984603,"teacher_disagreement_score":0.27706647,"about_ca_system_score_codex":0.0003964931,"about_ca_system_score_gemma":0.00022794827,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W4312290451","doi":"10.7202/1091168ar","title":"Étude de la distribution d’échantillonnage de l’estimateur du niveau d’habileté en testing adaptatif en fonction de deux règles d’arrêt dans le contexte de l’application du modèle de Rasch","year":2022,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Moncton","funders":"","keywords":"Humanities; Mathematics; Philosophy","score_opus":0.18163221741362054,"score_gpt":0.4087868405127797,"score_spread":0.22715462309915915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312290451","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":[0.4653236,0.000447987,0.5267224,0.005473625,0.00060375937,0.00055293384,0.00007980753,0.00014552542,0.00065039797],"genre_scores_gemma":[0.8628189,0.00027046667,0.13468689,0.00030659747,0.0004910029,0.0006531071,0.00030595786,0.00006311365,0.00040398806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96163845,0.033598453,0.001258039,0.001071636,0.0014402762,0.000993172],"domain_scores_gemma":[0.9486801,0.0481774,0.0013080302,0.00075469003,0.00078315265,0.00029662123],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11602723,0.000444973,0.0005071722,0.00050312636,0.0017401265,0.0004695216,0.0009474587,0.00042654623,0.00018331884],"category_scores_gemma":[0.14593576,0.0005096414,0.00021486895,0.0027726514,0.00021773724,0.0008488951,0.00028895703,0.00090841425,0.000033442473],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011539845,0.0007019556,0.3406285,0.00009026777,0.000078724435,0.000013110949,0.070588,0.26503024,0.056824114,0.011369522,0.0025368147,0.25202334],"study_design_scores_gemma":[0.0006485682,0.00012998354,0.51861423,0.00006420099,0.00011831958,0.00028161722,0.009790941,0.43997237,0.0013905427,0.025507716,0.0031852422,0.00029627903],"about_ca_topic_score_codex":0.0061292024,"about_ca_topic_score_gemma":0.00033579228,"teacher_disagreement_score":0.39749527,"about_ca_system_score_codex":0.004562857,"about_ca_system_score_gemma":0.0039353585,"threshold_uncertainty_score":0.99973553},"labels":[],"label_agreement":null},{"id":"W4312415226","doi":"10.7202/1093066ar","title":"Une comparaison de l’étendue intra- et interindividuelle du niveau de sévérité d’examinateurs en français langue étrangère","year":2021,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Physics; Art","score_opus":0.2770929620073718,"score_gpt":0.47052420783587606,"score_spread":0.19343124582850424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312415226","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":[0.5776273,0.004685651,0.2964879,0.099132665,0.004916534,0.0003897483,0.000066634995,0.000119191514,0.016574364],"genre_scores_gemma":[0.9314532,0.0013028278,0.06059947,0.001334407,0.0004031802,0.00004881756,0.00019704446,0.000044103184,0.0046169213],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97615325,0.020151526,0.0009882922,0.0008566467,0.0012388331,0.0006114767],"domain_scores_gemma":[0.9703237,0.027336283,0.0005038626,0.0007103673,0.0009111189,0.0002146588],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04931848,0.00035320647,0.0005540423,0.0005493958,0.00027665094,0.00043012554,0.0007067642,0.0004382152,0.002569116],"category_scores_gemma":[0.076263204,0.00035887095,0.00021119829,0.0031222913,0.00012658797,0.0006258076,0.00016448513,0.0007254902,0.00034642997],"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":[0.000035061752,0.0006257431,0.12658171,0.00011808156,0.00012621921,0.000055173758,0.21824664,0.004790339,0.004674277,0.007485451,0.034800876,0.60246044],"study_design_scores_gemma":[0.0007944088,0.000116724244,0.90113026,0.00030063555,0.00012298032,0.00018964343,0.014738012,0.017676955,0.002100402,0.014752395,0.0476861,0.00039150484],"about_ca_topic_score_codex":0.004443778,"about_ca_topic_score_gemma":0.0018939177,"teacher_disagreement_score":0.77454853,"about_ca_system_score_codex":0.00043873803,"about_ca_system_score_gemma":0.00152274,"threshold_uncertainty_score":0.99988633},"labels":[],"label_agreement":null},{"id":"W4317042011","doi":"10.47626/2237-6089-2022-0573","title":"Cross-cultural adaptation and psychometric properties of the Iowa-Netherlands Comparison Orientation Measure for the Brazilian context","year":2023,"lang":"en","type":"article","venue":"Trends in Psychiatry and Psychotherapy","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cronbach's alpha; Psychology; Exploratory factor analysis; Reliability (semiconductor); Context (archaeology); Population; Affect (linguistics); Structural equation modeling; Scale (ratio); Adaptation (eye); Validity; Measure (data warehouse); Psychometrics; Content validity; Statistics; Social psychology; Applied psychology; Clinical psychology; Mathematics; Computer science; Medicine; Geography; Data mining","score_opus":0.4114900239795509,"score_gpt":0.4807827599795328,"score_spread":0.06929273599998187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317042011","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":[0.9746424,0.011831528,0.003697917,0.0048691095,0.0038894678,0.00042230028,0.00002926618,0.00004468053,0.0005733269],"genre_scores_gemma":[0.99655026,0.00083844253,0.0012039134,0.00025102976,0.0001584805,0.00006576406,0.0000034385482,0.000015451427,0.0009132009],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974612,0.00037648133,0.00078420516,0.00049254193,0.0006155213,0.0002700644],"domain_scores_gemma":[0.99556327,0.0032321755,0.0004581595,0.0004897455,0.00020638408,0.00005026679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004055022,0.00019539702,0.000347499,0.0007288847,0.0004113639,0.0002600115,0.0005547278,0.000119914184,0.00005788279],"category_scores_gemma":[0.001146949,0.00009185096,0.00013434839,0.006242755,0.0003569086,0.00023604624,0.000014022858,0.00019730745,0.0000020443058],"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":[0.00038645644,0.000046936708,0.38593692,0.000012343515,0.000028023502,2.4339352e-8,0.0034272692,0.00012334737,0.0001384941,0.0011508663,0.0032321373,0.6055172],"study_design_scores_gemma":[0.0025859831,0.00025520564,0.95148265,0.00007002275,0.000015432568,0.0000044686844,0.0059659258,0.0065254327,0.00007688148,0.023133943,0.009712417,0.00017160509],"about_ca_topic_score_codex":0.00006391457,"about_ca_topic_score_gemma":0.0005055835,"teacher_disagreement_score":0.6053456,"about_ca_system_score_codex":0.000007953449,"about_ca_system_score_gemma":0.00002349731,"threshold_uncertainty_score":0.37455735},"labels":[],"label_agreement":null},{"id":"W4318715460","doi":"10.2139/ssrn.4294644","title":"Assessing the Practice Sensitivity and Test-Retest Reliability of Behavioral and N400 Measures in a Particular Semantic Categorization Task","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Categorization; N400; Reliability (semiconductor); Task (project management); Psychology; Test (biology); Sensitivity (control systems); Natural language processing; Cognitive psychology; Computer science; Artificial intelligence; Cognition; Event-related potential; Neuroscience; Engineering","score_opus":0.15031042232292804,"score_gpt":0.4364639250692351,"score_spread":0.286153502746307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318715460","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":[0.9843609,0.001666752,0.011999337,0.0016720503,0.00011520579,0.00013180221,0.0000016368322,0.000007995637,0.00004435611],"genre_scores_gemma":[0.99872744,0.0002953858,0.0008777464,0.00004511411,0.000028809622,0.0000045243105,3.7523867e-7,0.0000063804127,0.00001421787],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9942684,0.0031868806,0.0005707136,0.00030653243,0.0009532762,0.00071415596],"domain_scores_gemma":[0.96653587,0.03197878,0.00075236254,0.00032196927,0.00034936046,0.000061657505],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056445688,0.00010128016,0.00024853513,0.00022245273,0.0005142643,0.00023982654,0.00019820221,0.000035062705,0.000005472183],"category_scores_gemma":[0.08880728,0.000066032975,0.000044376655,0.0013956353,0.00013237963,0.00054857775,0.00017691035,0.0013302321,2.4582e-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":[0.000033297187,0.00017769626,0.9014832,0.0000035263208,0.000013492968,0.000017566394,0.00083586253,0.00079341483,0.0043128915,0.0016051433,0.000012104685,0.09071181],"study_design_scores_gemma":[0.0008080181,0.00079824054,0.7286013,0.000017152544,0.00011644571,0.0031213982,0.049988713,0.011060951,0.00018933942,0.20466843,0.00040002697,0.00023001953],"about_ca_topic_score_codex":0.00048597783,"about_ca_topic_score_gemma":0.00030704736,"teacher_disagreement_score":0.20306328,"about_ca_system_score_codex":0.00022695253,"about_ca_system_score_gemma":0.00062390155,"threshold_uncertainty_score":0.9715877},"labels":[],"label_agreement":null},{"id":"W4319294726","doi":"10.1080/09638288.2023.2169772","title":"Interpreting results from Rasch analysis 2. Advanced model applications and the data-model fit assessment","year":2023,"lang":"en","type":"article","venue":"Disability and Rehabilitation","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":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Ministero della Salute; Fondazione Italiana Sclerosi Multipla","keywords":"Rasch model; Polytomous Rasch model; Item response theory; Psychology; Computer science; Psychometrics; Clinical psychology; Developmental psychology","score_opus":0.3573555448026704,"score_gpt":0.5186150707381851,"score_spread":0.16125952593551474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319294726","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":[0.6867536,0.00008684999,0.301598,0.009809444,0.00005090932,0.00051311863,0.00045604783,0.00007436479,0.00065770384],"genre_scores_gemma":[0.8682097,0.000044075405,0.131356,0.00006264682,0.000018247916,0.000098590266,0.00014395376,0.00000442558,0.00006232183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964545,0.0008617818,0.0008843438,0.0010287152,0.00059499784,0.00017569873],"domain_scores_gemma":[0.85692173,0.1404403,0.0003496111,0.0019822612,0.0002187815,0.00008732512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017936343,0.00012351046,0.00037676233,0.00019501528,0.00039086113,0.00021559373,0.00058807246,0.000068968075,0.00000806894],"category_scores_gemma":[0.09703199,0.00007315851,0.00010809638,0.0028404405,0.0010016026,0.00039168345,0.0005340111,0.00016655732,0.0000041268463],"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":[0.0004530077,0.00013355099,0.18291347,0.000028331662,0.0001510248,9.72893e-8,0.0074982634,0.32232165,0.00009949042,0.0066023828,0.0007494823,0.47904927],"study_design_scores_gemma":[0.0004797117,0.000013077754,0.14933115,0.0000053486838,0.000061018723,5.7890663e-8,0.0036778636,0.67068636,4.6047643e-7,0.17558588,0.000097532924,0.00006154012],"about_ca_topic_score_codex":0.00015452747,"about_ca_topic_score_gemma":0.00010807191,"teacher_disagreement_score":0.47898772,"about_ca_system_score_codex":0.000033351567,"about_ca_system_score_gemma":0.000030400442,"threshold_uncertainty_score":0.9105741},"labels":[],"label_agreement":null},{"id":"W4319295072","doi":"10.1080/09638288.2023.2169771","title":"Interpreting results from Rasch analysis 1. The “most likely” measures coming from the model","year":2023,"lang":"en","type":"article","venue":"Disability and Rehabilitation","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":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Ministero della Salute","keywords":"Rasch model; Polytomous Rasch model; Psychology; Item response theory; Econometrics; Psychometrics; Clinical psychology; Developmental psychology; Mathematics","score_opus":0.2957634636922884,"score_gpt":0.43973304557704995,"score_spread":0.14396958188476155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319295072","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":[0.9575696,0.00019493817,0.017056273,0.02388211,0.0002763732,0.00026730803,0.00024417057,0.00009064696,0.00041858107],"genre_scores_gemma":[0.9915528,0.000023861861,0.00799764,0.00022222853,0.00008360829,0.000023256243,0.000048125672,0.0000065650793,0.000041896175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99454033,0.0024024472,0.001004693,0.00082158524,0.0009924663,0.0002384638],"domain_scores_gemma":[0.6450461,0.35287076,0.0003597429,0.0013733862,0.00027769135,0.00007230213],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02203927,0.00015390357,0.00036220995,0.00014286888,0.00070325227,0.00038909473,0.00074890075,0.000098810124,0.000030977953],"category_scores_gemma":[0.3619486,0.000073384756,0.00026040486,0.0046468414,0.0009775418,0.00022572148,0.00029186235,0.0002637364,0.00002068418],"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":[0.00019414158,0.00004585437,0.7788986,0.0000037404275,0.00014381376,2.0091035e-7,0.024731243,0.021155583,0.0001648758,0.00029263095,0.002831875,0.17153741],"study_design_scores_gemma":[0.00016926545,0.000021260763,0.6082726,0.000013500384,0.00008366611,5.3525753e-8,0.01602497,0.27811882,0.0000065510403,0.0969222,0.00029313934,0.00007395231],"about_ca_topic_score_codex":0.0030053267,"about_ca_topic_score_gemma":0.0010439578,"teacher_disagreement_score":0.35046834,"about_ca_system_score_codex":0.000038453738,"about_ca_system_score_gemma":0.000025665357,"threshold_uncertainty_score":0.7638415},"labels":[],"label_agreement":null},{"id":"W4319655880","doi":"10.1007/s11136-023-03347-8","title":"Implications of the syntheses on definition, theory, and methods conducted by the Response Shift – in Sync Working Group","year":2023,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; McGill University Health Centre; McGill University; University of Calgary; Trinity Western University; University of British Columbia; Centre for Advancing Health Outcomes; Western University","funders":"","keywords":"Paradigm shift; Shift work; Explication; Psychology; Cognitive psychology; Quality (philosophy); Epistemology","score_opus":0.902174769477158,"score_gpt":0.6553476401513275,"score_spread":0.2468271293258305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319655880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.9781776,0.00047376606,0.0026152902,0.015617048,0.00008584394,0.0003314526,0.000034676894,0.000020990106,0.0026433095],"genre_scores_gemma":[0.99726456,0.000072691044,0.0023810556,0.00012282675,0.000015329822,0.000028250239,9.073293e-7,0.000007054018,0.00010731594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9309082,0.065331966,0.0011186417,0.00046311726,0.001783636,0.00039442233],"domain_scores_gemma":[0.20992865,0.7879973,0.00039419322,0.0012426797,0.00035577745,0.00008139475],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27965075,0.00008503945,0.00034447998,0.00071127986,0.00037528286,0.00009345357,0.0013193485,0.00008424228,0.00006635359],"category_scores_gemma":[0.7819044,0.000043396198,0.00008428326,0.007664178,0.0010273327,0.000059515653,0.00048923824,0.00043682265,0.000007959239],"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":[0.0020160046,0.00021366235,0.29327068,0.000054617612,0.000045799592,6.495539e-7,0.005193154,0.000018131843,0.024543643,0.47157025,0.007234879,0.19583854],"study_design_scores_gemma":[0.00009514974,0.00004492131,0.6133778,0.000049564896,0.0000012984552,4.4526413e-7,0.0054549645,0.000019666415,0.0004180601,0.37987983,0.000621554,0.00003669747],"about_ca_topic_score_codex":0.00031235197,"about_ca_topic_score_gemma":0.000036616573,"teacher_disagreement_score":0.7226653,"about_ca_system_score_codex":0.000025016512,"about_ca_system_score_gemma":0.0001256487,"threshold_uncertainty_score":0.74175113},"labels":[],"label_agreement":null},{"id":"W4319657012","doi":"10.1037/tra0001439","title":"Bayesian mediation analysis in trauma research.","year":2023,"lang":"en","type":"article","venue":"Psychological Trauma Theory Research Practice and Policy","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Mediation; Bayesian probability; Psychology; Computer science; Clinical psychology; Sociology; Artificial intelligence; Social science","score_opus":0.8320655316913358,"score_gpt":0.6951724291735961,"score_spread":0.13689310251773967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319657012","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":[0.71793216,0.000562957,0.0024482051,0.033818617,0.00018315234,0.00062429707,0.000021116584,0.00016628059,0.24424322],"genre_scores_gemma":[0.99335486,0.0012360761,0.00215818,0.0005328585,0.00047115138,0.00010854357,0.000008190533,0.000016792103,0.0021133698],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9584632,0.033380926,0.0010373034,0.0014185904,0.004070616,0.0016293647],"domain_scores_gemma":[0.68215686,0.31506598,0.00021157836,0.0011570449,0.00092004705,0.00048852025],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.23076038,0.0002071367,0.0005901771,0.012279147,0.0007399219,0.0007441414,0.0015502493,0.000346857,0.0009096281],"category_scores_gemma":[0.6263865,0.00014023611,0.0001880798,0.06208756,0.0010444189,0.0007704331,0.00047696283,0.0021839107,0.0008377918],"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":[0.00071525655,0.00037176898,0.017818896,0.000007201142,0.000103025835,0.00017191135,0.0022716776,0.000073755305,0.0001098702,0.092360966,0.005813493,0.8801822],"study_design_scores_gemma":[0.00048542424,0.00042865748,0.36914974,0.000007334665,0.000011388206,0.00001930919,0.010115787,0.0008309306,0.000013870813,0.59728986,0.021509778,0.00013792032],"about_ca_topic_score_codex":0.0003498782,"about_ca_topic_score_gemma":0.00006573196,"teacher_disagreement_score":0.8800443,"about_ca_system_score_codex":0.000101291764,"about_ca_system_score_gemma":0.00007152561,"threshold_uncertainty_score":0.99994016},"labels":[],"label_agreement":null},{"id":"W4320302550","doi":"10.53841/bpsadm.2018.10.2.22","title":"Assessment in the digital age: Some challenges for Test Developers and Users","year":2018,"lang":"en","type":"article","venue":"Assessment and Development Matters","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Key (lock); Test (biology); Psychometrics; Computer science; Data science; Psychometric testing; Engineering ethics; Psychology; Applied psychology; Engineering; Clinical psychology; Computer security","score_opus":0.40412666237586337,"score_gpt":0.4711374105617989,"score_spread":0.06701074818593555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320302550","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":[0.94126314,0.00048690423,0.013503499,0.028600944,0.0008040847,0.0011260776,0.000013377755,0.00007575388,0.0141262235],"genre_scores_gemma":[0.88798934,0.00014148834,0.10888663,0.0026272251,0.00007022319,0.000095914314,0.0000066255184,0.000012269,0.00017025956],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975328,0.00013572745,0.00058883365,0.00059864984,0.00073684833,0.00040714757],"domain_scores_gemma":[0.986307,0.01303752,0.00018992185,0.0002824118,0.00009316641,0.00008996457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052600997,0.00021705987,0.00031197877,0.00039334112,0.0003371337,0.0008790784,0.0004977121,0.000061390834,0.00002297104],"category_scores_gemma":[0.0022552405,0.00013172312,0.000031184063,0.0004704416,0.00020853606,0.00042757427,0.00022382135,0.0001441508,0.000009492634],"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":[0.000012035405,0.0000942168,0.5321596,0.0000272173,0.000035025212,0.00001267102,0.0027209457,9.021695e-7,0.00007138764,0.0030128947,0.005790448,0.45606261],"study_design_scores_gemma":[0.00058913743,0.00012856291,0.9171428,0.000026547254,0.0000044958833,0.0000104064375,0.00819094,0.0000905786,0.000014020927,0.005324342,0.06826164,0.0002165077],"about_ca_topic_score_codex":0.000005532599,"about_ca_topic_score_gemma":0.00002181819,"teacher_disagreement_score":0.45584613,"about_ca_system_score_codex":0.00006857992,"about_ca_system_score_gemma":0.0001713064,"threshold_uncertainty_score":0.8476973},"labels":[],"label_agreement":null},{"id":"W4321330224","doi":"10.1177/00131644231155804","title":"The Impact of Measurement Model Misspecification on Coefficient Omega Estimates of Composite Reliability","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"York University","funders":"","keywords":"Omega; Statistics; Reliability (semiconductor); Mathematics; Econometrics; Scale (ratio); Population; Factor analysis; Composite index; Hierarchical database model; Computer science; Physics; Thermodynamics; Demography; Data mining; Composite indicator","score_opus":0.7526933176330004,"score_gpt":0.5302071217753532,"score_spread":0.22248619585764717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321330224","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":[0.9833092,0.00057841645,0.0061979233,0.0045854147,0.000490271,0.00037015407,0.000020462876,0.000027818583,0.0044203154],"genre_scores_gemma":[0.99677193,0.000074178315,0.0029869552,0.000031013224,0.000044048786,0.00003463157,0.0000028982795,0.00000445835,0.00004989232],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954539,0.0003919173,0.0008555696,0.00047883106,0.002588518,0.00023125112],"domain_scores_gemma":[0.98896104,0.008310819,0.000455873,0.0005967426,0.0015598639,0.0001156689],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015923006,0.00014768315,0.00028514175,0.00021525029,0.00024132397,0.000055055905,0.00051286095,0.000057795412,0.00005803184],"category_scores_gemma":[0.039014056,0.00007235716,0.00016005035,0.0013736675,0.0002544428,0.000036835947,0.000055143053,0.00012480891,0.000023081742],"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":[0.0018076261,0.007374702,0.29549968,0.00006804936,0.00026130117,8.026783e-7,0.0014435269,0.1672411,0.07724416,0.026172886,0.10040194,0.32248423],"study_design_scores_gemma":[0.00021794262,0.00039686152,0.87487763,0.00003247514,0.000006602136,0.0000013399334,0.00010997382,0.009941641,0.00045286625,0.11369736,0.00018477312,0.000080561964],"about_ca_topic_score_codex":0.000017748744,"about_ca_topic_score_gemma":7.2654734e-7,"teacher_disagreement_score":0.57937795,"about_ca_system_score_codex":0.00011724166,"about_ca_system_score_gemma":0.00009104267,"threshold_uncertainty_score":0.96908075},"labels":[],"label_agreement":null},{"id":"W4327910164","doi":"10.1177/01466216231165299","title":"Confidence Screening Detector: A New Method for Detecting Test Collusion","year":2023,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Collusion; Cheating; Clique; Computer science; Test (biology); Detector; Item response theory; Scale (ratio); Statistical hypothesis testing; Variable (mathematics); Similarity (geometry); Selection (genetic algorithm); Statistics; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics; Psychology; Psychometrics; Social psychology","score_opus":0.7210023253769497,"score_gpt":0.531043618285663,"score_spread":0.1899587070912867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327910164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01494691,0.00012976084,0.9746787,0.0009962765,0.000871349,0.00121214,0.000009984331,0.00059185195,0.006563029],"genre_scores_gemma":[0.60958844,0.000009999426,0.3889287,0.00071853714,0.00030532756,0.00020987757,0.0000014371795,0.000024236153,0.00021344342],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99299604,0.00043098303,0.0012276926,0.0015474571,0.0028792233,0.0009186168],"domain_scores_gemma":[0.94710565,0.050225694,0.0006227305,0.0010749369,0.0005475571,0.00042341326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03331906,0.00034571654,0.0006634211,0.00062933745,0.00061284396,0.0003055469,0.0014014973,0.00025424015,0.00028642823],"category_scores_gemma":[0.16427304,0.00024203834,0.00026447696,0.004983244,0.000076057215,0.00008341152,0.00030160134,0.00036942572,0.00031265846],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019230135,0.0000743027,0.0018226623,0.0000074879704,0.000023547389,0.0000058899273,0.00013260554,0.0002920153,0.09936117,0.0015195876,0.018075733,0.8784927],"study_design_scores_gemma":[0.006413399,0.0021063124,0.26540652,0.00016957095,0.000101673824,0.00006194335,0.003065366,0.014022233,0.024205284,0.59286326,0.08991892,0.0016654966],"about_ca_topic_score_codex":0.000028961029,"about_ca_topic_score_gemma":0.000013381505,"teacher_disagreement_score":0.8768272,"about_ca_system_score_codex":0.000089491536,"about_ca_system_score_gemma":0.00004891637,"threshold_uncertainty_score":0.99540144},"labels":[],"label_agreement":null},{"id":"W433564594","doi":"","title":"Culture-specific findings from the CAR study : Canada – Toronto","year":2001,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Sociology; Advertising; Business","score_opus":0.42930028238649376,"score_gpt":0.4356001364176618,"score_spread":0.006299854031168062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W433564594","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":[0.91112447,0.0015114511,0.004971775,0.0008072528,0.0016323441,0.00024516633,0.000010011394,0.000046693625,0.07965085],"genre_scores_gemma":[0.98483956,0.000067115485,0.0039807777,0.0007167598,0.00027113326,0.0000068599848,9.87684e-7,0.000005721026,0.010111064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99712014,0.0003766603,0.00043021826,0.00046855255,0.0013345637,0.0002698389],"domain_scores_gemma":[0.9805647,0.018263565,0.000100504374,0.0008198569,0.0001556145,0.00009576207],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030780705,0.00012380879,0.00022635868,0.000020283482,0.0003190329,0.00026798985,0.0013067459,0.000035648332,0.004606494],"category_scores_gemma":[0.01647059,0.000055864548,0.000053505122,0.0009957489,0.000028151935,0.00014919655,0.00016974859,0.00011315162,0.0000449815],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009027921,0.000027879541,0.56945235,5.0598015e-8,0.00001252052,0.00001899442,0.0011393097,0.0000095638125,0.000028116605,0.00017109417,0.3782762,0.05085487],"study_design_scores_gemma":[0.00019110799,0.00004134098,0.52584386,0.000001269148,0.0000036821375,0.0000031747695,0.037196547,0.000045412537,0.000014972939,0.0019375077,0.43462843,0.00009268768],"about_ca_topic_score_codex":0.87738997,"about_ca_topic_score_gemma":0.93303114,"teacher_disagreement_score":0.07371513,"about_ca_system_score_codex":0.00014131871,"about_ca_system_score_gemma":0.0000832188,"threshold_uncertainty_score":0.99630344},"labels":[],"label_agreement":null},{"id":"W4361991005","doi":"10.2196/44084","title":"Scoring Single-Response Multiple-Choice Items: Scoping Review and Comparison of Different Scoring Methods","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multiple choice; PsycINFO; Metric (unit); Test (biology); MEDLINE; Medicine; Psychology; Statistics; Mathematics","score_opus":0.5643011162701261,"score_gpt":0.625437994430518,"score_spread":0.06113687816039182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361991005","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":[0.9679292,0.016934136,0.008997628,0.002997422,0.0019404205,0.00080318126,0.0000012080357,0.00012171851,0.0002750878],"genre_scores_gemma":[0.9713147,0.0011961344,0.025954917,0.000677122,0.00031217234,0.0002207787,0.0000059925974,0.000023311793,0.0002948639],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9942268,0.0021686975,0.0013247055,0.0005568676,0.0014071333,0.00031580502],"domain_scores_gemma":[0.8558693,0.14187816,0.00081211916,0.00068626273,0.00032802485,0.0004261345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015228386,0.00016814486,0.0007455336,0.00069778453,0.00014680404,0.000084272295,0.0005555344,0.00011886596,0.0002289286],"category_scores_gemma":[0.59589434,0.00012221698,0.000091260335,0.0029883003,0.00014269225,0.000180517,0.00028567045,0.00028507243,0.000017055147],"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":[0.00002917766,0.00017660556,0.18420507,0.0010233358,0.000009315521,5.586344e-7,0.000627388,0.0000029938735,0.001816049,0.000029994859,0.0015454799,0.810534],"study_design_scores_gemma":[0.0007793489,0.0003521631,0.93303984,0.04636957,0.00007776279,0.00002126281,0.0036255398,0.0077133994,0.002397902,0.0020876601,0.0030643444,0.00047119363],"about_ca_topic_score_codex":0.00003329792,"about_ca_topic_score_gemma":0.000010331851,"teacher_disagreement_score":0.8100628,"about_ca_system_score_codex":0.0000532705,"about_ca_system_score_gemma":0.00034932795,"threshold_uncertainty_score":0.5277885},"labels":[],"label_agreement":null},{"id":"W4362673096","doi":"10.1111/emip.12553","title":"Validation as Evaluating Desired and Undesired Effects: Insights From Cross‐Classified Mixed Effects Model","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reliability (semiconductor); Variance (accounting); Computer science; Reliability engineering; Variance components; Validity; External validity; Cross-validation; Random effects model; Statistics; Data mining; Econometrics; Psychology; Artificial intelligence; Psychometrics; Mathematics; Engineering; Medicine","score_opus":0.7119997234981603,"score_gpt":0.5622263498475483,"score_spread":0.14977337365061205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362673096","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":[0.97638386,0.005302481,0.0056377235,0.007132469,0.0016126372,0.0005514916,0.000004216169,0.00009106506,0.0032840406],"genre_scores_gemma":[0.9405107,0.00025019422,0.057584263,0.0003746934,0.0003159837,0.000084049214,0.000021435892,0.000017107977,0.00084157294],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99337715,0.0025200113,0.00058284425,0.0007529683,0.0025087607,0.00025828657],"domain_scores_gemma":[0.890418,0.10727979,0.000547323,0.00042019144,0.0011483055,0.00018639129],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0134797525,0.00021386797,0.00031444078,0.00037877684,0.0005754098,0.00086506625,0.00027751352,0.00010701006,0.000040289808],"category_scores_gemma":[0.4101432,0.00017070115,0.000047736634,0.0012947412,0.00008779406,0.0009524752,0.00012736762,0.0001685876,0.0001028595],"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":[0.0019213455,0.0011286873,0.06301504,0.0004484719,0.0008575063,0.000030448007,0.015887924,0.006930881,0.22736813,0.04712259,0.029536793,0.60575217],"study_design_scores_gemma":[0.0012903309,0.00027342723,0.5001058,0.00017584494,0.00016061777,0.000014085617,0.0016693048,0.035603505,0.006539955,0.45025653,0.0035129269,0.00039767486],"about_ca_topic_score_codex":0.00020918867,"about_ca_topic_score_gemma":0.000003984146,"teacher_disagreement_score":0.60535455,"about_ca_system_score_codex":0.00008545153,"about_ca_system_score_gemma":0.00023149817,"threshold_uncertainty_score":0.83418536},"labels":[],"label_agreement":null},{"id":"W4365813887","doi":"10.1080/08957347.2023.2201703","title":"Multi-Group Generalizations of SIBTEST and Crossing-SIBTEST","year":2023,"lang":"en","type":"article","venue":"Applied Measurement in Education","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":"York University","funders":"","keywords":"Type I and type II errors; Differential item functioning; Statistics; Mathematics; Monte Carlo method; Logistic regression; Set (abstract data type); Population; Group (periodic table); Statistical power; Applied mathematics; Item response theory; Computer science; Psychometrics; Demography","score_opus":0.5905972101310687,"score_gpt":0.4788309874553456,"score_spread":0.11176622267572311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365813887","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":[0.975493,0.0005826306,0.017548906,0.0004522743,0.0010384307,0.00046510441,0.000004358495,0.000079835234,0.00433544],"genre_scores_gemma":[0.9632537,0.000049177106,0.03631192,0.00009164553,0.00006309922,0.000075605196,0.000009985295,0.000009390904,0.0001355049],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977792,0.00012856298,0.0006096356,0.00038144796,0.00090005825,0.00020107515],"domain_scores_gemma":[0.99705875,0.0018913733,0.00028256123,0.00037279635,0.0003295388,0.00006495764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007057887,0.000102563485,0.00020191568,0.0007882515,0.00016049361,0.00015325543,0.00026667438,0.000057274287,0.00002914561],"category_scores_gemma":[0.01823118,0.00008741942,0.000027102933,0.003610788,0.000100470286,0.000098751494,0.000066862216,0.000076338605,0.000029260744],"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":[0.000011867692,0.00049654697,0.49147722,0.00003178439,0.000010117152,2.2788562e-7,0.0017933613,0.0007562803,0.11214468,0.0051278747,0.0049496475,0.3832004],"study_design_scores_gemma":[0.0003832292,0.000021048085,0.97671694,0.000034824625,0.0000071641257,9.450978e-7,0.0025246104,0.0014354517,0.0012168546,0.013031607,0.004500809,0.00012654284],"about_ca_topic_score_codex":0.00010914609,"about_ca_topic_score_gemma":0.00010171845,"teacher_disagreement_score":0.4852397,"about_ca_system_score_codex":0.000067469846,"about_ca_system_score_gemma":0.00019752115,"threshold_uncertainty_score":0.9900387},"labels":[],"label_agreement":null},{"id":"W4376106412","doi":"10.1016/j.ajpe.2023.100081","title":"Using Automatic Item Generation to Create Multiple-Choice Questions for Pharmacy Assessment","year":2023,"lang":"en","type":"article","venue":"American Journal of Pharmaceutical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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":"Item bank; Pharmacy; Summative assessment; Multiple choice; Quality (philosophy); Computer science; Test (biology); Sample (material); Medical education; Scope (computer science); Worksheet; Set (abstract data type); Item response theory; Medicine; Formative assessment; Psychometrics; Psychology; Family medicine; Mathematics education; Clinical psychology","score_opus":0.7467467061115505,"score_gpt":0.6691299934978945,"score_spread":0.07761671261365599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376106412","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":[0.7884627,0.00006361169,0.20434342,0.0043629087,0.0023052362,0.00030272186,0.000007895667,0.00004027291,0.00011123127],"genre_scores_gemma":[0.789865,0.000030157968,0.20809796,0.00097143603,0.0009030456,0.000027018663,0.000003548706,0.000015172333,0.00008661481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966643,0.0007290727,0.001099973,0.00029798085,0.00087883126,0.0003298653],"domain_scores_gemma":[0.9636298,0.033526834,0.00094653835,0.0002466689,0.0011966416,0.0004535215],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006331572,0.00014572983,0.00038926452,0.0011795842,0.0002492962,0.00022208007,0.0004738149,0.0000221434,0.00011679162],"category_scores_gemma":[0.10357144,0.00011440375,0.0001687138,0.003901522,0.00008994763,0.0003705342,0.000058610476,0.0002202502,0.00002598041],"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":[0.000028951994,0.00016610375,0.054087266,0.000008550842,0.000039275663,0.0000014562174,0.00027493283,0.0042725517,0.028939387,0.00013981294,0.0070294193,0.9050123],"study_design_scores_gemma":[0.0008063465,0.00036515127,0.11883092,0.00006882977,0.00013991611,0.000083579514,0.0023631868,0.8318982,0.0017641658,0.0013787261,0.04205838,0.00024260176],"about_ca_topic_score_codex":0.00007029428,"about_ca_topic_score_gemma":0.0000022493473,"teacher_disagreement_score":0.9047697,"about_ca_system_score_codex":0.0002167727,"about_ca_system_score_gemma":0.00077237596,"threshold_uncertainty_score":0.90397954},"labels":[],"label_agreement":null},{"id":"W4376645007","doi":"10.1027/2698-1866/a000039","title":"Effects of a Neutral Response Option on Occupational Interest Circumplex Fit","year":2023,"lang":"en","type":"article","venue":"Psychological Test Adaptation and Development","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Wilfrid Laurier University","funders":"","keywords":"Generalizability theory; Equivalence (formal languages); Psychology; Econometrics; Correlation; Statistics; Sample (material); Structural equation modeling; Hexagonal crystal system; Social psychology; Mathematics; Pure mathematics","score_opus":0.7527729537058937,"score_gpt":0.5201070910133551,"score_spread":0.23266586269253864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376645007","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":[0.9810517,0.000031073283,0.017230103,0.00055017153,0.00037195696,0.00021574889,0.0000045885604,0.00010876174,0.00043593347],"genre_scores_gemma":[0.9766,0.000019632369,0.022690162,0.00033687433,0.000027953674,0.00003855111,0.0000072576777,0.000005660062,0.00027389522],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99760133,0.00045391155,0.0006579083,0.0005028956,0.0005619948,0.00022193405],"domain_scores_gemma":[0.9595797,0.039710004,0.00025399707,0.00018439762,0.00015967255,0.00011222601],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038861553,0.00013961627,0.00024319722,0.0006306734,0.00013754543,0.00007260422,0.00025285032,0.000094871095,0.000096094875],"category_scores_gemma":[0.060754605,0.000096451804,0.0000492605,0.0015763056,0.000087743596,0.000085484724,0.00007581316,0.00012417913,0.00023492836],"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":[0.0022846574,0.0007522305,0.045507852,0.00003443484,0.000030623596,0.000049750073,0.0022708718,0.00070611935,0.008341313,0.0048891627,0.0057350826,0.9293979],"study_design_scores_gemma":[0.00064741896,0.00042390305,0.9862561,0.000028233475,0.0000020040325,0.00000619056,0.000317929,0.0010587898,0.0005554335,0.007498518,0.0030844181,0.00012102214],"about_ca_topic_score_codex":0.0000016866649,"about_ca_topic_score_gemma":0.0000012548728,"teacher_disagreement_score":0.9407483,"about_ca_system_score_codex":0.000026360876,"about_ca_system_score_gemma":0.00003600221,"threshold_uncertainty_score":0.9471571},"labels":[],"label_agreement":null},{"id":"W4378220707","doi":"10.1177/00131644231165520","title":"The Accuracy of Bayesian Model Fit Indices in Selecting Among Multidimensional Item Response Theory Models","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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":"Curse of dimensionality; Nested set model; Deviance information criterion; Bayesian probability; Item response theory; Statistics; Bayesian information criterion; Computer science; Mathematics; Econometrics; Bayesian inference; Data mining; Psychometrics","score_opus":0.7180011966789275,"score_gpt":0.5115401562574108,"score_spread":0.2064610404215167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378220707","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":[0.98656976,0.0005475775,0.004657246,0.0061954604,0.00038982581,0.00022976089,0.0000054340594,0.000025566824,0.0013793798],"genre_scores_gemma":[0.9950299,0.000060155722,0.0042201187,0.00021428376,0.000056138437,0.000057729783,0.0000011307201,0.000005704479,0.00035482424],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99526614,0.0015899941,0.00076584576,0.00051529985,0.0015489646,0.000313745],"domain_scores_gemma":[0.92431265,0.07451524,0.00035820733,0.0003234392,0.00038367088,0.00010680149],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033753507,0.00013762357,0.00022747666,0.0004037244,0.0003423304,0.000076383476,0.0004799435,0.00008811115,0.00007409475],"category_scores_gemma":[0.13423745,0.00007556276,0.000073150906,0.0019417796,0.00020311681,0.00015600638,0.0001087669,0.00024115978,0.000010825334],"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":[0.0037242302,0.0014483021,0.47417554,0.000024233801,0.0001051602,0.00000752765,0.0055283713,0.06979506,0.0051349415,0.070539236,0.019744718,0.3497727],"study_design_scores_gemma":[0.00020682527,0.00006301989,0.6286461,0.000028522638,0.0000024775977,0.000002911229,0.0007493426,0.04117201,0.000026461355,0.3288742,0.00014860446,0.000079551886],"about_ca_topic_score_codex":0.00001190186,"about_ca_topic_score_gemma":0.000010142141,"teacher_disagreement_score":0.34969312,"about_ca_system_score_codex":0.00004232831,"about_ca_system_score_gemma":0.00010527906,"threshold_uncertainty_score":0.9949541},"labels":[],"label_agreement":null},{"id":"W4380550839","doi":"10.1007/978-3-031-27781-8_6","title":"Equating Different Test Scores with Landmark Registration Compared to Equipercentile Equating","year":2023,"lang":"en","type":"book-chapter","venue":"Springer proceedings in mathematics & statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Equating; Landmark; Test (biology); Statistics; Test score; Mathematics; Estimation; Econometrics; Computer science; Artificial intelligence; Standardized test; Engineering","score_opus":0.3451230541909948,"score_gpt":0.4111740948922778,"score_spread":0.06605104070128298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380550839","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":[0.01982813,0.00010878541,0.5637548,0.00027305243,0.0011441188,0.0028342742,0.00058014586,0.00065310556,0.41082358],"genre_scores_gemma":[0.035674527,0.000059134807,0.8430639,0.000075295524,0.000378405,0.000103658684,0.000046110425,0.00027531953,0.12032368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99250007,0.000029429002,0.0024695534,0.0012289368,0.0029897832,0.0007822392],"domain_scores_gemma":[0.9672254,0.028751055,0.0021444366,0.00063123077,0.0009910538,0.00025682885],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005764277,0.0007320524,0.0014227091,0.0013759609,0.00027334597,0.001048589,0.0012807306,0.0002833251,0.00014675583],"category_scores_gemma":[0.097794496,0.0005536826,0.000109661654,0.0007722953,0.00015953019,0.00017242787,0.0006349567,0.0008250138,0.00024437282],"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":[0.00013338278,0.00037950277,0.04307835,0.002838833,0.00020458805,0.0002366009,0.011266165,0.00075424154,0.0008145303,0.85131735,0.013868519,0.07510794],"study_design_scores_gemma":[0.0007099939,0.0004735269,0.0065309145,0.0047386056,0.00013014372,0.000024930785,0.0021886337,0.047036484,0.00006521888,0.9350179,0.0017012637,0.0013823849],"about_ca_topic_score_codex":0.00003109127,"about_ca_topic_score_gemma":0.00017532884,"teacher_disagreement_score":0.2904999,"about_ca_system_score_codex":0.0002345853,"about_ca_system_score_gemma":0.000102803126,"threshold_uncertainty_score":0.99998844},"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":"W4384277172","doi":"10.1111/bmsp.12317","title":"Evaluating the performance of existing and novel equivalence tests for fit indices in structural equation modelling","year":2023,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"York University","funders":"","keywords":"Equivalence (formal languages); Mathematics; Monte Carlo method; Statistics; Sample size determination; Structural equation modeling; Statistical hypothesis testing; Goodness of fit; Applied mathematics; Discrete mathematics","score_opus":0.8160285585535664,"score_gpt":0.5966260124549783,"score_spread":0.2194025460985881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384277172","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":[0.644032,0.00021428449,0.35523757,0.00022268762,0.00008612178,0.00009201142,0.000016770631,0.000003392664,0.00009516274],"genre_scores_gemma":[0.7977203,0.000085217966,0.20207407,0.000051384675,0.00004143378,0.000003857413,5.578423e-7,0.0000048469838,0.000018335253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975231,0.0002505213,0.0011916792,0.00022488457,0.0005697307,0.00024003332],"domain_scores_gemma":[0.9502944,0.048759904,0.00053611153,0.00009832848,0.00024272596,0.00006857844],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012167774,0.00008411139,0.00040608548,0.00021813103,0.00013624478,0.00009453848,0.00028299575,0.00006407997,0.000032799184],"category_scores_gemma":[0.0734489,0.00005670528,0.000036529604,0.00058013585,0.00029459113,0.00013815046,0.000076994584,0.00023944692,0.0000010977437],"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":[0.00023394471,0.00007821571,0.010221301,0.0002664848,0.000025239999,0.000029459201,0.0006891447,0.005330279,0.00079794537,0.04399235,0.00019563577,0.93814],"study_design_scores_gemma":[0.00050202385,0.0003964854,0.07313863,0.00018145717,0.000010366991,0.0005097189,0.00019881556,0.57613105,0.0000040955915,0.34887016,0.0000063256293,0.000050848896],"about_ca_topic_score_codex":0.0000050317667,"about_ca_topic_score_gemma":0.0000014171909,"teacher_disagreement_score":0.93808913,"about_ca_system_score_codex":0.0000062995186,"about_ca_system_score_gemma":0.000021461858,"threshold_uncertainty_score":0.93435585},"labels":[],"label_agreement":null},{"id":"W4384942374","doi":"10.1186/s40536-023-00177-5","title":"Incorporating test-taking engagement into the item selection algorithm in low-stakes computerized adaptive tests","year":2023,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Psychometric Methodologies and Testing","field":"Decision 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":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Test (biology); Selection (genetic algorithm); Psychology; Computer science; Trait; Machine learning; Psychometrics; Developmental psychology","score_opus":0.22621138543561922,"score_gpt":0.48643086407962577,"score_spread":0.2602194786440065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384942374","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":[0.8694857,0.00008672995,0.12396698,0.0006881715,0.0026853913,0.00077796594,0.000006555131,0.00014753816,0.0021549885],"genre_scores_gemma":[0.75973773,0.000017959439,0.23933049,0.00020919196,0.00020831317,0.00019121886,0.000024293808,0.000017153248,0.00026364863],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99521804,0.0015003581,0.0010471314,0.00072879344,0.0010305477,0.00047511893],"domain_scores_gemma":[0.97649634,0.021790117,0.00087928463,0.00047607286,0.00028840042,0.000069802125],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014077806,0.00021354797,0.00033939688,0.0012656159,0.00040592017,0.00036040548,0.0007245248,0.000106701555,0.00004951039],"category_scores_gemma":[0.023254363,0.00016061502,0.000063363164,0.00912062,0.00005017805,0.0005403825,0.00028082443,0.00050020235,0.00004263187],"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":[0.000006795857,0.000335582,0.46743602,0.0000074958934,0.0000062074955,0.0000022440313,0.0027942935,0.0009741139,0.00028568882,0.00018102769,0.0004704804,0.52750003],"study_design_scores_gemma":[0.0003787735,0.00007571436,0.6898748,0.00011486379,0.0000040887485,0.000002052246,0.018801054,0.27498505,0.000074803494,0.014924453,0.00061387685,0.00015047615],"about_ca_topic_score_codex":0.00037966642,"about_ca_topic_score_gemma":0.0004709535,"teacher_disagreement_score":0.5273496,"about_ca_system_score_codex":0.00039717698,"about_ca_system_score_gemma":0.00040647405,"threshold_uncertainty_score":0.9849732},"labels":[],"label_agreement":null},{"id":"W4385742310","doi":"10.2196/48444","title":"Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis","year":2023,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; Science Foundation Ireland; Department of Health and Social Care; Wellcome Trust","keywords":"Patient Health Questionnaire; Major depressive disorder; Mood; Anhedonia; Item response theory; Psychology; Clinical psychology; Logistic regression; Generalizability theory; Ordered logit; Medicine; Artificial intelligence; Psychiatry; Machine learning; Psychometrics; Depressive symptoms; Computer science; Developmental psychology; Cognition","score_opus":0.19755978587444412,"score_gpt":0.48287468355734275,"score_spread":0.28531489768289864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385742310","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":[0.8891335,0.0023020892,0.09898001,0.005177744,0.0009724219,0.0021737996,0.00023729834,0.0008690697,0.00015403934],"genre_scores_gemma":[0.9913011,0.0001233792,0.0072554406,0.00048663694,0.00007714235,0.00033106876,0.00015623412,0.00002827112,0.00024071183],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939187,0.0019244644,0.0013288816,0.00096558814,0.00096316345,0.00089919934],"domain_scores_gemma":[0.98810077,0.009606308,0.0012495685,0.00047824063,0.00017470629,0.00039039573],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008185597,0.00025104545,0.00088886346,0.0016432058,0.0013657613,0.00013608021,0.0004696544,0.00009363637,0.000029918989],"category_scores_gemma":[0.01052333,0.0002029681,0.00029910594,0.0059337504,0.00007198427,0.00024439575,0.00032977152,0.00030605966,0.00002061975],"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":[0.000083889565,0.000057146957,0.7154149,0.00007864561,0.00012371909,0.0000023022876,0.0025906924,0.0036078556,0.000008506072,0.00016305117,0.0021666011,0.27570271],"study_design_scores_gemma":[0.0008589844,0.0009826183,0.75269425,0.00023488134,0.00002330961,0.000016302643,0.003561281,0.2363158,0.00003716282,0.0011581283,0.0038744758,0.00024280846],"about_ca_topic_score_codex":0.00073908485,"about_ca_topic_score_gemma":0.00021206442,"teacher_disagreement_score":0.27545992,"about_ca_system_score_codex":0.00031782905,"about_ca_system_score_gemma":0.00019722433,"threshold_uncertainty_score":0.9999343},"labels":[],"label_agreement":null},{"id":"W4386019277","doi":"10.1037/cep0000316","title":"Item-method directed forgetting is (usually) impaired in clinical populations: A meta-analysis.","year":2023,"lang":"en","type":"review","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Motivated forgetting; Forgetting; Psychology; PsycINFO; Meta-analysis; Anxiety; Clinical psychology; Cognitive psychology; Developmental psychology; Psychiatry; MEDLINE; Medicine","score_opus":0.8438268100674826,"score_gpt":0.6243083518482093,"score_spread":0.2195184582192733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386019277","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057223113,0.98178816,0.0008922192,0.00075071515,0.0066502905,0.0013458814,0.0005784077,0.00010459548,0.0021674156],"genre_scores_gemma":[0.012128392,0.81541806,0.15003122,0.008278649,0.0032137253,0.0011298979,0.0004799053,0.0010439758,0.008276175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9771126,0.0068924595,0.009547846,0.002852751,0.0006984776,0.0028958945],"domain_scores_gemma":[0.97040784,0.016562404,0.0064839832,0.0029395842,0.00052092667,0.003085244],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.03546929,0.0013966502,0.010226705,0.012700346,0.0004396456,0.00044890036,0.0055353614,0.0016084163,0.0031382127],"category_scores_gemma":[0.035976384,0.0011514869,0.008920223,0.015675243,0.0005736523,0.00047644894,0.00025630297,0.0026131936,0.00015371905],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022103083,0.0014892049,0.034447074,0.0006458658,0.121386684,0.007930772,0.0074056624,0.00012197757,0.00003890663,0.00063168915,0.24758907,0.5780921],"study_design_scores_gemma":[0.0035354518,0.001998653,0.019619869,0.0015883246,0.07178959,0.004652545,0.008643823,0.00027661823,0.000015821402,0.011205871,0.8730527,0.0036207198],"about_ca_topic_score_codex":0.00954313,"about_ca_topic_score_gemma":0.060693473,"teacher_disagreement_score":0.62546366,"about_ca_system_score_codex":0.0020745727,"about_ca_system_score_gemma":0.0017924185,"threshold_uncertainty_score":0.9998784},"labels":[],"label_agreement":null},{"id":"W4386073897","doi":"10.17275/per.23.74.10.5","title":"A Comparison of Covariates, Equating Designs, and Methods in Equating TIMSS 2019 Science Tests","year":2023,"lang":"en","type":"article","venue":"Participatory Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Equating; Covariate; Statistics; Mathematics; Test (biology); Econometrics","score_opus":0.9561788602789288,"score_gpt":0.7700835773416688,"score_spread":0.18609528293726008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386073897","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":[0.9892569,0.0007339661,0.0055786474,0.0009938444,0.00034560155,0.00028418843,0.0000043566038,0.000019878249,0.0027826044],"genre_scores_gemma":[0.88656014,0.000009589132,0.11294984,0.000015848478,0.000059264235,0.000078850426,0.0000018335703,0.000008689627,0.0003159538],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904652,0.0036804117,0.00118546,0.0007438421,0.0030263439,0.00089873804],"domain_scores_gemma":[0.63635087,0.36072323,0.00040021716,0.00067120005,0.0015354285,0.00031908366],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12741956,0.00011039856,0.00038194648,0.0027297193,0.00051157566,0.00023685081,0.0009796689,0.00006164776,0.00028346264],"category_scores_gemma":[0.65008974,0.00009183774,0.000034801706,0.014688229,0.00088066666,0.0003142002,0.00058579165,0.00040839936,0.00014374609],"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":[0.000014642043,0.00011808582,0.8853026,0.000018007955,0.0000042974248,6.5207087e-7,0.003012598,0.00075303967,0.027525445,0.011327716,0.0013019695,0.07062094],"study_design_scores_gemma":[0.00015309145,0.00008721245,0.8166829,0.00005671235,0.0000023178443,0.0000011242455,0.004492591,0.10286512,0.0031466444,0.07225229,0.00015758054,0.0001024268],"about_ca_topic_score_codex":0.0003064422,"about_ca_topic_score_gemma":0.0000186913,"teacher_disagreement_score":0.5226702,"about_ca_system_score_codex":0.00013019907,"about_ca_system_score_gemma":0.0015202869,"threshold_uncertainty_score":0.8985052},"labels":[],"label_agreement":null},{"id":"W4386219788","doi":"10.1111/ijsa.12449","title":"Examining the assumption of measurement invariance in job performance ratings across time: The role of rater experience","year":2023,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","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":"University of Guelph","funders":"","keywords":"Psychology; Performance appraisal; Job performance; Conceptualization; Measurement invariance; Social psychology; Set (abstract data type); Applied psychology; Interpretation (philosophy); Statistics; Job satisfaction; Structural equation modeling; Confirmatory factor analysis; Computer science","score_opus":0.39285618885312257,"score_gpt":0.48944106173982277,"score_spread":0.0965848728867002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386219788","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":[0.99544454,0.000088309906,0.0028965534,0.00060898514,0.00039530854,0.000057551893,9.96078e-7,0.000003351554,0.0005043848],"genre_scores_gemma":[0.9983031,0.00012973003,0.0013840364,0.000040967185,0.000068175825,0.000004449523,1.5466605e-7,0.0000023871366,0.00006696355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973562,0.00027155058,0.0007171525,0.00011002517,0.0014463302,0.00009873954],"domain_scores_gemma":[0.9962441,0.0019233933,0.0008265549,0.00008142311,0.0009059079,0.000018627965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010459323,0.00005784453,0.0001480381,0.00022555166,0.000086438806,0.000100410114,0.00045056423,0.000022886206,0.000055633125],"category_scores_gemma":[0.0036768592,0.000029835252,0.00003695725,0.0008411359,0.000061117156,0.00027082732,0.000085227846,0.00017467097,0.0000015907464],"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":[0.000062397725,0.000034856588,0.68307054,0.000003000406,0.000037349368,0.0000012010207,0.0026693947,0.0026572535,0.074974746,0.00017043624,0.00013770761,0.2361811],"study_design_scores_gemma":[0.00029096773,0.000120185556,0.95588744,0.00007774995,0.0000029524774,0.0000309853,0.004968749,0.026578955,0.009991906,0.0010502656,0.0009634477,0.00003637467],"about_ca_topic_score_codex":0.00002534467,"about_ca_topic_score_gemma":0.000008232829,"teacher_disagreement_score":0.2728169,"about_ca_system_score_codex":0.000060346116,"about_ca_system_score_gemma":0.000069612055,"threshold_uncertainty_score":0.44018096},"labels":[],"label_agreement":null},{"id":"W4387040294","doi":"10.1080/10705511.2023.2243387","title":"Comparing Factor Score Approaches to SEM in Multigroup Models with Small Samples","year":2023,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Structural equation modeling; Statistics; Econometrics; Factor analysis; Sample (material); Reflection (computer programming); Mathematics; Computer science; Psychology; Physics","score_opus":0.9078051462744978,"score_gpt":0.4546789784729287,"score_spread":0.4531261678015691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387040294","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":[0.56242853,0.0000465918,0.4365327,0.00035603583,0.00027650336,0.00021710433,0.000007932282,0.00007811201,0.00005646649],"genre_scores_gemma":[0.76854753,0.000008400437,0.23118606,0.000012250814,0.0001545831,0.000014021259,0.000010787415,0.000025212606,0.000041142837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950393,0.00054721814,0.0013618956,0.0008141419,0.0015052832,0.00073216803],"domain_scores_gemma":[0.9940285,0.004330715,0.00048571476,0.0004826243,0.00033009006,0.00034236768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049492535,0.00034394886,0.0006137997,0.0020222508,0.0007567153,0.00059132016,0.0009946695,0.00011868786,0.000026317803],"category_scores_gemma":[0.0067873634,0.0002253087,0.00014864467,0.003743931,0.00005793436,0.0008715414,0.00044444096,0.0006729955,0.000024999574],"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":[0.00014084365,0.00000915774,0.1412206,0.0000062851886,0.000012724725,0.00001747055,0.004476793,0.82246983,0.00019878388,0.00025247567,0.000004764463,0.031190276],"study_design_scores_gemma":[0.0007100962,0.00009513962,0.13127734,0.00009976631,0.0000058140618,0.00007283634,0.0056431135,0.79858565,0.00001751039,0.063222684,9.347683e-7,0.0002691261],"about_ca_topic_score_codex":0.00014120409,"about_ca_topic_score_gemma":0.00022345943,"teacher_disagreement_score":0.20611899,"about_ca_system_score_codex":0.00016523292,"about_ca_system_score_gemma":0.00012175106,"threshold_uncertainty_score":0.91878223},"labels":[],"label_agreement":null},{"id":"W4387397390","doi":"10.1177/08445621231204296","title":"Notes to Factor Analysis Techniques for Construct Validity","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Nursing Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Construct validity; Construct (python library); Computer science; Data science; Management science; Engineering; Mathematics; Statistics; Psychometrics; Programming language","score_opus":0.9120610586715329,"score_gpt":0.6653551474292457,"score_spread":0.24670591124228713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387397390","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":[0.930138,0.00014747471,0.05473249,0.011188875,0.0010884401,0.00030876906,0.000119630626,0.000027731574,0.002248595],"genre_scores_gemma":[0.96627706,0.0000060369325,0.033167556,0.000043987304,0.00025487924,0.0000036736867,0.0000010300971,0.000009390771,0.00023640075],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99626267,0.0007616387,0.0006293779,0.00027536915,0.0013558054,0.0007151363],"domain_scores_gemma":[0.93883854,0.057073604,0.00019556923,0.00038144007,0.0024838652,0.0010269732],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022996303,0.000085878375,0.00040935483,0.010540059,0.0005049412,0.00052539853,0.0011480332,0.00008609031,0.00017591381],"category_scores_gemma":[0.3397447,0.00006456027,0.00026375195,0.016334796,0.00026540156,0.00014215933,0.000026141133,0.000359837,0.000023627752],"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":[0.000024760504,0.0000071507884,0.13330434,0.0000025869042,0.00004512901,0.00004589054,0.0010120013,0.00007514612,0.0005535612,0.00025594435,0.060328268,0.80434525],"study_design_scores_gemma":[0.0003227364,0.0011508763,0.72201097,0.00035703162,0.00009400644,0.0001018263,0.008108699,0.0011763554,0.0047861515,0.2279832,0.033573158,0.000334974],"about_ca_topic_score_codex":0.00083657604,"about_ca_topic_score_gemma":0.0011068229,"teacher_disagreement_score":0.8040103,"about_ca_system_score_codex":0.0003875054,"about_ca_system_score_gemma":0.0010596638,"threshold_uncertainty_score":0.9404785},"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":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4387816148","doi":"10.33902/jpsp.202321212","title":"A naturalistic study of elementary recess in Canada","year":2023,"lang":"en","type":"article","venue":"Journal of Pedagogical Sociology and Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Naturalism; Psychology; Mathematics education; Mathematics; Epistemology; Philosophy","score_opus":0.7443260589678452,"score_gpt":0.6026564314227395,"score_spread":0.1416696275451057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387816148","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":[0.9951244,0.0007051458,0.00011117342,0.0023649763,0.0012121863,0.00007532307,0.0000036830338,0.0000034559619,0.00039963378],"genre_scores_gemma":[0.99841195,0.00021880743,0.00048779225,0.0007439145,0.000083890634,0.0000016693857,5.2250147e-7,0.0000028509728,0.000048593192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99621326,0.0016480719,0.0012143563,0.00024645388,0.00042167315,0.00025620006],"domain_scores_gemma":[0.97988945,0.018986175,0.0007128626,0.00016718569,0.00016149129,0.00008281765],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007106171,0.000094502444,0.0006213671,0.0004712714,0.000056872424,0.0000064001583,0.0005145681,0.00012319586,0.0002559761],"category_scores_gemma":[0.01583086,0.00005795641,0.000055169545,0.0010132793,0.00017802799,0.000052441374,0.00008921738,0.00052493316,0.0000027096573],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020671348,0.000101288875,0.9530666,0.000002922459,0.000039482355,0.00025664244,0.0022108306,0.00005194085,0.000086391236,0.00019153663,0.0072359135,0.036549743],"study_design_scores_gemma":[0.001091216,0.00089435757,0.9293221,0.000004616771,0.000009674992,0.00008850271,0.020970121,0.000022423483,0.0000012572541,0.045783084,0.0017543697,0.000058232323],"about_ca_topic_score_codex":0.032579858,"about_ca_topic_score_gemma":0.075751044,"teacher_disagreement_score":0.045591548,"about_ca_system_score_codex":0.00003927754,"about_ca_system_score_gemma":0.0001541376,"threshold_uncertainty_score":0.99245924},"labels":[],"label_agreement":null},{"id":"W4387907602","doi":"10.1186/s13722-023-00416-8","title":"A 13-item Health of the Nation Outcome Scale (HoNOS-13): validation by item response theory (IRT) in patients with substance use disorder","year":2023,"lang":"en","type":"article","venue":"Addiction Science & Clinical Practice","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":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Université de Lausanne","keywords":"Health psychology; Item response theory; Psychology; Clinical psychology; Public health; Psychiatry; Scale (ratio); Quality of Life Research; Outcome (game theory); Psychometrics; Medicine","score_opus":0.4393833823714097,"score_gpt":0.5404402434536221,"score_spread":0.10105686108221235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387907602","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":[0.98476744,0.000044860204,0.008149023,0.0045617544,0.0015376405,0.00054190936,0.000031325282,0.00007580192,0.00029024034],"genre_scores_gemma":[0.99488187,0.000038686365,0.0032476499,0.0013120353,0.000037573176,0.00001813804,0.0000057432553,0.000012240261,0.0004460746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9869394,0.0059643188,0.0022101444,0.0009834149,0.003458598,0.00044417588],"domain_scores_gemma":[0.76633924,0.22770691,0.002961138,0.0012305479,0.0015836422,0.00017849445],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10545732,0.00016526888,0.00041859533,0.0008062782,0.00056940276,0.0003307945,0.0012034032,0.000111000554,0.000036233938],"category_scores_gemma":[0.65589887,0.000100136356,0.00011173991,0.016171176,0.00083637703,0.0038909959,0.00022063387,0.0005384055,0.00006565525],"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":[0.0010988459,0.00024912518,0.94640875,0.0000017163994,0.0000048111892,4.2057928e-7,0.0002453579,0.00028685585,0.000020933525,0.00017007496,0.0016792793,0.049833857],"study_design_scores_gemma":[0.0009284692,0.00032190818,0.9864322,0.00003369898,0.000009315303,0.000001410068,0.0010727975,0.0016085058,0.000019698846,0.001199412,0.008255164,0.00011741895],"about_ca_topic_score_codex":0.00020730653,"about_ca_topic_score_gemma":0.00010396083,"teacher_disagreement_score":0.55044156,"about_ca_system_score_codex":0.0001613977,"about_ca_system_score_gemma":0.00037356658,"threshold_uncertainty_score":0.9211199},"labels":[],"label_agreement":null},{"id":"W4388140417","doi":"10.1177/00131644231202949","title":"Comparing RMSEA-Based Indices for Assessing Measurement Invariance in Confirmatory Factor Models","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"York University","funders":"","keywords":"Structural equation modeling; Confirmatory factor analysis; Mathematics; Goodness of fit; Statistics","score_opus":0.9282427079429465,"score_gpt":0.5543654165441689,"score_spread":0.37387729139877757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388140417","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":[0.9347901,0.0010865417,0.048337452,0.007699773,0.0019406482,0.0007530217,0.0000146997545,0.000095104806,0.005282701],"genre_scores_gemma":[0.9898903,0.000014055745,0.009096093,0.0005831067,0.0001556268,0.00021281437,0.00000510135,0.000008370866,0.000034557524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953379,0.0004935041,0.0007831517,0.0007400192,0.0022366408,0.00040880954],"domain_scores_gemma":[0.9921908,0.0063786656,0.0003024663,0.00030728488,0.0006512982,0.00016950656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013993557,0.00019045633,0.00037542733,0.0005678244,0.0002572484,0.0002998393,0.0004941294,0.00010225235,0.00013893096],"category_scores_gemma":[0.02272173,0.00013594676,0.000085629945,0.0014480755,0.000097597345,0.00024312137,0.00005408397,0.00019587151,0.00002928321],"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":[0.00024310275,0.0014651378,0.8307145,0.00010556007,0.00006048222,0.0000046144964,0.0009188183,0.0061347275,0.0034590296,0.012275587,0.017682029,0.12693639],"study_design_scores_gemma":[0.00077007787,0.00007291818,0.88264036,0.00008748665,0.0000044623025,0.0000017222519,0.00037162757,0.008063969,0.000047565063,0.105673514,0.0020794913,0.00018682107],"about_ca_topic_score_codex":0.00001956253,"about_ca_topic_score_gemma":0.00001836127,"teacher_disagreement_score":0.12674958,"about_ca_system_score_codex":0.00014762382,"about_ca_system_score_gemma":0.0001702269,"threshold_uncertainty_score":0.9855103},"labels":[],"label_agreement":null},{"id":"W4388180784","doi":"10.1016/j.jclinepi.2023.10.005","title":"GRADE guidance 37: rating imprecision in a body of evidence on test accuracy","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"McMaster University; Impact","funders":"","keywords":"Certainty; Test (biology); Grading (engineering); Sample size determination; Rating scale; Statistics; Sample (material); Computer science; Confidence interval; Mathematics; Engineering","score_opus":0.9563425643518924,"score_gpt":0.7288577227698326,"score_spread":0.22748484158205973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388180784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.96922547,0.001042065,0.011824363,0.014393132,0.002952668,0.00013097891,0.0000035165076,0.00001893143,0.00040889173],"genre_scores_gemma":[0.95050883,0.0024225025,0.045090668,0.0012374626,0.00062945276,0.00000227096,1.7325239e-7,0.000009462829,0.000099173514],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9614305,0.019773949,0.016011413,0.0007261938,0.0014038861,0.0006540552],"domain_scores_gemma":[0.041989867,0.9459634,0.010380135,0.00073212915,0.00068773737,0.00024675767],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33589596,0.0001747558,0.0029978843,0.0008997353,0.00006277871,0.000020954118,0.0017418354,0.00033095636,0.00006615427],"category_scores_gemma":[0.99495757,0.0000942895,0.0007430693,0.003552208,0.00027983403,0.00032275816,0.00032067433,0.0013268385,0.00007615453],"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":[0.00019374638,0.000103691506,0.75081205,0.0000070973956,0.000010230179,0.00004654893,0.000028823792,0.0012370623,0.0005124688,0.00020563719,0.008793155,0.23804948],"study_design_scores_gemma":[0.0006126172,0.0015987252,0.8909871,0.0005615174,0.0000073312553,0.000030800344,0.00011794296,0.00811046,0.00007852942,0.09604509,0.0017620383,0.000087830944],"about_ca_topic_score_codex":0.000020788279,"about_ca_topic_score_gemma":0.0000045649294,"teacher_disagreement_score":0.9261894,"about_ca_system_score_codex":0.00003071709,"about_ca_system_score_gemma":0.00021869928,"threshold_uncertainty_score":0.68383485},"labels":[],"label_agreement":null},{"id":"W4388459609","doi":"10.3102/10769986231207879","title":"Analyzing Polytomous Test Data: A Comparison Between an Information-Based IRT Model and the Generalized Partial Credit Model","year":2023,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Polytomous Rasch model; Item response theory; Measure (data warehouse); Econometrics; Computer science; Statistics; Metric (unit); Parametric statistics; Nonparametric statistics; Scale (ratio); Psychometrics; Mathematics; Data mining","score_opus":0.5966527320784061,"score_gpt":0.5378534698798701,"score_spread":0.05879926219853593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388459609","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":[0.7339148,0.00010811729,0.26218885,0.0023088455,0.00025270323,0.00008576706,0.001116574,0.0000072829475,0.000017078748],"genre_scores_gemma":[0.82470286,0.00002844968,0.174674,0.000093751616,0.00026298722,0.0000029565656,0.00016231152,0.0000048669285,0.00006782503],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975981,0.00017973808,0.0010513297,0.00016560956,0.00082778,0.00017742728],"domain_scores_gemma":[0.98392123,0.01417947,0.00085476943,0.00027954942,0.00057943567,0.0001855418],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043035364,0.00011506517,0.00036329142,0.00038209592,0.0003173557,0.00045083705,0.0005658611,0.00004895252,0.000029942436],"category_scores_gemma":[0.014946214,0.00006826322,0.000036912807,0.0007032066,0.00020078097,0.00071441283,0.00012642525,0.00021317448,0.0000035545374],"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":[0.00015276954,0.00021481296,0.80154586,0.00001047315,0.00002563644,0.0000021308892,0.0009728634,0.06562241,0.000034854893,0.0039854683,0.03709242,0.09034031],"study_design_scores_gemma":[0.0007622006,0.00009302018,0.13300088,0.000007692512,0.00009696215,0.000008909387,0.00033974712,0.8326971,0.0000024348037,0.032728266,0.00017604808,0.00008671821],"about_ca_topic_score_codex":0.00007898918,"about_ca_topic_score_gemma":0.000014863936,"teacher_disagreement_score":0.7670747,"about_ca_system_score_codex":0.00002056512,"about_ca_system_score_gemma":0.00038465197,"threshold_uncertainty_score":0.99335134},"labels":[],"label_agreement":null},{"id":"W4388574245","doi":"10.1111/jedm.12380","title":"Incorporating Test‐Taking Engagement into Multistage Adaptive Testing Design for Large‐Scale Assessments","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"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":"Operationalization; Computerized adaptive testing; Test (biology); Item response theory; Premise; Scale (ratio); Computer science; Test design; Reliability (semiconductor); Psychology; Applied psychology; Reliability engineering; Psychometrics; Statistics; Test method; Mathematics; Engineering; Clinical psychology","score_opus":0.8135852760237042,"score_gpt":0.547201763889805,"score_spread":0.2663835121338992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388574245","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":[0.07395511,0.00035005537,0.9180561,0.002275494,0.0031424793,0.0007315764,0.000015341413,0.000032646458,0.0014412553],"genre_scores_gemma":[0.5209432,0.0000023391226,0.4783773,0.00007950716,0.00043552584,0.00003613986,0.0000011578211,0.0000119586875,0.000112837224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934541,0.0008953885,0.0016093957,0.00038148265,0.0032679816,0.00039165118],"domain_scores_gemma":[0.9104707,0.08028877,0.0035073657,0.00033492822,0.005177811,0.00022041751],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056673456,0.0001905845,0.0004038898,0.0009897898,0.00060918194,0.00026468924,0.00075963244,0.000056711284,0.00010249743],"category_scores_gemma":[0.34966627,0.00014618225,0.00017063945,0.0025725982,0.000032660464,0.00038341267,0.00013493974,0.0002986209,0.000027281565],"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":[0.00025399314,0.0015999478,0.6261827,0.00008904078,0.00033166615,0.000018096856,0.0036546227,0.023194948,0.03623732,0.0025284835,0.05043581,0.2554734],"study_design_scores_gemma":[0.0023738577,0.0018478034,0.6918802,0.0006326229,0.00010874836,0.000044173805,0.016413268,0.07280599,0.0016799355,0.20756572,0.0040995344,0.00054812327],"about_ca_topic_score_codex":0.000010802124,"about_ca_topic_score_gemma":0.0000076255897,"teacher_disagreement_score":0.4469881,"about_ca_system_score_codex":0.0005020077,"about_ca_system_score_gemma":0.001058621,"threshold_uncertainty_score":0.9713532},"labels":[],"label_agreement":null},{"id":"W4389129333","doi":"10.3758/s13428-023-02247-6","title":"Does strict invariance matter? Valid group mean comparisons with ordered-categorical items","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":29,"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":"Social Sciences and Humanities Research Council of Canada","keywords":"Polytomous Rasch model; Measurement invariance; Categorical variable; Mathematics; Statistics; Scalar (mathematics); Factor analysis; Item response theory; Confirmatory factor analysis; Psychometrics; Structural equation modeling; Geometry","score_opus":0.8548829296835958,"score_gpt":0.6812477469221532,"score_spread":0.17363518276144263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389129333","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":[0.38887933,0.0002535101,0.58921,0.0031131138,0.0018611972,0.0018264223,0.000057569385,0.0006691259,0.014129786],"genre_scores_gemma":[0.41374004,0.000058347705,0.5797751,0.00007162117,0.0002590348,0.0005025362,0.000016059063,0.00006918427,0.005508106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97215366,0.018483132,0.001205803,0.0016462596,0.0048384,0.0016727332],"domain_scores_gemma":[0.8819157,0.114091985,0.00034338192,0.0020086237,0.001058348,0.00058196037],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.09698318,0.00034202213,0.0008706169,0.0026738932,0.0009892049,0.0010611019,0.002867051,0.00022564737,0.001290971],"category_scores_gemma":[0.07725983,0.00017433245,0.00018724558,0.02128239,0.00060349377,0.00041988798,0.0011611275,0.0014174372,0.0010384034],"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":[0.000170274,0.0003349662,0.582754,0.000020244892,0.0000332909,0.00029000203,0.00045738852,0.00003603299,0.0075715184,0.002353738,0.046396047,0.3595825],"study_design_scores_gemma":[0.0007965682,0.0005016102,0.9068286,0.000033122582,0.00003054459,0.000057831563,0.007405352,0.001446115,0.0017707533,0.02315564,0.057449106,0.00052479183],"about_ca_topic_score_codex":0.00064223906,"about_ca_topic_score_gemma":0.00006451687,"teacher_disagreement_score":0.3590577,"about_ca_system_score_codex":0.00013386966,"about_ca_system_score_gemma":0.0001922306,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W4389324451","doi":"10.55016/ojs/ajer.v64i1.56472","title":"Deciding Whether to Respond: A Latent Class Analysis of Nonresponse on Ontario’s Grade 9 Assessment of Mathematics","year":2018,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Psychology; Class (philosophy); Multiple choice; Covariate; Latent class model; Mathematics education; Social psychology; Mathematics; Statistics; Computer science","score_opus":0.6910746457722797,"score_gpt":0.6233383899710665,"score_spread":0.06773625580121323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389324451","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":[0.9784277,0.000036325608,0.000727001,0.0056964355,0.0003132188,0.00012690062,0.0000045368247,2.91532e-7,0.0146675855],"genre_scores_gemma":[0.9471618,0.000009247166,0.03884211,0.000080735874,0.000119990495,0.0000047638837,7.474082e-7,0.000008815658,0.013771774],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99254954,0.0016315804,0.0015436319,0.0002871841,0.0036582022,0.0003298711],"domain_scores_gemma":[0.6945355,0.3011324,0.00077977934,0.0005055839,0.0028446515,0.00020211296],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02937781,0.00011512357,0.00061477773,0.0056699086,0.00014371931,0.00009055944,0.0012821456,0.00007079086,0.010540057],"category_scores_gemma":[0.38105828,0.00007725378,0.00030662157,0.007523173,0.00020774838,0.0001392549,0.00017838614,0.00039614353,0.000047545785],"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":[0.0008774372,0.0017327901,0.9380614,0.00001459587,0.0011087725,0.0000017904114,0.008443051,0.0013978418,0.0118344575,0.019204078,0.014632672,0.0026911087],"study_design_scores_gemma":[0.00026704936,0.0012955335,0.98065674,0.00013127018,0.00011461202,0.00001406129,0.0017724416,0.0010051411,0.001136839,0.008599758,0.0049136947,0.000092840244],"about_ca_topic_score_codex":0.0038630203,"about_ca_topic_score_gemma":0.010573893,"teacher_disagreement_score":0.35168046,"about_ca_system_score_codex":0.00034058772,"about_ca_system_score_gemma":0.0017902736,"threshold_uncertainty_score":0.9994598},"labels":[],"label_agreement":null},{"id":"W4390048276","doi":"10.1007/s11136-023-03560-5","title":"Unsupervised item response theory models for assessing sample heterogeneity in patient-reported outcomes measures","year":2023,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Saskatchewan; Trinity Western University; University of British Columbia; University of Calgary; McGill University; Western University; University of Lethbridge; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Item response theory; Quality of Life Research; Sample (material); Psychology; Public health; Psychometrics; Econometrics; Medicine; Clinical psychology; Economics; Nursing","score_opus":0.9246502373271043,"score_gpt":0.6511370832006224,"score_spread":0.2735131541264819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390048276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.9576885,0.00019709945,0.039736338,0.0012328733,0.00018095133,0.0006033755,0.00007342386,0.00008018579,0.0002072425],"genre_scores_gemma":[0.98776895,0.0000175112,0.011898321,0.000084245505,0.00002545924,0.00007603364,0.000006742999,0.000018866665,0.000103886014],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9675355,0.023478376,0.0024164103,0.00089241524,0.0047753975,0.00090189226],"domain_scores_gemma":[0.26728854,0.72792214,0.00066644116,0.0016499788,0.0021612223,0.0003116767],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25554806,0.00016790973,0.0008457779,0.0023850685,0.00029143394,0.00026576483,0.0011106465,0.00016370966,0.000039651248],"category_scores_gemma":[0.85755205,0.00012370636,0.0002876801,0.0063429163,0.0003045665,0.00039443694,0.0004686207,0.00036252837,0.000010985804],"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":[0.002319323,0.00018368501,0.8849608,0.000069312235,0.00006367067,0.000008225948,0.002122603,0.0017476582,0.0028803793,0.0019390708,0.0006407988,0.10306449],"study_design_scores_gemma":[0.00083490246,0.00011486744,0.7257165,0.000033411146,0.0000024214655,5.845158e-7,0.007813731,0.010185181,0.0005184233,0.25435057,0.0002844732,0.00014495687],"about_ca_topic_score_codex":0.0007683785,"about_ca_topic_score_gemma":0.00007962212,"teacher_disagreement_score":0.70444375,"about_ca_system_score_codex":0.00008631972,"about_ca_system_score_gemma":0.00049792475,"threshold_uncertainty_score":0.7665699},"labels":[],"label_agreement":null},{"id":"W4391062202","doi":"10.2196/49916","title":"Psychometric Assessment of an Item Bank for Adaptive Testing on Patient-Reported Experience of Care Environment for Severe Mental Illness: Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mental illness; Computerized adaptive testing; Clinical psychology; Psychometrics; Psychiatry; Psychology; Psychometric testing; Medicine; Mental health; Internal consistency","score_opus":0.37208629765095036,"score_gpt":0.5275054198998453,"score_spread":0.15541912224889498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391062202","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":[0.9864321,0.00031650547,0.006469304,0.00006690728,0.0010822116,0.004978599,0.00041987674,0.0000453783,0.00018916334],"genre_scores_gemma":[0.9446784,0.000011000048,0.054390352,0.00004150586,0.000044291355,0.0007186127,0.000061683495,0.000022295411,0.000031805583],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99535453,0.00038963626,0.0014864934,0.0008864701,0.0015217343,0.00036115764],"domain_scores_gemma":[0.99067926,0.0074541317,0.0010109509,0.00051568315,0.00018570083,0.00015425577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003242821,0.00022908351,0.000549652,0.0009085532,0.000323324,0.00007200155,0.00037920676,0.00005808276,0.00003755249],"category_scores_gemma":[0.0022684385,0.00017584054,0.00014456185,0.0021636677,0.00006275783,0.0002913597,0.00010314903,0.000112703674,0.0000011191238],"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":[0.00030839173,0.0011447424,0.058819097,0.00017830312,0.00004545909,0.0000010474077,0.018966177,0.00020321371,0.0005269829,0.0000786027,0.00031876867,0.9194092],"study_design_scores_gemma":[0.0044685383,0.05168724,0.49071318,0.0006178644,0.000041242136,0.000027019034,0.4148762,0.028735882,0.0038423145,0.0011592467,0.0030985312,0.0007327374],"about_ca_topic_score_codex":0.000097506716,"about_ca_topic_score_gemma":0.000007347935,"teacher_disagreement_score":0.9186765,"about_ca_system_score_codex":0.00049304747,"about_ca_system_score_gemma":0.00014508948,"threshold_uncertainty_score":0.7170569},"labels":[],"label_agreement":null},{"id":"W4391729657","doi":"10.1007/978-3-031-17299-1_1522","title":"Interval Scale","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Scale (ratio); Interval (graph theory); Mathematics; Geography; Cartography; Combinatorics","score_opus":0.7457728730689724,"score_gpt":0.5034532795406143,"score_spread":0.2423195935283582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391729657","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028729799,0.00009802231,0.007023831,0.0004059873,0.0026758746,0.00008922084,0.000015792712,0.000271784,0.98939073],"genre_scores_gemma":[0.00017572366,0.000050433748,0.011667582,0.00024410646,0.0003079343,0.0000019791025,0.0000028410252,0.000034914825,0.9875145],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996851,0.00006048741,0.00077115523,0.0006935689,0.0013912114,0.00023254128],"domain_scores_gemma":[0.97103375,0.027410885,0.00033855776,0.0008850483,0.00022417125,0.00010757895],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005451811,0.00021390257,0.0005455719,0.0009371609,0.00007472536,0.00021134487,0.0012324275,0.0002698525,0.011065716],"category_scores_gemma":[0.033344626,0.00013635242,0.00031385315,0.00037154948,0.000071383765,0.00006481333,0.0005681801,0.00033500753,0.014543492],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005369497,0.0000029939738,0.00032555763,0.0000033233312,0.00002125791,0.000023695997,0.000028453553,0.0000015660003,0.0000027769565,0.14707036,0.31364956,0.5388651],"study_design_scores_gemma":[0.000046746703,0.000031432453,0.0005996816,0.000028794047,0.0000058632236,0.0000064741103,0.00004412006,0.0000644564,0.0000035435455,0.53888565,0.46013787,0.00014536266],"about_ca_topic_score_codex":0.000012936375,"about_ca_topic_score_gemma":0.000024117979,"teacher_disagreement_score":0.5387197,"about_ca_system_score_codex":0.000021542692,"about_ca_system_score_gemma":0.000033887965,"threshold_uncertainty_score":0.9898383},"labels":[],"label_agreement":null},{"id":"W4391730158","doi":"10.1007/978-3-031-17299-1_751","title":"Discriminant Validity","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Discriminant; Linear discriminant analysis; Discriminant validity; Psychology; Mathematics; Artificial intelligence; Statistics; Computer science; Psychometrics","score_opus":0.902487588348602,"score_gpt":0.5315537204929214,"score_spread":0.3709338678556806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391730158","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029438152,0.000072056624,0.009197645,0.00046107173,0.0031569207,0.00012570729,0.000031398493,0.00025923562,0.9866665],"genre_scores_gemma":[0.00034190007,0.00013300072,0.0073517174,0.0001430891,0.00032585257,0.000002926458,0.0000052916516,0.000039494156,0.9916567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960429,0.000103426384,0.000859091,0.0008486196,0.001848524,0.0002974107],"domain_scores_gemma":[0.95351154,0.044488322,0.0004528106,0.0011797119,0.00023684332,0.000130771],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007914288,0.0002721053,0.00064244535,0.0008277569,0.0001328228,0.0002262449,0.0012714708,0.00029253663,0.0062921993],"category_scores_gemma":[0.075704955,0.00015976788,0.00034601265,0.00036637057,0.000107541986,0.00007377899,0.0005753022,0.0003525394,0.008488021],"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":[0.0000047284593,0.0000048640245,0.0002929326,0.0000056889767,0.000016974654,0.00005697186,0.000025524954,0.0000019719582,0.0000038533294,0.44176984,0.28874457,0.26907206],"study_design_scores_gemma":[0.000036058762,0.000033388114,0.0017070618,0.000020364505,0.000011318791,0.0000055475266,0.00003591653,0.000035418514,0.0000037038421,0.5963189,0.4016252,0.00016715695],"about_ca_topic_score_codex":0.000026002488,"about_ca_topic_score_gemma":0.000020288728,"teacher_disagreement_score":0.26890492,"about_ca_system_score_codex":0.000027389437,"about_ca_system_score_gemma":0.00005378329,"threshold_uncertainty_score":0.9946162},"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":"W4392297929","doi":"10.5539/ijsp.v13n1p1","title":"How Does the Elimination of Group Mean-Differences Affect Factor Score Determinacy?","year":2024,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Determinacy; Affect (linguistics); Mathematics; Factor (programming language); Statistics; Econometrics; Computer science; Psychology; Mathematical analysis","score_opus":0.28700071078692757,"score_gpt":0.4365430709525081,"score_spread":0.14954236016558053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392297929","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":[0.7826683,0.00055262464,0.21264099,0.0019899816,0.0017284282,0.00009253055,0.00022851535,0.0000053427802,0.00009328755],"genre_scores_gemma":[0.9701639,0.00013785862,0.029460687,0.000018195955,0.00015711346,0.0000014619192,0.000001120014,0.000003257773,0.00005640947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755186,0.00034478435,0.0006181112,0.00018675214,0.0012075076,0.000090993395],"domain_scores_gemma":[0.97415864,0.024121465,0.0005250004,0.00013524275,0.0010123247,0.000047331032],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004269016,0.000091757945,0.00022781329,0.0002510247,0.00005295377,0.000582954,0.0006186891,0.000037428843,0.000068930894],"category_scores_gemma":[0.033471495,0.000039838902,0.00008616738,0.0002792402,0.00021199524,0.00026642677,0.0000957528,0.00017876166,5.468849e-7],"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":[0.00006142168,0.00004234635,0.09498495,0.000044704313,0.00007857399,0.000020805479,0.000648972,0.000005109359,0.0006113748,0.031909477,0.0003243427,0.8712679],"study_design_scores_gemma":[0.00013293458,0.00024157671,0.49504107,0.000094269795,0.00002054561,0.000060977214,0.0004174443,0.0028831726,0.00034736426,0.4998293,0.0008674914,0.00006386813],"about_ca_topic_score_codex":0.00001530064,"about_ca_topic_score_gemma":0.000034030963,"teacher_disagreement_score":0.8712041,"about_ca_system_score_codex":0.00003332528,"about_ca_system_score_gemma":0.000055599856,"threshold_uncertainty_score":0.97467},"labels":[],"label_agreement":null},{"id":"W4392856628","doi":"10.1089/derm.2024.29030.sas","title":"Self-Assessment","year":2024,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2823254602382604,"score_gpt":0.48112366561142916,"score_spread":0.19879820537316878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392856628","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0864867,0.0038529185,0.32848093,0.016300404,0.0064137178,0.00022669691,0.000023861143,0.0011844438,0.5570303],"genre_scores_gemma":[0.8505827,0.00008282699,0.14714542,0.0011499183,0.0001384281,0.000010151999,0.0000011891104,0.000007226629,0.0008820944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830633,0.00020235282,0.0003473699,0.00026817207,0.0007084841,0.0001672649],"domain_scores_gemma":[0.98751307,0.011993599,0.000046408164,0.00032011422,0.00006578775,0.000061048],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024786936,0.00007041934,0.00013827656,0.00035352295,0.000082408995,0.0006199645,0.00037956852,0.000035370784,0.0010326811],"category_scores_gemma":[0.0040933318,0.000047368612,0.00007483028,0.0016618384,0.000016998196,0.00023215481,0.000089028705,0.00011224131,0.0010045745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0108769e-7,0.000013656282,0.020993436,0.00002040258,0.000018855862,0.00009692058,0.00031588538,0.000008743033,0.000016256045,0.021497685,0.3753948,0.58162326],"study_design_scores_gemma":[0.000046371948,0.000014281469,0.18972655,0.000015714622,0.0000044359485,0.00006342084,0.0001368732,0.019531265,0.000040440253,0.061289288,0.7290559,0.000075473836],"about_ca_topic_score_codex":0.000009860561,"about_ca_topic_score_gemma":0.0000017119518,"teacher_disagreement_score":0.764096,"about_ca_system_score_codex":0.000038600323,"about_ca_system_score_gemma":0.00005871489,"threshold_uncertainty_score":0.9998805},"labels":[],"label_agreement":null},{"id":"W4393408830","doi":"10.3758/s13428-024-02384-6","title":"Examining the performance of the chi-square difference test when the unrestricted model is slightly misspecified","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Nested set model; Context (archaeology); Statistics; Test (biology); Econometrics; Structural equation modeling; Statistical hypothesis testing; Chi-square test; Mean squared error; Mathematics; Computer science; Data mining","score_opus":0.8815597692413241,"score_gpt":0.6416555860264059,"score_spread":0.23990418321491813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393408830","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":[0.96305823,0.0019346633,0.025688658,0.0028757055,0.0008118467,0.0009710828,0.000047134272,0.000084081126,0.0045286044],"genre_scores_gemma":[0.89907974,0.00020418971,0.089262955,0.0001013746,0.00015837309,0.00022062435,8.196057e-7,0.000034091427,0.01093785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.986015,0.0074625523,0.0009956815,0.0008851916,0.003838476,0.00080307684],"domain_scores_gemma":[0.8402189,0.15528546,0.00028777012,0.003067341,0.0009787536,0.00016177852],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051863663,0.00025534746,0.00041414925,0.00062401406,0.0011876595,0.0008299726,0.005344063,0.00015862416,0.00035238636],"category_scores_gemma":[0.10527421,0.00009607773,0.00023403144,0.007940572,0.0009662933,0.0001932107,0.0014704807,0.0017238782,0.00003188386],"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":[0.000027834789,0.00010109772,0.09642911,0.00003109833,0.000020105283,0.000007722775,0.0042126165,0.00010260327,0.02577219,0.0009793227,0.007926655,0.86438966],"study_design_scores_gemma":[0.00019858785,0.00027640385,0.80728006,0.00019438346,0.000046118632,0.000030649455,0.0034048893,0.15212521,0.016782982,0.010668768,0.008750347,0.00024158112],"about_ca_topic_score_codex":0.00011407566,"about_ca_topic_score_gemma":0.000005797638,"teacher_disagreement_score":0.8641481,"about_ca_system_score_codex":0.000077395394,"about_ca_system_score_gemma":0.00037939675,"threshold_uncertainty_score":0.99306875},"labels":[],"label_agreement":null},{"id":"W4394143605","doi":"10.6084/m9.figshare.5705479","title":"Upper Quarter Y Balance Test","year":2017,"lang":"en","type":"dataset","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Quarter (Canadian coin); Test (biology); Balance (ability); Geography; Psychology; Geology; Archaeology; Paleontology","score_opus":0.5700244997756031,"score_gpt":0.5135375589958429,"score_spread":0.05648694077976024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394143605","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.4255767e-7,0.00048291023,0.0000011567693,0.00015869038,0.00082207884,0.00016363867,0.9941723,0.000045619454,0.0041530104],"genre_scores_gemma":[0.000009495683,0.000010102942,0.00037370826,0.00035859196,0.00079042435,0.0000814178,0.9966227,0.000013088582,0.0017405043],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99636436,0.00020839683,0.0006233823,0.00093476684,0.0014114013,0.00045772656],"domain_scores_gemma":[0.9449582,0.049362328,0.0013062172,0.0037423323,0.0004463635,0.00018455302],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012716866,0.00031093205,0.0006393113,0.00046485555,0.00033637154,0.0011715508,0.004642066,0.00043194115,0.52433366],"category_scores_gemma":[0.66064215,0.00022588286,0.00024476406,0.0005790699,0.0000200468,0.0002368356,0.0007140297,0.00059668685,0.08943747],"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":[0.0000015406525,0.000018412418,0.00023127686,0.00003200113,0.0000060973084,0.000038919345,0.0000028606182,2.7761394e-7,2.2436816e-7,7.8351604e-8,0.99168557,0.007982733],"study_design_scores_gemma":[0.000107889005,0.000046573186,0.014133094,0.00077259674,0.000006037392,0.00001848569,0.00001149774,0.000021622525,0.0000011158672,0.00036524842,0.9842209,0.00029490658],"about_ca_topic_score_codex":0.000018382492,"about_ca_topic_score_gemma":0.000012040019,"teacher_disagreement_score":0.6593705,"about_ca_system_score_codex":0.000026788328,"about_ca_system_score_gemma":0.00012014427,"threshold_uncertainty_score":0.99986535},"labels":[],"label_agreement":null},{"id":"W4395002215","doi":"10.1111/ijsa.12474","title":"Rating accuracy, leniency, and rater perceptions when using the RPM and BARS","year":2024,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","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":"Western University; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Perception; Applied psychology; Social psychology","score_opus":0.368191937024431,"score_gpt":0.5496742645416532,"score_spread":0.18148232751722226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395002215","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":[0.86773354,0.0007912976,0.12535784,0.0043886495,0.0011469785,0.00004501003,0.0000020662808,0.000008501279,0.00052611955],"genre_scores_gemma":[0.96603984,0.0003896553,0.032992188,0.00016215158,0.0002843784,9.0234767e-7,2.0325277e-7,0.0000037207676,0.00012697227],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985377,0.00019801431,0.0004210681,0.0001561868,0.0006055895,0.00008143021],"domain_scores_gemma":[0.9955142,0.003830637,0.00020963933,0.00004364915,0.00035127666,0.000050586612],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030646718,0.0000694647,0.00011296288,0.00037135545,0.00018702648,0.0010590972,0.00016382246,0.000026509082,0.0001831988],"category_scores_gemma":[0.0023890447,0.00003849755,0.00004064174,0.0002586299,0.0000547037,0.00049954676,0.0000842119,0.00023837453,6.439737e-7],"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":[0.000028217397,0.00003601949,0.12902418,0.000008077728,0.00016726866,0.000024034556,0.0020552538,0.00038941845,0.019465266,0.003186531,0.002311992,0.84330374],"study_design_scores_gemma":[0.00090831745,0.00038737414,0.5775607,0.00032580856,0.00009669545,0.0060604345,0.01326477,0.287944,0.00047924125,0.07020796,0.042470664,0.00029401813],"about_ca_topic_score_codex":0.000024866551,"about_ca_topic_score_gemma":0.000005178662,"teacher_disagreement_score":0.8430097,"about_ca_system_score_codex":0.000048197868,"about_ca_system_score_gemma":0.0000834512,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W4396840580","doi":"10.1017/9781009282284.008","title":"Multilevel Models, and Repeated Measures","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Repeated measures design; Computer science; Psychology; Econometrics; Mathematics; Statistics","score_opus":0.46524928591681475,"score_gpt":0.3548884217742436,"score_spread":0.11036086414257112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396840580","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025480153,0.0015456477,0.008968911,0.000023998138,0.00061215746,0.0002658816,0.0002181826,0.00023365373,0.9878768],"genre_scores_gemma":[0.0038671535,0.00024364376,0.0017147415,0.00004061944,0.000100917576,4.129021e-7,0.0000066820307,0.000039863306,0.99398595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969505,0.00009213374,0.00044767416,0.0011755188,0.001028509,0.00030565602],"domain_scores_gemma":[0.99391496,0.0041353772,0.00034119922,0.00093115587,0.00044225727,0.00023505972],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016530578,0.00039490982,0.000643412,0.00089734886,0.00022383458,0.0003149162,0.0009755855,0.0004358382,0.000009168187],"category_scores_gemma":[0.0021712717,0.00034604417,0.00024486237,0.000053795837,0.00030704896,0.00017879978,0.0009966298,0.0006263722,0.000028572598],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054630415,0.0000034803768,0.0000043764708,0.0000288798,0.00011301576,0.0003444719,0.00006556258,0.000025706539,0.000018830897,0.90485024,0.04198214,0.052508667],"study_design_scores_gemma":[0.00034762293,0.000043882235,0.000043043194,0.00018801593,0.00016655299,0.00005058475,0.00012961091,0.0064682704,0.00003608568,0.0091766,0.9828577,0.0004920314],"about_ca_topic_score_codex":0.0001469947,"about_ca_topic_score_gemma":0.0000018704707,"teacher_disagreement_score":0.9408756,"about_ca_system_score_codex":0.00009207246,"about_ca_system_score_gemma":0.00007742806,"threshold_uncertainty_score":0.99989915},"labels":[],"label_agreement":null},{"id":"W4396889150","doi":"10.1186/s12955-024-02253-y","title":"A scoping review to create a framework for the steps in developing condition-specific preference-based instruments de novo or from an existing non-preference-based instrument: use of item response theory or Rasch analysis","year":2024,"lang":"en","type":"review","venue":"Health and Quality of Life Outcomes","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":"Sunnybrook Health Science Centre; University Health Network; University of Toronto; Health Sciences Centre; Canadian Centre for Applied Research in Cancer Control; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; Public Health Ontario; Hospital for Sick Children","funders":"","keywords":"Rasch model; Preference; Item response theory; Dimension (graph theory); CINAHL; MEDLINE; Differential item functioning; Psychology; Computer science; Applied psychology; Psychometrics; Data science; Statistics; Clinical psychology; Mathematics; Psychological intervention; Developmental psychology","score_opus":0.9153296354092962,"score_gpt":0.6317443933356811,"score_spread":0.28358524207361513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396889150","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023715619,0.8273168,0.1410218,0.001541643,0.0003362848,0.0049743187,0.001041841,0.000046350127,0.0000053441713],"genre_scores_gemma":[0.0012062329,0.80561215,0.18789314,0.004484632,0.0000415441,0.0005652776,0.00011636948,0.00003685718,0.00004382733],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98111683,0.010108541,0.005604119,0.0012432064,0.0012514269,0.0006758607],"domain_scores_gemma":[0.69051117,0.30298296,0.00400231,0.0015440622,0.000405267,0.00055426516],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04130951,0.0006090525,0.00568591,0.0019595975,0.00032467884,0.00031110065,0.001156434,0.00032888103,0.000104924045],"category_scores_gemma":[0.24163492,0.00031660224,0.00067993975,0.0067238715,0.000177844,0.00019726079,0.00023326669,0.0005527607,0.0000027427236],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024082444,0.000101849015,0.038759463,0.092549175,0.0005090869,0.0000027035217,0.00077443157,0.000018583325,1.07208265e-7,0.001320435,0.00005168878,0.86350423],"study_design_scores_gemma":[0.00246515,0.0011690733,0.070998415,0.87193507,0.0017817465,0.0000029693538,0.0023517031,0.00050300104,0.0000031723227,0.0053006234,0.042071413,0.0014176392],"about_ca_topic_score_codex":0.00052507356,"about_ca_topic_score_gemma":0.000525883,"teacher_disagreement_score":0.8620866,"about_ca_system_score_codex":0.00025640847,"about_ca_system_score_gemma":0.0061734784,"threshold_uncertainty_score":0.9999286},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4399234968","doi":"10.1111/jedm.12401","title":"Modeling Response Styles in Cross‐Classified Data Using a Cross‐Classified Multidimensional Nominal Response Model","year":2024,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Covariate; Item response theory; Cross-validation; Computer science; Data set; Statistics; Multilevel model; Set (abstract data type); Econometrics; Psychology; Mathematics; Psychometrics","score_opus":0.8252373857984466,"score_gpt":0.5741859983791489,"score_spread":0.2510513874192978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399234968","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":[0.9304871,0.0027904252,0.05987651,0.0043447292,0.0021274819,0.00017457422,0.000050958515,0.000012589505,0.00013561502],"genre_scores_gemma":[0.8831483,0.000013441046,0.115879096,0.00012179876,0.00042935775,0.000005618737,0.0000028745828,0.000025864914,0.00037364796],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98831683,0.0025172578,0.0027732346,0.00088994595,0.0049926303,0.00051010994],"domain_scores_gemma":[0.9629046,0.031725656,0.00084919255,0.0011568231,0.0030131314,0.00035061524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08857544,0.00030053215,0.00057053444,0.0023092832,0.00029870804,0.000897821,0.0016609865,0.00015477855,0.00025357344],"category_scores_gemma":[0.21586531,0.0002266179,0.0002402783,0.0018950322,0.00016254073,0.0013098498,0.0003711816,0.00070984155,0.000027750713],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014327251,0.00055817876,0.018191976,0.000029847131,0.00012443138,0.00006370104,0.00068639783,0.8537162,0.104743004,0.0007528346,0.0029306263,0.0038755855],"study_design_scores_gemma":[0.00086956477,0.00010454428,0.10290483,0.00042563045,0.000031023796,0.0002176871,0.00054611324,0.88547534,0.00019124974,0.008191646,0.00080414256,0.00023826257],"about_ca_topic_score_codex":0.000045393987,"about_ca_topic_score_gemma":0.000016526385,"teacher_disagreement_score":0.12728988,"about_ca_system_score_codex":0.0011307298,"about_ca_system_score_gemma":0.0065484303,"threshold_uncertainty_score":0.9990835},"labels":[],"label_agreement":null},{"id":"W4399246403","doi":"10.1111/1748-8583.12563","title":"Isolating the effect of rater experience as a time‐variant predictor of performance ratings","year":2024,"lang":"en","type":"article","venue":"Human Resource Management Journal","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 Guelph","funders":"","keywords":"Psychology","score_opus":0.12263329537280344,"score_gpt":0.40774706346175077,"score_spread":0.28511376808894734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399246403","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":[0.9300047,0.0004556587,0.0038618469,0.00012616462,0.00025646563,0.00023365236,0.000001109025,0.000032142372,0.06502825],"genre_scores_gemma":[0.99358183,0.000015034788,0.0017118746,0.0000425362,0.00016795573,0.000010328152,3.4460405e-7,0.000013355613,0.0044567557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99610305,0.00080296875,0.0010554784,0.00032697723,0.0014177802,0.00029376382],"domain_scores_gemma":[0.9921651,0.006577609,0.0005993882,0.0004992234,0.000089776266,0.000068940695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013158639,0.00016554768,0.00035133245,0.00059167406,0.0004215903,0.0004585034,0.0012087349,0.000040101455,0.0011724368],"category_scores_gemma":[0.004260918,0.00008346887,0.00019155792,0.0013447434,0.0001832027,0.00019844796,0.000394488,0.00033835266,0.00004563164],"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":[0.00065850734,0.00012420763,0.13924864,0.0010503842,0.00086700416,0.0006445794,0.029698791,0.0064377543,0.020485472,0.008267273,0.033515774,0.7590016],"study_design_scores_gemma":[0.007481625,0.014633,0.23559423,0.008590659,0.00096489745,0.0028140226,0.039711744,0.3388655,0.029105894,0.029800138,0.29031298,0.002125334],"about_ca_topic_score_codex":0.0000034173675,"about_ca_topic_score_gemma":9.9079834e-8,"teacher_disagreement_score":0.7568763,"about_ca_system_score_codex":0.000025158264,"about_ca_system_score_gemma":0.000011955921,"threshold_uncertainty_score":0.9997406},"labels":[],"label_agreement":null},{"id":"W4399289104","doi":"10.1093/asj/sjae124","title":"Unit of Analysis Guide, Part 2: Not Everything That Can Be Counted Counts","year":2024,"lang":"en","type":"editorial","venue":"Aesthetic Surgery Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine","score_opus":0.38353845033480777,"score_gpt":0.4503756003796832,"score_spread":0.06683715004487545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399289104","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056970324,0.0023373305,0.0007716445,0.0008240708,0.9838897,0.00006809759,0.00031476666,0.000051103925,0.006046278],"genre_scores_gemma":[0.055468846,0.013783676,0.005753755,0.0008655458,0.83130324,0.000025746936,0.00038649453,0.00039971602,0.09201301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99009055,0.0013999788,0.0020238815,0.00060985866,0.005375547,0.00050016155],"domain_scores_gemma":[0.8904448,0.10346912,0.0026402748,0.0011183531,0.0020286192,0.000298831],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035886686,0.00035653124,0.0015677315,0.003441414,0.00024508548,0.0007009541,0.0011849313,0.00054421235,0.0017715269],"category_scores_gemma":[0.057914175,0.00025083913,0.0011597745,0.0056167357,0.0001668242,0.00013438142,0.00016662417,0.0016997079,0.00009924878],"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":[0.000015560854,0.00001476255,0.0022183142,0.0000073484525,0.0002721166,0.00014238463,0.00007290782,0.000040895018,3.2273326e-7,0.000007419718,0.9220025,0.0752055],"study_design_scores_gemma":[0.00008574315,0.000019590423,0.00013168082,0.00024930987,0.00048373523,0.00054508867,0.00024699912,0.00015138566,0.0000069651196,0.0014993389,0.99631596,0.000264193],"about_ca_topic_score_codex":0.00014692046,"about_ca_topic_score_gemma":0.000023076956,"teacher_disagreement_score":0.15258646,"about_ca_system_score_codex":0.00012056997,"about_ca_system_score_gemma":0.0012994751,"threshold_uncertainty_score":0.9999944},"labels":[],"label_agreement":null},{"id":"W4399295484","doi":"10.1007/s11336-024-09977-2","title":"The InterModel Vigorish as a Lens for Understanding (and Quantifying) the Value of Item Response Models for Dichotomously Coded Items","year":2024,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"York University","funders":"Jacobs Foundation; Leverhulme Trust","keywords":"Item response theory; Value (mathematics); Computer science; Psychometrics; Statistics; Econometrics; Mathematics","score_opus":0.6941929902442963,"score_gpt":0.5167567847765115,"score_spread":0.1774362054677847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399295484","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":[0.14750652,0.008243239,0.8343368,0.004104012,0.0026908864,0.0013364259,0.00012207041,0.00010048668,0.0015595607],"genre_scores_gemma":[0.98674303,0.0005730536,0.010835639,0.00021580001,0.00016057951,0.00019716356,0.0000018658643,0.000045942266,0.0012269414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955651,0.00071204803,0.0011795236,0.0008567,0.0011077268,0.0005788572],"domain_scores_gemma":[0.6946864,0.30366632,0.0003793724,0.000845233,0.0003253244,0.000097338416],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031224106,0.00026888552,0.0005257612,0.0014618409,0.00078805396,0.0011088329,0.0013491166,0.00015100383,0.0000124707885],"category_scores_gemma":[0.15250282,0.00013799655,0.00041500118,0.005397151,0.00035385924,0.00037725994,0.00016795793,0.00028549382,0.000005543578],"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":[0.008523574,0.00015074352,0.0018127183,0.00025403744,0.0005619668,0.0000061994424,0.0076866834,0.0013908272,0.00476689,0.66125745,0.05422121,0.2593677],"study_design_scores_gemma":[0.0008244172,0.00052034535,0.00060281606,0.00013313758,0.000055100783,0.000027385344,0.0055673337,0.35459188,0.00025058616,0.59681904,0.040390268,0.00021772372],"about_ca_topic_score_codex":0.00003403075,"about_ca_topic_score_gemma":0.000012965694,"teacher_disagreement_score":0.8392365,"about_ca_system_score_codex":0.000106304156,"about_ca_system_score_gemma":0.00012053167,"threshold_uncertainty_score":0.9999281},"labels":[],"label_agreement":null},{"id":"W4399380790","doi":"10.31219/osf.io/bxr54","title":"A comparison of regularization, alignment, and a traditional method for estimating structural relationships across multiple groups","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regularization (linguistics); Mathematics; Computer science; Algorithm; Artificial intelligence","score_opus":0.6857009403865407,"score_gpt":0.5561256710083546,"score_spread":0.1295752693781861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399380790","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":[0.110191055,0.0004414009,0.88558865,0.00046320798,0.0015797836,0.00062520243,0.0004839821,0.00008292279,0.0005438196],"genre_scores_gemma":[0.4189795,9.2420873e-7,0.58050895,0.000014388822,0.00013088307,0.000050173992,0.00007117579,0.000012863849,0.00023116707],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952972,0.0007548722,0.0016893692,0.00097452453,0.0010062408,0.0002778017],"domain_scores_gemma":[0.9194361,0.078331254,0.0010909156,0.00055762014,0.00047961102,0.00010450628],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012187131,0.00026578963,0.00081803143,0.0004348861,0.00039123322,0.0004825368,0.00056876475,0.00032746466,0.000058448328],"category_scores_gemma":[0.12337191,0.0001976263,0.00022310918,0.00096714403,0.00013748735,0.0001101773,0.0009259397,0.00060985814,0.000002156342],"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":[0.00015004423,0.00013124348,0.35558078,0.0011623834,0.00043749335,0.0000024564627,0.014689942,0.1068961,0.00082346564,0.19892684,0.013272979,0.3079263],"study_design_scores_gemma":[0.0001765929,0.000026998237,0.02000251,0.00006500958,0.000026755171,0.0000063906627,0.001322616,0.5047144,0.00012245288,0.47337264,0.00004715115,0.00011642789],"about_ca_topic_score_codex":0.00004253784,"about_ca_topic_score_gemma":0.000022972521,"teacher_disagreement_score":0.39781836,"about_ca_system_score_codex":0.000048480983,"about_ca_system_score_gemma":0.00008473969,"threshold_uncertainty_score":0.8840123},"labels":[],"label_agreement":null},{"id":"W4399568090","doi":"10.1007/s11136-024-03690-4","title":"Translation and linguistic validation of 24 PROMIS item banks into French","year":2024,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean; McGill University; Centre de réadaptation Lethbridge-Layton-Mackay; Centre for Interdisciplinary Research in Rehabilitation; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Strategy for Patient-Oriented Research; Centre for Interdisciplinary Research in Rehabilitation","keywords":"Quality of Life Research; Linguistics; Translation (biology); Public health; Psychology; Natural language processing; Computer science; Medicine; Nursing; Philosophy","score_opus":0.8967886007634996,"score_gpt":0.6453574115789563,"score_spread":0.2514311891845433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399568090","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":[0.9771568,0.0043739523,0.012157699,0.0011292332,0.00028238792,0.00022793206,0.000013449593,0.00002627086,0.0046322625],"genre_scores_gemma":[0.9843616,0.0000698538,0.015183608,0.0000054601487,0.000101090416,0.0000059802287,0.0000029306752,0.000005501268,0.0002639839],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99351704,0.002577553,0.0010338261,0.00040697455,0.0022654952,0.00019909104],"domain_scores_gemma":[0.8199935,0.1776748,0.00024760928,0.00058554154,0.0013378295,0.00016069536],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05385852,0.00006972431,0.00032267784,0.0009431623,0.00009358293,0.00015068967,0.00036726144,0.00009196052,0.00016747724],"category_scores_gemma":[0.37031755,0.000051937386,0.000070905604,0.0028242297,0.00026514192,0.000122068384,0.00009247178,0.0002738748,0.000010289073],"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":[0.000067288995,0.00007593131,0.12989274,0.0009530181,0.000038909853,0.0000018030065,0.008945137,0.0000190918,0.009120941,0.0052842638,0.0015641878,0.8440367],"study_design_scores_gemma":[0.00066927634,0.0005866277,0.47573468,0.00043537247,0.000016135924,0.0000025074396,0.0027941437,0.022304842,0.010878158,0.4756626,0.010641038,0.00027462796],"about_ca_topic_score_codex":0.0009459268,"about_ca_topic_score_gemma":0.00002133121,"teacher_disagreement_score":0.84376204,"about_ca_system_score_codex":0.000019812487,"about_ca_system_score_gemma":0.0001939238,"threshold_uncertainty_score":0.97425175},"labels":[],"label_agreement":null},{"id":"W4399587962","doi":"10.32614/cran.package.capl","title":"capl: Compute and Visualize CAPL-2 Scores and Interpretations","year":2021,"lang":"en","type":"dataset","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Computer science; Psychology","score_opus":0.4508177195094503,"score_gpt":0.5291559676888464,"score_spread":0.07833824817939611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399587962","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016253557,0.004643284,0.014250967,0.00036688827,0.0014583583,0.00018535308,0.9762516,0.00004956689,0.0011685982],"genre_scores_gemma":[0.00084337953,0.0042861565,0.110767774,0.0029128224,0.00050909224,0.00003227909,0.87768364,0.000036235982,0.002928609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968552,0.00059018994,0.0007007386,0.00086135673,0.0007476408,0.0002448621],"domain_scores_gemma":[0.9635934,0.034900777,0.00034063615,0.0007388175,0.0002556381,0.00017069261],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002915406,0.00024665773,0.00064304186,0.00073675043,0.00019056781,0.0008952815,0.00061035727,0.00019656161,0.00084258255],"category_scores_gemma":[0.06080722,0.00016839568,0.00007501667,0.0013012043,0.0002155238,0.0001388382,0.0008566307,0.0003025221,0.000039844366],"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":[0.0000030990318,0.000013965606,0.00062693557,0.00001965349,0.000024646713,0.000021601138,0.00004233128,0.0000017015453,0.0000021773972,0.00007999451,0.9736715,0.025492419],"study_design_scores_gemma":[0.00018184006,0.000060694696,0.005069197,0.0000839182,0.000034734112,0.000089008914,0.00043803698,0.0006770289,0.000003970603,0.004067196,0.9890449,0.0002494944],"about_ca_topic_score_codex":0.00066892296,"about_ca_topic_score_gemma":0.00035242055,"teacher_disagreement_score":0.09856798,"about_ca_system_score_codex":0.000012093178,"about_ca_system_score_gemma":0.00007589723,"threshold_uncertainty_score":0.947104},"labels":[],"label_agreement":null},{"id":"W4399615670","doi":"10.31219/osf.io/chfwq","title":"New Computations for RMSEA and CFI following FIML and TS Estimation with Missing Data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Structural equation modeling; Missing data; Population; Computation; Econometrics; Mean squared error; Sample size determination; Statistics; Mathematics; Structural estimation; Sample (material); Algorithm; Physics","score_opus":0.7157877277672647,"score_gpt":0.564853354415018,"score_spread":0.1509343733522467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399615670","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":[0.018915536,0.0022325255,0.972496,0.0026954566,0.0007803373,0.00042523674,0.000057331865,0.00010861062,0.0022889948],"genre_scores_gemma":[0.077364884,0.00001924986,0.9214139,0.00007959582,0.00009748313,0.000007123084,0.000061271145,0.000015246124,0.0009412423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975822,0.00010949213,0.0004986903,0.0010735773,0.00054932886,0.00018668898],"domain_scores_gemma":[0.9731542,0.02550792,0.0002418984,0.00083776057,0.000107676045,0.00015055032],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0034000308,0.00019205597,0.000401923,0.00048637463,0.00021399208,0.0017219515,0.00060657755,0.00012135269,0.000021678665],"category_scores_gemma":[0.030554427,0.0001234053,0.00004868499,0.00069317996,0.00004141088,0.00021328949,0.0020490952,0.00024718593,0.0000038103233],"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":[0.000008632197,0.000004475112,0.0018759253,0.0000762273,0.000049981798,0.0000042107627,0.00021867658,0.0016514314,0.0000061237974,0.00047242342,0.010514778,0.98511714],"study_design_scores_gemma":[0.00022851783,0.000033802153,0.005004737,0.00024798515,0.000084700725,0.000015185979,0.00027359294,0.6404081,0.0000052856253,0.35223854,0.0012930185,0.00016654705],"about_ca_topic_score_codex":0.00016468394,"about_ca_topic_score_gemma":0.000027741358,"teacher_disagreement_score":0.98495054,"about_ca_system_score_codex":0.000014995844,"about_ca_system_score_gemma":0.00021218728,"threshold_uncertainty_score":0.99931437},"labels":[],"label_agreement":null},{"id":"W4399707353","doi":"10.1016/j.jval.2024.03.1525","title":"MSR92 Quantitative Bias Analysis Under the Marginal Structural Modelling Framework","year":2024,"lang":"en","type":"article","venue":"Value in Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Marginal structural model; Econometrics; Marginal model; Computer science; Economics; Machine learning; Causal inference; Regression analysis","score_opus":0.7966582806538572,"score_gpt":0.563932937089473,"score_spread":0.23272534356438423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399707353","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":[0.37691107,0.0066677695,0.6089005,0.00604667,0.00092507264,0.00012322642,0.000010147632,0.000048269318,0.00036728766],"genre_scores_gemma":[0.83432525,0.00016666093,0.16482864,0.00044442818,0.00009368386,0.000004735751,0.000001235242,0.000008703197,0.00012668986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948993,0.0020835653,0.0009132392,0.00060074584,0.001064786,0.00043841582],"domain_scores_gemma":[0.9078073,0.091150485,0.00024796603,0.00058716635,0.00009843932,0.00010866882],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017274708,0.00014248959,0.00043059347,0.0013403186,0.00026115304,0.00042640913,0.0006666655,0.00008138624,0.00019283574],"category_scores_gemma":[0.016194737,0.00007701696,0.00020182409,0.013075447,0.00009706869,0.00015723646,0.000094745665,0.0005913191,0.000049120976],"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":[0.000010085666,0.000004259756,0.013903984,0.000013324749,0.00005509391,0.000005309552,0.0014061618,0.8374964,3.4222637e-7,0.1368763,0.0002295702,0.0099991895],"study_design_scores_gemma":[0.000025081532,0.00003496261,0.014637263,0.000048673974,0.000012419534,0.000002761747,0.0023345144,0.6098952,4.5503145e-7,0.37244597,0.0005050642,0.000057584693],"about_ca_topic_score_codex":0.0036111167,"about_ca_topic_score_gemma":0.000050351373,"teacher_disagreement_score":0.45741415,"about_ca_system_score_codex":0.00012171696,"about_ca_system_score_gemma":0.0002129822,"threshold_uncertainty_score":0.99209225},"labels":[],"label_agreement":null},{"id":"W4399932302","doi":"10.69758/rwot6417","title":"A Thorough Analysis of the Address Corrector: Improving Validity of Data and Reliability","year":2024,"lang":"en","type":"article","venue":"Gurukul multidisciplinary research journal.","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Reliability (semiconductor); Reliability engineering; Computer science; Predictor–corrector method; Engineering; Algorithm; Physics","score_opus":0.7405719524951859,"score_gpt":0.6018433097939174,"score_spread":0.1387286427012685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399932302","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":[0.98134124,0.0034681773,0.010937105,0.0011400239,0.0010316871,0.00031771543,0.0003233415,0.000021585922,0.0014191379],"genre_scores_gemma":[0.98961526,0.0004035418,0.009244659,0.00000337699,0.00014072414,0.0000044735716,0.000004210727,0.000012536247,0.00057123316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9880616,0.0053926664,0.0014825603,0.0009371479,0.0035947904,0.00053124235],"domain_scores_gemma":[0.8902338,0.10329886,0.00072077935,0.0036287892,0.0018316937,0.00028603876],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0961024,0.00016825375,0.00071740476,0.002009995,0.0006796066,0.0005050811,0.0039043967,0.000119098404,0.00022203002],"category_scores_gemma":[0.16977052,0.00008758471,0.00035259328,0.01325464,0.00090421375,0.0008990173,0.0057236305,0.0013327148,0.00000395641],"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":[0.00017630905,0.00021617272,0.71729434,0.00017440003,0.00044788903,0.000056486897,0.002656779,0.0008547825,0.004407277,0.00013026304,0.0067520174,0.2668333],"study_design_scores_gemma":[0.00021485817,0.00021938086,0.6872961,0.00019987693,0.00028064093,0.0000770912,0.004609182,0.2885025,0.00042642164,0.016463645,0.0015647797,0.00014549712],"about_ca_topic_score_codex":0.0002065417,"about_ca_topic_score_gemma":0.000055086817,"teacher_disagreement_score":0.28764772,"about_ca_system_score_codex":0.00008046518,"about_ca_system_score_gemma":0.00041395926,"threshold_uncertainty_score":0.9307528},"labels":[],"label_agreement":null},{"id":"W4399980767","doi":"10.1080/21624887.2024.2370130","title":"CSoS ECR Outstanding Research Article Award 2023 Winner","year":2024,"lang":"en","type":"article","venue":"Critical Studies on Security","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Engineering ethics; Political science; Sociology; Engineering","score_opus":0.8481845419493018,"score_gpt":0.6703292882993692,"score_spread":0.1778552536499326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399980767","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":[0.8419762,0.0305858,0.0037057265,0.043411847,0.009658877,0.00043754926,0.00007364604,0.0005168348,0.069633484],"genre_scores_gemma":[0.9969782,0.00026065967,0.0011390778,0.00033665626,0.0005932716,0.000030682677,3.68415e-7,0.000015378288,0.00064568344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935018,0.001362753,0.0007588576,0.0010031473,0.0025044295,0.0008690007],"domain_scores_gemma":[0.82626206,0.17163624,0.000037685724,0.0007301829,0.0010274715,0.00030634986],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023847545,0.00019168787,0.0004844312,0.0005721279,0.00076217006,0.0007540746,0.0006633792,0.00011470138,0.0005169608],"category_scores_gemma":[0.4365559,0.0001231707,0.00018335758,0.003910656,0.00093828345,0.00025194042,0.0006744067,0.0009063318,0.0023300068],"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":[0.00010852599,0.00027861443,0.009113985,0.00018591154,0.00016951308,0.0005915151,0.0059406394,0.000022085895,0.0003155592,0.5404683,0.38505098,0.05775441],"study_design_scores_gemma":[0.00016945506,0.00031553782,0.003199916,0.00021411463,0.000018504774,0.000012189651,0.021359004,0.0031756172,0.00055221905,0.89004993,0.080678925,0.00025457417],"about_ca_topic_score_codex":0.00001893744,"about_ca_topic_score_gemma":0.000014101621,"teacher_disagreement_score":0.41270837,"about_ca_system_score_codex":0.00017588424,"about_ca_system_score_gemma":0.000048237427,"threshold_uncertainty_score":0.9984468},"labels":[],"label_agreement":null},{"id":"W4400020738","doi":"10.1089/derm.2024.35324.sas","title":"Self-Assessment","year":2024,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2823254602382604,"score_gpt":0.48112366561142916,"score_spread":0.19879820537316878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400020738","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0864867,0.0038529185,0.32848093,0.016300404,0.0064137178,0.00022669691,0.000023861143,0.0011844438,0.5570303],"genre_scores_gemma":[0.8505827,0.00008282699,0.14714542,0.0011499183,0.0001384281,0.000010151999,0.0000011891104,0.000007226629,0.0008820944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830633,0.00020235282,0.0003473699,0.00026817207,0.0007084841,0.0001672649],"domain_scores_gemma":[0.98751307,0.011993599,0.000046408164,0.00032011422,0.00006578775,0.000061048],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024786936,0.00007041934,0.00013827656,0.00035352295,0.000082408995,0.0006199645,0.00037956852,0.000035370784,0.0010326811],"category_scores_gemma":[0.0040933318,0.000047368612,0.00007483028,0.0016618384,0.000016998196,0.00023215481,0.000089028705,0.00011224131,0.0010045745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0108769e-7,0.000013656282,0.020993436,0.00002040258,0.000018855862,0.00009692058,0.00031588538,0.000008743033,0.000016256045,0.021497685,0.3753948,0.58162326],"study_design_scores_gemma":[0.000046371948,0.000014281469,0.18972655,0.000015714622,0.0000044359485,0.00006342084,0.0001368732,0.019531265,0.000040440253,0.061289288,0.7290559,0.000075473836],"about_ca_topic_score_codex":0.000009860561,"about_ca_topic_score_gemma":0.0000017119518,"teacher_disagreement_score":0.764096,"about_ca_system_score_codex":0.000038600323,"about_ca_system_score_gemma":0.00005871489,"threshold_uncertainty_score":0.9998805},"labels":[],"label_agreement":null},{"id":"W4400982999","doi":"10.1037/apl0001214","title":"A longitudinal meta-analysis of range restriction estimates and general mental ability validity coefficients: Better addressing overcorrection amid decline effects.","year":2024,"lang":"en","type":"review","venue":"Journal of Applied Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Mount Royal University; University of Calgary","funders":"","keywords":"Psychology; Statistics; Homogeneity (statistics); Range (aeronautics); Variance (accounting); Population; Econometrics; Divergence (linguistics); Social psychology; Mathematics; Demography","score_opus":0.693000175735403,"score_gpt":0.5734002998863317,"score_spread":0.11959987584907128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400982999","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011154644,0.9570113,0.026968505,0.00011176451,0.0036256902,0.0005194742,0.000094127696,0.000025964266,0.0004885375],"genre_scores_gemma":[0.00619279,0.964007,0.028904716,0.00018912471,0.00055848644,0.000041885953,0.000027965143,0.00004997115,0.000028061566],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99219114,0.0014744154,0.0035309861,0.001024355,0.0014189405,0.0003601632],"domain_scores_gemma":[0.9750578,0.019260798,0.00439801,0.0007413496,0.00037900097,0.0001630885],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015209594,0.0005448656,0.006370126,0.0041099736,0.00014247895,0.00021994553,0.00080322183,0.0004985699,0.00019891658],"category_scores_gemma":[0.007841244,0.00031733848,0.0031228221,0.0064357067,0.00029255787,0.00014637034,0.00027779108,0.0010394764,0.000010303081],"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":[0.00021327888,0.00031034212,0.0015935682,0.0012224873,0.042708613,0.00004350078,0.00009363916,0.0001070202,0.00003847282,0.00004969555,0.004533964,0.9490854],"study_design_scores_gemma":[0.00140373,0.00114977,0.025130928,0.00077060965,0.77035135,0.0009376306,0.00007440112,0.0010782855,0.000017563125,0.01485025,0.18328196,0.0009535133],"about_ca_topic_score_codex":0.000017207303,"about_ca_topic_score_gemma":0.0000042815623,"teacher_disagreement_score":0.9481319,"about_ca_system_score_codex":0.00012839772,"about_ca_system_score_gemma":0.000077452285,"threshold_uncertainty_score":0.9999279},"labels":[],"label_agreement":null},{"id":"W4401073429","doi":"10.1089/derm.2024.94682.sas","title":"Self-Assessment","year":2024,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2823254602382604,"score_gpt":0.48112366561142916,"score_spread":0.19879820537316878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401073429","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0864867,0.0038529185,0.32848093,0.016300404,0.0064137178,0.00022669691,0.000023861143,0.0011844438,0.5570303],"genre_scores_gemma":[0.8505827,0.00008282699,0.14714542,0.0011499183,0.0001384281,0.000010151999,0.0000011891104,0.000007226629,0.0008820944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830633,0.00020235282,0.0003473699,0.00026817207,0.0007084841,0.0001672649],"domain_scores_gemma":[0.98751307,0.011993599,0.000046408164,0.00032011422,0.00006578775,0.000061048],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024786936,0.00007041934,0.00013827656,0.00035352295,0.000082408995,0.0006199645,0.00037956852,0.000035370784,0.0010326811],"category_scores_gemma":[0.0040933318,0.000047368612,0.00007483028,0.0016618384,0.000016998196,0.00023215481,0.000089028705,0.00011224131,0.0010045745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0108769e-7,0.000013656282,0.020993436,0.00002040258,0.000018855862,0.00009692058,0.00031588538,0.000008743033,0.000016256045,0.021497685,0.3753948,0.58162326],"study_design_scores_gemma":[0.000046371948,0.000014281469,0.18972655,0.000015714622,0.0000044359485,0.00006342084,0.0001368732,0.019531265,0.000040440253,0.061289288,0.7290559,0.000075473836],"about_ca_topic_score_codex":0.000009860561,"about_ca_topic_score_gemma":0.0000017119518,"teacher_disagreement_score":0.764096,"about_ca_system_score_codex":0.000038600323,"about_ca_system_score_gemma":0.00005871489,"threshold_uncertainty_score":0.9998805},"labels":[],"label_agreement":null},{"id":"W4401091997","doi":"10.1111/jep.14114","title":"A many‐facet Rasch measurement model approach to investigating objective structured clinical examination item parameter drift","year":2024,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Touchstone Exploration (Canada); McMaster University","funders":"","keywords":"Rasch model; Polytomous Rasch model; Facet (psychology); Item response theory; Psychology; Medicine; Psychometrics; Clinical psychology; Social psychology; Developmental psychology","score_opus":0.816087781485377,"score_gpt":0.6373573978864153,"score_spread":0.17873038359896165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401091997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.5331036,0.00088855566,0.44946647,0.0035446614,0.004186637,0.0008095718,0.000003363655,0.000028203116,0.007968972],"genre_scores_gemma":[0.66937673,0.000037049176,0.3290925,0.0009160578,0.00050974597,0.000014682102,7.2027734e-7,0.00001391868,0.000038594077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96116185,0.020917611,0.007825841,0.0010648539,0.008614428,0.00041543503],"domain_scores_gemma":[0.47100767,0.50800735,0.006600173,0.0012254963,0.012342219,0.00081709295],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4042676,0.00022145589,0.00086141017,0.0011282287,0.00011104652,0.00065655675,0.0007095846,0.0003344839,0.000059300666],"category_scores_gemma":[0.9502617,0.00015602366,0.00042017398,0.0031819253,0.000121421144,0.0016932847,0.0001782091,0.0020189623,0.000035737532],"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":[0.0003026358,0.00050542416,0.015949484,0.000022063501,0.00019235529,0.000017901104,0.001202199,0.070862435,0.000109527355,0.0008927352,0.0074959835,0.9024472],"study_design_scores_gemma":[0.00095827813,0.000559052,0.28547683,0.00014941883,0.00018656826,0.000073401614,0.0017943366,0.6637247,0.000012703831,0.04569306,0.0012146163,0.00015703414],"about_ca_topic_score_codex":0.000009744358,"about_ca_topic_score_gemma":0.0000051164693,"teacher_disagreement_score":0.9022902,"about_ca_system_score_codex":0.0003750153,"about_ca_system_score_gemma":0.0010965063,"threshold_uncertainty_score":0.8771499},"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":"W4402461068","doi":"10.7759/cureus.69151","title":"Item Analysis of Multiple-Choice Question (MCQ)-Based Exam Efficiency Among Postgraduate Pediatric Medical Students: An Observational, Cross-Sectional Study From Saudi Arabia","year":2024,"lang":"en","type":"article","venue":"Cureus","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":"Child, Adolescent and Family Mental Health","funders":"","keywords":"Medicine; Observational study; Cross-sectional study; Multiple choice; Family medicine; Medical education; Pathology; Internal medicine; Significant difference","score_opus":0.47435159950516703,"score_gpt":0.5321652294323643,"score_spread":0.057813629927197296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402461068","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":[0.9779914,0.0009966397,0.018365772,0.000087147586,0.0018324336,0.00033653446,0.00014354195,0.00017895352,0.00006754838],"genre_scores_gemma":[0.99660385,0.000020822352,0.0025901545,0.000075442746,0.0004586297,0.000032640128,0.000108816275,0.000018142398,0.00009148467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9889446,0.0014753293,0.0017493865,0.0012725433,0.0062129083,0.0003452577],"domain_scores_gemma":[0.9116782,0.08566549,0.0005645357,0.0008907863,0.00092340034,0.00027758503],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015861804,0.0002690843,0.00063771475,0.0016211646,0.00026622287,0.00088319025,0.0020781292,0.00021745505,0.0009165799],"category_scores_gemma":[0.21777272,0.00020477298,0.00033917069,0.010961104,0.0001759648,0.0006461728,0.00026829407,0.00038808826,0.00002922951],"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":[0.000028332424,0.0008336735,0.99239564,0.000007686498,0.00027862596,0.000026451327,0.00020935686,0.0043253787,0.000032389467,0.000047602192,0.000146157,0.0016687091],"study_design_scores_gemma":[0.00048040884,0.00020844559,0.86889076,0.000014905266,0.00032873146,9.0518245e-7,0.00019180671,0.12896912,0.0000061649307,0.00068086147,0.00004330233,0.00018457393],"about_ca_topic_score_codex":0.003356615,"about_ca_topic_score_gemma":0.0012938011,"teacher_disagreement_score":0.20191091,"about_ca_system_score_codex":0.00013122158,"about_ca_system_score_gemma":0.00027223193,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W4402926402","doi":"10.1089/derm.2024.94685.cme","title":"Self-Assessment","year":2024,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.2823254602382604,"score_gpt":0.48112366561142916,"score_spread":0.19879820537316878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402926402","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0864867,0.0038529185,0.32848093,0.016300404,0.0064137178,0.00022669691,0.000023861143,0.0011844438,0.5570303],"genre_scores_gemma":[0.8505827,0.00008282699,0.14714542,0.0011499183,0.0001384281,0.000010151999,0.0000011891104,0.000007226629,0.0008820944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830633,0.00020235282,0.0003473699,0.00026817207,0.0007084841,0.0001672649],"domain_scores_gemma":[0.98751307,0.011993599,0.000046408164,0.00032011422,0.00006578775,0.000061048],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024786936,0.00007041934,0.00013827656,0.00035352295,0.000082408995,0.0006199645,0.00037956852,0.000035370784,0.0010326811],"category_scores_gemma":[0.0040933318,0.000047368612,0.00007483028,0.0016618384,0.000016998196,0.00023215481,0.000089028705,0.00011224131,0.0010045745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0108769e-7,0.000013656282,0.020993436,0.00002040258,0.000018855862,0.00009692058,0.00031588538,0.000008743033,0.000016256045,0.021497685,0.3753948,0.58162326],"study_design_scores_gemma":[0.000046371948,0.000014281469,0.18972655,0.000015714622,0.0000044359485,0.00006342084,0.0001368732,0.019531265,0.000040440253,0.061289288,0.7290559,0.000075473836],"about_ca_topic_score_codex":0.000009860561,"about_ca_topic_score_gemma":0.0000017119518,"teacher_disagreement_score":0.764096,"about_ca_system_score_codex":0.000038600323,"about_ca_system_score_gemma":0.00005871489,"threshold_uncertainty_score":0.9998805},"labels":[],"label_agreement":null},{"id":"W4403109221","doi":"10.1002/ijop.13252","title":"How to evaluate local fit (residuals) in large structural equation models","year":2024,"lang":"en","type":"article","venue":"International Journal of Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Concordia University","funders":"","keywords":"Structural equation modeling; Econometrics; Mathematics; Goodness of fit; Statistics; Latent variable; Variable (mathematics); Applied mathematics; Mathematical analysis","score_opus":0.5907930099858318,"score_gpt":0.5805461274116845,"score_spread":0.010246882574147298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403109221","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":[0.3440733,0.000818215,0.62431777,0.02158438,0.0074825403,0.00006408182,0.0000147409455,0.000012870111,0.0016321419],"genre_scores_gemma":[0.982591,0.00003623862,0.015369344,0.0010832463,0.00056474656,0.0000023855066,0.0000012167853,0.000009071085,0.00034280462],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99633133,0.0004942445,0.00094863813,0.00034164745,0.0016397161,0.00024442497],"domain_scores_gemma":[0.99322546,0.005285389,0.00033568742,0.00020281885,0.0008458056,0.00010482317],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008170773,0.000117141266,0.00028219706,0.0021383986,0.000026132106,0.0003891123,0.0012594049,0.000096065945,0.00040946936],"category_scores_gemma":[0.017036866,0.00008162283,0.00014468461,0.0011380442,0.000044459357,0.0006280351,0.00012288333,0.00035384015,0.000058405185],"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":[0.00042172254,0.00007860376,0.014637742,0.0000039669508,0.00016173955,0.0006663972,0.0013213478,0.03372615,0.0010726869,0.022598902,0.025828542,0.8994822],"study_design_scores_gemma":[0.0013125874,0.0003496394,0.08678341,0.00010733331,0.000013089244,0.0008506895,0.000702135,0.17354086,0.00010521044,0.7144737,0.021570798,0.00019052524],"about_ca_topic_score_codex":0.00000921834,"about_ca_topic_score_gemma":0.000019918594,"teacher_disagreement_score":0.8992917,"about_ca_system_score_codex":0.000108835746,"about_ca_system_score_gemma":0.00007846081,"threshold_uncertainty_score":0.99124306},"labels":[],"label_agreement":null},{"id":"W4403200622","doi":"10.1111/ijsa.12500","title":"Scoring the Big Five for longitudinally assessed academic achievement predictiveness: Manifest, correlated‐factors model, and bifactor modeling across multiple contexts","year":2024,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Clinical psychology; Applied psychology","score_opus":0.35921329028342386,"score_gpt":0.5094914948266814,"score_spread":0.15027820454325758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403200622","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":[0.5760826,0.0005094173,0.42097923,0.00066464726,0.0015860312,0.00011734447,0.000019583891,0.0000146883485,0.000026473655],"genre_scores_gemma":[0.9945205,0.00052075693,0.004407664,0.00006585627,0.000348988,0.000010957673,0.0000022906756,0.000011860831,0.00011112829],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975289,0.00013808373,0.0008027988,0.00031871835,0.0010152635,0.00019624054],"domain_scores_gemma":[0.99183196,0.0066847606,0.00043109158,0.00007520841,0.0008846444,0.00009234922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004107428,0.00015141301,0.00024798454,0.00038647585,0.00026049942,0.0006826442,0.00040687036,0.000085987325,0.000007540992],"category_scores_gemma":[0.0034865176,0.00009205238,0.00011622234,0.00036996312,0.000045142624,0.000543257,0.00012936984,0.0005444751,3.9279936e-7],"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":[0.00043386425,0.00015865393,0.4723064,0.000040948788,0.00097577507,0.000023587334,0.0023791913,0.26635784,0.007073182,0.0023784812,0.00041959682,0.24745247],"study_design_scores_gemma":[0.00063039834,0.00018937304,0.10964464,0.00017380185,0.00003579682,0.00010403322,0.0016122716,0.8803316,0.00014431699,0.006570734,0.00046393217,0.00009912249],"about_ca_topic_score_codex":0.000034156103,"about_ca_topic_score_gemma":0.000019801979,"teacher_disagreement_score":0.61397374,"about_ca_system_score_codex":0.00016950724,"about_ca_system_score_gemma":0.00018861503,"threshold_uncertainty_score":0.65827537},"labels":[],"label_agreement":null},{"id":"W4404375616","doi":"10.1108/978-1-83797-799-420241008","title":"Concept Evaluation and the MVP","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Environmental science","score_opus":0.6702884371702098,"score_gpt":0.5268839555567533,"score_spread":0.14340448161345654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404375616","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016665625,0.01249519,0.0020123755,0.0019885427,0.0013388024,0.00031864722,0.0000064839514,0.00004350128,0.9817798],"genre_scores_gemma":[0.0030370022,0.00018181956,0.0018820231,0.0003810835,0.00025608094,0.000007269003,0.0000018591708,0.000012377989,0.99424046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970874,0.00017236867,0.00050168234,0.0004999504,0.0016305217,0.0001080721],"domain_scores_gemma":[0.9552056,0.043703232,0.00022197282,0.0005187648,0.0003104473,0.000039966493],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017221129,0.00015068515,0.0003437278,0.00029359089,0.000095145566,0.00038850043,0.00044647814,0.00014824078,0.007053929],"category_scores_gemma":[0.043035425,0.000063303305,0.00012744551,0.0001866356,0.0003476097,0.00004905409,0.000246109,0.00026579612,0.0005372135],"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":[0.00000506886,3.5335364e-7,0.0000047869644,0.0000011135227,0.000015787253,9.962657e-7,0.00007910497,0.0000027843273,1.8181923e-7,0.608922,0.025671551,0.36529627],"study_design_scores_gemma":[0.00018990117,0.000011207532,0.000046192486,0.00001705676,0.000042770687,0.000007975893,0.00008982268,0.0022769992,6.958687e-7,0.68869275,0.30855888,0.00006578461],"about_ca_topic_score_codex":0.000012625933,"about_ca_topic_score_gemma":0.0000047144104,"teacher_disagreement_score":0.3652305,"about_ca_system_score_codex":0.000018266086,"about_ca_system_score_gemma":0.000046613455,"threshold_uncertainty_score":0.99385375},"labels":[],"label_agreement":null},{"id":"W4404744480","doi":"10.1089/derm.2024.98654.cme","title":"Self-Assessment","year":2024,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.2823254602382604,"score_gpt":0.48112366561142916,"score_spread":0.19879820537316878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404744480","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0864867,0.0038529185,0.32848093,0.016300404,0.0064137178,0.00022669691,0.000023861143,0.0011844438,0.5570303],"genre_scores_gemma":[0.8505827,0.00008282699,0.14714542,0.0011499183,0.0001384281,0.000010151999,0.0000011891104,0.000007226629,0.0008820944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830633,0.00020235282,0.0003473699,0.00026817207,0.0007084841,0.0001672649],"domain_scores_gemma":[0.98751307,0.011993599,0.000046408164,0.00032011422,0.00006578775,0.000061048],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024786936,0.00007041934,0.00013827656,0.00035352295,0.000082408995,0.0006199645,0.00037956852,0.000035370784,0.0010326811],"category_scores_gemma":[0.0040933318,0.000047368612,0.00007483028,0.0016618384,0.000016998196,0.00023215481,0.000089028705,0.00011224131,0.0010045745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0108769e-7,0.000013656282,0.020993436,0.00002040258,0.000018855862,0.00009692058,0.00031588538,0.000008743033,0.000016256045,0.021497685,0.3753948,0.58162326],"study_design_scores_gemma":[0.000046371948,0.000014281469,0.18972655,0.000015714622,0.0000044359485,0.00006342084,0.0001368732,0.019531265,0.000040440253,0.061289288,0.7290559,0.000075473836],"about_ca_topic_score_codex":0.000009860561,"about_ca_topic_score_gemma":0.0000017119518,"teacher_disagreement_score":0.764096,"about_ca_system_score_codex":0.000038600323,"about_ca_system_score_gemma":0.00005871489,"threshold_uncertainty_score":0.9998805},"labels":[],"label_agreement":null},{"id":"W4405271707","doi":"10.1109/bsn63547.2024.10780670","title":"Influential Factors in rPPG: Insights from a Diverse and Inclusive Empirical Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; National Research Council Canada","funders":"","keywords":"Computer science; Empirical research; Data science; Artificial intelligence; Epistemology","score_opus":0.4758258126945327,"score_gpt":0.5341714659539336,"score_spread":0.05834565325940089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405271707","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":[0.9930551,0.0003498292,0.0011625104,0.00013988344,0.0010184165,0.00018405856,0.000006430008,0.00007301216,0.004010751],"genre_scores_gemma":[0.9983402,0.0000060989714,0.0012284126,0.0000988928,0.000065960274,0.0000035996143,8.5036754e-7,0.000005097009,0.00025092255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974388,0.00050344766,0.0004746793,0.00062957656,0.00078617426,0.00016734157],"domain_scores_gemma":[0.9747362,0.024782406,0.00005255365,0.00027532646,0.00005541618,0.000098095894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013342631,0.00012849741,0.0002840506,0.0008553345,0.00010091877,0.00040892616,0.0003745108,0.000070668044,0.0004890449],"category_scores_gemma":[0.022167997,0.0000729416,0.0000502271,0.002454611,0.000063580315,0.0003090213,0.0007714878,0.00020319913,0.000064382315],"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":[0.000009738667,0.00007204889,0.966101,8.8131003e-7,0.000017737224,0.00009269668,0.0075633503,0.000007999556,0.00006383535,0.00010859003,0.0010012854,0.024960816],"study_design_scores_gemma":[0.0003341472,0.00011058078,0.9401393,0.000008922155,0.000008752127,0.0000013754284,0.026030848,0.0011647256,0.000035072128,0.02933013,0.0027253823,0.000110757865],"about_ca_topic_score_codex":0.0013553755,"about_ca_topic_score_gemma":0.0005392362,"teacher_disagreement_score":0.02922154,"about_ca_system_score_codex":0.000033173663,"about_ca_system_score_gemma":0.000044030436,"threshold_uncertainty_score":0.9860687},"labels":[],"label_agreement":null},{"id":"W4405622011","doi":"10.1177/01466216241310600","title":"An Information Manifold Perspective for Analyzing Test Data","year":2024,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Item response theory; Mathematics; Measure (data warehouse); Metric (unit); Computer science; Test (biology); Manifold (fluid mechanics); Perspective (graphical); Scale (ratio); Artificial intelligence; Data mining; Statistics; Psychometrics","score_opus":0.7563916288387372,"score_gpt":0.5558183455944733,"score_spread":0.20057328324426393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405622011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009968944,0.0010179516,0.91314125,0.002160958,0.0017157239,0.0012667975,0.00016466418,0.00054900977,0.07001472],"genre_scores_gemma":[0.9578236,0.00001782837,0.041151702,0.0005583303,0.00028818127,0.00010134753,0.00002729786,0.000010299975,0.000021453996],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959873,0.00011208923,0.0007973635,0.001057425,0.0016507447,0.00039506017],"domain_scores_gemma":[0.98934716,0.008083365,0.00019275032,0.0016512835,0.00055532856,0.0001701278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017932411,0.00020749216,0.0003120292,0.00047198657,0.00021045325,0.00090785476,0.0019126268,0.00013274903,0.00024461717],"category_scores_gemma":[0.035417154,0.00013275571,0.00009340419,0.0018448551,0.000054285203,0.00070074433,0.00017084806,0.00024462774,0.0002875839],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013484221,0.00037387345,0.0022883017,0.000022293128,0.00007631572,0.0000049162927,0.00052523066,0.000071512455,0.0052818693,0.13202271,0.048787616,0.8104105],"study_design_scores_gemma":[0.0016819321,0.0016426276,0.12361095,0.00008674321,0.00014393627,0.00003515967,0.009089461,0.01582799,0.0005510147,0.63980675,0.20643166,0.0010917754],"about_ca_topic_score_codex":0.0000100995985,"about_ca_topic_score_gemma":0.0000040662458,"teacher_disagreement_score":0.94785464,"about_ca_system_score_codex":0.00013876829,"about_ca_system_score_gemma":0.000033774188,"threshold_uncertainty_score":0.9727079},"labels":[],"label_agreement":null},{"id":"W4405636900","doi":"10.1016/j.nsa.2024.104535","title":"A framework for rating scale development: example from the depression inventory development project","year":2024,"lang":"en","type":"article","venue":"Neuroscience Applied","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Indoc Research","funders":"","keywords":"Rating scale; Scale (ratio); Depression (economics); Development (topology); Concept inventory; Psychology; Computer science; Operations research; Engineering; Economics; Geography; Mathematics; Cartography; Developmental psychology","score_opus":0.5878259806641543,"score_gpt":0.4778536494283459,"score_spread":0.10997233123580835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405636900","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":[0.40265468,0.00034039075,0.5925348,0.00015376165,0.0018360944,0.00074600475,0.0000040760156,0.00019596302,0.0015342584],"genre_scores_gemma":[0.65742546,0.000007171214,0.34066764,0.001039043,0.00020257449,0.0003596109,0.0000029906985,0.000019814772,0.00027567707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960484,0.00015388432,0.00071049144,0.0012075076,0.0013840458,0.0004956902],"domain_scores_gemma":[0.97338676,0.025578601,0.00022325951,0.00063516555,0.00007818851,0.0000980066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063713645,0.00020065215,0.00024578624,0.00026370637,0.0010462076,0.0010242703,0.001594477,0.00009096697,0.000033605],"category_scores_gemma":[0.016949441,0.00011330827,0.000068013855,0.002997866,0.00016568076,0.00020582022,0.00045949727,0.0002966071,0.0000431086],"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":[0.000041778134,0.00004754583,0.011505515,0.000020489828,0.0000056351837,0.000004378513,0.009128431,0.000078795434,0.021630894,0.003439461,0.0063027055,0.9477944],"study_design_scores_gemma":[0.0005071641,0.000050614366,0.08545664,0.000292165,0.000015580694,0.000009888321,0.0036302395,0.01356349,0.043998446,0.090770565,0.7610266,0.0006785916],"about_ca_topic_score_codex":0.00003328411,"about_ca_topic_score_gemma":0.000015525786,"teacher_disagreement_score":0.9471158,"about_ca_system_score_codex":0.000050200084,"about_ca_system_score_gemma":0.00046727128,"threshold_uncertainty_score":0.9913312},"labels":[],"label_agreement":null},{"id":"W4406051520","doi":"10.1027/1015-5759/a000877","title":"Cracks, Gaps, and Holes in Validation Practice as Evidenced From a Validation Synthesis of the English Version of the Rosenberg Self-Esteem Scale","year":2024,"lang":"en","type":"article","venue":"European Journal of Psychological Assessment","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 British Columbia","funders":"","keywords":"Psychology; Scale (ratio); Self-esteem; Psychometrics; Test validity; Social psychology; Clinical psychology; Cartography","score_opus":0.1700920110475426,"score_gpt":0.4586256186510765,"score_spread":0.28853360760353386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406051520","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":[0.9861865,0.0006748676,0.0018027634,0.002554861,0.0014620306,0.00014619662,0.000008672524,0.000012748232,0.0071513825],"genre_scores_gemma":[0.97925484,0.00034942816,0.020110412,0.00010052347,0.00013087472,0.0000010613295,2.7602738e-7,0.000008190003,0.000044374436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902671,0.00664806,0.0012408145,0.00033815225,0.0013686664,0.00013722398],"domain_scores_gemma":[0.9739674,0.023659306,0.001373967,0.00044495342,0.00049254484,0.00006186649],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017332643,0.0001285091,0.00032631878,0.00023334836,0.000085273045,0.00021052384,0.0009535319,0.00005044482,0.00011030151],"category_scores_gemma":[0.057199895,0.000059580987,0.00018829983,0.0015100546,0.00015164577,0.00046143643,0.00026396988,0.000449224,0.0000064157525],"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":[0.0005465083,0.002306497,0.4898992,0.00010131551,0.00026866634,0.00019843008,0.0054305885,0.0017711644,0.047524024,0.0013290412,0.008242403,0.4423822],"study_design_scores_gemma":[0.00041454553,0.00044955546,0.980904,0.00072353234,0.000097495045,0.000056715908,0.00237842,0.00016542536,0.004588816,0.0043383776,0.0057832836,0.00009984612],"about_ca_topic_score_codex":0.000009362614,"about_ca_topic_score_gemma":4.2031206e-7,"teacher_disagreement_score":0.4910048,"about_ca_system_score_codex":0.000046201756,"about_ca_system_score_gemma":0.00005382036,"threshold_uncertainty_score":0.9507417},"labels":[],"label_agreement":null},{"id":"W4406530729","doi":"10.1075/ml.24023.lan","title":"A psycholinguistic analysis of clinical list-learning tests","year":2024,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Brock University","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Psychology","score_opus":0.634623376166255,"score_gpt":0.6216009030149111,"score_spread":0.01302247315134386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530729","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":[0.9517572,0.0014692921,0.0030427608,0.00066235935,0.002762023,0.00015145184,0.00001594903,0.00009730426,0.040041666],"genre_scores_gemma":[0.9950932,0.000044273333,0.0022823724,0.00012478212,0.00020681863,0.0000053612266,0.0000035783971,0.0000074891755,0.0022321255],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965618,0.0009078322,0.0010616165,0.00043739536,0.0008417887,0.00018953279],"domain_scores_gemma":[0.95848244,0.040553402,0.00029086793,0.0005141069,0.000090248854,0.00006893599],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015693069,0.00010374873,0.00047109474,0.000618878,0.00012071212,0.00018853343,0.00071020983,0.0000584694,0.0008685812],"category_scores_gemma":[0.07780542,0.000055000404,0.00044462955,0.0056472286,0.00018325007,0.000055562978,0.00015784465,0.00033143596,0.00011004237],"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":[0.00007845344,0.00010817499,0.3499678,0.000012439543,0.00085337396,0.000020777454,0.001314087,0.0005345921,0.0007129977,0.0057540783,0.0056315293,0.6350117],"study_design_scores_gemma":[0.00040939235,0.00043880424,0.648804,0.00010882173,0.0009287308,0.000018070905,0.0019988331,0.18232538,0.00017506602,0.045646645,0.11885552,0.000290737],"about_ca_topic_score_codex":0.00006938615,"about_ca_topic_score_gemma":0.000011899963,"teacher_disagreement_score":0.6347209,"about_ca_system_score_codex":0.00001630418,"about_ca_system_score_gemma":0.000035109853,"threshold_uncertainty_score":0.95103544},"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":"W4406779237","doi":"10.1177/00131644241308528","title":"A Comparison of the Next Eigenvalue Sufficiency Test to Other Stopping Rules for the Number of Factors in Factor Analysis","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"Université TÉLUQ","funders":"","keywords":"Curse of dimensionality; Exploratory factor analysis; Statistics; Mathematics; Test (biology); Eigenvalues and eigenvectors; Sample (material); Computer science; Identification (biology); Hull; Factor (programming language); Algorithm; Psychometrics; Engineering","score_opus":0.7892882399583666,"score_gpt":0.5763748813874294,"score_spread":0.21291335857093718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406779237","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":[0.98106676,0.00048721407,0.011769974,0.0040275,0.00049336936,0.00034590758,0.000026399499,0.000003040176,0.0017798134],"genre_scores_gemma":[0.99672085,0.000004135899,0.002855303,0.00022195924,0.000023633147,0.000034547687,4.3928267e-7,0.0000016707749,0.00013748967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978908,0.00024994955,0.0006447368,0.00031174166,0.00075848075,0.00014433819],"domain_scores_gemma":[0.9801772,0.018841805,0.00025476416,0.0003372872,0.00035233548,0.000036600948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034076837,0.0000938237,0.00031134248,0.0002438046,0.00013278014,0.000041190553,0.0005979179,0.00004614795,0.00034241067],"category_scores_gemma":[0.041079074,0.000040634226,0.00015274648,0.0026956133,0.00011173182,0.000027219354,0.000060527218,0.00008909927,0.0000019000447],"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":[0.000015870377,0.00046240963,0.98393613,0.0000042783604,0.00004103419,4.284838e-9,0.0005440089,0.00015701875,0.00063241704,0.002754586,0.00053681177,0.010915437],"study_design_scores_gemma":[0.000109033106,0.000045431145,0.9860746,0.000020825766,0.00003156988,1.03727224e-7,0.001541307,0.00018134816,0.00015823527,0.010484605,0.001305158,0.000047728998],"about_ca_topic_score_codex":0.00008247871,"about_ca_topic_score_gemma":0.000035138597,"teacher_disagreement_score":0.03767139,"about_ca_system_score_codex":0.000030799503,"about_ca_system_score_gemma":0.00005177184,"threshold_uncertainty_score":0.96699834},"labels":[],"label_agreement":null},{"id":"W4406822813","doi":"10.1089/derm.2025.87966.cme","title":"Self-Assessment","year":2025,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.22205417422236798,"score_gpt":0.4786558655265343,"score_spread":0.2566016913041663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406822813","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054928593,0.00037497768,0.24564531,0.010171555,0.0017568453,0.0001402873,0.000005091755,0.00020711278,0.6867702],"genre_scores_gemma":[0.78987926,0.000042558244,0.20339336,0.004703398,0.000035142053,0.0000123449845,8.332429e-7,0.000002874379,0.0019302152],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99848115,0.00025655338,0.00038712908,0.00022283135,0.0004927289,0.00015963113],"domain_scores_gemma":[0.98861694,0.010685142,0.00010292162,0.00042775235,0.000128083,0.000039144586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021445972,0.00006544524,0.00016998168,0.00040214846,0.00013263663,0.00021020592,0.0005103548,0.000038138936,0.00038525017],"category_scores_gemma":[0.009288278,0.000047528894,0.000059532584,0.0019390482,0.000019534255,0.00012439844,0.00013475258,0.000086284264,0.00016102442],"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":[2.617714e-7,0.00002996178,0.25653198,0.000008850705,0.000017445722,0.000009975419,0.00009401697,0.000010747215,0.000011472094,0.029302252,0.35089904,0.36308396],"study_design_scores_gemma":[0.00011535381,0.000006230752,0.5768729,0.0000069441244,0.0000032054436,0.000004463609,0.00013269522,0.0023482402,0.000058384678,0.06759477,0.3528131,0.000043760843],"about_ca_topic_score_codex":0.000014260926,"about_ca_topic_score_gemma":0.0000033980655,"teacher_disagreement_score":0.73495066,"about_ca_system_score_codex":0.00003877896,"about_ca_system_score_gemma":0.00006956201,"threshold_uncertainty_score":0.99905694},"labels":[],"label_agreement":null},{"id":"W4407088834","doi":"10.3390/encyclopedia5010018","title":"Likert-Type Scale","year":2025,"lang":"en","type":"article","venue":"Encyclopedia","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Likert scale; Scale (ratio); Psychology; Statistics; Mathematics; Geography; Cartography","score_opus":0.22985816241553517,"score_gpt":0.47570409764759325,"score_spread":0.24584593523205808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407088834","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23778364,0.0007696565,0.0090781115,0.0009058364,0.003915146,0.000083795356,0.0000015315343,0.000091447495,0.74737084],"genre_scores_gemma":[0.6588865,0.0005381154,0.07910638,0.0021544516,0.0005590427,0.000015345655,0.0000026772157,0.000016663744,0.25872084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981531,0.00022297021,0.00043288415,0.00040749967,0.00053373666,0.00024983822],"domain_scores_gemma":[0.985777,0.01320734,0.00010290873,0.00063788984,0.00020304804,0.00007180456],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031243477,0.00009810734,0.00022247082,0.00046019093,0.00013549394,0.0001167524,0.0007836204,0.00007335152,0.00087780633],"category_scores_gemma":[0.076435745,0.00006839506,0.000071019276,0.0040823063,0.00005665383,0.00012233519,0.00020357514,0.0001455201,0.00064859475],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010676816,0.000022199298,0.3467158,0.0000019896008,0.0000054959332,0.000003687684,0.00010214275,0.000009652884,0.000074706586,0.0010830568,0.19281872,0.45915186],"study_design_scores_gemma":[0.00012493653,0.000022618116,0.3266636,0.000008742785,0.0000047877534,0.000001632485,0.00021683447,0.00012323243,0.00007285547,0.058825392,0.6138514,0.00008393513],"about_ca_topic_score_codex":0.000024163242,"about_ca_topic_score_gemma":0.000009997626,"teacher_disagreement_score":0.48865,"about_ca_system_score_codex":0.000017070626,"about_ca_system_score_gemma":0.000080265825,"threshold_uncertainty_score":0.9611364},"labels":[],"label_agreement":null},{"id":"W4407098810","doi":"10.1080/15434303.2025.2455196","title":"Differential Item Functioning Due to Cultural Familiarity on a Large-Scale Reading Test: Does the Length of Residence Matter?","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","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 Toronto","funders":"","keywords":"Differential item functioning; Psychology; Reading (process); Scale (ratio); Test (biology); Residence; Item response theory; Psychometrics; Developmental psychology; Linguistics; Geography; Sociology; Demography","score_opus":0.07156230965493464,"score_gpt":0.4314743672554329,"score_spread":0.35991205760049827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407098810","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":[0.9002083,0.0000388525,0.08772122,0.00143408,0.0008612484,0.00027546682,0.000029869521,0.000059552323,0.009371401],"genre_scores_gemma":[0.9884573,0.0000016838775,0.007358666,0.00057042844,0.00011802593,0.000033598317,0.0000037220857,0.000007793355,0.003448737],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967728,0.00060523255,0.0007084486,0.00059009343,0.0009425812,0.00038080904],"domain_scores_gemma":[0.9796287,0.01891887,0.00030373118,0.0008863478,0.00019035429,0.00007202741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026358694,0.00019760913,0.00041614965,0.00038167898,0.00034887152,0.0004043621,0.00089542015,0.000076025804,0.0004235713],"category_scores_gemma":[0.006917705,0.00009908403,0.00014641254,0.0017856214,0.000058051897,0.00022424984,0.00012690744,0.00031463918,0.000043804983],"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":[0.00009287456,0.00029886523,0.71061397,0.00004427918,0.00006531377,0.000036284157,0.01502431,0.000031768654,0.024955917,0.0020645247,0.011521459,0.23525043],"study_design_scores_gemma":[0.0003476424,0.00044014264,0.934936,0.00016739138,0.000026726811,0.0000055333385,0.05745522,0.002297265,0.0011440403,0.002765784,0.0002525607,0.00016169458],"about_ca_topic_score_codex":0.0003421109,"about_ca_topic_score_gemma":0.0001998626,"teacher_disagreement_score":0.23508874,"about_ca_system_score_codex":0.000062662126,"about_ca_system_score_gemma":0.00003928794,"threshold_uncertainty_score":0.82816386},"labels":[],"label_agreement":null},{"id":"W4407172876","doi":"10.1016/j.inpsyc.2025.100042","title":"Harmonized Cognitive Assessment Protocol in the English Longitudinal Study of Ageing: Contrasting approaches to evaluation of factor structure","year":2025,"lang":"en","type":"article","venue":"International Psychogeriatrics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"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":"Health Data Research UK; National Institute on Aging; National Institutes of Health; Alzheimer’s Research UK; Economic and Social Research Council; National Institute for Health and Care Research; Alzheimer Society","keywords":"Cognition; Ageing; Protocol (science); Computer science; Psychology; Medicine; Neuroscience; Pathology; Internal medicine","score_opus":0.7072509071900492,"score_gpt":0.5574466177307364,"score_spread":0.1498042894593128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407172876","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":[0.9536166,0.0000117901145,0.01576151,0.00020991842,0.0010573436,0.022857139,0.00005681708,0.00001033232,0.0064185276],"genre_scores_gemma":[0.991665,2.968634e-7,0.003691105,0.000039356575,0.00010472352,0.0044728783,0.0000035013484,0.0000049408495,0.00001818221],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939391,0.0013514571,0.0012142045,0.0005160408,0.0028180964,0.0001610991],"domain_scores_gemma":[0.9831342,0.013718962,0.00077474705,0.00032324262,0.0020198743,0.000028935516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010739164,0.00014553021,0.00034639862,0.0011501573,0.000059987968,0.00014794919,0.0010947139,0.00006477829,0.00014174366],"category_scores_gemma":[0.07715197,0.000095028874,0.00008116799,0.0033493477,0.000036614445,0.00014976601,0.00013422895,0.00022617287,5.57342e-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":[0.0003188988,0.0008092716,0.8857494,0.000014142251,0.00011517398,0.000002208181,0.0034685284,0.0012478007,0.00026024037,0.0008206626,0.00020874331,0.10698493],"study_design_scores_gemma":[0.0032803118,0.00020819478,0.9749874,0.000045635214,0.000038275626,7.1354657e-7,0.009207649,0.004207045,0.000095888085,0.0077421754,0.000102114645,0.00008461556],"about_ca_topic_score_codex":0.00004815971,"about_ca_topic_score_gemma":0.00004187011,"teacher_disagreement_score":0.10690031,"about_ca_system_score_codex":0.000082980754,"about_ca_system_score_gemma":0.00014914667,"threshold_uncertainty_score":0.93062156},"labels":[],"label_agreement":null},{"id":"W4407928271","doi":"10.1177/00131644251319047","title":"Shortening Psychological Scales: Semantic Similarity Matters","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Similarity (geometry); Sentence; Semantic similarity; Scale (ratio); Computer science; Natural language processing; Sample (material); Artificial intelligence; Embedding; Correlation; Information retrieval; Mathematics","score_opus":0.6635170864862416,"score_gpt":0.5275220275597801,"score_spread":0.13599505892646158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407928271","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":[0.759869,0.0025673837,0.06129149,0.11446027,0.005202896,0.00059770915,0.000010885766,0.0001384848,0.05586191],"genre_scores_gemma":[0.97600085,0.000051089955,0.015218386,0.007644137,0.00017794794,0.000056597855,0.0000026868083,0.000005075284,0.00084322976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99565524,0.00065781776,0.0008245712,0.0010659363,0.0013931545,0.00040326157],"domain_scores_gemma":[0.9921536,0.006434592,0.00018756608,0.00056176644,0.0004642158,0.0001983021],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00783861,0.00023309265,0.00039648573,0.0004035595,0.00037368556,0.00025648423,0.00073129724,0.00016762014,0.0010992244],"category_scores_gemma":[0.021034056,0.00014825634,0.00014160456,0.0015640837,0.00027925638,0.00010343034,0.00013450641,0.00035483117,0.00009916684],"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":[0.00015834553,0.001835996,0.42708433,0.000027072721,0.00007493682,0.0000065455715,0.00012342165,0.000025490906,0.0012898165,0.021281336,0.24013582,0.30795687],"study_design_scores_gemma":[0.00030649104,0.00012462701,0.787795,0.000045357123,0.000012111469,0.000021479738,0.0002035467,0.00006445942,0.0000124420485,0.20212162,0.009130483,0.00016240907],"about_ca_topic_score_codex":0.000008676394,"about_ca_topic_score_gemma":0.0000033818892,"teacher_disagreement_score":0.36071065,"about_ca_system_score_codex":0.00006525017,"about_ca_system_score_gemma":0.000030093039,"threshold_uncertainty_score":0.9998139},"labels":[],"label_agreement":null},{"id":"W4408586195","doi":"10.58837/chula.the.2014.438","title":"ผลของโปรแกรมกระตนการรคดตอความจำของผสงอายในชมชนทมการรคดบกพรอง","year":2014,"lang":"th","type":"dissertation","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Computer science","score_opus":0.5401836105947119,"score_gpt":0.5351116556626767,"score_spread":0.005071954932035161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408586195","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053315017,0.0022842172,0.02862702,0.0006112772,0.019666396,0.0008863243,0.000039608007,0.0005043118,0.89406586],"genre_scores_gemma":[0.49795434,0.0006361883,0.054003865,0.0017365625,0.0021612614,0.00008985353,0.00036115423,0.00023061632,0.44282618],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98394024,0.002513354,0.0037750665,0.0032486115,0.0047415667,0.0017811407],"domain_scores_gemma":[0.9156735,0.07575467,0.0028088922,0.0032826802,0.0016516891,0.00082858873],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.018483749,0.0014352775,0.0026760262,0.0029486502,0.0010311843,0.0016313391,0.004996277,0.0015830358,0.03544763],"category_scores_gemma":[0.20892806,0.0010771431,0.0011996655,0.006937141,0.00028251813,0.00043458203,0.00048598385,0.0016227687,0.015240511],"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":[0.0002822951,0.00024216062,0.011737962,0.00018539983,0.00022608349,0.000044155553,0.0008499649,0.00014012468,0.00031113342,0.01333409,0.09826769,0.8743789],"study_design_scores_gemma":[0.0026607672,0.0014180527,0.14640336,0.00078784215,0.0005155754,0.000100256846,0.013080416,0.018832888,0.00165766,0.08465892,0.72533774,0.004546522],"about_ca_topic_score_codex":0.0007617821,"about_ca_topic_score_gemma":0.00019543892,"teacher_disagreement_score":0.8698324,"about_ca_system_score_codex":0.00014865087,"about_ca_system_score_gemma":0.0005073246,"threshold_uncertainty_score":0.9998397},"labels":[],"label_agreement":null},{"id":"W4409011465","doi":"10.1089/derm.2025.87451.cme","title":"Self-Assessment","year":2025,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Traditional medicine","score_opus":0.22205417422236798,"score_gpt":0.4786558655265343,"score_spread":0.2566016913041663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409011465","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054928593,0.00037497768,0.24564531,0.010171555,0.0017568453,0.0001402873,0.000005091755,0.00020711278,0.6867702],"genre_scores_gemma":[0.78987926,0.000042558244,0.20339336,0.004703398,0.000035142053,0.0000123449845,8.332429e-7,0.000002874379,0.0019302152],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99848115,0.00025655338,0.00038712908,0.00022283135,0.0004927289,0.00015963113],"domain_scores_gemma":[0.98861694,0.010685142,0.00010292162,0.00042775235,0.000128083,0.000039144586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021445972,0.00006544524,0.00016998168,0.00040214846,0.00013263663,0.00021020592,0.0005103548,0.000038138936,0.00038525017],"category_scores_gemma":[0.009288278,0.000047528894,0.000059532584,0.0019390482,0.000019534255,0.00012439844,0.00013475258,0.000086284264,0.00016102442],"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":[2.617714e-7,0.00002996178,0.25653198,0.000008850705,0.000017445722,0.000009975419,0.00009401697,0.000010747215,0.000011472094,0.029302252,0.35089904,0.36308396],"study_design_scores_gemma":[0.00011535381,0.000006230752,0.5768729,0.0000069441244,0.0000032054436,0.000004463609,0.00013269522,0.0023482402,0.000058384678,0.06759477,0.3528131,0.000043760843],"about_ca_topic_score_codex":0.000014260926,"about_ca_topic_score_gemma":0.0000033980655,"teacher_disagreement_score":0.73495066,"about_ca_system_score_codex":0.00003877896,"about_ca_system_score_gemma":0.00006956201,"threshold_uncertainty_score":0.99905694},"labels":[],"label_agreement":null},{"id":"W4409073897","doi":"10.1093/jbcr/iraf019.027","title":"27 The MacHAND Performance Assessment: Psychometric Testing of the Short English (MPA-S) and French-Canadian (MPA-SF) Forms","year":2025,"lang":"en","type":"article","venue":"Journal of Burn Care & Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; McGill University","funders":"","keywords":"Medicine; Psychometric testing; Psychometrics; Gerontology; Clinical psychology; Internal consistency","score_opus":0.4494653947264664,"score_gpt":0.5162622685314993,"score_spread":0.06679687380503285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409073897","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":[0.9382568,0.0052040187,0.00033017265,0.0010002389,0.00128276,0.00027298395,0.000011214774,0.000005259247,0.05363654],"genre_scores_gemma":[0.99690574,0.00035552416,0.0019174786,0.00008216016,0.00022066342,0.0000041615385,2.0756941e-7,0.000008997621,0.0005050836],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939534,0.0009784827,0.0010743799,0.00031865394,0.0030426055,0.0006324735],"domain_scores_gemma":[0.965269,0.028165277,0.00046823084,0.0007845093,0.005052855,0.00026008845],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027037714,0.00015452645,0.0004500537,0.003362219,0.00085547083,0.0005185779,0.002413604,0.00012054414,0.000074635645],"category_scores_gemma":[0.11250162,0.00007195466,0.00018042131,0.01443064,0.00040308601,0.00035756908,0.00045140716,0.0015019779,0.0000014954263],"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":[0.000009872383,0.000014462529,0.62899387,0.00002609123,0.000024786079,0.000004339799,0.00071436557,0.000055019376,0.00006407496,0.00007059397,0.0026495212,0.36737302],"study_design_scores_gemma":[0.0003682366,0.00037877,0.9650656,0.00026933584,0.000020156136,0.000046956135,0.012023455,0.000987964,0.0002036758,0.003643014,0.016901331,0.00009149185],"about_ca_topic_score_codex":0.001384515,"about_ca_topic_score_gemma":0.0010489041,"teacher_disagreement_score":0.36728153,"about_ca_system_score_codex":0.00024295133,"about_ca_system_score_gemma":0.0011177566,"threshold_uncertainty_score":0.9370786},"labels":[],"label_agreement":null},{"id":"W4409155725","doi":"10.2196/65726","title":"Using a Hybrid of AI and Template-Based Method in Automatic Item Generation to Create Multiple-Choice Questions in Medical Education: Hybrid AIG","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Summative assessment; Formative assessment; Field (mathematics); Artificial intelligence; Template; Subject-matter expert; Machine learning; Expert system; Programming language; Psychology","score_opus":0.5171630694068262,"score_gpt":0.6303167085209163,"score_spread":0.11315363911409004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409155725","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":[0.85105145,0.0001516196,0.14471236,0.0024202345,0.00023191082,0.0006771929,0.000011542681,0.000018220133,0.00072546984],"genre_scores_gemma":[0.9496148,0.0000076294045,0.049781792,0.00029100414,0.000048701007,0.00017688233,0.0000052711193,0.000006244642,0.000067629975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928897,0.0035519535,0.0011053083,0.00043190795,0.001618701,0.00040241258],"domain_scores_gemma":[0.9240765,0.07411651,0.00019278425,0.00047569987,0.00093071075,0.00020777826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021631423,0.00013142836,0.0004226134,0.004245714,0.00020301843,0.00017549483,0.0005337601,0.00007575114,0.00010469302],"category_scores_gemma":[0.25857857,0.000103872364,0.000047668902,0.0062017804,0.0001509474,0.00042692933,0.0002792791,0.00057007023,0.000007422577],"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":[0.00009090679,0.0006419345,0.4048661,0.00021336466,0.000018812509,0.000013825862,0.0023123936,0.0020941072,0.0015468036,0.0012641832,0.009915644,0.5770219],"study_design_scores_gemma":[0.0006548719,0.000096036536,0.22053832,0.0004994066,0.000002000394,0.000009969572,0.00073849503,0.76986307,0.0017785565,0.005042576,0.0006808665,0.00009584054],"about_ca_topic_score_codex":0.0012053037,"about_ca_topic_score_gemma":0.00029503767,"teacher_disagreement_score":0.767769,"about_ca_system_score_codex":0.00023988239,"about_ca_system_score_gemma":0.0013668123,"threshold_uncertainty_score":0.7497063},"labels":[],"label_agreement":null},{"id":"W4409665275","doi":"10.3758/s13428-025-02658-7","title":"Assessing multiple abilities through process data in computer-based assessments: The multidimensional sequential response model (MSRM)","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"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 Toronto","funders":"Beijing Municipal Social Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Data mining; Machine learning; Artificial intelligence; Programming language","score_opus":0.920767338243147,"score_gpt":0.759212213405075,"score_spread":0.161555124838072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409665275","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":[0.4453298,0.0001525013,0.5523787,0.000743724,0.00043063945,0.0006700474,0.000041920175,0.000048709255,0.00020396286],"genre_scores_gemma":[0.35935256,0.000004349949,0.6399703,0.0001332543,0.0000439366,0.00020272905,0.000014619057,0.000016721346,0.00026149934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9544425,0.036956534,0.0015639786,0.0018926047,0.004008024,0.001136342],"domain_scores_gemma":[0.7379035,0.2559777,0.00033323275,0.0040260674,0.0016080029,0.00015152304],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17743869,0.00029508723,0.0006301436,0.0015263046,0.001034844,0.0012393835,0.0044509345,0.00021637703,0.00009794051],"category_scores_gemma":[0.24627991,0.00018954882,0.00013858726,0.006938378,0.0009016287,0.001382144,0.002594382,0.0014432744,0.000008045399],"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":[0.0013396555,0.001418917,0.20468552,0.000065638975,0.000034123044,0.00006830843,0.0011326793,0.026800703,0.017795844,0.0006226175,0.0017144243,0.7443216],"study_design_scores_gemma":[0.0012384125,0.00010255926,0.13630463,0.00012785714,0.000016346215,0.000005124619,0.004390987,0.8380329,0.0025239123,0.015884694,0.001146303,0.00022629106],"about_ca_topic_score_codex":0.0006638377,"about_ca_topic_score_gemma":0.00006259336,"teacher_disagreement_score":0.8112322,"about_ca_system_score_codex":0.0002828278,"about_ca_system_score_gemma":0.0021878425,"threshold_uncertainty_score":0.9997974},"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":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4410436460","doi":"10.1007/s40520-025-03026-3","title":"Convergence and equating norms between the Telephone Interview for Cognitive Status (TICS), the MMSE and the MoCA in an Italian population sample","year":2025,"lang":"en","type":"article","venue":"Aging Clinical and Experimental Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Ministero della Salute","keywords":"Equating; Tics; Sample (material); Telephone interview; Convergence (economics); Population; Psychology; Cognitive impairment; Cognition; Demography; Telephone survey; Gerontology; Medicine; Psychiatry; Sociology; Developmental psychology; Economics; Advertising","score_opus":0.8000424341366335,"score_gpt":0.6806966223514711,"score_spread":0.11934581178516235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410436460","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":[0.9895366,0.0031347563,0.0026539443,0.0037535634,0.00014124479,0.0006014679,0.000013084842,0.0000071287373,0.00015823421],"genre_scores_gemma":[0.9982181,0.0002701087,0.00091188756,0.0003966251,0.00006636776,0.000060987517,0.0000041227527,0.0000044441636,0.000067351175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99559057,0.0024623373,0.00067516026,0.00043973848,0.00049151067,0.00034070562],"domain_scores_gemma":[0.8081658,0.19126324,0.00010531017,0.00023744267,0.00014317107,0.00008504378],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03187631,0.000092230395,0.00027996072,0.00013031895,0.00070410443,0.0004072954,0.00038010284,0.000051393614,0.000014169169],"category_scores_gemma":[0.106276795,0.000038671347,0.000041975014,0.0008714519,0.001167144,0.0001562075,0.0006248215,0.0003934211,0.000001186652],"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":[0.0001306976,0.000026458314,0.6958165,0.0000075947446,0.000013105728,3.7725582e-7,0.0016760873,6.2690776e-7,0.000019773315,0.0009636052,0.000055708548,0.30128947],"study_design_scores_gemma":[0.002110253,0.00034070647,0.8591401,0.00012634763,0.000011033938,0.0000011081792,0.03694098,0.0108011225,0.00020385683,0.089793935,0.00043679134,0.000093783856],"about_ca_topic_score_codex":0.0015863917,"about_ca_topic_score_gemma":0.00012632993,"teacher_disagreement_score":0.30119568,"about_ca_system_score_codex":0.000014851519,"about_ca_system_score_gemma":0.000028887205,"threshold_uncertainty_score":0.9968871},"labels":[],"label_agreement":null},{"id":"W4410855435","doi":"10.1089/derm.2025.97851.cme","title":"Self-Assessment","year":2025,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.22205417422236798,"score_gpt":0.4786558655265343,"score_spread":0.2566016913041663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410855435","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054928593,0.00037497768,0.24564531,0.010171555,0.0017568453,0.0001402873,0.000005091755,0.00020711278,0.6867702],"genre_scores_gemma":[0.78987926,0.000042558244,0.20339336,0.004703398,0.000035142053,0.0000123449845,8.332429e-7,0.000002874379,0.0019302152],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99848115,0.00025655338,0.00038712908,0.00022283135,0.0004927289,0.00015963113],"domain_scores_gemma":[0.98861694,0.010685142,0.00010292162,0.00042775235,0.000128083,0.000039144586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021445972,0.00006544524,0.00016998168,0.00040214846,0.00013263663,0.00021020592,0.0005103548,0.000038138936,0.00038525017],"category_scores_gemma":[0.009288278,0.000047528894,0.000059532584,0.0019390482,0.000019534255,0.00012439844,0.00013475258,0.000086284264,0.00016102442],"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":[2.617714e-7,0.00002996178,0.25653198,0.000008850705,0.000017445722,0.000009975419,0.00009401697,0.000010747215,0.000011472094,0.029302252,0.35089904,0.36308396],"study_design_scores_gemma":[0.00011535381,0.000006230752,0.5768729,0.0000069441244,0.0000032054436,0.000004463609,0.00013269522,0.0023482402,0.000058384678,0.06759477,0.3528131,0.000043760843],"about_ca_topic_score_codex":0.000014260926,"about_ca_topic_score_gemma":0.0000033980655,"teacher_disagreement_score":0.73495066,"about_ca_system_score_codex":0.00003877896,"about_ca_system_score_gemma":0.00006956201,"threshold_uncertainty_score":0.99905694},"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":"W4411638719","doi":"10.18653/v1/2024.eacl-tutorials.2","title":"Item Response Theory for Natural Language Processing","year":2024,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Atomic Energy of Canada Limited; York University; Institute for Catastrophic Loss Reduction; University of Notre Dame","keywords":"Computer science; Natural (archaeology); Natural language processing","score_opus":0.4064670903822485,"score_gpt":0.5454917346558178,"score_spread":0.1390246442735693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411638719","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":[0.49435756,0.027865052,0.4466675,0.0023044467,0.0025462338,0.00031546532,0.000011690349,0.00063716416,0.025294898],"genre_scores_gemma":[0.90363795,0.000001686329,0.055228256,0.00030301444,0.00014186493,0.000011659026,5.9578394e-7,0.00000927037,0.04066574],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982248,0.0004517246,0.0003002081,0.00037942734,0.00043315327,0.00021070067],"domain_scores_gemma":[0.8759565,0.12360633,0.00004848346,0.00024248155,0.000103746235,0.000042498916],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018823506,0.00008186016,0.0001437923,0.00045521234,0.0001128986,0.0005691088,0.00041625538,0.000042483192,0.00030050776],"category_scores_gemma":[0.21230368,0.000044594966,0.00010138475,0.0016883395,0.000041174782,0.0002189867,0.00007066655,0.00010931206,0.000074291835],"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":[0.00020908687,0.000004248525,0.00016893158,0.000011662605,0.000004682709,0.000011040819,0.00071846845,0.0000018445592,0.002214683,0.00365896,0.008049774,0.9849466],"study_design_scores_gemma":[0.0007606603,0.00033305274,0.029353347,0.00023296123,0.000036627578,0.00014978915,0.032577366,0.21458973,0.0059395027,0.39454678,0.32074633,0.0007338684],"about_ca_topic_score_codex":0.0000020562861,"about_ca_topic_score_gemma":9.969754e-7,"teacher_disagreement_score":0.98421276,"about_ca_system_score_codex":0.00001766593,"about_ca_system_score_gemma":0.00006387697,"threshold_uncertainty_score":0.79433143},"labels":[],"label_agreement":null},{"id":"W4412520505","doi":"10.1007/s11136-025-04018-6","title":"Tree-based latent variable model for assessing differential item functioning in patient-reported outcome measures: a simulation study","year":2025,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity Western University; University of British Columbia; Western University; University of Manitoba; University of Saskatchewan; University of Alberta; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Bonferroni correction; Type I and type II errors; Statistics; Polytomous Rasch model; Mathematics; Differential item functioning; Statistical power; Multiple comparisons problem; Econometrics; Item response theory; Psychometrics","score_opus":0.9128303773161305,"score_gpt":0.6416932658765836,"score_spread":0.2711371114395469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412520505","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":[0.54090667,0.000027348577,0.45789367,0.00012285965,0.0001546153,0.0005773751,0.000004036826,0.000019121379,0.00029431927],"genre_scores_gemma":[0.98613065,4.667742e-7,0.013473181,0.000036688045,0.000025688516,0.00007820732,0.000004072149,0.000008689293,0.00024233964],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9885125,0.0046367664,0.0024922295,0.0007073628,0.003164137,0.0004869615],"domain_scores_gemma":[0.80982417,0.18512921,0.0008920811,0.0010824134,0.0029162029,0.00015594326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058197547,0.00013841018,0.0006799563,0.0019222223,0.000365207,0.0003412073,0.0005095196,0.00012307608,0.000035914054],"category_scores_gemma":[0.46791485,0.000108474625,0.00014696385,0.004364814,0.000087267545,0.00023653894,0.00019547048,0.00037218435,0.0000011971132],"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":[0.00039045894,0.00062748394,0.78907937,0.00005381287,0.000033364162,6.643778e-7,0.00034838874,0.1748409,0.00046388735,0.0002618914,0.00004423724,0.03385558],"study_design_scores_gemma":[0.0012392417,0.000093293325,0.38447368,0.000037615257,0.0000066086427,2.2010571e-8,0.0021739346,0.6056856,0.000018150728,0.006191584,0.000015042185,0.00006522732],"about_ca_topic_score_codex":0.00087043416,"about_ca_topic_score_gemma":0.00011739668,"teacher_disagreement_score":0.44522402,"about_ca_system_score_codex":0.00016696703,"about_ca_system_score_gemma":0.0005794026,"threshold_uncertainty_score":0.96978384},"labels":[],"label_agreement":null},{"id":"W4412743569","doi":"10.1089/derm.2025.74859.cme","title":"Self-Assessment","year":2025,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.22205417422236798,"score_gpt":0.4786558655265343,"score_spread":0.2566016913041663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412743569","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054928593,0.00037497768,0.24564531,0.010171555,0.0017568453,0.0001402873,0.000005091755,0.00020711278,0.6867702],"genre_scores_gemma":[0.78987926,0.000042558244,0.20339336,0.004703398,0.000035142053,0.0000123449845,8.332429e-7,0.000002874379,0.0019302152],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99848115,0.00025655338,0.00038712908,0.00022283135,0.0004927289,0.00015963113],"domain_scores_gemma":[0.98861694,0.010685142,0.00010292162,0.00042775235,0.000128083,0.000039144586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021445972,0.00006544524,0.00016998168,0.00040214846,0.00013263663,0.00021020592,0.0005103548,0.000038138936,0.00038525017],"category_scores_gemma":[0.009288278,0.000047528894,0.000059532584,0.0019390482,0.000019534255,0.00012439844,0.00013475258,0.000086284264,0.00016102442],"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":[2.617714e-7,0.00002996178,0.25653198,0.000008850705,0.000017445722,0.000009975419,0.00009401697,0.000010747215,0.000011472094,0.029302252,0.35089904,0.36308396],"study_design_scores_gemma":[0.00011535381,0.000006230752,0.5768729,0.0000069441244,0.0000032054436,0.000004463609,0.00013269522,0.0023482402,0.000058384678,0.06759477,0.3528131,0.000043760843],"about_ca_topic_score_codex":0.000014260926,"about_ca_topic_score_gemma":0.0000033980655,"teacher_disagreement_score":0.73495066,"about_ca_system_score_codex":0.00003877896,"about_ca_system_score_gemma":0.00006956201,"threshold_uncertainty_score":0.99905694},"labels":[],"label_agreement":null},{"id":"W4413413384","doi":"10.1007/s11136-025-04046-2","title":"Tree-based item-response theory model for evaluating differential item functioning in patient-reported outcome measures: a web-based R Shiny implementation","year":2025,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Manitoba; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Differential item functioning; Item response theory; Quality of Life Research; Patient-reported outcome; Outcome (game theory); Psychometrics; Quality of life (healthcare); Differential (mechanical device); Public health; Psychology; Clinical psychology; Medicine; Mathematics; Psychotherapist; Nursing","score_opus":0.8819502951575374,"score_gpt":0.6573421513145343,"score_spread":0.2246081438430031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413413384","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":[0.6536089,0.000075840864,0.34424222,0.0008357943,0.00018156206,0.00082983414,0.00003689705,0.00003542171,0.00015351315],"genre_scores_gemma":[0.9843435,0.000001082136,0.01487049,0.0002011343,0.000026294832,0.00026686196,0.000017019212,0.000015593037,0.00025799932],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96936965,0.02066087,0.003500212,0.00095539645,0.0047426415,0.0007712332],"domain_scores_gemma":[0.6337835,0.36131757,0.0011016291,0.0010620564,0.0025494215,0.00018577282],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17928596,0.0002097059,0.0007580848,0.0030213315,0.00047046263,0.00025481742,0.0007791933,0.00016058804,0.00020351661],"category_scores_gemma":[0.67951125,0.0001694371,0.00031998198,0.004200256,0.0002157942,0.00018871688,0.00018649476,0.00045580344,0.000003092063],"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":[0.0117179025,0.0003193542,0.7208325,0.00015790257,0.00006204976,0.0000014279555,0.00080663495,0.0075156884,0.015204136,0.00096012274,0.00050092523,0.24192132],"study_design_scores_gemma":[0.004511096,0.0003579672,0.33951673,0.00008691358,0.000015047257,1.003289e-7,0.006227101,0.6309115,0.00088262383,0.017290078,0.000042404088,0.00015836807],"about_ca_topic_score_codex":0.00037815882,"about_ca_topic_score_gemma":0.00031815373,"teacher_disagreement_score":0.62339586,"about_ca_system_score_codex":0.00023128843,"about_ca_system_score_gemma":0.0020206447,"threshold_uncertainty_score":0.84509784},"labels":[],"label_agreement":null},{"id":"W4414106902","doi":"10.6009/jjrt.25-1575","title":"Development of the CT Scan Attitude Scale and Evaluation of Its Reliability and Validity","year":2025,"lang":"en","type":"article","venue":"Japanese Journal of Radiological Technology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"Japan Society for the Promotion of Science","keywords":"Reliability (semiconductor); Scale (ratio); Computed tomography; Psychological intervention","score_opus":0.37435436047960663,"score_gpt":0.46828569946994064,"score_spread":0.09393133899033401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414106902","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":[0.99669933,0.0007167215,0.00077688287,0.0011395343,0.00016823226,0.00014623343,6.4127386e-7,0.000008481986,0.00034393548],"genre_scores_gemma":[0.96967334,0.000051641815,0.030232439,0.000021086298,0.000007736351,0.0000028206027,3.0676695e-8,0.000001078807,0.000009855343],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971377,0.00084223814,0.0010315339,0.00021881098,0.0006388023,0.00013089186],"domain_scores_gemma":[0.991236,0.00672571,0.0008076598,0.00030627826,0.0008857886,0.000038597685],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021780042,0.00008261176,0.00048697533,0.00043429257,0.000108649976,0.000010985351,0.0006172781,0.00010780762,0.000023907514],"category_scores_gemma":[0.11493136,0.00003889084,0.00006861621,0.0017006659,0.0005560072,0.000069469585,0.0003005804,0.0002327721,2.4647002e-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":[0.000048462673,0.00006977359,0.76104,0.000011524289,0.000020759917,9.1903e-7,0.00018272584,0.000113167865,0.026800765,0.0005391153,0.000032051095,0.21114075],"study_design_scores_gemma":[0.0005061074,0.00015260723,0.92690164,0.000036127385,0.000025700152,0.00016901153,0.0010999885,0.00072367635,0.013445767,0.056649398,0.0002448146,0.000045170742],"about_ca_topic_score_codex":0.0000017446025,"about_ca_topic_score_gemma":0.0000028897693,"teacher_disagreement_score":0.21109559,"about_ca_system_score_codex":0.00004309376,"about_ca_system_score_gemma":0.000106184234,"threshold_uncertainty_score":0.89252394},"labels":[],"label_agreement":null},{"id":"W4414358699","doi":"10.21105/joss.07869","title":"FedIRT: An R package and shiny app for estimating federated item response theory models","year":2025,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Toronto","funders":"","keywords":"R package; Item response theory; Response time","score_opus":0.3234165144361462,"score_gpt":0.4792493143557467,"score_spread":0.15583279991960047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414358699","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":[0.3291821,0.0005285082,0.6686656,0.00074954063,0.00026629295,0.00026521616,0.000007813884,0.000025402933,0.0003095638],"genre_scores_gemma":[0.5987429,0.000014886277,0.39697075,0.000879762,0.00012595387,0.0000068829604,7.3084436e-7,0.000023930752,0.0032342004],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945469,0.0032793444,0.000992251,0.00026727875,0.0006305655,0.00028367905],"domain_scores_gemma":[0.85486406,0.14252822,0.001095921,0.00056677184,0.0007925961,0.00015243016],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06130262,0.00017130675,0.00053225487,0.00040486662,0.00096340966,0.0015396549,0.0022860598,0.00008732822,0.000041569892],"category_scores_gemma":[0.21723843,0.000092749244,0.00010656359,0.0011848131,0.00014046924,0.0009259987,0.00062642276,0.0003509865,0.000002063734],"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":[0.008248234,0.00008859812,0.0048545436,0.000025620117,0.0001314002,0.000011390561,0.006965123,0.022003734,0.0004703128,0.0009005435,0.011432555,0.94486797],"study_design_scores_gemma":[0.002809587,0.0009016566,0.016087497,0.000451089,0.00015475597,0.0003250255,0.030856255,0.1273744,0.00032982984,0.81617564,0.004155818,0.00037845565],"about_ca_topic_score_codex":0.000017220747,"about_ca_topic_score_gemma":0.0000027654223,"teacher_disagreement_score":0.9444895,"about_ca_system_score_codex":0.000035615416,"about_ca_system_score_gemma":0.00019280372,"threshold_uncertainty_score":0.9994968},"labels":[],"label_agreement":null},{"id":"W4414667063","doi":"10.2139/ssrn.5549064","title":"Determining the Effects of League of Legends Ranked Tiers on Outcome Prediction Models","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"League; Logistic regression; Predictive modelling; Battle; Test (biology); Bronze; Outcome (game theory)","score_opus":0.25441488690894265,"score_gpt":0.4370370929715155,"score_spread":0.18262220606257284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414667063","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":[0.7314032,0.0038893945,0.2516078,0.00028350114,0.0055866526,0.00055668864,0.000033466196,0.000039544037,0.0065997867],"genre_scores_gemma":[0.995947,0.0014923089,0.001068044,0.000051428775,0.00018986753,0.000010798991,0.000001849625,0.00001403949,0.0012246848],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935661,0.0013179559,0.0017511669,0.00051187107,0.0016264071,0.0012265296],"domain_scores_gemma":[0.9743054,0.022171304,0.0020401415,0.0008899872,0.00052881887,0.000064372165],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.022203447,0.0002937666,0.0009128619,0.0011720316,0.00021265922,0.00008683201,0.002055114,0.00030116967,0.0000081430235],"category_scores_gemma":[0.041102745,0.00017364183,0.00058737583,0.0011308454,0.00013355026,0.00012560569,0.00046094458,0.004012415,0.0000014072727],"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":[0.0004180349,0.00023763052,0.14170808,0.00027715715,0.0012597799,0.0000043756154,0.0010741483,0.06066003,0.00022354045,0.044730015,0.00066408474,0.7487431],"study_design_scores_gemma":[0.0014446882,0.0010748019,0.021622822,0.0004995087,0.00022930358,0.00003380757,0.0012318619,0.015321608,0.0005236465,0.9576689,0.00009739821,0.00025164703],"about_ca_topic_score_codex":0.00003758713,"about_ca_topic_score_gemma":0.00001884183,"teacher_disagreement_score":0.9129389,"about_ca_system_score_codex":0.00043083375,"about_ca_system_score_gemma":0.0017109712,"threshold_uncertainty_score":0.99828535},"labels":[],"label_agreement":null},{"id":"W4414826896","doi":"10.1016/b978-0-443-26629-4.00103-9","title":"Structural equation modeling","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Structural equation modeling; Range (aeronautics); Regression analysis; Causal model; Regression; Core (optical fiber); Observational study","score_opus":0.4467826167836653,"score_gpt":0.4316575861427557,"score_spread":0.015125030640909642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414826896","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016034018,0.0012358505,0.005585024,0.000084252286,0.0018641746,0.00029948432,0.000020905398,0.00009361874,0.9906564],"genre_scores_gemma":[0.0027539593,0.000025827097,0.0130854845,0.0002634737,0.00036011543,0.0000078490975,0.000008505838,0.00002677476,0.983468],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99604446,0.0001459737,0.0011843,0.0008684141,0.0014434479,0.00031342538],"domain_scores_gemma":[0.98955846,0.00819807,0.00058234035,0.001080479,0.0004780291,0.00010262746],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036957578,0.00036862944,0.00073308626,0.0009784353,0.00023239489,0.0002798807,0.0011059629,0.0003771624,0.0006278183],"category_scores_gemma":[0.018011052,0.00027318537,0.00034597638,0.00013042794,0.00007366157,0.00008010958,0.00037635828,0.00054827955,0.00017171373],"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":[0.000006865064,5.4104356e-7,0.000024960318,0.000009539995,0.000024635045,0.0000046495356,0.0000605693,0.00024444252,0.0000020774157,0.014894389,0.00026842384,0.9844589],"study_design_scores_gemma":[0.000120812445,0.000021183674,0.000013593857,0.00015320344,0.000036148143,0.00000517652,0.000023402683,0.050585315,0.000002329075,0.61015666,0.3386041,0.0002780873],"about_ca_topic_score_codex":0.0000011165911,"about_ca_topic_score_gemma":0.000004766146,"teacher_disagreement_score":0.9841808,"about_ca_system_score_codex":0.00008019419,"about_ca_system_score_gemma":0.00016370809,"threshold_uncertainty_score":0.99997205},"labels":[],"label_agreement":null},{"id":"W4415216473","doi":"10.3389/fpsyg.2025.1592658","title":"Clarifying the reliability paradox: poor measurement reliability attenuates group differences","year":2025,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Krembil Foundation","keywords":"Reliability (semiconductor); Cognition; Variance (accounting); Set (abstract data type); Group (periodic table); Psychometrics; Rendering (computer graphics); Measure (data warehouse)","score_opus":0.2971812503985126,"score_gpt":0.4443418164964959,"score_spread":0.14716056609798328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415216473","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":[0.3481143,0.0049204966,0.5735549,0.031875193,0.019360296,0.00093830324,0.000009581931,0.0001404513,0.021086505],"genre_scores_gemma":[0.93088645,0.00022833653,0.0657227,0.0027568112,0.00009008028,0.00010460046,0.000001182607,0.00001012535,0.00019969267],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99159014,0.0034778374,0.0014979636,0.0014769359,0.0012601229,0.0006970275],"domain_scores_gemma":[0.98462105,0.01225123,0.00044409872,0.0021841857,0.00040413736,0.00009527573],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031631697,0.00028752483,0.00078897673,0.0007805884,0.00034988593,0.00015964085,0.0024515167,0.0003348544,0.00009703284],"category_scores_gemma":[0.10258865,0.00016822568,0.00021793037,0.004116452,0.00073537475,0.00016832292,0.00030426504,0.00087441714,0.000025449332],"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":[0.00011363227,0.00012200054,0.6952044,0.0000074585823,0.000018039236,0.000002503181,0.0001053863,0.000017188537,0.000045003733,0.00036138506,0.07702804,0.22697496],"study_design_scores_gemma":[0.00045785907,0.000063313804,0.58374494,0.000023727822,0.000011345521,0.0000020894647,0.0007900991,0.000805611,0.000011737422,0.38602108,0.027944034,0.00012419913],"about_ca_topic_score_codex":0.000118107404,"about_ca_topic_score_gemma":0.000033843706,"teacher_disagreement_score":0.5827722,"about_ca_system_score_codex":0.00016853925,"about_ca_system_score_gemma":0.00007366581,"threshold_uncertainty_score":0.997139},"labels":[],"label_agreement":null},{"id":"W4415685411","doi":"10.3389/fcvm.2025.1605130","title":"Validation of PROMIS anxiety item bank computer adaptive test among patients with heart failure","year":2025,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University; Institute for Clinical Evaluative Sciences; Ted Rogers Centre for Heart Research; University Health Network","funders":"Heart and Stroke Foundation of Canada","keywords":"Computerized adaptive testing; Heart failure; Item bank; Reliability (semiconductor); Test (biology); Anxiety; Psychometrics; Item response theory","score_opus":0.052141734486403586,"score_gpt":0.3086298078865425,"score_spread":0.2564880734001389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415685411","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":[0.37343144,0.0034739897,0.6184713,0.00038767818,0.0018533198,0.000809111,0.000010999213,0.00004060677,0.0015215359],"genre_scores_gemma":[0.84268576,0.000018911394,0.15695278,0.00009271939,0.0001247346,0.000021446116,0.000011637317,0.000011474482,0.00008052871],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959439,0.0006534416,0.0007586932,0.0006545286,0.0017146881,0.00027473798],"domain_scores_gemma":[0.99417335,0.003917658,0.00024648692,0.00094684947,0.00063749746,0.00007818312],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006867246,0.00020280057,0.0011339659,0.0010255727,0.00007366543,0.000026928052,0.00050409726,0.00012418689,0.000023384404],"category_scores_gemma":[0.020223765,0.00012847917,0.00028815653,0.003979033,0.00032706247,0.00019453114,0.00011883045,0.0002446619,0.0000013745258],"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":[0.00003401534,0.000040600065,0.90478927,0.000017519504,0.00022193765,0.0000021320143,0.00014092702,0.000993016,0.0000039967244,0.0000068534823,0.033130374,0.06061936],"study_design_scores_gemma":[0.002280509,0.00025319043,0.9836205,0.00031042402,0.00012177899,0.0000017768971,0.0007471516,0.0022966743,0.00016190534,0.000754576,0.009315378,0.00013611198],"about_ca_topic_score_codex":0.00009786897,"about_ca_topic_score_gemma":0.000003473207,"teacher_disagreement_score":0.46925434,"about_ca_system_score_codex":0.00008421475,"about_ca_system_score_gemma":0.00006173451,"threshold_uncertainty_score":0.9880293},"labels":[],"label_agreement":null},{"id":"W4415699443","doi":"10.15626/mp.2020.2643","title":"A Multi-faceted Mess: A Review of Statistical Power Analysis in Psychology Journal Articles","year":2025,"lang":"","type":"article","venue":"Meta-Psychology","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":"York University","funders":"","keywords":"Sample size determination; Statistical power; Sample (material); Power (physics); Identification (biology); A priori and a posteriori; Order (exchange)","score_opus":0.5836364185346339,"score_gpt":0.5957669098937192,"score_spread":0.012130491359085283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415699443","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":[0.012410782,0.31868622,0.6416471,0.015573133,0.0036155616,0.0007683611,0.00014807995,0.000038313032,0.007112452],"genre_scores_gemma":[0.35868454,0.14435813,0.45413816,0.041505136,0.000095105264,0.00014120691,0.000014830414,0.000061343795,0.0010015749],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96997905,0.016498674,0.007722181,0.0025133677,0.001655506,0.001631202],"domain_scores_gemma":[0.9601957,0.03181493,0.002923715,0.0031151979,0.0014982396,0.00045222143],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049143042,0.00083017716,0.006470586,0.008634497,0.0002528507,0.00018294959,0.003305682,0.0007446437,0.024976153],"category_scores_gemma":[0.17254733,0.00060426875,0.002092863,0.033740368,0.0013440485,0.00029353375,0.00052779476,0.0018920864,0.00018471661],"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":[0.0011877657,0.00475889,0.1420352,0.00094132073,0.029695967,0.00073851325,0.00061392784,0.00010073736,0.0022114958,0.0018708477,0.089141764,0.7267036],"study_design_scores_gemma":[0.005721979,0.0010426154,0.85095525,0.0011249803,0.019399922,0.0002852894,0.00039628858,0.0017337082,0.000048328362,0.038235888,0.08018063,0.0008751069],"about_ca_topic_score_codex":0.0000615627,"about_ca_topic_score_gemma":0.00006799946,"teacher_disagreement_score":0.72582847,"about_ca_system_score_codex":0.000076311946,"about_ca_system_score_gemma":0.0003497608,"threshold_uncertainty_score":0.9996409},"labels":[],"label_agreement":null},{"id":"W4415813563","doi":"10.3390/educsci15111475","title":"A Comparison of Different Methods for Measuring Individual Change in Kindergarten Children","year":2025,"lang":"en","type":"article","venue":"Education Sciences","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thames Valley Children's Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normalization (sociology); Evaluation methods; Significant difference; Statistical analysis; Change analysis; Teaching method","score_opus":0.8177700004776367,"score_gpt":0.6685093208051843,"score_spread":0.14926067967245238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415813563","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":[0.92713577,0.0022526153,0.062004767,0.0019392691,0.0022547238,0.00059951487,0.0000039711817,0.000019529163,0.0037898468],"genre_scores_gemma":[0.86452097,0.000007048999,0.13508652,0.00012268455,0.000051721585,0.000101145146,0.0000012891967,0.0000019183785,0.00010669936],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99733174,0.0006274536,0.00072379725,0.00045812957,0.00063031516,0.00022855143],"domain_scores_gemma":[0.9821635,0.01690045,0.00040119578,0.00027845768,0.00021196829,0.00004445659],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011245856,0.00009677458,0.0003630982,0.0015920296,0.00018832726,0.00016319343,0.0011307733,0.00005187437,0.000042318356],"category_scores_gemma":[0.044956114,0.00006637624,0.000072832896,0.0042202673,0.00017624049,0.00023497126,0.00013525538,0.00008573133,0.0000013536522],"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":[0.0000018969832,0.000083950625,0.53775847,0.0000028768923,0.0000029512719,2.5350586e-9,0.0008526225,0.0000061605315,0.000064817876,0.0018195129,0.00023137481,0.45917538],"study_design_scores_gemma":[0.00013814188,0.000054367963,0.9455805,0.000060875223,0.000006815646,3.4657265e-7,0.003105214,0.0012072935,0.0018000223,0.04753517,0.0004417452,0.0000695378],"about_ca_topic_score_codex":0.00012262541,"about_ca_topic_score_gemma":0.000038378592,"teacher_disagreement_score":0.45910585,"about_ca_system_score_codex":0.000028633007,"about_ca_system_score_gemma":0.00024829333,"threshold_uncertainty_score":0.96308863},"labels":[],"label_agreement":null},{"id":"W4415906860","doi":"10.15390/es.2014.1247","title":"Comparability between the American and Turkish Versions of the TIMSS Mathematics Test Results","year":2014,"lang":"","type":"article","venue":"TED EĞİTİM VE BİLİM","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ottawa Hospital","funders":"","keywords":"Comparability; Turkish; Test (biology); Student's t-test","score_opus":0.36926587330586585,"score_gpt":0.4405121815083178,"score_spread":0.07124630820245192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415906860","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":[0.97750497,0.00035607992,0.004207292,0.0050161695,0.00095377024,0.000878732,0.00059151236,0.000088666304,0.010402819],"genre_scores_gemma":[0.9864079,0.00010582793,0.012462972,0.00031380306,0.00028728604,0.000009980929,0.0000066299626,0.000030221649,0.00037539177],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904828,0.002738453,0.0025501286,0.0012363396,0.0020905035,0.00090175273],"domain_scores_gemma":[0.77976406,0.21161689,0.0034348553,0.003986229,0.00080013607,0.00039784546],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01894754,0.00056793186,0.0016200274,0.00043686116,0.0012569902,0.00035639424,0.0034189478,0.0002220517,0.00011777748],"category_scores_gemma":[0.22914205,0.0003001466,0.0004221421,0.0075794924,0.0039323266,0.00019044372,0.0015812214,0.0009755933,0.00009076094],"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":[0.0002109011,0.00080881524,0.73095363,0.0001292144,0.00021996383,0.0000027748395,0.00575616,0.00023391243,0.0007481998,0.0006284784,0.023374636,0.23693332],"study_design_scores_gemma":[0.0011799525,0.0007257325,0.9497491,0.00022919461,0.00025329622,0.00001635034,0.0055081993,0.013670424,0.00048226476,0.015616011,0.012108258,0.00046122697],"about_ca_topic_score_codex":0.00033243417,"about_ca_topic_score_gemma":0.000030574898,"teacher_disagreement_score":0.23647209,"about_ca_system_score_codex":0.000082463186,"about_ca_system_score_gemma":0.00017530736,"threshold_uncertainty_score":0.99994504},"labels":[],"label_agreement":null},{"id":"W4415917403","doi":"10.1038/s41598-025-20032-7","title":"Using item response theory as a methodology to impute categorical missing values","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","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":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health","keywords":"Missing data; Categorical variable; Imputation (statistics); Probabilistic logic; Item response theory; Statistical model; Regression; Binary data","score_opus":0.5962277551925372,"score_gpt":0.5607249096711437,"score_spread":0.03550284552139349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415917403","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":[0.52050334,0.0003700167,0.45633262,0.001020205,0.016846394,0.00023283352,6.1405075e-7,0.00010307812,0.004590913],"genre_scores_gemma":[0.5237219,0.0000011553504,0.44592968,0.00074822735,0.0001252487,0.00001226769,0.0000013724036,0.000018242556,0.029441914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9859491,0.0074631562,0.0018217815,0.0022264565,0.0017673972,0.0007721217],"domain_scores_gemma":[0.87443906,0.11961484,0.0009937822,0.0033662845,0.0011325642,0.00045348154],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14719298,0.000237043,0.000634364,0.002788198,0.0008702037,0.0013709583,0.00094823015,0.00016775103,0.000265027],"category_scores_gemma":[0.58182275,0.00017285431,0.00024623217,0.010344426,0.00041095514,0.00025429414,0.0007507223,0.000248422,0.00007229559],"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":[0.0011042394,0.00015193116,0.023494223,0.000020955134,0.00009751275,0.0026021695,0.003778415,0.0016556919,0.24532185,0.014333745,0.06729054,0.6401487],"study_design_scores_gemma":[0.00008994747,0.000048574748,0.007517179,0.0000339778,0.000025288848,0.0006998694,0.0009859066,0.0012925422,0.010320866,0.9152728,0.06350813,0.00020492416],"about_ca_topic_score_codex":0.000059341233,"about_ca_topic_score_gemma":0.0000018812299,"teacher_disagreement_score":0.90093905,"about_ca_system_score_codex":0.00015386597,"about_ca_system_score_gemma":0.00080041116,"threshold_uncertainty_score":0.99966574},"labels":[],"label_agreement":null},{"id":"W4416101570","doi":"10.5539/jel.v15n2p1","title":"From Labels to Profiles: Using Discriminant Analysis to Deepen Post Hoc ANOVA Results","year":2025,"lang":"","type":"article","venue":"Journal of Education and Learning","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Post-hoc analysis; Post hoc; Linear discriminant analysis; Descriptive statistics; Analysis of variance; Scheffé's method; Multivariate analysis of variance; Interpretation (philosophy); Discriminant","score_opus":0.24832404201174657,"score_gpt":0.514378120231525,"score_spread":0.2660540782197784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416101570","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":[0.9290922,0.00254349,0.055110544,0.008306086,0.003377061,0.0002004891,0.000013352808,0.0000064831893,0.0013502497],"genre_scores_gemma":[0.8367492,0.00012742987,0.15780047,0.0010988367,0.0005239573,0.0000018417762,0.0000035257785,0.000009354573,0.0036853927],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99450856,0.0015406923,0.0020776163,0.0006148878,0.00088750955,0.00037075148],"domain_scores_gemma":[0.98083764,0.014307749,0.0018388657,0.00042997618,0.0020936034,0.0004921868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011403333,0.0002418463,0.00086082,0.0048433715,0.000650626,0.0009907893,0.0006983958,0.00012941404,0.00030801198],"category_scores_gemma":[0.17007141,0.00018439034,0.00026551314,0.011001661,0.00005244407,0.00042149375,0.00026860426,0.00072448526,0.000016256168],"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":[0.00074092974,0.00028057667,0.061097383,0.000018035136,0.0005713661,0.000007361787,0.02282764,0.009357,0.0054605557,0.00006871525,0.0032842483,0.8962862],"study_design_scores_gemma":[0.00094152626,0.0011212075,0.72632354,0.001265577,0.0016058381,0.00003174568,0.2036809,0.004730793,0.0004086105,0.0011481784,0.058281835,0.00046024297],"about_ca_topic_score_codex":0.00079219096,"about_ca_topic_score_gemma":0.00003125347,"teacher_disagreement_score":0.8958259,"about_ca_system_score_codex":0.00017080785,"about_ca_system_score_gemma":0.0011654964,"threshold_uncertainty_score":0.95542043},"labels":[],"label_agreement":null},{"id":"W4416102162","doi":"10.1017/psy.2025.10059","title":"Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm","year":2025,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of Toronto; Employment and Social Development Canada","funders":"Connaught Fund; Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; University of Cambridge","keywords":"Inference; Discriminator; Latent variable; Adversarial system; Bayes' theorem; Generative grammar; Latent variable model; Deep learning; Representation (politics)","score_opus":0.15423947157658507,"score_gpt":0.4262096146266989,"score_spread":0.2719701430501138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416102162","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":[0.026974954,0.0014877704,0.9601248,0.0004948139,0.008721905,0.0006249702,0.00009379098,0.00016809498,0.0013089213],"genre_scores_gemma":[0.7019482,0.00006093171,0.29164395,0.0006487834,0.0016893235,0.000114454066,0.00010463429,0.000033566103,0.0037561483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933888,0.0010477082,0.0015016734,0.0016054354,0.0015880241,0.00086839806],"domain_scores_gemma":[0.9302205,0.066969045,0.00076772843,0.00083776104,0.0009575692,0.0002474021],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.006465421,0.00045277478,0.0012613866,0.0062489496,0.00075928983,0.00050901505,0.0012593247,0.00038785947,0.0008880327],"category_scores_gemma":[0.114345744,0.00035776853,0.0008392597,0.02762257,0.00014096394,0.00033457586,0.0002790426,0.0006179652,0.000039008646],"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":[0.0005877789,0.00019013046,0.051435206,0.0000061164965,0.0020356455,0.0000062147838,0.00019517266,0.040178876,0.00008697088,0.0014222846,0.011199096,0.8926565],"study_design_scores_gemma":[0.0061252275,0.00053472753,0.17124225,0.000029902385,0.00083172275,0.0000033505091,0.0007308574,0.76898986,0.00016077823,0.016110169,0.034407143,0.00083401485],"about_ca_topic_score_codex":0.00009172746,"about_ca_topic_score_gemma":0.000025996282,"teacher_disagreement_score":0.8918225,"about_ca_system_score_codex":0.00015830205,"about_ca_system_score_gemma":0.00013374734,"threshold_uncertainty_score":0.9998874},"labels":[],"label_agreement":null},{"id":"W4416195809","doi":"10.1177/00131644251389891","title":"Reliability as Projection in Operator-Theoretic Test Theory: Conditional Expectation, Hilbert Space Geometry, and Implications for Psychometric Practice","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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 British Columbia","funders":"","keywords":"Reliability (semiconductor); Projection (relational algebra); Mathematical proof; Hilbert space; Complement (music); Statistical hypothesis testing; Space (punctuation); Conditional expectation; Perspective (graphical)","score_opus":0.3733883313779877,"score_gpt":0.5068659574544272,"score_spread":0.13347762607643948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416195809","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":[0.7334268,0.004177211,0.081816785,0.14007856,0.0017684805,0.0025692962,0.00006686148,0.000064875036,0.036031134],"genre_scores_gemma":[0.9790429,0.00015350645,0.017885314,0.0015141807,0.00012305488,0.00066619326,0.0000146166585,0.0000059449408,0.00059428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966762,0.00072557625,0.00071638374,0.00094528217,0.00067791087,0.00025862546],"domain_scores_gemma":[0.95057714,0.047050066,0.00027696564,0.0004145866,0.0015478114,0.0001334011],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012101807,0.00018442587,0.00027800893,0.0009963759,0.00036956207,0.00021354124,0.0002977102,0.00012768533,0.0002456322],"category_scores_gemma":[0.32103285,0.00013252051,0.000061372666,0.0037613162,0.00025048474,0.00023322941,0.000051410807,0.00020457178,0.000013550942],"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":[0.00031641612,0.0021127516,0.4150243,0.00002828673,0.00003305205,1.820009e-7,0.00031305867,0.00001762933,0.0006144523,0.50302887,0.015670482,0.06284052],"study_design_scores_gemma":[0.00041003787,0.00018194487,0.54774636,0.000014484978,0.000011346308,0.000013740486,0.0005551404,0.000016846549,0.000012313065,0.44424412,0.006706484,0.00008720127],"about_ca_topic_score_codex":0.00002137415,"about_ca_topic_score_gemma":0.000003787007,"teacher_disagreement_score":0.30893105,"about_ca_system_score_codex":0.00014692631,"about_ca_system_score_gemma":0.00016170299,"threshold_uncertainty_score":0.68468636},"labels":[],"label_agreement":null},{"id":"W4416211129","doi":"10.1080/08957347.2025.2563889","title":"Establishing Cognitive Item Models for Fair and Theory-Grounded Automatic Item Generation: A Large-Scale Assessment Study with Image-Based Math Items","year":2025,"lang":"en","type":"article","venue":"Applied Measurement in Education","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 Alberta","funders":"Fonds National de la Recherche Luxembourg","keywords":"Item response theory; Cognition; Item analysis; Differential item functioning; Test (biology); Equating; Item bank; Standardized test","score_opus":0.26271347576987486,"score_gpt":0.44115256739937964,"score_spread":0.17843909162950478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416211129","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":[0.39944476,0.00012693237,0.5934358,0.00024384023,0.0003385436,0.0021778515,0.0000053827507,0.00004937891,0.0041774907],"genre_scores_gemma":[0.9039317,0.0000027107935,0.093821004,0.00033482775,0.0000735252,0.0017247977,0.000019464018,0.000014462915,0.00007752952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963232,0.0005662334,0.0007674625,0.0007831723,0.0012417309,0.00031818077],"domain_scores_gemma":[0.9875879,0.010566975,0.0003995275,0.0004351857,0.0009371789,0.000073192474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018860351,0.00022766332,0.00039317846,0.0007776427,0.00033685638,0.000779983,0.00031584807,0.00006958295,0.000012970147],"category_scores_gemma":[0.009214113,0.00017206432,0.000040616585,0.0018736823,0.000046960435,0.00043635097,0.00005854543,0.00016333946,0.0000014031282],"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":[0.00054494495,0.0069910088,0.10529426,0.0002907903,0.000233188,0.000001314129,0.011323143,0.0024511875,0.003906493,0.06665377,0.0022662543,0.80004364],"study_design_scores_gemma":[0.0067346264,0.0005339031,0.18445231,0.00044553785,0.00024220167,0.0000019990716,0.17696886,0.48734587,0.00077583134,0.14160612,0.00027370956,0.00061902264],"about_ca_topic_score_codex":0.000038233193,"about_ca_topic_score_gemma":0.00018519266,"teacher_disagreement_score":0.79942465,"about_ca_system_score_codex":0.0003303513,"about_ca_system_score_gemma":0.0007973295,"threshold_uncertainty_score":0.9991317},"labels":[],"label_agreement":null},{"id":"W4416260299","doi":"10.48550/arxiv.2506.21744","title":"Federated Item Response Models: A Gradient-driven Privacy-preserving Framework for Distributed Psychometric Estimation","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Social Sciences and Humanities Research Council of Canada; Connaught Fund; University of Toronto","keywords":"Item response theory; Estimation; Field (mathematics); Raw data; Information privacy; Data modeling; Federated learning; Privacy protection","score_opus":0.5639737864270469,"score_gpt":0.37375016217314194,"score_spread":0.19022362425390493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416260299","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":[0.31489328,0.00015657957,0.6813078,0.00032895175,0.0012526968,0.00084914727,0.0004565334,0.00026111564,0.0004938939],"genre_scores_gemma":[0.8827434,0.00010727226,0.11523824,0.000086482614,0.00007384055,0.00001342355,0.000114182156,0.0000274478,0.0015956709],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933145,0.0018557839,0.0010621068,0.0024434915,0.00055355334,0.0007705669],"domain_scores_gemma":[0.9127311,0.081402436,0.0015125797,0.0024894117,0.0015128958,0.00035158521],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006640038,0.0005876529,0.001064015,0.0038322455,0.0007227394,0.0007675794,0.0038386125,0.0008835367,0.000087572575],"category_scores_gemma":[0.23423782,0.0005751266,0.00062553823,0.013128106,0.00014192396,0.00054748164,0.0030932557,0.0010696154,0.000024970957],"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":[0.0017282795,0.00017834068,0.011942825,0.000118651165,0.00020124468,0.000029108834,0.0002150269,0.947031,0.000011181302,0.024249643,0.0047421656,0.009552512],"study_design_scores_gemma":[0.0005122668,0.00006865149,0.007731095,0.00022426654,0.00007532985,0.0000014231481,0.00024927783,0.57298917,0.000012417543,0.41743505,0.00036965116,0.00033139926],"about_ca_topic_score_codex":0.000081523736,"about_ca_topic_score_gemma":0.000008807527,"teacher_disagreement_score":0.5678502,"about_ca_system_score_codex":0.00051193044,"about_ca_system_score_gemma":0.00040528065,"threshold_uncertainty_score":0.99967},"labels":[],"label_agreement":null},{"id":"W4416261064","doi":"10.5555/0tg5me50","title":"Affiliation Test 7","year":2025,"lang":"","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Council for the Arts; Statistics Canada","funders":"","keywords":"","score_opus":0.39044659527329123,"score_gpt":0.5286459727958729,"score_spread":0.13819937752258166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416261064","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0115364995,0.001650502,0.26219583,0.0061096186,0.0048836395,0.0002102541,0.0000061848364,0.000095087744,0.7133124],"genre_scores_gemma":[0.7621954,0.00021084344,0.053606853,0.001452714,0.00011283661,0.0000056377935,6.564355e-7,0.000004942336,0.1824101],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964366,0.00041165858,0.001098374,0.0007766204,0.00085713324,0.00041960884],"domain_scores_gemma":[0.80504405,0.1926688,0.00038145008,0.0011745245,0.00060593773,0.00012521216],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009059656,0.0001908075,0.0003912302,0.0012843766,0.000356125,0.00061525503,0.0011111058,0.0001814421,0.0060389335],"category_scores_gemma":[0.4986764,0.00013905033,0.00016452435,0.010616901,0.00012793556,0.0002615001,0.0003814417,0.00022169999,0.0008770219],"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":[0.000007522625,0.000098954035,0.17836526,0.000008368857,0.000012262339,0.0000017201979,0.000041108495,0.000027541631,0.00021810175,0.013078983,0.0768875,0.7312527],"study_design_scores_gemma":[0.00073661364,0.00018749667,0.542332,0.0001139097,0.00004298969,0.0000031728882,0.0022634985,0.033361502,0.0015402113,0.1616821,0.25739628,0.00034026412],"about_ca_topic_score_codex":0.000054492855,"about_ca_topic_score_gemma":0.00000864226,"teacher_disagreement_score":0.7506589,"about_ca_system_score_codex":0.000060918373,"about_ca_system_score_gemma":0.00023990982,"threshold_uncertainty_score":0.99990094},"labels":[],"label_agreement":null},{"id":"W4416309139","doi":"10.2139/ssrn.5757617","title":"Do Test Scores Misrepresent Test Results? An Item-by-Item Analysis","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Test (biology); Download; Aggregate (composite); Aggregate data; Ex-ante; Test data","score_opus":0.21331889915175967,"score_gpt":0.45929822826823513,"score_spread":0.24597932911647546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416309139","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":[0.5232028,0.10277062,0.27690694,0.016431537,0.008516939,0.0023925502,0.004300436,0.00094241585,0.064535774],"genre_scores_gemma":[0.938846,0.015566264,0.009297022,0.0002956841,0.0016802308,0.000043176435,0.00017305561,0.00006801099,0.03403059],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9847581,0.0020177157,0.0032795677,0.0024709208,0.0034166048,0.0040570833],"domain_scores_gemma":[0.85240114,0.13557726,0.0045742933,0.0046524876,0.0020634488,0.00073136634],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04958668,0.00079245435,0.0018495271,0.004469583,0.0007620134,0.002384741,0.005986365,0.00067617797,0.00021115619],"category_scores_gemma":[0.36697012,0.00058609847,0.0013458858,0.009228374,0.00020869036,0.00038855753,0.0016898604,0.0082833795,0.00004838013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021417918,0.0007616525,0.6487758,0.0000239044,0.00243965,0.000041711188,0.00032008538,0.0043642805,0.00020061439,0.0024491951,0.022056246,0.31835267],"study_design_scores_gemma":[0.0016346085,0.0011063648,0.08706318,0.00023593684,0.0015996225,0.00026408184,0.004511985,0.011449371,0.00016460243,0.87918663,0.0113434335,0.001440186],"about_ca_topic_score_codex":0.0006307549,"about_ca_topic_score_gemma":0.0011990971,"teacher_disagreement_score":0.8767374,"about_ca_system_score_codex":0.0013746102,"about_ca_system_score_gemma":0.0058687376,"threshold_uncertainty_score":0.99976707},"labels":[],"label_agreement":null},{"id":"W4416368436","doi":"10.2139/ssrn.5771962","title":"Do Test Scores Misrepresent Test Results? An Item-by-Item Analysis","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Test (biology); Aggregate (composite); Aggregate data; Ex-ante; Test data","score_opus":0.1679397505946936,"score_gpt":0.43908312645093145,"score_spread":0.2711433758562378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416368436","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":[0.33550084,0.19267601,0.37261653,0.017993057,0.013896613,0.0041701207,0.0063462015,0.0008180168,0.05598262],"genre_scores_gemma":[0.8473468,0.09186768,0.010282055,0.00035763913,0.0024719334,0.00006760898,0.00021508777,0.00012188109,0.047269337],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.964962,0.005184079,0.007838031,0.0054534287,0.006202431,0.010360034],"domain_scores_gemma":[0.67135024,0.30002084,0.012190287,0.00921409,0.0049991487,0.0022253627],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.09474405,0.0019989782,0.0041244286,0.0088960575,0.0025265987,0.005391168,0.010522157,0.0015436744,0.00079759804],"category_scores_gemma":[0.48931414,0.0016107216,0.0032410226,0.024060786,0.0007085816,0.0010725526,0.0031175362,0.018137382,0.00013895947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006044073,0.0018810095,0.4899717,0.000051540967,0.0054875547,0.00007068883,0.00060311786,0.0051081954,0.00035248097,0.0025123393,0.007857741,0.48549923],"study_design_scores_gemma":[0.0058879512,0.0055056806,0.12982358,0.0010812159,0.00787602,0.0012294996,0.020852355,0.043290302,0.00042235668,0.75492406,0.024470443,0.004636534],"about_ca_topic_score_codex":0.0013684996,"about_ca_topic_score_gemma":0.0018508385,"teacher_disagreement_score":0.7524117,"about_ca_system_score_codex":0.0037766714,"about_ca_system_score_gemma":0.017642839,"threshold_uncertainty_score":0.9997525},"labels":[],"label_agreement":null},{"id":"W4416390404","doi":"10.1111/1911-3846.70019","title":"An Explanation of Path Analysis and Recommendations for Best Practice","year":2025,"lang":"en","type":"article","venue":"Contemporary Accounting Research","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":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Warwick; University of Bristol; Florida State University; University of Southern California","keywords":"Endogeneity; Uncorrelated; Instrumental variable; Path analysis (statistics); Path (computing); Identification (biology); Contrast (vision); Estimation","score_opus":0.6380214363417919,"score_gpt":0.6128231545378965,"score_spread":0.025198281803895384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416390404","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":[0.53842944,0.0030579604,0.35981318,0.027764782,0.0006224643,0.0013457522,0.00014300743,0.00007672296,0.06874666],"genre_scores_gemma":[0.9594586,0.000053000906,0.039561015,0.00010734959,0.000042157197,0.000034864603,0.000027247164,0.000004510957,0.0007112891],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99656117,0.0012254351,0.00068602693,0.00048061894,0.00083156617,0.00021515411],"domain_scores_gemma":[0.8796597,0.11651212,0.00039030917,0.0006103858,0.0027701317,0.00005733495],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04097615,0.00007404729,0.00029432305,0.0028104759,0.00044298454,0.00040344,0.0005993942,0.00007193591,0.000035073128],"category_scores_gemma":[0.2955472,0.000059991817,0.00007178354,0.008441614,0.00011748877,0.0011054038,0.00016048954,0.00020149154,0.0000024515355],"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":[0.00021898617,0.00030598658,0.6036332,0.000047439615,0.00026199376,0.0000017869068,0.00066596206,0.000023911956,0.0013658833,0.01127777,0.03680679,0.3453903],"study_design_scores_gemma":[0.002401276,0.0010937798,0.28181025,0.00030098468,0.00025944156,0.0000043744717,0.086299405,0.06981697,0.0019435069,0.13128212,0.4242633,0.0005245891],"about_ca_topic_score_codex":0.00040304163,"about_ca_topic_score_gemma":0.00001991554,"teacher_disagreement_score":0.42102912,"about_ca_system_score_codex":0.000021720054,"about_ca_system_score_gemma":0.00019287123,"threshold_uncertainty_score":0.9875169},"labels":[],"label_agreement":null},{"id":"W4416430682","doi":"10.1177/17103568251392012","title":"Self-Assessment","year":2025,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.22205417422236798,"score_gpt":0.4786558655265343,"score_spread":0.2566016913041663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416430682","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054928593,0.00037497768,0.24564531,0.010171555,0.0017568453,0.0001402873,0.000005091755,0.00020711278,0.6867702],"genre_scores_gemma":[0.78987926,0.000042558244,0.20339336,0.004703398,0.000035142053,0.0000123449845,8.332429e-7,0.000002874379,0.0019302152],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99848115,0.00025655338,0.00038712908,0.00022283135,0.0004927289,0.00015963113],"domain_scores_gemma":[0.98861694,0.010685142,0.00010292162,0.00042775235,0.000128083,0.000039144586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021445972,0.00006544524,0.00016998168,0.00040214846,0.00013263663,0.00021020592,0.0005103548,0.000038138936,0.00038525017],"category_scores_gemma":[0.009288278,0.000047528894,0.000059532584,0.0019390482,0.000019534255,0.00012439844,0.00013475258,0.000086284264,0.00016102442],"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":[2.617714e-7,0.00002996178,0.25653198,0.000008850705,0.000017445722,0.000009975419,0.00009401697,0.000010747215,0.000011472094,0.029302252,0.35089904,0.36308396],"study_design_scores_gemma":[0.00011535381,0.000006230752,0.5768729,0.0000069441244,0.0000032054436,0.000004463609,0.00013269522,0.0023482402,0.000058384678,0.06759477,0.3528131,0.000043760843],"about_ca_topic_score_codex":0.000014260926,"about_ca_topic_score_gemma":0.0000033980655,"teacher_disagreement_score":0.73495066,"about_ca_system_score_codex":0.00003877896,"about_ca_system_score_gemma":0.00006956201,"threshold_uncertainty_score":0.99905694},"labels":[],"label_agreement":null},{"id":"W4416436875","doi":"10.1108/979-8-88730-606-320251010","title":"From Adaptive Testing to Personalized Adaptive Testing","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Adaptive control; Test (biology); Key (lock); Matching (statistics)","score_opus":0.723959688406624,"score_gpt":0.4605334489804211,"score_spread":0.26342623942620286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416436875","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024144692,0.0017042765,0.05265993,0.00027190158,0.0020400546,0.00059304986,0.00031441095,0.00060370157,0.94157124],"genre_scores_gemma":[0.0008825939,0.0000041892577,0.46648738,0.00044185488,0.0011566887,0.000018531182,0.000005637629,0.00009486808,0.5309083],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916089,0.00020211085,0.0017438532,0.0027075945,0.0029337243,0.0008037802],"domain_scores_gemma":[0.8491212,0.1468058,0.00084377365,0.0011970173,0.0015445703,0.00048760916],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0058463844,0.0009079091,0.0015645482,0.0017759642,0.00036124102,0.0007966721,0.0019198189,0.0005563851,0.004495494],"category_scores_gemma":[0.12834918,0.0006547983,0.00046539865,0.0022218283,0.00023970641,0.0002135686,0.0013804061,0.0012285267,0.006198204],"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":[0.000121775956,0.000025199495,0.00024458242,0.000010839571,0.00029602228,0.00036837414,0.00080306455,0.00012768878,0.00021136436,0.13121355,0.034767903,0.83180964],"study_design_scores_gemma":[0.0002819659,0.0007114161,0.0002681373,0.000982417,0.00015278811,0.00004193147,0.002030277,0.012305216,0.000022960863,0.8572987,0.124763586,0.0011406369],"about_ca_topic_score_codex":0.0008491687,"about_ca_topic_score_gemma":0.00003532827,"teacher_disagreement_score":0.830669,"about_ca_system_score_codex":0.00023960673,"about_ca_system_score_gemma":0.00030052362,"threshold_uncertainty_score":0.99959034},"labels":[],"label_agreement":null},{"id":"W4416524802","doi":"10.1016/b978-0-323-90509-1.00027-8","title":"Outcome measures: The properties and process of measurement","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Outcome (game theory); Process (computing); Feature (linguistics); Medical diagnosis; Relation (database)","score_opus":0.5758219924651566,"score_gpt":0.41937124903735556,"score_spread":0.15645074342780108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416524802","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013381777,0.009824508,0.0001264776,0.00033253757,0.00052429154,0.00065836584,0.000010698907,0.000032846146,0.9883565],"genre_scores_gemma":[0.022852276,0.00009067654,0.00063490536,0.0002709011,0.00012409773,0.0000367379,2.3700476e-7,0.000022964923,0.9759672],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946949,0.00023961121,0.0013662868,0.00063142,0.0028244,0.00024338388],"domain_scores_gemma":[0.9930333,0.0037432576,0.0008038463,0.0010339244,0.001313861,0.00007184546],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012208708,0.00034321976,0.00089838245,0.00047098327,0.00020735792,0.00014744585,0.0012392787,0.00020457632,0.000054076998],"category_scores_gemma":[0.027488753,0.00016594058,0.00022526228,0.00012643047,0.0004068422,0.000042413558,0.00032880768,0.00042636562,0.000011785568],"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":[0.000017946113,0.0000039384095,0.00054365396,0.000111789566,0.000070463284,0.0000015069243,0.00034515973,0.0000010620735,0.000017338352,0.0013997789,0.0002719773,0.9972154],"study_design_scores_gemma":[0.00020711847,0.00006771273,0.00049840054,0.00078491063,0.00011963637,0.00000805965,0.00027707522,0.000015569562,0.00012464476,0.10662833,0.8909843,0.0002842604],"about_ca_topic_score_codex":0.0000013834348,"about_ca_topic_score_gemma":0.000012948848,"teacher_disagreement_score":0.99693114,"about_ca_system_score_codex":0.00004227023,"about_ca_system_score_gemma":0.00023908689,"threshold_uncertainty_score":0.9807031},"labels":[],"label_agreement":null},{"id":"W4416563680","doi":"10.1002/jcsm.70122","title":"Psychometric Properties of the SarQoL Questionnaire: A Systematic Review and Meta‐Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Cachexia Sarcopenia and Muscle","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"National Institute on Aging; National Institutes of Health; Agence Nationale de la Recherche; U.S. Department of Agriculture","keywords":"Psychometrics; Psychometric testing; MEDLINE; Item response theory; Reliability (semiconductor)","score_opus":0.26166315235761817,"score_gpt":0.41753159030875264,"score_spread":0.15586843795113448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416563680","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":[0.08889409,0.9005338,0.0032703192,0.005613324,0.00024896918,0.0006768572,0.0000042444885,0.000007700486,0.0007506707],"genre_scores_gemma":[0.9915512,0.0055122264,0.0013786275,0.0007700095,0.000011087281,0.000009743109,3.0201022e-8,0.000004130132,0.000762941],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9962795,0.0010418886,0.0015252766,0.00021759095,0.0007960638,0.00013972967],"domain_scores_gemma":[0.9943058,0.0028885615,0.0014980664,0.0005218787,0.0007048157,0.00008086053],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010451633,0.00014338439,0.0019416701,0.0011862634,0.00013294003,0.00013250117,0.00070794346,0.000053608965,0.00003982181],"category_scores_gemma":[0.047721263,0.000061033774,0.000649529,0.0074507897,0.00014280269,0.00021594243,0.00017207822,0.0001929931,8.627264e-7],"study_design_candidate":"meta_analysis","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":[0.00043964476,0.001355658,0.1647513,0.3883374,0.32345995,0.000029881534,0.0038932026,0.00031457792,0.012604433,0.007279011,0.022283643,0.07525128],"study_design_scores_gemma":[0.0012953705,0.00030829216,0.30178416,0.016161796,0.66308206,0.00022053935,0.0012338015,0.00027519756,0.0010210614,0.012666351,0.0014656152,0.00048575562],"about_ca_topic_score_codex":0.000030296758,"about_ca_topic_score_gemma":0.000008010327,"teacher_disagreement_score":0.9026571,"about_ca_system_score_codex":0.000016161548,"about_ca_system_score_gemma":0.00008515687,"threshold_uncertainty_score":0.9603002},"labels":[],"label_agreement":null},{"id":"W4416685778","doi":"10.1016/j.jcjd.2025.10.028","title":"Translation, Cultural Adaptation, and Psychometric Validation of the Chinese DiAbeTes Education Questionnaire (DATE-Q-Chinese)","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; Toronto Public Health","funders":"","keywords":"Psychometric testing; Psychometrics; Diabetes mellitus; Chinese people","score_opus":0.11846744866141479,"score_gpt":0.3869456395000148,"score_spread":0.26847819083860003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416685778","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":[0.98493814,0.008272184,0.0007663467,0.0027884725,0.0021733444,0.00013338536,0.00001168285,0.000005122153,0.0009113387],"genre_scores_gemma":[0.9969456,0.000020770936,0.0025797805,0.00020706805,0.00011944691,0.000003320434,0.0000024467897,0.00000577976,0.00011577017],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99775416,0.0004620945,0.0009194635,0.0001942076,0.00045844677,0.00021164473],"domain_scores_gemma":[0.9930879,0.0040983013,0.0008157263,0.00030153932,0.0014861458,0.00021039286],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003076456,0.00014255237,0.00034016697,0.00187079,0.00026585686,0.00022672705,0.0006074136,0.00008085467,0.0000403636],"category_scores_gemma":[0.061989382,0.000079767364,0.0001400709,0.006929001,0.00017430643,0.00054298365,0.000015954438,0.00018236645,0.0000013040219],"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":[9.499355e-7,0.000011097353,0.83921534,0.000014545517,0.000022250086,3.5949014e-8,0.00034859596,0.00023792787,0.00017426681,0.00017574546,0.0010381176,0.15876111],"study_design_scores_gemma":[0.00022913498,0.000038169732,0.9592391,0.00014969545,0.000028222363,9.977e-7,0.0004100728,0.00058780314,0.00020112957,0.038242564,0.0007935107,0.000079600315],"about_ca_topic_score_codex":0.00020410802,"about_ca_topic_score_gemma":0.00069791253,"teacher_disagreement_score":0.15868151,"about_ca_system_score_codex":0.00004459296,"about_ca_system_score_gemma":0.00089344144,"threshold_uncertainty_score":0.9459119},"labels":[],"label_agreement":null},{"id":"W4416819669","doi":"10.1108/978-1-64113-953-320251002","title":"Augmented Intelligence and the Future of Item Development","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Field (mathematics); Focus (optics); Development (topology); Matching (statistics); Key (lock)","score_opus":0.4748730287517274,"score_gpt":0.41802046322958764,"score_spread":0.05685256552213974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416819669","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005796401,0.0059902873,0.05268003,0.002283812,0.0007517399,0.0002956916,0.000005435807,0.000036120084,0.93789893],"genre_scores_gemma":[0.010985475,0.0020437336,0.1459082,0.0015961416,0.0004956764,0.00001020111,0.000005005674,0.000037235626,0.8389183],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973864,0.00010406504,0.00092642114,0.00046174764,0.0010044283,0.000116964904],"domain_scores_gemma":[0.9747654,0.023920132,0.00059180777,0.00042462765,0.00022343302,0.000074603],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039994726,0.00019597169,0.00056882115,0.00024063072,0.000088637375,0.00007879993,0.0008592034,0.00014457095,0.0012125722],"category_scores_gemma":[0.012293107,0.00008935616,0.000107246065,0.0002904644,0.00025334093,0.000035759276,0.00047361152,0.0002635198,0.00006772901],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003641877,0.000001934342,0.00009981382,0.000008277465,0.000034224893,0.0000022895354,0.00023119216,0.000001079658,0.0000010423233,0.29404727,0.0034836738,0.7020528],"study_design_scores_gemma":[0.00017635421,0.000034488952,0.00048353476,0.00005079957,0.000015316034,0.000008330202,0.00077008764,0.00019881317,0.00008558251,0.28278074,0.7152304,0.00016554516],"about_ca_topic_score_codex":0.0000031888792,"about_ca_topic_score_gemma":0.00000561847,"teacher_disagreement_score":0.71174675,"about_ca_system_score_codex":0.000012616397,"about_ca_system_score_gemma":0.0000700256,"threshold_uncertainty_score":0.9997004},"labels":[],"label_agreement":null},{"id":"W4416943753","doi":"10.1002/sim.70336","title":"System of Linear Equations to Derive Unreported Test Accuracy Counts for Meta‐Analysis","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Cancer Care Ontario","funders":"","keywords":"Rounding; Sensitivity (control systems); Test (biology); Linear system; Linear model; Accuracy and precision; Linear equation; Limit (mathematics)","score_opus":0.544600576239449,"score_gpt":0.5683193730780832,"score_spread":0.023718796838634204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416943753","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":[0.00015413338,0.00035658205,0.9911566,0.00051169505,0.00036269307,0.00023498423,0.0003247438,0.000012966878,0.006885652],"genre_scores_gemma":[0.4647554,0.000016696782,0.5331714,0.00024850597,0.00004979215,0.00006696085,0.00003020908,0.0000051772445,0.0016558527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980963,0.00012628899,0.0008882932,0.00024097746,0.0005239896,0.00012413807],"domain_scores_gemma":[0.8593911,0.13914452,0.00033648548,0.00037204014,0.0007111113,0.000044747245],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0053319405,0.00007500551,0.0006769074,0.0011486056,0.000051263494,0.000010785675,0.0002905742,0.00003384147,0.00030391358],"category_scores_gemma":[0.47459623,0.000048860027,0.000074190066,0.005093323,0.00006363098,0.000018949224,0.00004274897,0.00006110648,0.000008619114],"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":[0.00011151661,0.00027481062,0.052029833,0.00052774773,0.026323138,0.00006702914,0.0019732865,0.010086912,0.0004907526,0.53373224,0.21935435,0.15502839],"study_design_scores_gemma":[0.0027058464,0.0008850005,0.06191216,0.0003170478,0.07538796,0.000005924166,0.011869711,0.5136558,0.00031533558,0.2770364,0.05527601,0.0006328308],"about_ca_topic_score_codex":0.00012568859,"about_ca_topic_score_gemma":0.000049478396,"teacher_disagreement_score":0.5035689,"about_ca_system_score_codex":0.000028109589,"about_ca_system_score_gemma":0.000068701374,"threshold_uncertainty_score":0.52982944},"labels":[],"label_agreement":null},{"id":"W4417036095","doi":"10.1177/09564624251391227","title":"Beyond the individual: Addressing structural and intersectional barriers to STBBI testing in Canada","year":2025,"lang":"en","type":"article","venue":"International Journal of STD & AIDS","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intersectionality; MEDLINE; Sexually transmitted disease; Ethnic group; Public health","score_opus":0.2637773961772312,"score_gpt":0.4449287332444088,"score_spread":0.18115133706717756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417036095","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":[0.988139,0.00026796223,0.0022491405,0.0033619895,0.0037608948,0.000052358457,0.000017427916,0.0000030230976,0.002148245],"genre_scores_gemma":[0.9866321,0.000003340774,0.011216029,0.0018800468,0.0001851378,0.0000012452251,3.564194e-7,0.0000035645671,0.00007814688],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99711543,0.00024777913,0.00082833524,0.00018731476,0.0014535178,0.00016760548],"domain_scores_gemma":[0.98474246,0.013726546,0.00043818387,0.0001214366,0.0008348324,0.00013651792],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003940523,0.000100108206,0.00021669669,0.000954438,0.00012864881,0.0003498051,0.0011817961,0.00002811942,0.00014266744],"category_scores_gemma":[0.08142539,0.00006161989,0.000050148363,0.001336576,0.00006232496,0.00026368914,0.00030043125,0.00035382505,5.847347e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051280946,0.000002865487,0.702577,0.0000010583968,0.00006581332,0.00003438353,0.0003449639,0.0015570272,0.00014341445,0.00069241977,0.0028721336,0.29165763],"study_design_scores_gemma":[0.00049982127,0.00007370851,0.9546889,0.00013471597,0.000011063844,0.00019659195,0.007119802,0.0012395248,0.00012042574,0.033665236,0.0021596544,0.00009057473],"about_ca_topic_score_codex":0.04197298,"about_ca_topic_score_gemma":0.04657321,"teacher_disagreement_score":0.29156706,"about_ca_system_score_codex":0.00030699023,"about_ca_system_score_gemma":0.0011633082,"threshold_uncertainty_score":0.97082436},"labels":[],"label_agreement":null},{"id":"W4417349448","doi":"10.1017/s1355617725101550","title":"Executive functions in Thai adolescents: Development of an inventory measure, its factors, and norms","year":2025,"lang":"en","type":"article","venue":"Journal of the International Neuropsychological Society","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Executive functions; Psychometrics; Sensitivity (control systems); Psychometric testing","score_opus":0.2865267336661949,"score_gpt":0.4323499409261793,"score_spread":0.14582320725998438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417349448","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":[0.9918024,0.00014009689,0.003405905,0.0009697741,0.002007726,0.000074218035,0.0000039764327,0.000005171032,0.0015907587],"genre_scores_gemma":[0.99657387,0.000023534862,0.0023719564,0.0007029156,0.000047555644,0.0000010198819,2.4789233e-7,0.0000028974305,0.00027601392],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973722,0.00038245184,0.0009393258,0.00020364123,0.0009768538,0.00012552933],"domain_scores_gemma":[0.99673337,0.0018311107,0.00071596605,0.00017606546,0.00048125267,0.00006223769],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003950272,0.00010671389,0.00025533387,0.0001928509,0.000101456615,0.00006572924,0.0011749553,0.00008008234,0.000037393896],"category_scores_gemma":[0.017667253,0.00005203654,0.00023186913,0.00092850416,0.000112384136,0.00021012124,0.00026119515,0.00044302567,9.996232e-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":[0.00015472416,0.00039475982,0.976507,0.000004435268,0.000065237866,0.000002958461,0.0007395656,0.00008907155,0.0036984498,0.00015652108,0.0025551538,0.015632136],"study_design_scores_gemma":[0.00051912735,0.000059857048,0.99162567,0.00008451881,0.000005895094,0.000014414662,0.0013219463,0.0001862675,0.000353314,0.003673842,0.0021041294,0.000051037645],"about_ca_topic_score_codex":0.000003105734,"about_ca_topic_score_gemma":0.000004270313,"teacher_disagreement_score":0.015581098,"about_ca_system_score_codex":0.000073487434,"about_ca_system_score_gemma":0.00008113154,"threshold_uncertainty_score":0.9906074},"labels":[],"label_agreement":null},{"id":"W4417416251","doi":"10.3389/fpsyg.2025.1727202","title":"Investigating the factor structure of the Montreal Cognitive Assessment: a qualitative review","year":2025,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Montreal Cognitive Assessment; Cognition; Equivalence (formal languages); Interpretation (philosophy); Factorial; Factor (programming language)","score_opus":0.31241044914770294,"score_gpt":0.5553296543094292,"score_spread":0.24291920516172621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417416251","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":[0.4545147,0.07423299,0.32748085,0.03730045,0.01864619,0.003001938,0.000383233,0.00006682692,0.08437284],"genre_scores_gemma":[0.94222116,0.0010450261,0.04555505,0.010761448,0.00004532948,0.00003072262,0.0000028499296,0.000009756959,0.00032862843],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9931944,0.004616999,0.00091316615,0.0004881822,0.00052486657,0.00026238905],"domain_scores_gemma":[0.97943527,0.01884136,0.0007072673,0.00072701357,0.0002557645,0.000033325112],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0046865377,0.00015200513,0.0005639916,0.000343691,0.0001439194,0.00002940835,0.0013874669,0.00011879996,0.00009028623],"category_scores_gemma":[0.08321785,0.00007254203,0.00013916333,0.004357508,0.0006478135,0.00007496613,0.00020013863,0.0005401704,0.0000012377712],"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":[0.00001750489,0.000034474982,0.4155353,0.00006059998,0.0000819528,0.0000010465892,0.0035181805,0.0000035978478,0.00015601986,0.0011218974,0.106821395,0.47264802],"study_design_scores_gemma":[0.0004504143,0.000033851124,0.5776324,0.0005355045,0.00002407278,0.0000026499579,0.0077403123,0.00012299935,0.000030257526,0.41171604,0.0016326393,0.00007884809],"about_ca_topic_score_codex":0.00006270077,"about_ca_topic_score_gemma":0.00004093076,"teacher_disagreement_score":0.48770648,"about_ca_system_score_codex":0.000030204012,"about_ca_system_score_gemma":0.00011034527,"threshold_uncertainty_score":0.9245046},"labels":[],"label_agreement":null},{"id":"W4417417655","doi":"10.31234/osf.io/r4dhw_v1","title":"Creation and validation of the LEVANTE core tasks: Internationalized measures of learning and development for children ages 5-12 years","year":2025,"lang":"","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Set (abstract data type); Reliability (semiconductor); Core (optical fiber); Sample (material); Measure (data warehouse); Cognition; Selection (genetic algorithm)","score_opus":0.3646703116239629,"score_gpt":0.45679231335893855,"score_spread":0.09212200173497564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417417655","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":[0.8792033,0.0013070109,0.11727653,0.00019477941,0.00029221296,0.00048814685,0.000009536143,0.000008642861,0.0012198357],"genre_scores_gemma":[0.95810294,0.0003286253,0.03935153,0.00002206357,0.000012204428,0.000009146386,0.0000049803193,0.0000042349293,0.002164282],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978135,0.00031909143,0.0008296224,0.00033225078,0.000583914,0.000121579586],"domain_scores_gemma":[0.98673797,0.011955628,0.00068574544,0.00015362717,0.00044066264,0.000026382357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005361973,0.00011565688,0.0003217268,0.00045792275,0.00018565277,0.000095718446,0.00028913852,0.000076529745,0.000061150866],"category_scores_gemma":[0.051577,0.000076315744,0.00006024758,0.00070385856,0.00020467874,0.00012059775,0.00024893784,0.00008980821,2.8275338e-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":[0.00006262535,0.000022666545,0.58581764,0.000028579037,0.00008743557,2.480123e-8,0.0007011305,0.00009386611,0.0011616076,0.001155058,0.00013343646,0.41073596],"study_design_scores_gemma":[0.0010369152,0.000068791014,0.9749577,0.00025297122,0.000046151523,0.00000185196,0.0012406935,0.0012965007,0.012734072,0.006135633,0.0021390647,0.00008967014],"about_ca_topic_score_codex":0.00006157754,"about_ca_topic_score_gemma":0.000011027749,"teacher_disagreement_score":0.4106463,"about_ca_system_score_codex":0.00002091778,"about_ca_system_score_gemma":0.00012037259,"threshold_uncertainty_score":0.95641196},"labels":[],"label_agreement":null},{"id":"W4417427433","doi":"10.1177/00131644251393483","title":"From Linear Geometry to Nonlinear and Information-Geometric Settings in Test Theory: Bregman Projections as a Unifying Framework","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"University of British Columbia","funders":"","keywords":"Bregman divergence; Nonlinear system; Hilbert space; Projection (relational algebra); Regular polygon; Reliability (semiconductor); Statistical hypothesis testing; Space (punctuation); Information geometry","score_opus":0.3273493193826945,"score_gpt":0.4780451314572261,"score_spread":0.1506958120745316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417427433","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":[0.9125359,0.0012527809,0.03357979,0.03878924,0.0014262393,0.00063343265,0.000043721153,0.000051476196,0.011687394],"genre_scores_gemma":[0.903976,0.000076760625,0.08863826,0.006647179,0.0002766061,0.0000971403,0.00000860051,0.0000046630876,0.0002747508],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972195,0.00030925198,0.00071217975,0.0005544957,0.00093757844,0.00026700323],"domain_scores_gemma":[0.97482055,0.023876686,0.00019157269,0.00037294472,0.00055376283,0.0001844526],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006965682,0.0001703374,0.00027901176,0.0018338719,0.00028287838,0.00028233533,0.00037695753,0.00014689563,0.00035503414],"category_scores_gemma":[0.21938342,0.00012111362,0.000045638513,0.0069537843,0.000094729905,0.00030278793,0.00014470425,0.00036421805,0.00008496165],"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":[0.00014418375,0.00092099025,0.46303105,0.000022905408,0.000045467677,0.0000013658318,0.0014034162,0.000057253208,0.00012467502,0.023860395,0.010863899,0.49952438],"study_design_scores_gemma":[0.00026581218,0.00015228173,0.74267113,0.00010731186,0.000007871962,0.000005242238,0.0014758051,0.000065096545,0.000016404601,0.22270276,0.03239162,0.00013865979],"about_ca_topic_score_codex":0.000104383806,"about_ca_topic_score_gemma":0.0000051559127,"teacher_disagreement_score":0.49938574,"about_ca_system_score_codex":0.00007499878,"about_ca_system_score_gemma":0.00010764068,"threshold_uncertainty_score":0.78719205},"labels":[],"label_agreement":null},{"id":"W4417447051","doi":"10.1080/0969594x.2025.2602452","title":"The validity of the assessment for learning measurement instrument for Ethiopian middle school mathematics teachers","year":2025,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","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":"University of Calgary","funders":"","keywords":"Measure (data warehouse); Reliability (semiconductor); Test validity; Test (biology)","score_opus":0.596064082416965,"score_gpt":0.5664535415641934,"score_spread":0.029610540852771594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417447051","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":[0.28895298,0.00079216197,0.34001386,0.26662776,0.004841681,0.0067486526,0.000024966124,0.000058972902,0.09193895],"genre_scores_gemma":[0.69831854,0.0003085405,0.29673377,0.0011803183,0.00013808892,0.00067629974,0.00000231742,0.000010619681,0.0026314943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957099,0.0017945943,0.00097567687,0.0003464481,0.0008991339,0.00027424653],"domain_scores_gemma":[0.892214,0.10457654,0.0014000052,0.0007401768,0.0009897684,0.000079487836],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038727444,0.00014027888,0.00024411967,0.00028681758,0.00071141095,0.00033017536,0.00066457957,0.000081037884,0.0000060171183],"category_scores_gemma":[0.34798747,0.00008251938,0.00010374053,0.0011471267,0.00010683187,0.0003339389,0.00021588035,0.00038026416,4.486896e-7],"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":[0.000049366772,0.0007329295,0.09627533,0.00016061879,0.00010323967,3.339102e-8,0.0021087714,0.0005693522,0.0003483622,0.66519296,0.0017895194,0.23266952],"study_design_scores_gemma":[0.00065108866,0.00014174613,0.26266718,0.00017868791,0.0000782771,0.0000034445175,0.047581524,0.0032219568,0.00023170505,0.16073868,0.5243675,0.00013820162],"about_ca_topic_score_codex":0.00019328117,"about_ca_topic_score_gemma":0.00007542888,"teacher_disagreement_score":0.522578,"about_ca_system_score_codex":0.00048256415,"about_ca_system_score_gemma":0.0033231059,"threshold_uncertainty_score":0.9898324},"labels":[],"label_agreement":null},{"id":"W68437104","doi":"10.1007/978-3-319-07794-9_1","title":"Setting the Stage for Validity and Validation in Social, Behavioral, and Health Sciences: Trends in Validation Practices","year":2014,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":32,"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":"Sketch; Psychology; Construct validity; Validity; Behavioural sciences; Test validity; External validity; Criterion validity; Applied psychology; Medical education; Psychometrics; Social psychology; Clinical psychology; Medicine; Computer science; Psychotherapist","score_opus":0.8435949426545746,"score_gpt":0.6445421174829625,"score_spread":0.19905282517161205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W68437104","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":[0.8145671,0.0023360692,0.00093001587,0.07910376,0.001041788,0.0046184203,0.00063995953,0.00016325034,0.096599646],"genre_scores_gemma":[0.93729067,0.0016917284,0.004826807,0.00024584454,0.0013103783,0.00029837765,0.00014119425,0.000091114074,0.054103915],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99275106,0.0024666765,0.0009932794,0.00091879594,0.002210629,0.0006595519],"domain_scores_gemma":[0.9789871,0.018446686,0.0019405852,0.00025173996,0.00027115786,0.00010270888],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07836369,0.00024295911,0.00062407576,0.003360026,0.0028246907,0.0011812341,0.0007424218,0.00037473996,0.00008974711],"category_scores_gemma":[0.024299959,0.0001771371,0.00008619211,0.002225595,0.0018440514,0.00061586744,0.00044065696,0.00096123246,0.000002289973],"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":[0.00013468822,0.0000753375,0.09529574,0.00019494566,0.000022343675,0.000004892947,0.017188225,0.000003199948,0.000023104276,0.17622538,0.015316405,0.69551575],"study_design_scores_gemma":[0.001265368,0.0016736026,0.17827883,0.00024560734,0.00003287451,0.0000072724065,0.03307884,0.00010787512,0.00011551912,0.5012495,0.28303903,0.00090566184],"about_ca_topic_score_codex":0.00061540795,"about_ca_topic_score_gemma":0.000635606,"teacher_disagreement_score":0.69461006,"about_ca_system_score_codex":0.00022105673,"about_ca_system_score_gemma":0.00045284812,"threshold_uncertainty_score":0.99985564},"labels":[],"label_agreement":null},{"id":"W6885941200","doi":"10.1371/journal.pone.0278863.s008","title":"Comparison of Rasch analysis results of current multi-center study in Ontario, Canada and previous single-center study in Ontario, Canada [17].","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rasch model; Current (fluid); Item response theory; Current Population Survey; Statistical analysis","score_opus":0.6279651513220251,"score_gpt":0.47251499246218326,"score_spread":0.15545015885984187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6885941200","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":[0.98786974,0.00009678249,0.0000011724168,0.000013388672,0.00022892299,0.00084240874,0.010721676,0.000009210154,0.00021669858],"genre_scores_gemma":[0.9976921,3.8136992e-7,0.000087996144,0.0000130136805,0.0000064815304,0.000051858155,0.0018102668,0.000007878606,0.00033000036],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949473,0.0006363905,0.0017702171,0.00075224385,0.0014962928,0.00039755553],"domain_scores_gemma":[0.9918652,0.006245255,0.0007589601,0.00069500937,0.00031071334,0.00012481783],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017830369,0.0002243348,0.0010658479,0.0010460663,0.000056402034,0.000060123126,0.00072739384,0.000048191534,0.00516018],"category_scores_gemma":[0.020882878,0.00018155799,0.00007813993,0.0045315656,0.000010028555,0.000094862335,0.00048425666,0.0004182605,0.00000300029],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059169484,0.0014014691,0.9297405,0.000013427648,0.00008037213,0.000044603254,0.0033725216,0.000763943,8.294988e-7,1.8535639e-8,0.062056325,0.002466851],"study_design_scores_gemma":[0.0031208987,0.00021275207,0.98489493,0.00023644252,0.000031008996,5.5318395e-7,0.004843412,0.0008513985,0.000004950329,0.0000016877057,0.0056439787,0.00015796605],"about_ca_topic_score_codex":0.9997215,"about_ca_topic_score_gemma":0.9999997,"teacher_disagreement_score":0.056412347,"about_ca_system_score_codex":0.00088785985,"about_ca_system_score_gemma":0.0015942687,"threshold_uncertainty_score":0.99574924},"labels":[],"label_agreement":null},{"id":"W6889002749","doi":"10.25384/sage.7550930","title":"Supplementary – Supplemental material for Applying Item Response Theory Analysis to the Montreal Cognitive Assessment in a Low-Education Older Population","year":2019,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Item response theory; Montreal Cognitive Assessment; Cognition; Population; Cognitive Assessment System; Differential item functioning; Psychometrics; Social cognitive theory","score_opus":0.24256000707659153,"score_gpt":0.5079373494936699,"score_spread":0.26537734241707833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889002749","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":[0.92335135,0.00018161772,0.05718874,0.001796235,0.000856511,0.0017495175,0.014807124,0.000008619952,0.000060284878],"genre_scores_gemma":[0.9827429,0.00003550882,0.013321372,0.0005690938,0.00020488992,0.0001454243,0.0028110105,0.000012009978,0.000157793],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9946635,0.0023430092,0.0010140144,0.0006448537,0.0009865263,0.00034809508],"domain_scores_gemma":[0.9732952,0.024874566,0.0005447618,0.0010314859,0.00015462578,0.00009935646],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03553667,0.00015640407,0.00037998866,0.0012468175,0.00021984939,0.00057612784,0.0013179809,0.000049074053,0.014339254],"category_scores_gemma":[0.015569665,0.00010045387,0.00011270961,0.0025617646,0.000015871037,0.0005249444,0.0005836961,0.00017254187,0.000013227215],"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":[0.0010968391,0.00014132232,0.50960577,0.0000054871716,0.00019471944,0.000002754047,0.0006396671,0.0001822319,0.000552666,0.000012946997,0.003944531,0.48362103],"study_design_scores_gemma":[0.0008652944,0.00008684955,0.9739762,0.00013436525,0.0001677743,0.000006196563,0.01642283,0.0038329086,0.000065444925,0.003088557,0.0012081179,0.00014546633],"about_ca_topic_score_codex":0.0010842833,"about_ca_topic_score_gemma":0.0011249437,"teacher_disagreement_score":0.48347557,"about_ca_system_score_codex":0.00012768985,"about_ca_system_score_gemma":0.00013244519,"threshold_uncertainty_score":0.993118},"labels":[],"label_agreement":null},{"id":"W6889031353","doi":"10.25384/sage.22154450","title":"Supplemental Material - Confirmatory Factor Analysis of the WJ IV Cognitive: What Does the Standard Battery Measure at School Age?","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Measure (data warehouse); Confirmatory factor analysis; Battery (electricity); Statistical analysis; Reliability (semiconductor)","score_opus":0.45477831724627876,"score_gpt":0.4843643910240474,"score_spread":0.029586073777768618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889031353","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":[0.9606759,0.0020205395,0.0012887226,0.00294344,0.0027914145,0.0003068308,0.029810555,0.00003523714,0.000127353],"genre_scores_gemma":[0.9960199,0.0023929074,0.0002492587,0.0004851523,0.00025307396,0.000006123944,0.0001966781,0.00001506375,0.0003818589],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931117,0.0021032302,0.0011146676,0.00053680467,0.0027305423,0.0004030044],"domain_scores_gemma":[0.98145074,0.015197008,0.0009852581,0.0019365157,0.00028592424,0.0001445694],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016099356,0.00019567442,0.0006131488,0.0006947892,0.0006109886,0.0014523925,0.003609458,0.00007840119,0.041361086],"category_scores_gemma":[0.04186675,0.00007970847,0.0002800441,0.004685577,0.00026271574,0.0011067287,0.0025431532,0.00032306957,0.000070602524],"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":[0.00029924663,0.000047282934,0.5968438,0.000015057451,0.0021827912,0.00009179678,0.0011160466,0.000032110547,0.013679679,0.0000024183394,0.0856764,0.30001336],"study_design_scores_gemma":[0.0006982248,0.000035403755,0.96276623,0.00035899543,0.0005695065,0.000020842697,0.015997503,0.00030189284,0.0025450261,0.00079272426,0.015708044,0.00020558086],"about_ca_topic_score_codex":0.00005130226,"about_ca_topic_score_gemma":0.0002904504,"teacher_disagreement_score":0.36592245,"about_ca_system_score_codex":0.00005298403,"about_ca_system_score_gemma":0.00010307446,"threshold_uncertainty_score":0.9995842},"labels":[],"label_agreement":null},{"id":"W6893219940","doi":"10.5281/zenodo.15649819","title":"Signal Cancellation Recovery of Factors","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"SIGNAL (programming language); LISREL; Signal processing; Signal transfer function; Covariance matrix; Factor (programming language); Matrix (chemical analysis)","score_opus":0.37789424876922134,"score_gpt":0.40068588016699397,"score_spread":0.022791631397772627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893219940","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":[0.43918663,0.001044754,0.1338361,0.0008222712,0.0012230631,0.0004568332,0.00035436102,0.0012107372,0.42186525],"genre_scores_gemma":[0.99688065,0.000053055337,0.00095562055,0.000020570493,0.00010501357,6.53037e-9,0.00010359865,0.00030836498,0.0015731086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766815,0.00053482625,0.0004148784,0.00039932888,0.0007738477,0.00020896851],"domain_scores_gemma":[0.99640816,0.0024852408,0.00013629076,0.00035714396,0.00052366575,0.000089516674],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0036252248,0.00008776909,0.00015779454,0.00067744526,0.0006229214,0.0008912922,0.000923917,0.00004956035,0.020843955],"category_scores_gemma":[0.025263308,0.00006960084,0.000078830606,0.0024431378,0.0000999967,0.0002868906,0.0004929224,0.00016834213,0.0017100885],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032189775,0.0000298523,0.00012239857,0.0000337229,0.00002977093,0.0000060448037,0.00082582847,0.00044391138,0.0061895964,0.0030565653,0.16756292,0.8216672],"study_design_scores_gemma":[0.00010809774,0.00018942716,0.00588869,0.00003706523,0.000007446876,0.000020969112,0.0006143688,0.0024795139,0.0013257522,0.006974625,0.9822449,0.00010912169],"about_ca_topic_score_codex":0.000020630301,"about_ca_topic_score_gemma":1.472614e-7,"teacher_disagreement_score":0.82155806,"about_ca_system_score_codex":0.00007029928,"about_ca_system_score_gemma":0.000005687481,"threshold_uncertainty_score":0.9990672},"labels":[],"label_agreement":null},{"id":"W6902147676","doi":"10.6084/m9.figshare.21251702","title":"Additional file 1 of Item response theory and differential test functioning analysis of the HBSC-Symptom-Checklist across 46 countries","year":2022,"lang":"en","type":"article","venue":"Open MIND","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Brock University","funders":"","keywords":"Residual; Table (database); Goodness of fit; Studentized residual; Residual entropy","score_opus":0.1895350037679794,"score_gpt":0.42861101257650974,"score_spread":0.23907600880853033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902147676","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":[0.6999239,0.00002894853,0.00013762982,0.00007059701,0.00012962816,0.00010691997,0.29713264,0.0000011585989,0.0024686006],"genre_scores_gemma":[0.9746008,0.0000014681419,0.0043061497,0.00006339005,0.000037077963,0.00009261146,0.0016910223,0.000008327783,0.019199166],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9965219,0.0014960396,0.00054881454,0.0003556911,0.00091700535,0.00016055898],"domain_scores_gemma":[0.7617899,0.23677853,0.000695873,0.000492654,0.00020324081,0.00003977905],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007665607,0.00009214706,0.00036306964,0.00030120838,0.0006561779,0.00022953909,0.0010036909,0.00003378029,0.83228105],"category_scores_gemma":[0.18148088,0.00005944414,0.00014732112,0.0033629388,0.00032529354,0.00013818519,0.0013223685,0.00013779843,0.0000122001675],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025437372,0.0002474244,0.09399536,0.000004773622,0.0006263256,0.0000053206086,0.0035126354,0.00059098017,0.0010921638,0.00014624691,0.764031,0.13320404],"study_design_scores_gemma":[0.00021874678,0.00010071884,0.7164949,0.000016410962,0.000092534356,0.000006751037,0.0063895113,0.00083374034,0.00019437377,0.0007505287,0.2748122,0.0000895629],"about_ca_topic_score_codex":0.000021717906,"about_ca_topic_score_gemma":0.00002577913,"teacher_disagreement_score":0.8322689,"about_ca_system_score_codex":0.000025635598,"about_ca_system_score_gemma":0.00011550894,"threshold_uncertainty_score":0.8254138},"labels":[],"label_agreement":null},{"id":"W6902148283","doi":"10.6084/m9.figshare.14881029","title":"Additional file 4 of Assessing the performance of a method for case-mix adjustment in the Korean Diagnosis-Related Groups (KDRG) system and its policy implications","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Data collection; Sample (material); Government (linguistics); Table (database)","score_opus":0.3697618199718948,"score_gpt":0.46805288057837746,"score_spread":0.09829106060648268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902148283","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004864858,0.0005069124,0.000039705406,0.00038360688,0.00002498099,0.0003379846,0.9923705,0.000010477271,0.0014610012],"genre_scores_gemma":[0.71516776,0.00002066201,0.047449347,0.00038591973,0.00026485123,0.007416622,0.22900537,0.000025625683,0.0002638431],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9981992,0.0005575285,0.0005137583,0.00024588307,0.00033092184,0.00015268335],"domain_scores_gemma":[0.8594671,0.13928595,0.0004488206,0.00034351455,0.0004259934,0.000028647102],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012297407,0.00008424074,0.00021602295,0.0001849779,0.00018686813,0.000068337424,0.00038059065,0.000057064874,0.244228],"category_scores_gemma":[0.15222421,0.0000461889,0.00008315987,0.0020996889,0.000013318136,0.00013477972,0.00013242532,0.00010453931,0.000014119127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017062707,0.000035354806,0.0001673743,0.00010727392,0.0000140649945,0.0000065875465,0.00029533892,0.00006630467,0.000011065524,0.0004896533,0.94572926,0.053076014],"study_design_scores_gemma":[0.0008086723,0.00023802329,0.7101254,0.0061390577,0.000051011688,0.0026274838,0.017513251,0.07736224,0.0007291003,0.0031563267,0.18087353,0.0003759263],"about_ca_topic_score_codex":0.000011450272,"about_ca_topic_score_gemma":0.000010271936,"teacher_disagreement_score":0.76485574,"about_ca_system_score_codex":0.00002821223,"about_ca_system_score_gemma":0.00015017061,"threshold_uncertainty_score":0.85491693},"labels":[],"label_agreement":null},{"id":"W6902149645","doi":"10.6084/m9.figshare.19367432","title":"Additional file 3 of Using linear and natural cubic splines, SITAR, and latent trajectory models to characterise nonlinear longitudinal growth trajectories in cohort studies","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Saskatchewan; Children's Hospital of Eastern Ontario","funders":"","keywords":"Trajectory; Nonlinear system; Latent growth modeling; Latent variable; Log-linear model; Longitudinal data","score_opus":0.46458698036661256,"score_gpt":0.41375436502923396,"score_spread":0.050832615337378595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902149645","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24001512,0.0008631931,0.0000025783088,0.000029032959,0.00009072237,0.00018194047,0.75877166,0.000016687209,0.000029049752],"genre_scores_gemma":[0.5247591,0.000060219343,0.079563595,0.00042106115,0.0006684496,0.0013411128,0.3924123,0.00007108263,0.0007030778],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.997882,0.00018718,0.00050646596,0.0004971589,0.0006983825,0.00022880615],"domain_scores_gemma":[0.9828701,0.016250648,0.00025616938,0.00018612378,0.00035293962,0.00008401046],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053185615,0.0001627592,0.00043797182,0.00049498613,0.00020689558,0.00004412585,0.0002655744,0.000038897266,0.42711717],"category_scores_gemma":[0.041731235,0.00013455715,0.000060530423,0.0013272752,0.000031144787,0.00025063698,0.00052720663,0.00024049467,0.000010996781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010559446,0.000081000515,0.012264607,0.00008968592,0.0000715019,0.000056919915,0.0008206294,0.0014297386,0.00006945162,0.0000037182924,0.98073083,0.004276314],"study_design_scores_gemma":[0.0005836168,0.00030980955,0.87786996,0.0010648072,0.000025656542,0.00014746709,0.0026823475,0.08081748,0.000053122134,0.0009960277,0.034841456,0.00060822215],"about_ca_topic_score_codex":0.000027162703,"about_ca_topic_score_gemma":0.000020675341,"teacher_disagreement_score":0.94588935,"about_ca_system_score_codex":0.000054839846,"about_ca_system_score_gemma":0.00007678223,"threshold_uncertainty_score":0.96634066},"labels":[],"label_agreement":null},{"id":"W6902155463","doi":"10.6084/m9.figshare.14881026.v1","title":"Additional file 3 of Assessing the performance of a method for case-mix adjustment in the Korean Diagnosis-Related Groups (KDRG) system and its policy implications","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sample (material); Data collection; Government (linguistics); Table (database)","score_opus":0.36796613395005184,"score_gpt":0.4675532896902662,"score_spread":0.09958715574021437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902155463","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048810923,0.0005044775,0.0000394116,0.00038382565,0.000025171505,0.0003372857,0.99235535,0.000010450572,0.0014629473],"genre_scores_gemma":[0.71098363,0.000020977348,0.048123036,0.00039139084,0.00027156877,0.007529253,0.23237683,0.000026023103,0.00027729844],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99819934,0.0005576007,0.000513578,0.00024585906,0.00033094257,0.00015266644],"domain_scores_gemma":[0.8594598,0.13928352,0.00044946474,0.00034388603,0.00043461143,0.00002869151],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012287714,0.00008423498,0.0002159728,0.00018489332,0.00018677674,0.000068301684,0.00038031559,0.00005706013,0.2473048],"category_scores_gemma":[0.15401952,0.00004618027,0.00008315354,0.0020999522,0.000013315783,0.00013476035,0.0001323757,0.0001045425,0.000014408439],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016816026,0.000035182595,0.00016627631,0.00010763367,0.000014003181,0.0000065363556,0.00029375457,0.00006693247,0.000011185666,0.0004706593,0.945942,0.052884154],"study_design_scores_gemma":[0.00080855354,0.00023315394,0.7042496,0.0060999384,0.000050432354,0.002590432,0.01739062,0.07679025,0.0007411338,0.0031125143,0.18755902,0.00037432712],"about_ca_topic_score_codex":0.000011551127,"about_ca_topic_score_gemma":0.000010230665,"teacher_disagreement_score":0.75997853,"about_ca_system_score_codex":0.000028319388,"about_ca_system_score_gemma":0.00015072606,"threshold_uncertainty_score":0.8531065},"labels":[],"label_agreement":null},{"id":"W6902159610","doi":"10.6084/m9.figshare.14314051.v1","title":"Additional file 2 of Cross-sectional trend analysis of the NCHA II survey data on Canadian post-secondary student mental health and wellbeing from 2013 to 2019","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Trend analysis; Table (database); Mental health; Data collection; Data file; Missing data","score_opus":0.42282885653717595,"score_gpt":0.46926499258703047,"score_spread":0.046436136049854526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902159610","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026507609,0.00023424032,3.2407124e-7,0.0002670231,0.00012009325,0.00007864641,0.97216207,0.0000034675948,0.0006265078],"genre_scores_gemma":[0.01636616,0.0000025515199,0.00073600264,0.00063438417,0.000040964893,0.000013858726,0.98130333,0.000004768696,0.0008979572],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9975476,0.00042949434,0.0004969254,0.00051330746,0.0008316229,0.00018102964],"domain_scores_gemma":[0.9700873,0.028188154,0.0003651845,0.0007837273,0.0003539707,0.0002216747],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079795095,0.000092604445,0.00029935536,0.00046894245,0.0003023937,0.000114662005,0.00087840104,0.00004882892,0.9592244],"category_scores_gemma":[0.08554132,0.0000668176,0.00009138814,0.002336707,0.00001897538,0.00012610512,0.00078495836,0.00012342393,0.000075173324],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066238367,0.000023751509,0.030731196,0.0000022602771,0.000096647826,9.84803e-7,0.00010339238,0.000054301006,0.0000021052126,5.242895e-7,0.9652695,0.0037086916],"study_design_scores_gemma":[0.000062119456,0.000036988098,0.7715835,0.00008731304,0.0000033402578,0.0000011414947,0.00016122316,0.00021569247,0.0000031989177,0.000015529118,0.22778022,0.000049731767],"about_ca_topic_score_codex":0.02375566,"about_ca_topic_score_gemma":0.24677506,"teacher_disagreement_score":0.95914924,"about_ca_system_score_codex":0.00005341296,"about_ca_system_score_gemma":0.00074971275,"threshold_uncertainty_score":0.98274523},"labels":[],"label_agreement":null},{"id":"W6902194365","doi":"10.6084/m9.figshare.11769705.v1","title":"Additional file 1 of Cross-cultural adaptions and measurement properties of the WORC (Western Ontario rotator cuff index): a systematic review","year":2020,"lang":"en","type":"article","venue":"Open MIND","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Rotator cuff; Cuff; MEDLINE; Rotator cuff injury","score_opus":0.7347246835947294,"score_gpt":0.4502659886831301,"score_spread":0.2844586949115993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902194365","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":[0.7903965,0.026786562,0.00045921025,0.005029843,0.0007137931,0.016395126,0.12348492,0.000016350114,0.036717653],"genre_scores_gemma":[0.96735394,0.00004984814,0.022512155,0.0007976568,0.000074718504,0.0008881456,0.00018282849,0.000017224467,0.008123508],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9974566,0.00035398323,0.0007944748,0.0002515261,0.0010441571,0.00009925276],"domain_scores_gemma":[0.9950935,0.0029890013,0.00075373315,0.00034151002,0.0007555659,0.0000666645],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019376626,0.00009227099,0.00049893506,0.000035287456,0.00010247024,0.0002266747,0.0008749892,0.000027914493,0.1668061],"category_scores_gemma":[0.10075381,0.0000435776,0.00009091357,0.0006250039,0.00016554233,0.00028497522,0.0003923906,0.00009750358,0.000054746462],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013845041,0.00022222383,0.023376346,0.02060089,0.0003220615,0.0000045256434,0.0072448314,0.00005480664,0.0007030969,0.000024769657,0.92509294,0.022215044],"study_design_scores_gemma":[0.001577122,0.0006147469,0.27143386,0.37955606,0.0004537917,0.00010794793,0.0067174993,0.0006539986,0.0020184615,0.0008920563,0.33504465,0.0009298279],"about_ca_topic_score_codex":0.00021585923,"about_ca_topic_score_gemma":0.0009829216,"teacher_disagreement_score":0.5900483,"about_ca_system_score_codex":0.00003112927,"about_ca_system_score_gemma":0.00022127973,"threshold_uncertainty_score":0.90682095},"labels":[],"label_agreement":null},{"id":"W6902298125","doi":"10.6084/m9.figshare.5726347.v1","title":"MOESM2 of Health-related quality of life for First Nations and Caucasian women in the First Nations Bone Health Study","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Quality of life (healthcare); Mental health; Bone health; Public health; Quality (philosophy); Developing country; Physical health; Component (thermodynamics)","score_opus":0.7013253069096399,"score_gpt":0.5423756454059079,"score_spread":0.15894966150373202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902298125","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":[0.7876297,0.0032241703,0.00011388141,0.0444567,0.00041935986,0.0058389828,0.15004893,0.00006284716,0.008205428],"genre_scores_gemma":[0.99881566,0.000011792175,0.00041666208,0.00012767423,0.000016116117,0.0002470738,0.0002913084,0.000005333342,0.00006837819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99695396,0.00059877726,0.0012931775,0.0002972535,0.0005841026,0.00027270618],"domain_scores_gemma":[0.93854797,0.057398558,0.002503639,0.0010156742,0.00041065176,0.00012353553],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0114341965,0.00009172349,0.0005247617,0.00051716313,0.0014653984,0.00011314941,0.0007944579,0.000050214338,0.0017086811],"category_scores_gemma":[0.47997475,0.00006174367,0.000059821232,0.001207325,0.00003383374,0.00016105686,0.0001635439,0.00011149316,0.0000069662533],"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":[0.00013431952,0.0021872416,0.6237996,0.0019227063,0.00015064266,0.0000033346207,0.11143143,0.00033056358,0.000001193131,0.002303435,0.1880227,0.0697128],"study_design_scores_gemma":[0.00072792434,0.00023788925,0.9813996,0.00023597917,0.0000010311978,9.493745e-7,0.010188301,0.0001819556,3.8389692e-7,0.0018091829,0.005155323,0.00006145715],"about_ca_topic_score_codex":0.00088910374,"about_ca_topic_score_gemma":0.016088605,"teacher_disagreement_score":0.46854055,"about_ca_system_score_codex":0.000056307592,"about_ca_system_score_gemma":0.0002637533,"threshold_uncertainty_score":0.99983454},"labels":[],"label_agreement":null},{"id":"W6902311744","doi":"10.6084/m9.figshare.21251702.v1","title":"Additional file 1 of Item response theory and differential test functioning analysis of the HBSC-Symptom-Checklist across 46 countries","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Brock University","funders":"","keywords":"Residual; Table (database); Goodness of fit; Studentized residual; Residual entropy","score_opus":0.1756125989108217,"score_gpt":0.3907214699556246,"score_spread":0.21510887104480292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902311744","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038025506,0.00007029968,0.000011909278,0.000034712546,0.000071078146,0.00006943328,0.96109986,0.000015328013,0.0006018655],"genre_scores_gemma":[0.68071115,8.233081e-7,0.0004256072,0.00019541608,0.000087678665,0.00045677106,0.31032124,0.000016158263,0.007785167],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9968962,0.001098113,0.00047447722,0.00030815843,0.0010503257,0.00017270233],"domain_scores_gemma":[0.62877196,0.36942834,0.0008238441,0.0005442398,0.00038290862,0.000048691367],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018976991,0.000100218844,0.00031327404,0.00034548284,0.00058975775,0.00009825998,0.0006091306,0.00004153992,0.9872156],"category_scores_gemma":[0.5070058,0.00006636913,0.00021477691,0.0036657562,0.00007742038,0.000090301575,0.00077025,0.00016572389,0.000029075974],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015997444,0.00002485873,0.0031960271,0.0000067290125,0.00008180135,9.652836e-7,0.00023960372,0.00012173597,0.000030129293,0.000014822569,0.99392253,0.002200798],"study_design_scores_gemma":[0.0001049502,0.000056831544,0.6925662,0.00008580749,0.000034183435,0.0000047539393,0.0014706725,0.00093751587,0.000040907435,0.00040396003,0.30421892,0.0000753119],"about_ca_topic_score_codex":0.0000043758446,"about_ca_topic_score_gemma":0.000006616674,"teacher_disagreement_score":0.9871865,"about_ca_system_score_codex":0.000027811597,"about_ca_system_score_gemma":0.00009111809,"threshold_uncertainty_score":0.49714687},"labels":[],"label_agreement":null},{"id":"W6902333412","doi":"10.6084/m9.figshare.14881023.v1","title":"Additional file 2 of Assessing the performance of a method for case-mix adjustment in the Korean Diagnosis-Related Groups (KDRG) system and its policy implications","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Diagram; Government (linguistics); Set (abstract data type); Data collection","score_opus":0.36426351411385594,"score_gpt":0.4674472825357802,"score_spread":0.10318376842192428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902333412","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004818092,0.00051008165,0.00003840172,0.000383941,0.00002509677,0.00033694736,0.99238926,0.000010468657,0.0014877339],"genre_scores_gemma":[0.7032458,0.000021472322,0.048220415,0.00039641818,0.0002756751,0.0076169907,0.23992066,0.000026301868,0.00027622445],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9981993,0.00055794354,0.00051357725,0.00024578488,0.0003307958,0.00015262316],"domain_scores_gemma":[0.8601268,0.13862127,0.00044983256,0.00034361688,0.00042978596,0.000028678724],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012227974,0.00008422056,0.00021600258,0.00018483614,0.0001868058,0.00006830815,0.00038034449,0.000057065216,0.24841398],"category_scores_gemma":[0.15252098,0.000046177138,0.00008314311,0.0020991303,0.000013314675,0.00013474842,0.00013245152,0.00010454006,0.000014107547],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016460344,0.00003483106,0.00015929977,0.00010571145,0.000013872591,0.0000065645395,0.0002909994,0.00006654261,0.000010672971,0.0004767807,0.9458508,0.05298227],"study_design_scores_gemma":[0.0008061484,0.00023442102,0.7005893,0.0060628336,0.000050899278,0.002630204,0.017365938,0.07647299,0.00072409713,0.0031397978,0.19154839,0.00037497576],"about_ca_topic_score_codex":0.000011535847,"about_ca_topic_score_gemma":0.000010221397,"teacher_disagreement_score":0.75430244,"about_ca_system_score_codex":0.000028217426,"about_ca_system_score_gemma":0.00014999235,"threshold_uncertainty_score":0.8546177},"labels":[],"label_agreement":null},{"id":"W6904654419","doi":"10.1371/journal.pone.0307367.s003","title":"Study quality assessment using the Newcastle-Ottawa Scale.","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Quality assessment; Risk assessment; Data collection; Work (physics)","score_opus":0.9015665323254481,"score_gpt":0.6385000775069511,"score_spread":0.263066454818497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6904654419","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":[0.6674638,0.005875414,0.006016515,0.0039818874,0.007422069,0.0037658012,0.1365264,0.0014881077,0.16746002],"genre_scores_gemma":[0.9928328,6.0172147e-7,0.004931115,0.00020341678,0.00038408634,0.00006282905,0.0003875253,0.000017281478,0.0011803936],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99600637,0.0011593297,0.000606456,0.0005610783,0.0014002952,0.00026647968],"domain_scores_gemma":[0.9567027,0.041735988,0.00020161027,0.0009947406,0.00027245114,0.000092530085],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0061913184,0.0001360986,0.00024170185,0.00022881624,0.00028631667,0.0011166184,0.0010295586,0.000051488307,0.08609752],"category_scores_gemma":[0.08258769,0.0000707344,0.00014204692,0.0027221285,0.000012151301,0.00021895922,0.000431169,0.00029783093,0.000999617],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000406698,0.00012107144,0.03242624,0.000036807738,0.00005134619,0.00008287357,0.0011547317,0.00024257445,0.00007842562,0.00012922389,0.7380962,0.22757645],"study_design_scores_gemma":[0.00023591866,0.00013742354,0.6808836,0.00043720283,0.000021233136,0.000042560067,0.010957346,0.012176972,0.000029182645,0.005527041,0.28922296,0.00032861088],"about_ca_topic_score_codex":0.000048521986,"about_ca_topic_score_gemma":0.000027488008,"teacher_disagreement_score":0.6484573,"about_ca_system_score_codex":0.0000565366,"about_ca_system_score_gemma":0.00012948558,"threshold_uncertainty_score":0.9999203},"labels":[],"label_agreement":null},{"id":"W6906392579","doi":"10.17605/osf.io/8ycj9","title":"Reliability of a domain-general adaptation of the Downs-Black (1998) tool: Pre-analytic plan","year":2021,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Reliability (semiconductor); Plan (archaeology); Adaptation (eye); Consistency (knowledge bases); Institution","score_opus":0.17141529564177904,"score_gpt":0.3805614041884226,"score_spread":0.20914610854664356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6906392579","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15087071,0.000011785532,0.0111920955,0.00009869053,0.0009566165,0.0010611631,0.00009664486,0.00006551841,0.83564675],"genre_scores_gemma":[0.0808538,0.000079931655,0.02724736,0.00004878354,0.00013516066,0.00005493806,0.000016533877,0.00011458712,0.8914489],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98854554,0.0038320734,0.0021196348,0.0028504608,0.002214096,0.0004381944],"domain_scores_gemma":[0.97211426,0.014075965,0.0030784637,0.010097769,0.00048921024,0.00014432016],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.023031374,0.00044541055,0.0013615157,0.0006154465,0.00009944399,0.00011107131,0.0037027416,0.0005528283,0.31771955],"category_scores_gemma":[0.15082066,0.00031707608,0.0007837977,0.0022097449,0.0006305921,0.00009648764,0.002523032,0.0006327153,0.031280793],"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":[0.00044536646,0.0012127347,0.41267893,0.0010713584,0.0010279374,0.00002935181,0.0065344465,0.023167275,0.005244222,0.0032580765,0.4523125,0.09301778],"study_design_scores_gemma":[0.0011874955,0.0000063536686,0.42522004,0.00086244335,0.0002770453,0.000038209237,0.0013044119,0.00546517,0.0016218224,0.06241468,0.50071406,0.000888298],"about_ca_topic_score_codex":0.0015730788,"about_ca_topic_score_gemma":0.0002607537,"teacher_disagreement_score":0.28643876,"about_ca_system_score_codex":0.00013477719,"about_ca_system_score_gemma":0.00037940854,"threshold_uncertainty_score":0.9999281},"labels":[],"label_agreement":null},{"id":"W6917822303","doi":"10.58052/ieltw001p","title":"QRND9162591 Core Quarter Round Igneous>Rock Dolerite","year":2017,"lang":"en","type":"other","venue":"System for Earth Sample Registration (SESAR)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Core (optical fiber); Quarter (Canadian coin); Window (computing); Margin (machine learning)","score_opus":0.46630133260493783,"score_gpt":0.46043253269994305,"score_spread":0.0058687999049947814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6917822303","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008536933,0.0015112485,0.473435,0.00018874404,0.0057018464,0.0020034383,0.0016227603,0.0005672764,0.5148843],"genre_scores_gemma":[0.022223841,0.000065427725,0.050315004,0.00007996338,0.003117317,0.00020275812,0.00037135062,0.00035870163,0.92326564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994283,0.00042367217,0.0014037933,0.0014423657,0.0017616246,0.0006854944],"domain_scores_gemma":[0.98143846,0.011121591,0.0037208542,0.0029503067,0.0005150279,0.0002537596],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051093725,0.00059613143,0.0013141333,0.0008937414,0.00061681075,0.0013531245,0.0017504718,0.0006958328,0.0010640654],"category_scores_gemma":[0.031760957,0.00046604584,0.00053655804,0.00062529545,0.0001250155,0.00023796935,0.00010254285,0.00028052134,0.00048462418],"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":[0.000051791816,0.000033308315,0.0012323393,0.00039267947,0.000097823075,0.000015177592,0.00006825692,0.000026048305,0.000040409384,0.003760099,0.96443415,0.029847912],"study_design_scores_gemma":[0.0006470729,0.00023439653,0.00063885556,0.0006146635,0.00005269999,0.00007521196,0.00052502373,0.0008154197,0.000014525861,0.002360329,0.99348205,0.00053974596],"about_ca_topic_score_codex":0.0012442382,"about_ca_topic_score_gemma":0.0015543174,"teacher_disagreement_score":0.42312002,"about_ca_system_score_codex":0.000069224254,"about_ca_system_score_gemma":0.00025064315,"threshold_uncertainty_score":0.9998491},"labels":[],"label_agreement":null},{"id":"W6920832006","doi":"10.6084/m9.figshare.19367432.v1","title":"Additional file 3 of Using linear and natural cubic splines, SITAR, and latent trajectory models to characterise nonlinear longitudinal growth trajectories in cohort studies","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Saskatchewan; Children's Hospital of Eastern Ontario","funders":"","keywords":"Trajectory; Nonlinear system; Latent growth modeling; Latent variable; Log-linear model; Longitudinal data","score_opus":0.46458698036661256,"score_gpt":0.41375436502923396,"score_spread":0.050832615337378595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920832006","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24001512,0.0008631931,0.0000025783088,0.000029032959,0.00009072237,0.00018194047,0.75877166,0.000016687209,0.000029049752],"genre_scores_gemma":[0.5247591,0.000060219343,0.079563595,0.00042106115,0.0006684496,0.0013411128,0.3924123,0.00007108263,0.0007030778],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.997882,0.00018718,0.00050646596,0.0004971589,0.0006983825,0.00022880615],"domain_scores_gemma":[0.9828701,0.016250648,0.00025616938,0.00018612378,0.00035293962,0.00008401046],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053185615,0.0001627592,0.00043797182,0.00049498613,0.00020689558,0.00004412585,0.0002655744,0.000038897266,0.42711717],"category_scores_gemma":[0.041731235,0.00013455715,0.000060530423,0.0013272752,0.000031144787,0.00025063698,0.00052720663,0.00024049467,0.000010996781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010559446,0.000081000515,0.012264607,0.00008968592,0.0000715019,0.000056919915,0.0008206294,0.0014297386,0.00006945162,0.0000037182924,0.98073083,0.004276314],"study_design_scores_gemma":[0.0005836168,0.00030980955,0.87786996,0.0010648072,0.000025656542,0.00014746709,0.0026823475,0.08081748,0.000053122134,0.0009960277,0.034841456,0.00060822215],"about_ca_topic_score_codex":0.000027162703,"about_ca_topic_score_gemma":0.000020675341,"teacher_disagreement_score":0.94588935,"about_ca_system_score_codex":0.000054839846,"about_ca_system_score_gemma":0.00007678223,"threshold_uncertainty_score":0.96634066},"labels":[],"label_agreement":null},{"id":"W6920960324","doi":"10.6084/m9.figshare.23151898","title":"R-squared Measures for Multilevel Models with Three or More Levels","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variance (accounting); Multilevel model; Set (abstract data type); Software; Cover (algebra); Computation","score_opus":0.9168830139217934,"score_gpt":0.5397385958164479,"score_spread":0.3771444181053455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920960324","genre_codex":"dataset","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":[0.0139259035,0.0005776504,0.19551507,0.0017473181,0.00084497774,0.0037167983,0.7725607,0.0020563928,0.0090552075],"genre_scores_gemma":[0.7966799,0.000004231083,0.1716749,0.0009531105,0.0007090462,0.0025158864,0.013394143,0.00017117591,0.01389759],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720865,0.00008918404,0.0004225682,0.000622428,0.0011941196,0.00046305222],"domain_scores_gemma":[0.96944785,0.028757812,0.000243726,0.0006898073,0.0007270606,0.00013373858],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014384792,0.00018990715,0.00035116784,0.0004531764,0.00024146681,0.00023726832,0.0010228187,0.0001088573,0.020984307],"category_scores_gemma":[0.17862503,0.00010525571,0.0001194372,0.0025591874,0.000015020891,0.00031051066,0.00019832469,0.00011895437,0.00079643057],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011954008,0.000016819511,0.0003853768,0.000040213068,0.000026264506,0.000024001436,0.00032723983,0.0061005987,0.000023901577,0.00004680599,0.6315313,0.36135796],"study_design_scores_gemma":[0.0027767932,0.0005228325,0.16407484,0.0013729379,0.000023112523,0.000037597285,0.001930143,0.59375197,0.00053344265,0.06746743,0.1665119,0.0009970192],"about_ca_topic_score_codex":0.000008155698,"about_ca_topic_score_gemma":0.000041525236,"teacher_disagreement_score":0.782754,"about_ca_system_score_codex":0.00002122452,"about_ca_system_score_gemma":0.00012998098,"threshold_uncertainty_score":0.9999816},"labels":[],"label_agreement":null},{"id":"W6921215727","doi":"10.6084/m9.figshare.26994757.v1","title":"Additional file 1 of A scoping review to create a framework for the steps in developing condition-specific preference-based instruments de novo or from an existing non-preference-based instrument: use of item response theory or Rasch analysis","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University Health Network; SickKids Foundation; University of Toronto; Canadian Centre for Applied Research in Cancer Control; Children's Hospital of Eastern Ontario","funders":"","keywords":"Key (lock); Identification (biology); Field (mathematics); Measure (data warehouse); Item response theory; Data collection; Troubleshooting","score_opus":0.7542516777462331,"score_gpt":0.4943969300381246,"score_spread":0.2598547477081085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921215727","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009696587,0.00047507114,0.020713327,0.00013698253,0.000063104344,0.0013041692,0.9675222,0.00004657486,0.000041999865],"genre_scores_gemma":[0.05366568,0.000091503935,0.6076496,0.0016960538,0.000121442215,0.0067638312,0.32970467,0.00006004238,0.0002471395],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9952844,0.0013319516,0.0013516472,0.00076630595,0.0008905053,0.00037519887],"domain_scores_gemma":[0.6557164,0.34224916,0.0006583887,0.00073240243,0.0005250791,0.00011858889],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027581272,0.00026330998,0.00076629524,0.0011995747,0.00018663186,0.00032761748,0.0009890887,0.00015076902,0.76420873],"category_scores_gemma":[0.38408348,0.00016110075,0.0002411611,0.00739459,0.000039866132,0.0003417754,0.00017086363,0.00025708752,0.000055567525],"study_design_candidate":"systematic_review","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":[0.0071723647,0.0002527613,0.0016467241,0.005650815,0.0006591887,0.000060754955,0.0009675237,0.0025504422,0.000054715572,0.0002569175,0.6209412,0.3597866],"study_design_scores_gemma":[0.0011778917,0.00072666584,0.10289534,0.74779713,0.0002192331,0.0000056788876,0.00092270237,0.033888742,0.000940828,0.005564095,0.10496123,0.0009004589],"about_ca_topic_score_codex":0.00001923844,"about_ca_topic_score_gemma":0.00009267777,"teacher_disagreement_score":0.7641532,"about_ca_system_score_codex":0.00014271533,"about_ca_system_score_gemma":0.0015741718,"threshold_uncertainty_score":0.6569498},"labels":[],"label_agreement":null},{"id":"W6923021097","doi":"10.1371/journal.pntd.0009370.s003","title":"Adapted Newcastle-Ottawa Scale for study quality assessment.","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Quality (philosophy); Measure (data warehouse); Data quality; Data collection","score_opus":0.8615850576735453,"score_gpt":0.6085436327446481,"score_spread":0.25304142492889725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923021097","genre_codex":"dataset","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":[0.22687916,0.0013206168,0.0143578695,0.0029491568,0.0033298577,0.004395434,0.52140266,0.0008848744,0.22448035],"genre_scores_gemma":[0.8928396,0.0000010201549,0.082436174,0.0007031183,0.00050723576,0.000559777,0.013030385,0.000039886338,0.009882812],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9963854,0.00084259687,0.0007090831,0.0006929913,0.0010569806,0.0003129269],"domain_scores_gemma":[0.95230293,0.044849772,0.00040715773,0.0010239726,0.0012682041,0.00014798132],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033438113,0.00013923347,0.00040337574,0.00016604243,0.00022740207,0.00036749622,0.00071458286,0.00007585431,0.15359785],"category_scores_gemma":[0.2972306,0.00010786986,0.00017889081,0.0020137308,0.0000058438595,0.00018488792,0.0003248294,0.00015462772,0.0004883022],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012080766,0.0003007185,0.04021476,0.000023062827,0.000024635245,0.000021606997,0.00019239164,0.000031771688,0.00011387437,0.00004691873,0.84161294,0.117405236],"study_design_scores_gemma":[0.00093996705,0.00017917393,0.67015386,0.00008994384,0.000009128277,0.000008118155,0.0052677994,0.0009752652,0.00019391507,0.003735849,0.3182015,0.0002454802],"about_ca_topic_score_codex":0.0000134595075,"about_ca_topic_score_gemma":0.00008175457,"teacher_disagreement_score":0.66596043,"about_ca_system_score_codex":0.000032410437,"about_ca_system_score_gemma":0.00017574422,"threshold_uncertainty_score":0.8471759},"labels":[],"label_agreement":null},{"id":"W6923504793","doi":"10.1371/journal.pone.0319107.s004","title":"Quality of studies based on Newcastle-Ottawa Scale scores.","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Scale (ratio); Quality (philosophy); Measure (data warehouse); Data quality; Field (mathematics)","score_opus":0.8284011746559903,"score_gpt":0.5988554886124963,"score_spread":0.229545686043494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923504793","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11715983,0.012328614,0.002457767,0.006156638,0.0038424386,0.0018773485,0.20871201,0.00064535224,0.64682],"genre_scores_gemma":[0.9849972,0.0000037878667,0.00911834,0.001398228,0.00008771024,0.00006847226,0.0007817467,0.000010040117,0.0035344614],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9974341,0.00048824615,0.0006705484,0.00039654112,0.0008224372,0.00018816927],"domain_scores_gemma":[0.92632437,0.071516424,0.00044923628,0.00089484587,0.0007579259,0.000057171175],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00263841,0.00011318116,0.000420089,0.00049307145,0.000100039855,0.000056283847,0.0007114117,0.00006385579,0.025422724],"category_scores_gemma":[0.45189798,0.00007665265,0.00014761947,0.002534134,0.000026554591,0.000067553876,0.00020464088,0.00011928867,0.00034089963],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002827531,0.000049945247,0.026112134,0.000117930176,0.000015613929,0.0000018762704,0.00005187179,0.0003129875,0.000042737876,0.000098660195,0.8828373,0.09033065],"study_design_scores_gemma":[0.0009227155,0.00016923097,0.86750156,0.0027961114,0.0000074144377,5.3021273e-7,0.0009681798,0.0028013452,0.0026226968,0.015398869,0.10653366,0.00027765994],"about_ca_topic_score_codex":0.000012506309,"about_ca_topic_score_gemma":0.0000174547,"teacher_disagreement_score":0.86783737,"about_ca_system_score_codex":0.000026522961,"about_ca_system_score_gemma":0.00008390689,"threshold_uncertainty_score":0.97546816},"labels":[],"label_agreement":null},{"id":"W6924561728","doi":"10.15468/dl.nm7qvu","title":"Occurrence Download","year":2023,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type); Order (exchange)","score_opus":0.2694676753159741,"score_gpt":0.3851025895720681,"score_spread":0.11563491425609401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924561728","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002854252,0.00002806817,0.00004307104,0.0002512937,0.0027670267,0.00024944145,0.99595827,0.00019502401,0.00022239664],"genre_scores_gemma":[0.000002147273,0.00008348475,0.000014652892,0.00037924884,0.0000031330958,0.0000028705447,0.9995136,1.3267156e-8,7.945008e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953694,0.00041408712,0.0010510716,0.00048774094,0.0022383002,0.00043941557],"domain_scores_gemma":[0.9933588,0.0034535215,0.0009371828,0.0012444232,0.00077577255,0.00023033845],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005789419,0.00030846405,0.0005254589,0.0005530041,0.00042191937,0.00062784733,0.0021574078,0.00043179846,0.0015141744],"category_scores_gemma":[0.074766874,0.00025222386,0.00027769263,0.0038201571,0.00021509021,0.0011061999,0.0010687776,0.0003957469,0.7420728],"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":[0.000023325441,0.000013528295,0.003487557,0.000026890817,0.000016357713,0.0000032577802,0.000016834882,0.000017781746,7.931516e-9,1.1195525e-7,0.98163563,0.014758715],"study_design_scores_gemma":[0.00020930922,0.000033068118,0.0016563758,0.0000019648312,0.0000199829,0.0000043080704,0.00035142925,5.785459e-7,3.0662062e-7,0.00005561853,0.997407,0.00026005824],"about_ca_topic_score_codex":0.0008064898,"about_ca_topic_score_gemma":0.000016662772,"teacher_disagreement_score":0.7405587,"about_ca_system_score_codex":0.00021300402,"about_ca_system_score_gemma":0.00016020522,"threshold_uncertainty_score":0.999993},"labels":[],"label_agreement":null},{"id":"W6926227009","doi":"10.18739/a2b56d65b","title":"Bias-Corrected Gridded Soil Temperatures (North of 30°N) Between 1982-2023 at 0.05° Resolution","year":2025,"lang":"en","type":"dataset","venue":"California Digital Library","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Permafrost; Moderate-resolution imaging spectroradiometer; Mean squared error; Soil water; Snowmelt; Snow; Linear regression; Vegetation (pathology)","score_opus":0.1790492808892814,"score_gpt":0.35260123582002734,"score_spread":0.17355195493074593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926227009","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016812496,0.0010281134,0.000061353625,0.00020092113,0.0015354671,0.0003555932,0.97708476,0.00017407068,0.0027472267],"genre_scores_gemma":[0.0016993312,0.00013338987,0.00040352085,0.00030820837,0.00065829774,0.000022191118,0.99220204,0.000030397,0.0045425976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933067,0.0006328833,0.002199399,0.0013590307,0.0018055962,0.0006963972],"domain_scores_gemma":[0.9678059,0.028197538,0.0014511407,0.00197019,0.00024574637,0.00032946956],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012537115,0.00066675583,0.0015379507,0.0018918642,0.00033897455,0.0014143398,0.0028027769,0.0006424606,0.00091111974],"category_scores_gemma":[0.07106163,0.00048682626,0.00056265504,0.00598827,0.0004345346,0.0008761565,0.0024521467,0.0008320973,0.00064079865],"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":[0.00009076599,0.000058106216,0.027901236,0.00010738532,0.000080615384,0.000044303248,0.000005163896,0.000023279661,0.0000023304347,0.0000031786594,0.961548,0.010135647],"study_design_scores_gemma":[0.00032687452,0.000115432995,0.007105333,0.00023762156,0.000059994632,0.000012687488,0.00003874483,0.000039895138,0.00013653393,0.0016407404,0.9897972,0.00048895343],"about_ca_topic_score_codex":0.000047949175,"about_ca_topic_score_gemma":0.000010477954,"teacher_disagreement_score":0.069807924,"about_ca_system_score_codex":0.0000717523,"about_ca_system_score_gemma":0.0005791856,"threshold_uncertainty_score":0.99975836},"labels":[],"label_agreement":null},{"id":"W6926717338","doi":"10.25384/sage.22799747.v1","title":"sj-pdf-1-mde-10.1177_23821205231170522 - Supplemental material for An Approach to Leadership Development and Patient Safety and Quality Improvement Education in the Context of Professional Identity Formation in Pre-Clinical Medical Students","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Context (archaeology); Patient safety; Quality management; Identity (music); Quality (philosophy); Professional development","score_opus":0.6883830368634372,"score_gpt":0.5692269942670025,"score_spread":0.11915604259643464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926717338","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":[0.9889744,0.000022327358,0.00007803412,0.00035376567,0.00026596646,0.0015842816,0.0086090835,0.000011133316,0.00010103358],"genre_scores_gemma":[0.9813735,0.000002427005,0.0020153325,0.00060906267,0.00005569233,0.00054839114,0.015283274,0.0000060024477,0.000106346786],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955286,0.0008240144,0.0013818138,0.00040691797,0.0016166324,0.00024205427],"domain_scores_gemma":[0.994312,0.004851286,0.0003638634,0.0002140775,0.00014617265,0.000112593596],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00997249,0.000112973896,0.0002838589,0.00028017268,0.00011330996,0.00015122548,0.0006344634,0.00010340864,0.006055278],"category_scores_gemma":[0.029981904,0.000075094016,0.000032533357,0.0006740734,0.000021494106,0.00038623632,0.0004674689,0.00012552278,0.00002388358],"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":[0.00061188807,0.001121035,0.057046276,0.00032866717,0.000013762691,8.435423e-7,0.017680865,0.000004530801,0.00004864573,0.000101895115,0.09791032,0.82513124],"study_design_scores_gemma":[0.0011422962,0.00027235044,0.9500112,0.00026094684,0.0000020860089,0.0000018727739,0.036796786,0.00035796754,0.00017264251,0.0002906689,0.0105693,0.00012187252],"about_ca_topic_score_codex":0.00005702374,"about_ca_topic_score_gemma":0.000341735,"teacher_disagreement_score":0.89296496,"about_ca_system_score_codex":0.00005682601,"about_ca_system_score_gemma":0.00017993379,"threshold_uncertainty_score":0.9948533},"labels":[],"label_agreement":null},{"id":"W6927991318","doi":"10.34943/e20177f6-cf69-42fe-aa16-fde67813e25a","title":"Strait of Georgia East Hydrophone Deployed 2017-11-01","year":2017,"lang":"en","type":"dataset","venue":"Ocean Networks Canada Society","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Hydrophone; Underwater; Sound (geography); Waveform; Data logger; Software deployment","score_opus":0.1899856313795851,"score_gpt":0.38373441765404703,"score_spread":0.19374878627446193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927991318","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011458938,0.001794263,0.0012639787,0.00034043944,0.005332789,0.0003281916,0.9896011,0.00003996493,0.000153391],"genre_scores_gemma":[0.016494162,0.001488146,0.0065820897,0.001363187,0.0030433037,0.000010363613,0.96761554,0.00012195684,0.003281247],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926481,0.00048589736,0.0015684183,0.001258163,0.0030090064,0.0010303677],"domain_scores_gemma":[0.982995,0.009819268,0.0029089248,0.0033606265,0.00044625334,0.0004699372],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0061137364,0.00063245604,0.0015506747,0.00015011238,0.00073059456,0.0003671738,0.004779424,0.00078215875,0.00036600998],"category_scores_gemma":[0.01453108,0.0005079529,0.00071628083,0.0013108613,0.00047792343,0.00016810183,0.0007468671,0.0011671174,0.0000036796475],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011264057,0.000029401865,0.0010497874,0.000036528825,0.00013772848,0.000046003857,0.000021216878,0.0021572968,7.322389e-7,0.0000018260764,0.99385756,0.0026506763],"study_design_scores_gemma":[0.00041018013,0.000041888386,0.0043809395,0.00011276702,0.000096060045,0.00002287929,0.00029829165,0.0030432723,0.0000010494031,0.0002672744,0.9907991,0.000526256],"about_ca_topic_score_codex":0.3886312,"about_ca_topic_score_gemma":0.4613041,"teacher_disagreement_score":0.07267291,"about_ca_system_score_codex":0.0003234636,"about_ca_system_score_gemma":0.0026425545,"threshold_uncertainty_score":0.9997372},"labels":[],"label_agreement":null},{"id":"W6929001914","doi":"10.3886/e108684v1","title":"Assessment of nutritional status of children of pastoralists in a humanitarian setting: A Cross-sectional Standardized Monitoring and Assessment of Relief and Transitions Survey","year":2017,"lang":"en","type":"dataset","venue":"ICPSR Data Holdings","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Research Foundation","funders":"","keywords":"Malnutrition; Breastfeeding; Anthropometry; Cluster (spacecraft); Pastoralism; Cluster sampling; Systematic sampling; Malnutrition in children","score_opus":0.4389408955306592,"score_gpt":0.5500030242652029,"score_spread":0.11106212873454369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929001914","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39421478,0.00039408257,0.00020996989,0.000009628727,0.00022382906,0.00023244975,0.6046951,0.000003324978,0.00001684506],"genre_scores_gemma":[0.45855007,0.0010750523,0.034949522,0.000002532898,0.00008118868,0.000013419308,0.5053102,0.000014200792,0.000003861629],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940063,0.0007652926,0.001990716,0.0009359423,0.0019648222,0.0003369244],"domain_scores_gemma":[0.98529625,0.009212779,0.0028009685,0.0017682371,0.0007990432,0.00012272158],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015855674,0.00027924325,0.0012709752,0.0011740604,0.00018097853,0.00020672208,0.0014819716,0.00025296074,0.00006695246],"category_scores_gemma":[0.02087692,0.00025512962,0.0001009005,0.00071629084,0.0006854964,0.0005460563,0.0008604626,0.0004978088,9.3225204e-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":[0.00007171581,0.00025535622,0.9693935,0.00020889012,0.00011525388,0.0000024124695,0.000033301247,0.000011791714,0.00034049148,0.000060357597,0.02882848,0.00067843444],"study_design_scores_gemma":[0.001420925,0.00021989214,0.9932278,0.00041781532,0.00004888301,0.000007799393,0.00006893147,0.00005151212,0.000040942392,0.00060552306,0.003701369,0.00018861459],"about_ca_topic_score_codex":0.0062924307,"about_ca_topic_score_gemma":0.00026057288,"teacher_disagreement_score":0.09938494,"about_ca_system_score_codex":0.00008302992,"about_ca_system_score_gemma":0.00055880303,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W6929055621","doi":"10.4232/1.10057","title":"European Values Study 2008: Ukraine (EVS 2008)","year":2010,"lang":"en","type":"dataset","venue":"GESIS Data Archive","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Politics; Criticism; Work (physics); Perception; Quarter (Canadian coin); Metadata; Compensation (psychology)","score_opus":0.5698541062626197,"score_gpt":0.5032059975689199,"score_spread":0.06664810869369975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929055621","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003160777,0.00059024175,0.0012348503,0.00023860371,0.0025579347,0.0006911426,0.9905726,0.00009756334,0.0037009967],"genre_scores_gemma":[0.000035426667,0.0005952785,0.026144257,0.0003092738,0.0014739949,0.00001542112,0.97074884,0.000047234684,0.0006302941],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98600554,0.0055677034,0.0017677416,0.0028554222,0.0029369704,0.00086662243],"domain_scores_gemma":[0.93071705,0.05418724,0.0014533657,0.012973829,0.000256575,0.00041193885],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.027259551,0.0006760176,0.0012657949,0.0018577683,0.0005706136,0.0008964935,0.01699051,0.00019722083,0.0029963097],"category_scores_gemma":[0.25196114,0.00047658038,0.00019423041,0.0021973117,0.00038689683,0.00045183708,0.010442665,0.0018704291,0.0044892523],"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":[0.000029654933,0.00028216894,0.00054201524,0.000009944494,0.00010230342,0.00021161065,0.00012144377,0.0000021440346,0.000007650138,0.0000012673569,0.9224401,0.07624968],"study_design_scores_gemma":[0.00045194605,0.00024372102,0.025146903,0.00003680437,0.00014452323,0.00003691283,0.00058537343,0.000051953404,9.270358e-7,0.0016078657,0.9711602,0.0005328954],"about_ca_topic_score_codex":0.001414891,"about_ca_topic_score_gemma":0.0010425433,"teacher_disagreement_score":0.22470158,"about_ca_system_score_codex":0.000017677488,"about_ca_system_score_gemma":0.00016867318,"threshold_uncertainty_score":0.9997686},"labels":[],"label_agreement":null},{"id":"W6929096184","doi":"10.4230/lipics.approx/random.2022","title":"LIPIcs, Volume 245, APPROX/RANDOM 2022, Complete Volume","year":2022,"lang":"en","type":"other","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Volume (thermodynamics); Work (physics); Compression (physics); Ventricular volume","score_opus":0.19952734369764433,"score_gpt":0.3852000474209052,"score_spread":0.18567270372326086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929096184","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000749609,0.0015208579,0.11473107,0.00072655175,0.014257541,0.0045289816,0.0126563,0.0011265577,0.84970254],"genre_scores_gemma":[0.0011342274,0.00025408593,0.066708386,0.0021707588,0.0018633954,0.0005992741,0.0029940791,0.0009018099,0.923374],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98882836,0.000603556,0.0038255074,0.0012003465,0.0038045612,0.0017376893],"domain_scores_gemma":[0.9860359,0.005941126,0.00375422,0.0032039941,0.0005330921,0.00053165655],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008969307,0.0011816042,0.0024389925,0.0029031814,0.00084446836,0.0012558078,0.005186393,0.00086981436,0.03541953],"category_scores_gemma":[0.020782273,0.0009722991,0.0011678721,0.002919338,0.00044300235,0.00066955725,0.0021535202,0.001780624,0.0028594087],"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":[0.00013411503,0.00018302846,0.011370408,0.00029996864,0.0002367813,0.00001073068,0.0009730448,0.000049399572,0.0000018236093,0.0004526727,0.9508229,0.03546515],"study_design_scores_gemma":[0.0038750742,0.00032293287,0.00061374897,0.000111018926,0.00009774118,0.00006897487,0.0024850592,0.015377594,0.0000015028834,0.0018976491,0.97403985,0.0011088304],"about_ca_topic_score_codex":0.00015209444,"about_ca_topic_score_gemma":0.000055658158,"teacher_disagreement_score":0.07367145,"about_ca_system_score_codex":0.0002920172,"about_ca_system_score_gemma":0.00021517345,"threshold_uncertainty_score":0.999781},"labels":[],"label_agreement":null},{"id":"W6929503750","doi":"10.48660/25020029","title":"What gravity induced entanglement can tell us about gravity","year":2025,"lang":"en","type":"other","venue":"PIRSA","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Waterloo","funders":"","keywords":"Quantum entanglement; Noise (video); Gravitation; Action (physics); Intersection (aeronautics)","score_opus":0.2887531586535422,"score_gpt":0.448492630779557,"score_spread":0.1597394721260148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929503750","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01184447,0.005026193,0.0018387994,0.00083850947,0.017792642,0.0008990541,0.00022978752,0.00038643373,0.9611441],"genre_scores_gemma":[0.017032187,0.0013189757,0.0085588405,0.0013839134,0.0009065181,0.00004901509,0.00003524908,0.00017500052,0.9705403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951556,0.00061795046,0.000808723,0.0011765193,0.0016697355,0.0005715162],"domain_scores_gemma":[0.9909619,0.006154459,0.00084503833,0.0016442817,0.00018717353,0.00020712614],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046102055,0.00043024076,0.00095852447,0.0013877514,0.00014723063,0.0007002606,0.001751528,0.00042339662,0.005419674],"category_scores_gemma":[0.018619763,0.00032026347,0.00027987733,0.0024440547,0.000095113086,0.00010818053,0.00058096304,0.0005066,0.000367631],"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":[0.00001542024,0.00009509793,0.036214978,0.00003174445,0.000078371384,0.000028485307,0.00010794438,0.0000010936058,0.00005143333,0.00045075838,0.61323136,0.3496933],"study_design_scores_gemma":[0.00031400775,0.00007070575,0.03721452,0.00027162491,0.00004153948,0.0000033700217,0.00030720833,0.000008318519,0.00015013412,0.013584143,0.94763756,0.00039686332],"about_ca_topic_score_codex":0.003603373,"about_ca_topic_score_gemma":0.001731119,"teacher_disagreement_score":0.34929645,"about_ca_system_score_codex":0.00013213232,"about_ca_system_score_gemma":0.0002218437,"threshold_uncertainty_score":0.99992496},"labels":[],"label_agreement":null},{"id":"W6929926639","doi":"10.5281/zenodo.11530799","title":"Pineal Guardian Brain Support Drops Official Website| Price Update| Special Offer!","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Guardian; Feeling; Mental state; Rest (music); Melatonin; Mental illness","score_opus":0.20936698337844814,"score_gpt":0.38521115265598405,"score_spread":0.1758441692775359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929926639","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009399086,0.00024144609,0.0054663825,0.0019291942,0.0022198225,0.0005607683,0.0009845266,0.0015898179,0.98691404],"genre_scores_gemma":[0.00156608,0.00018051532,0.0027272778,0.0008043771,0.010189393,9.7548806e-8,0.0016770895,0.01132992,0.97152525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933724,0.0014063583,0.000872093,0.0014624961,0.0020696863,0.0008170088],"domain_scores_gemma":[0.99607706,0.0010028398,0.0005519435,0.001389145,0.0005976926,0.0003813089],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006819094,0.0004174335,0.00064264174,0.0023509464,0.0009842932,0.0030246652,0.0036662105,0.00035287277,0.3334482],"category_scores_gemma":[0.048704084,0.00036711048,0.00024617085,0.003987376,0.00031686245,0.00017875218,0.0029578083,0.00084113464,0.18339042],"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":[0.000033611217,0.00005687963,0.0000031789552,0.000043006632,0.000064010244,0.00008385222,0.00023767907,0.0000031083466,0.00004486777,0.0022650212,0.8591669,0.13799787],"study_design_scores_gemma":[0.00032515769,0.00021757574,0.000219299,0.00006635071,0.000025683465,0.00014186422,0.00026521453,0.00006663837,0.000009069123,0.002275411,0.9959947,0.0003930757],"about_ca_topic_score_codex":0.000038727074,"about_ca_topic_score_gemma":0.0000029535154,"teacher_disagreement_score":0.15005778,"about_ca_system_score_codex":0.00017718463,"about_ca_system_score_gemma":0.000026166277,"threshold_uncertainty_score":0.9998781},"labels":[],"label_agreement":null},{"id":"W6929988978","doi":"10.5281/zenodo.1181920","title":"Ruthwell_Cross_Runes_East_Line_13_17_3D","year":2018,"lang":"en","type":"other","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Rendering (computer graphics); 3d model; Software; 3D rendering","score_opus":0.6103618608549277,"score_gpt":0.5040327159943805,"score_spread":0.10632914486054723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929988978","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.2115013e-7,0.00083154027,0.000032877306,0.000028952085,0.0007936824,0.00015922061,0.14341636,0.0003728443,0.8543641],"genre_scores_gemma":[0.000012549116,0.0000032436424,0.0039401683,0.00017283011,0.002475862,0.000045956276,0.0151141165,0.00030773718,0.97792757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99682814,0.00020217868,0.00050047156,0.00083701755,0.0012393319,0.0003928663],"domain_scores_gemma":[0.9868741,0.009710358,0.0010355485,0.0018438047,0.0003298928,0.00020626707],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007388478,0.0003032534,0.00052597915,0.00092344935,0.00008409042,0.0003876651,0.0019661752,0.00043198027,0.97695214],"category_scores_gemma":[0.23931654,0.00021440907,0.00021492907,0.001800541,0.000026999085,0.000051432613,0.0005270722,0.00019482482,0.2768562],"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":[0.0000014399449,0.000007171744,0.00007217184,0.00001876674,0.000010534631,0.000009629422,0.000006397165,2.7201241e-7,3.0837057e-7,0.0000073782303,0.97190505,0.027960863],"study_design_scores_gemma":[0.0000984325,0.000026846186,0.0004743546,0.00079357694,0.0000034754103,0.000008572462,0.00001835554,0.000046656856,0.000005328704,0.00085237774,0.9974091,0.00026290354],"about_ca_topic_score_codex":0.00001443831,"about_ca_topic_score_gemma":0.000015046033,"teacher_disagreement_score":0.70009595,"about_ca_system_score_codex":0.000015645406,"about_ca_system_score_gemma":0.00008444211,"threshold_uncertainty_score":0.8743348},"labels":[],"label_agreement":null},{"id":"W6930040370","doi":"10.5281/zenodo.12120319","title":"Aquarium guide pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Fish <Actinopterygii>; Marine fish; Reef; Fishing; Aquaculture","score_opus":0.31043387397802374,"score_gpt":0.4137680794566574,"score_spread":0.10333420547863365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930040370","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000073487477,0.0009801873,0.009420417,0.00068485434,0.0012308419,0.00031550968,0.00023047772,0.0015914993,0.98553884],"genre_scores_gemma":[0.00024963813,0.00015720699,0.0029372517,0.0001624305,0.00071295025,2.5862317e-8,0.0002798282,0.006698749,0.9888019],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954204,0.0009590293,0.0006239444,0.0010656937,0.0014469402,0.00048401402],"domain_scores_gemma":[0.9965418,0.0009902497,0.00037531776,0.001349349,0.00050981296,0.00023346288],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005550803,0.00026284467,0.00039372,0.0018419989,0.0006973535,0.0026801664,0.0033045036,0.00022855218,0.43102327],"category_scores_gemma":[0.06820919,0.0002171908,0.00015155193,0.003014854,0.00020125417,0.00010558548,0.0024952076,0.00054031063,0.4347871],"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":[0.000005367183,0.000022674049,0.0000010912504,0.000032229138,0.000036060213,0.000025097834,0.00008718195,0.000002119233,0.000047412886,0.0013794316,0.8436158,0.15474555],"study_design_scores_gemma":[0.0001470214,0.00009444707,0.000044453893,0.00008947417,0.00001766856,0.00008600718,0.0002442236,0.00008679146,0.000009814395,0.0043765064,0.99456525,0.00023832207],"about_ca_topic_score_codex":0.00005189379,"about_ca_topic_score_gemma":5.397943e-7,"teacher_disagreement_score":0.15450722,"about_ca_system_score_codex":0.000102337086,"about_ca_system_score_gemma":0.0000059964264,"threshold_uncertainty_score":0.99835515},"labels":[],"label_agreement":null},{"id":"W6930048941","doi":"10.5281/zenodo.10085318","title":"Antibody Characterization Report for TATA-binding protein associated factor 2N (TAF15)","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Antibody; Cell culture; Association (psychology); Cell; Characterization (materials science); Disease","score_opus":0.40651720557728244,"score_gpt":0.43539383698832734,"score_spread":0.028876631411044906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930048941","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":[0.78287977,0.000010977365,0.19434886,0.0012250876,0.0006159459,0.0015292817,0.0011419246,0.0022565727,0.015991572],"genre_scores_gemma":[0.91422886,0.000035417845,0.0027268005,0.00011458185,0.00042137035,8.1832917e-7,0.0598323,0.0017990276,0.020840822],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959781,0.0008124104,0.0007557046,0.00075616356,0.0011382577,0.0005593405],"domain_scores_gemma":[0.99554336,0.0015396444,0.0006304656,0.00067723176,0.0014356361,0.00017363216],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008221991,0.00016870494,0.00029550775,0.001011125,0.0024327845,0.0016834575,0.0014467274,0.0000938248,0.004027458],"category_scores_gemma":[0.19288261,0.00015113314,0.000108861816,0.004734171,0.00009227788,0.00049688213,0.00096277305,0.00022046946,0.004268191],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007563982,0.00012681773,0.0006145292,0.0000404775,0.00007734674,0.00008734113,0.0008685555,0.000021962616,0.79599607,0.000827951,0.023204874,0.17805843],"study_design_scores_gemma":[0.0005323372,0.00022106053,0.032758262,0.00004128479,0.000009794206,0.00007478457,0.00044711496,0.0021220897,0.0015892187,0.0010708156,0.9608779,0.00025533693],"about_ca_topic_score_codex":0.000004862114,"about_ca_topic_score_gemma":9.968042e-8,"teacher_disagreement_score":0.93767303,"about_ca_system_score_codex":0.00012443571,"about_ca_system_score_gemma":0.000008492629,"threshold_uncertainty_score":0.9993529},"labels":[],"label_agreement":null},{"id":"W6930061558","doi":"10.5281/zenodo.10603020","title":"Contextual factors related to vector-control interventions for malaria: a scoping review and evidence and gap map","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"World Health Organization","keywords":"Psychological intervention; Systematic review; Guideline; Relation (database); Control (management); Context (archaeology); MEDLINE","score_opus":0.4761331256820911,"score_gpt":0.4695019535061156,"score_spread":0.006631172175975475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930061558","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038278016,0.54574144,0.09126394,0.01639992,0.0025390147,0.016107118,0.0022820958,0.0035643913,0.32171932],"genre_scores_gemma":[0.052154068,0.03207275,0.014252078,0.002124793,0.00083503843,0.0000056898175,0.00067700865,0.019177169,0.8787014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967857,0.00085082854,0.0006632877,0.00088860793,0.0004929096,0.00031866258],"domain_scores_gemma":[0.99574906,0.0026932668,0.00035515174,0.0005461661,0.0004254747,0.00023089591],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005409251,0.00022406393,0.000578112,0.00092159974,0.0005650093,0.0013027734,0.0009486437,0.0001344011,0.013437121],"category_scores_gemma":[0.10722686,0.00018106146,0.00013604539,0.0012390853,0.00014424071,0.0001514104,0.0011442297,0.0002990076,0.0022496788],"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":[0.000017772978,0.000021658321,0.00001378471,0.004957384,0.00009751168,0.000005113052,0.00023595855,6.8814546e-7,0.000038154445,0.002170866,0.9517967,0.040644374],"study_design_scores_gemma":[0.0004210016,0.0004366086,0.00059535255,0.046561923,0.0001830844,0.00005571878,0.00029085606,0.000051456598,0.0000022879578,0.0014429687,0.94963,0.0003287359],"about_ca_topic_score_codex":0.00001941852,"about_ca_topic_score_gemma":0.0000018993818,"teacher_disagreement_score":0.5569821,"about_ca_system_score_codex":0.00004946836,"about_ca_system_score_gemma":0.0000064263586,"threshold_uncertainty_score":0.999734},"labels":[],"label_agreement":null},{"id":"W6930105279","doi":"10.5281/zenodo.11820391","title":"d&d essentials kit pdf download free","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Download; Adventure; Class (philosophy); Character (mathematics); Wizard; The Internet; Set (abstract data type); Fantasy","score_opus":0.28532741510322174,"score_gpt":0.39867796556041196,"score_spread":0.11335055045719022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930105279","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002438902,0.0014025784,0.0056315423,0.00081324467,0.0012165365,0.0004003412,0.000894804,0.0018140376,0.9878025],"genre_scores_gemma":[0.0006581772,0.0003204659,0.0024094456,0.00017310565,0.00089962775,5.8183822e-8,0.00060560484,0.0062475735,0.98868597],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99475,0.0011647902,0.00066588575,0.0011845387,0.001698761,0.00053602015],"domain_scores_gemma":[0.9955563,0.0011530003,0.00046776902,0.0020177672,0.00054115657,0.0002640152],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005555605,0.00030251194,0.00048279512,0.0019911833,0.00079788076,0.0032004467,0.0048417347,0.00026132193,0.44056532],"category_scores_gemma":[0.08306836,0.00024976066,0.00018257533,0.0032387625,0.00024997606,0.0001305224,0.0041328147,0.0005635879,0.36866418],"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":[0.000008556096,0.000032660217,0.0000011019199,0.000048860442,0.000056318207,0.00003074697,0.0001004975,0.000002028456,0.00012213053,0.0011935674,0.87933975,0.1190638],"study_design_scores_gemma":[0.00023675172,0.00008617412,0.0000403414,0.00010675699,0.000026850399,0.00007691014,0.00019481989,0.000030087589,0.000028654744,0.0077162697,0.991184,0.00027236162],"about_ca_topic_score_codex":0.00004805427,"about_ca_topic_score_gemma":8.072435e-7,"teacher_disagreement_score":0.11879144,"about_ca_system_score_codex":0.00008076774,"about_ca_system_score_gemma":0.0000062701665,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W6930150572","doi":"10.5281/zenodo.13135859","title":"zakodium-oss/react-plot: v2.0.0","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Dependency (UML); Identification (biology); Process (computing); Troubleshooting; Relation (database)","score_opus":0.3946188253513518,"score_gpt":0.4161533837878903,"score_spread":0.02153455843653851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930150572","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053974567,0.0014895682,0.004491018,0.0006577467,0.0012261857,0.00041702104,0.00045830247,0.0027472156,0.988459],"genre_scores_gemma":[0.0027255237,0.00036791633,0.002726662,0.00024365225,0.00121244,6.644199e-8,0.0005089664,0.013449021,0.9787657],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946923,0.0010909063,0.00066919427,0.00128938,0.0016543868,0.000603795],"domain_scores_gemma":[0.9958892,0.0012050301,0.00046875083,0.001584344,0.0005513556,0.0003013037],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0055033523,0.00034100146,0.0005005617,0.0021502168,0.0008619021,0.0031592883,0.003721508,0.000284421,0.16578658],"category_scores_gemma":[0.058481455,0.0002802485,0.00019474061,0.0035415802,0.00026504154,0.00015229078,0.0028226173,0.00072250294,0.18699573],"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":[0.000010117989,0.00003593468,0.0000018096084,0.000039926465,0.0000452532,0.000031914544,0.0001760093,0.0000017058163,0.00008419737,0.0016359653,0.7993288,0.19860835],"study_design_scores_gemma":[0.00020418919,0.00012172288,0.000120779965,0.00011616257,0.000023900147,0.00011515518,0.0002866911,0.00007164867,0.00001543096,0.004374192,0.9942428,0.0003073106],"about_ca_topic_score_codex":0.000049556522,"about_ca_topic_score_gemma":7.171259e-7,"teacher_disagreement_score":0.19830105,"about_ca_system_score_codex":0.000117407006,"about_ca_system_score_gemma":0.000007603127,"threshold_uncertainty_score":0.99996495},"labels":[],"label_agreement":null},{"id":"W6930253459","doi":"10.5281/zenodo.11618731","title":"Are Nexalyn Testo Booster UK the Secret to Better Bedroom Performance?","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Tribulus terrestris; Libido; Testosterone (patch); Reproductive health; Sexual desire; Erectile dysfunction; Human sexuality","score_opus":0.31814584388217526,"score_gpt":0.3848377397070139,"score_spread":0.06669189582483864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930253459","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001699692,0.00055011455,0.0021925601,0.004305039,0.0008931406,0.0006801437,0.00035198012,0.0010381334,0.9882892],"genre_scores_gemma":[0.018335182,0.00012671211,0.0021061487,0.0034403556,0.0017685608,3.0420844e-7,0.00023223541,0.009498662,0.96449184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956193,0.0008187681,0.00053348264,0.001010134,0.0014634597,0.00055485923],"domain_scores_gemma":[0.996238,0.0010293404,0.00044649997,0.0015760562,0.000466568,0.00024356955],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004672551,0.0003050893,0.0003894745,0.0013290513,0.0010818973,0.0028572073,0.0037415838,0.00018373439,0.09858936],"category_scores_gemma":[0.030279929,0.00019852881,0.0001301098,0.0031254971,0.00018827454,0.000108796245,0.0032924402,0.00066911796,0.103122],"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":[0.000011573331,0.00001309943,0.000060327064,0.00003266044,0.000034218458,0.000015455575,0.00027881566,0.0000057779025,0.00002771925,0.00008485751,0.8724473,0.12698816],"study_design_scores_gemma":[0.00012691435,0.0001241732,0.0022992298,0.00016458907,0.000020751033,0.00007572066,0.00038711712,0.00009433578,0.0000105034205,0.00069708575,0.9957443,0.0002552907],"about_ca_topic_score_codex":0.000020636016,"about_ca_topic_score_gemma":0.0000012851588,"teacher_disagreement_score":0.12673286,"about_ca_system_score_codex":0.000092275935,"about_ca_system_score_gemma":0.000004577413,"threshold_uncertainty_score":0.99817795},"labels":[],"label_agreement":null},{"id":"W6930265234","doi":"10.5281/zenodo.12260310","title":"city of ottawa zoning bylaw pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Zoning; Setback; Property value; Local planning; Land use; Minor (academic); Urban planning","score_opus":0.3161002787681395,"score_gpt":0.40232166457242624,"score_spread":0.08622138580428673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930265234","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009681128,0.0008823168,0.009235013,0.00020495993,0.000581204,0.00025509248,0.0002362135,0.0007286979,0.9877797],"genre_scores_gemma":[0.007677419,0.00012735084,0.0054624625,0.0000770057,0.0004705573,2.65508e-8,0.00021367986,0.005499869,0.9804716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959818,0.00086626573,0.00065536844,0.00080936495,0.0013138133,0.00037337092],"domain_scores_gemma":[0.996579,0.001114144,0.0005565042,0.0010396495,0.0005458381,0.0001648527],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0056934822,0.00021558611,0.00043828087,0.0015942677,0.00048391434,0.0010068591,0.002595056,0.00019111676,0.26825],"category_scores_gemma":[0.058966707,0.00018132756,0.0001473538,0.0030265523,0.00026189417,0.000095966294,0.0019861415,0.0004641825,0.06839359],"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":[0.0000057958787,0.000029462279,0.000011867511,0.000060711678,0.000043473054,0.000010886366,0.00012621937,0.0000023292494,0.000103315855,0.0037079786,0.9093299,0.08656808],"study_design_scores_gemma":[0.00014272804,0.000107347056,0.00019823796,0.00014312821,0.000016904782,0.000038423466,0.00017100808,0.0000561071,0.000046973008,0.0037260002,0.99517596,0.00017719557],"about_ca_topic_score_codex":0.00005409423,"about_ca_topic_score_gemma":8.1752785e-7,"teacher_disagreement_score":0.19985642,"about_ca_system_score_codex":0.00006079903,"about_ca_system_score_gemma":0.0000055187047,"threshold_uncertainty_score":0.9709165},"labels":[],"label_agreement":null},{"id":"W6930266844","doi":"10.5281/zenodo.12458601","title":"dictionnaire généalogique des prénoms pdf","year":2024,"lang":"fr","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Paraphernalia; Nucleofection; Limiting","score_opus":0.2408597683710006,"score_gpt":0.37302082319899615,"score_spread":0.13216105482799556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930266844","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009245925,0.0035778717,0.037468433,0.001262058,0.0020373699,0.000644445,0.00025582788,0.0012512789,0.9525781],"genre_scores_gemma":[0.018205944,0.0012805809,0.006430778,0.00023090385,0.0013314763,1.4099467e-7,0.00035137034,0.0062856874,0.96588314],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99304426,0.0024574213,0.00089395663,0.0014950574,0.0012425834,0.0008667157],"domain_scores_gemma":[0.99496573,0.001757423,0.00045318552,0.0012397713,0.0011319919,0.00045189384],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0064493013,0.0004575137,0.0005494993,0.0016659113,0.0028611121,0.004077584,0.00326895,0.00044524565,0.52213037],"category_scores_gemma":[0.083009295,0.00041098852,0.0002606517,0.0045470903,0.0010865785,0.00033398016,0.0030447152,0.0010915399,0.4296475],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019904703,0.00009496244,0.00001963512,0.00017091172,0.0000842284,0.00004513816,0.00083132676,0.00002382326,0.00014794241,0.007422265,0.47935554,0.5117843],"study_design_scores_gemma":[0.0002671388,0.00045673756,0.0015356286,0.00049427943,0.000052980453,0.00036302302,0.000944331,0.00044542333,0.000029223549,0.01999456,0.975,0.00041662197],"about_ca_topic_score_codex":0.00006491468,"about_ca_topic_score_gemma":0.0000022955733,"teacher_disagreement_score":0.5113677,"about_ca_system_score_codex":0.00045370092,"about_ca_system_score_gemma":0.000017916649,"threshold_uncertainty_score":0.9998342},"labels":[],"label_agreement":null},{"id":"W6930336539","doi":"10.5281/zenodo.12203668","title":"beekeeping in northern climates pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Beekeeping; Apiary; Brood; Training (meteorology); Northern ireland; Vegetation (pathology)","score_opus":0.2882034123791839,"score_gpt":0.39834610027316103,"score_spread":0.11014268789397713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930336539","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003461069,0.0011789683,0.0015126705,0.000385162,0.0005278327,0.00032794508,0.000121092955,0.00093514763,0.9946651],"genre_scores_gemma":[0.012786754,0.0006526758,0.0035961014,0.00027301445,0.0010708347,1.2930572e-7,0.00065545854,0.016101446,0.9648636],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960888,0.0008717828,0.00060324353,0.0009321735,0.0010179387,0.0004860755],"domain_scores_gemma":[0.9973204,0.0010300025,0.00032295668,0.0008729907,0.00030587884,0.00014776412],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0051445956,0.00020888295,0.00039488304,0.002268205,0.0004460703,0.0017644885,0.0023588475,0.00019190184,0.085197605],"category_scores_gemma":[0.044848848,0.00020026842,0.00010616495,0.0033152928,0.0001504168,0.00011038816,0.0019492764,0.00054487947,0.19472575],"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":[0.0000075031503,0.000030867865,0.000051314193,0.000050310497,0.00002075576,0.0000347482,0.00021656774,0.000008604099,0.00004048028,0.00047159512,0.738238,0.2608293],"study_design_scores_gemma":[0.00017075246,0.00006416052,0.00067993253,0.0001924696,0.00000820027,0.00004335737,0.00040911487,0.00013382189,0.0000052113696,0.0035890525,0.9944893,0.00021461082],"about_ca_topic_score_codex":0.000066854205,"about_ca_topic_score_gemma":0.000014832649,"teacher_disagreement_score":0.2606147,"about_ca_system_score_codex":0.00012387162,"about_ca_system_score_gemma":0.000004642667,"threshold_uncertainty_score":0.99927175},"labels":[],"label_agreement":null},{"id":"W6930342006","doi":"10.5281/zenodo.11758788","title":"Java lernen mit bluej pdf download","year":2024,"lang":"de","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Paraphernalia; Limiting; Filter (signal processing); Demotion","score_opus":0.24590395476717536,"score_gpt":0.37347116615255926,"score_spread":0.1275672113853839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930342006","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002809016,0.006797578,0.0041018883,0.0012042758,0.0026841632,0.00085436786,0.0010483643,0.0014879213,0.98154056],"genre_scores_gemma":[0.004833257,0.0017551596,0.0031707508,0.00047975383,0.002207054,1.3149545e-7,0.0017693583,0.009257572,0.976527],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99065876,0.0023530019,0.0012477904,0.002206545,0.0023740837,0.0011598007],"domain_scores_gemma":[0.993221,0.002136878,0.00075058587,0.002115716,0.0011708849,0.00060496014],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008272344,0.00064029754,0.0008339058,0.0025914523,0.002217133,0.0062800157,0.005715228,0.0005146805,0.64733046],"category_scores_gemma":[0.06848995,0.00056433334,0.0003704356,0.00548067,0.00061943196,0.00027900454,0.005250123,0.0013888181,0.8266132],"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":[0.000036703972,0.0000910208,0.000005150516,0.00011891383,0.00018882018,0.00008208433,0.0005177292,0.0000099468725,0.000203975,0.0008184784,0.7375938,0.26033336],"study_design_scores_gemma":[0.00047354982,0.00034654458,0.00019347618,0.00031981902,0.00011563947,0.00016512515,0.0006605639,0.00025414574,0.000036444206,0.0024027,0.99441665,0.00061536115],"about_ca_topic_score_codex":0.00006093987,"about_ca_topic_score_gemma":7.204814e-7,"teacher_disagreement_score":0.259718,"about_ca_system_score_codex":0.00029189998,"about_ca_system_score_gemma":0.000019146177,"threshold_uncertainty_score":0.9996808},"labels":[],"label_agreement":null},{"id":"W6930362902","doi":"10.5281/zenodo.11996856","title":"Iso 22367 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Nucleofection; Work (physics); Subpoena; Filter (signal processing); Frame (networking); Limiting","score_opus":0.333995337552321,"score_gpt":0.4071682278948445,"score_spread":0.0731728903425235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930362902","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019727637,0.0011680165,0.0061826427,0.00057003147,0.0009729076,0.00031353426,0.00024882454,0.001577259,0.98894703],"genre_scores_gemma":[0.0006795723,0.00019245275,0.002055043,0.00015969225,0.000712893,2.5943148e-8,0.00026245133,0.0070975255,0.98884034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99563795,0.000932971,0.00052748277,0.0010406392,0.0013906235,0.00047032651],"domain_scores_gemma":[0.9967998,0.0009394773,0.00034401543,0.0012502447,0.00043824234,0.00022820504],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004702993,0.00025608082,0.00038562418,0.0018304285,0.0007375403,0.0026361854,0.003135928,0.00022249625,0.44167587],"category_scores_gemma":[0.054203264,0.00021071258,0.0001477573,0.0031462607,0.00020935692,0.000106239706,0.0024398493,0.0005555507,0.45899585],"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":[0.0000061817154,0.000023993714,0.000001251747,0.000033380416,0.000034202025,0.000022035674,0.00010538648,0.0000015345811,0.000036697813,0.0013786503,0.82235444,0.17600226],"study_design_scores_gemma":[0.00014923756,0.000100645266,0.000059190366,0.00009454368,0.00001622619,0.00008149618,0.00023989884,0.00007377326,0.000007812837,0.004988714,0.9939569,0.00023153158],"about_ca_topic_score_codex":0.000028033937,"about_ca_topic_score_gemma":4.1448084e-7,"teacher_disagreement_score":0.17577073,"about_ca_system_score_codex":0.000084195664,"about_ca_system_score_gemma":0.000004885221,"threshold_uncertainty_score":0.9983992},"labels":[],"label_agreement":null},{"id":"W6930389605","doi":"10.5281/zenodo.12415455","title":"filosofía de vida pdf","year":2024,"lang":"es","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Subject (documents); Filter (signal processing); Interpretation (philosophy); Feature (linguistics); Context (archaeology)","score_opus":0.26230277966288823,"score_gpt":0.3894365728519154,"score_spread":0.12713379318902718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930389605","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004898438,0.0015329565,0.009087525,0.0011307622,0.0010655359,0.0005054125,0.00042311166,0.001094174,0.9846707],"genre_scores_gemma":[0.01347062,0.0012712574,0.0067500807,0.00051017327,0.0017859782,9.035191e-8,0.000549291,0.010356392,0.9653061],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99323195,0.002047851,0.0008077639,0.0014618636,0.0015269743,0.00092358334],"domain_scores_gemma":[0.99471253,0.0021108838,0.00048678194,0.001457834,0.0007676734,0.00046430805],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0074902037,0.00043531536,0.00056642096,0.0019298788,0.0017919441,0.005549702,0.004192486,0.00037767054,0.5124151],"category_scores_gemma":[0.08083885,0.00038781646,0.00024908164,0.004085371,0.0004267882,0.00020828616,0.0036177668,0.001008441,0.52041775],"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":[0.000025273579,0.00006614078,0.000009275218,0.00012910733,0.0000837506,0.000061736544,0.00038805255,0.000010077931,0.00028774064,0.0024337545,0.7574739,0.23903121],"study_design_scores_gemma":[0.00028004448,0.0002672972,0.0004481678,0.00032614847,0.000050161965,0.00023578042,0.00055035204,0.00040304573,0.000041267624,0.006426827,0.99055856,0.00041234097],"about_ca_topic_score_codex":0.000042895794,"about_ca_topic_score_gemma":2.575379e-7,"teacher_disagreement_score":0.23861887,"about_ca_system_score_codex":0.00028357143,"about_ca_system_score_gemma":0.00001747853,"threshold_uncertainty_score":0.99985737},"labels":[],"label_agreement":null},{"id":"W6930472654","doi":"10.5281/zenodo.14971622","title":"Figure 3 in Phoridae (Diptera) mating behaviour: identification of general patterns, exceptions and the use of sexually dimorphic structures based on vast citizen science data","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Phoridae; Identification (biology); Deed; Citizen science; Collectable; Mating","score_opus":0.3526444329979296,"score_gpt":0.4009733922358075,"score_spread":0.048328959237877944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930472654","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34788138,0.0011124075,0.20251447,0.0033812947,0.0026934922,0.0069777328,0.02916342,0.0012886834,0.40498713],"genre_scores_gemma":[0.9499285,0.00022343837,0.011232578,0.00019338372,0.00021402158,2.9159926e-7,0.002151003,0.0014199911,0.03463679],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99610746,0.0011029948,0.0006995521,0.0007057512,0.0011657493,0.0002184841],"domain_scores_gemma":[0.99508286,0.0018905305,0.00078769756,0.0016218047,0.00055664364,0.000060486873],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0062474846,0.00015030733,0.00031510243,0.0016645305,0.0005840733,0.0009129361,0.0030226754,0.00008378821,0.004957239],"category_scores_gemma":[0.049956463,0.000109272434,0.000036378147,0.0023324024,0.00064189057,0.00020118945,0.0018280629,0.00027908527,0.00004476305],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019027207,0.00021331417,0.0054261256,0.00028127476,0.000058947604,0.000008093479,0.00093010435,0.0022809692,0.0040389104,0.0063060275,0.49332443,0.48694155],"study_design_scores_gemma":[0.0039533367,0.00038942235,0.5398241,0.001270388,0.00013620159,0.00003048577,0.0016045029,0.080084376,0.0005608281,0.0031559058,0.3681021,0.0008883196],"about_ca_topic_score_codex":0.0002813036,"about_ca_topic_score_gemma":0.0000032721543,"teacher_disagreement_score":0.60204715,"about_ca_system_score_codex":0.000040072107,"about_ca_system_score_gemma":0.000021178486,"threshold_uncertainty_score":0.99595237},"labels":[],"label_agreement":null},{"id":"W6930608627","doi":"10.5281/zenodo.15519615","title":"rism-digital/verovio: Version 5.3.1","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"","score_opus":0.2490806850199866,"score_gpt":0.384735956271011,"score_spread":0.1356552712510244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930608627","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003578697,0.000357056,0.01854511,0.00038729113,0.00062471203,0.00032866537,0.00078090304,0.0013919206,0.97754854],"genre_scores_gemma":[0.0028777425,0.00023328843,0.0018278376,0.00020415109,0.00037397255,2.2632115e-8,0.0009893271,0.0040755323,0.98941815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99611217,0.0007018157,0.00049789634,0.0009346341,0.0013178546,0.00043565908],"domain_scores_gemma":[0.9956599,0.0016951184,0.00045257917,0.0013095723,0.0006792358,0.00020361251],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002833928,0.00025026756,0.00039282802,0.0018389707,0.0012078017,0.0025521345,0.003350238,0.00024039201,0.13452303],"category_scores_gemma":[0.0842555,0.00021870852,0.00014616463,0.0028342996,0.00018831617,0.00020172709,0.002835145,0.00042758958,0.045105442],"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":[0.000012621389,0.00003200573,0.0000060012526,0.000015928674,0.000022940161,0.000007583099,0.00003399204,0.0000039064325,0.00001416197,0.00063155615,0.70755464,0.29166463],"study_design_scores_gemma":[0.00030248243,0.00009821596,0.00019662426,0.00008827781,0.00001197307,0.000020417114,0.00022019881,0.000080775666,0.000009802513,0.0018573673,0.99689853,0.00021532939],"about_ca_topic_score_codex":0.000038372033,"about_ca_topic_score_gemma":2.0297162e-7,"teacher_disagreement_score":0.2914493,"about_ca_system_score_codex":0.00011302243,"about_ca_system_score_gemma":0.000010048,"threshold_uncertainty_score":0.9984833},"labels":[],"label_agreement":null},{"id":"W6930621565","doi":"10.5281/zenodo.15152300","title":"The Pandya Dynasty: Scholars and Warriors","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Tamil; Politics; Identity (music); Government (linguistics); National identity; Canadian literature","score_opus":0.24260169582606625,"score_gpt":0.4044819271355125,"score_spread":0.16188023130944626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930621565","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27921534,0.002027353,0.038848624,0.01206847,0.0010492596,0.00074540393,0.000079119105,0.0010718316,0.6648946],"genre_scores_gemma":[0.9902453,0.00037353567,0.0013956563,0.00039534748,0.00007671058,3.7935134e-8,0.000026256426,0.00031999123,0.007167199],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973932,0.00094246556,0.00034649414,0.00042504177,0.0005929073,0.00029990188],"domain_scores_gemma":[0.99503404,0.00346223,0.00012723992,0.0006357318,0.0006286888,0.000112087866],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007703974,0.00009302518,0.00013587729,0.00039347244,0.004663027,0.0029475668,0.0016256304,0.000047369867,0.0016489819],"category_scores_gemma":[0.115281545,0.00006159824,0.000041595125,0.0022653714,0.00026402366,0.00022655838,0.001699652,0.00027320598,0.0010771372],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025814605,0.000014342445,0.00023273377,0.0000043276477,0.00001586454,0.0000024290398,0.00018479169,0.000007829422,0.0003965818,0.009436834,0.108437136,0.8812413],"study_design_scores_gemma":[0.00022564098,0.000055499095,0.02149304,0.000012183426,0.0000048061347,0.000023978015,0.0011238416,0.00044231743,0.00006225841,0.011415546,0.9650713,0.0000695579],"about_ca_topic_score_codex":0.0000072820258,"about_ca_topic_score_gemma":2.972698e-7,"teacher_disagreement_score":0.88117176,"about_ca_system_score_codex":0.000045224704,"about_ca_system_score_gemma":0.0000042722836,"threshold_uncertainty_score":0.99970067},"labels":[],"label_agreement":null},{"id":"W6930749667","doi":"10.5281/zenodo.16365847","title":"SEM_raw_images_Leiter_et_al_2025","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Phreatomagmatic eruption; Impact crater; Tephra; Grain size; Pyroclastic rock; Deposition (geology)","score_opus":0.28144917329355384,"score_gpt":0.4117306414657958,"score_spread":0.13028146817224195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930749667","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009848397,0.00051743904,0.029751731,0.0007593576,0.0006289992,0.00033731968,0.00043448998,0.0014800471,0.9660808],"genre_scores_gemma":[0.0005272721,0.0001993774,0.004370999,0.00038667288,0.00041702043,2.7218077e-8,0.00048726695,0.0039766356,0.98963475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958876,0.0011404435,0.0005088396,0.00092223694,0.0011085498,0.00043234517],"domain_scores_gemma":[0.99567735,0.0016967703,0.0003967697,0.0013680586,0.0006883444,0.00017273324],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003541418,0.00024412335,0.0004064701,0.001872594,0.0010810768,0.0020031736,0.0036751318,0.00020388312,0.15801346],"category_scores_gemma":[0.07698967,0.0002120672,0.0001356917,0.0030255099,0.00017862601,0.00010839052,0.0028679338,0.00045359074,0.024402019],"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":[0.0000061877727,0.000023153938,0.0000027108217,0.00001989742,0.000026527647,0.000008110583,0.000037845748,0.0000017880163,0.000025616897,0.0012656107,0.67654365,0.3220389],"study_design_scores_gemma":[0.00021932251,0.000059786464,0.00023962143,0.000085609296,0.000013822068,0.00002497842,0.00012443666,0.00006523859,0.000013707044,0.0021773034,0.99677277,0.0002034048],"about_ca_topic_score_codex":0.000035064913,"about_ca_topic_score_gemma":3.6220254e-7,"teacher_disagreement_score":0.3218355,"about_ca_system_score_codex":0.0000812674,"about_ca_system_score_gemma":0.000008514785,"threshold_uncertainty_score":0.99903286},"labels":[],"label_agreement":null},{"id":"W6930820021","doi":"10.5281/zenodo.15155454","title":"TABLE 2 in Bunites distigma (Brullé, 1837): discovery of the second- and third-instar larvae and phylogenetic relationships within the Colymbetinae (Coleoptera: Dytiscidae)","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Seta; Table (database); Larva; Phylogenetic tree; Phylogenetics","score_opus":0.19637574641016434,"score_gpt":0.33590965249302046,"score_spread":0.13953390608285612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930820021","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18790369,0.0011923191,0.00024603188,0.0014082087,0.00065765664,0.0015395882,0.80026424,0.00018945776,0.0065988023],"genre_scores_gemma":[0.665889,0.0019643623,0.0011704502,0.0006258581,0.0005302825,0.0000018904733,0.31531793,0.001943151,0.012557049],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945081,0.0028097897,0.0007580321,0.00067223306,0.00092270627,0.00032917663],"domain_scores_gemma":[0.9916994,0.006094924,0.0006441677,0.0010871041,0.0003783757,0.00009600291],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008447062,0.00022407646,0.00037001108,0.0005949841,0.002126043,0.0015740163,0.0022422853,0.00015504274,0.0005633776],"category_scores_gemma":[0.06839726,0.0001394542,0.000053778083,0.0034126136,0.00076469016,0.00024403851,0.0034126607,0.0008372383,0.00043267378],"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":[0.000032329946,0.00004174206,0.0015610716,0.00009106059,0.000026628057,0.000007089157,0.00036883424,0.00006145095,0.00008465347,0.00042357013,0.99434084,0.0029607352],"study_design_scores_gemma":[0.00033560986,0.000111926674,0.14483036,0.00011730574,0.000025078469,0.000047482077,0.0011751769,0.00023368986,0.000026948172,0.0031743913,0.849731,0.00019101269],"about_ca_topic_score_codex":0.00024821472,"about_ca_topic_score_gemma":0.00015144791,"teacher_disagreement_score":0.48494634,"about_ca_system_score_codex":0.00004528613,"about_ca_system_score_gemma":0.000018582625,"threshold_uncertainty_score":0.9994624},"labels":[],"label_agreement":null},{"id":"W6930850422","doi":"10.5281/zenodo.14593677","title":"Reboulia hemisphaerica Raddi","year":2024,"lang":"fr","type":"article","venue":"Open MIND","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Atlas (anatomy); Massif; Plateau (mathematics); Karst; Stratum","score_opus":0.6751818711559903,"score_gpt":0.5688737349943801,"score_spread":0.10630813616161017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930850422","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052928705,0.08701633,0.008681591,0.015186872,0.018483438,0.0005091254,0.00012563981,0.000009769188,0.8170585],"genre_scores_gemma":[0.07064867,0.0009727572,0.43660343,0.00025203318,0.0007663152,0.000013737869,0.00000490141,0.00003245738,0.4907057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962016,0.00055819534,0.0007951928,0.0010869304,0.0007680185,0.0005900649],"domain_scores_gemma":[0.97321385,0.02543189,0.0001572863,0.0008156511,0.000113622766,0.00026771062],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008240552,0.00022621569,0.00046702952,0.0002897118,0.00018706785,0.0032183495,0.0023867793,0.00015201911,0.13386683],"category_scores_gemma":[0.030866552,0.00017689416,0.00016841662,0.0044168034,0.00019655804,0.0007779351,0.001114246,0.00039682584,0.02971447],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001370319,0.000024385326,0.0007818325,0.000011356417,0.000031061605,0.00020015959,0.00045395314,0.000015468771,0.0001823704,0.00021489049,0.07847941,0.9195914],"study_design_scores_gemma":[0.00015856039,0.000081170176,0.0009542876,0.000294469,0.00003509287,0.00012920759,0.0010746828,0.006479459,0.000845952,0.009792613,0.97991157,0.00024294037],"about_ca_topic_score_codex":0.001515015,"about_ca_topic_score_gemma":0.00006946953,"teacher_disagreement_score":0.9193485,"about_ca_system_score_codex":0.00017324867,"about_ca_system_score_gemma":0.0007589449,"threshold_uncertainty_score":0.9978164},"labels":[],"label_agreement":null},{"id":"W6930975310","doi":"10.5281/zenodo.4293671","title":"New World Information and Communication Order","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Government (linguistics); Gloom; Nucleofection; Subpoena; Work (physics); Derogation","score_opus":0.3222887743551475,"score_gpt":0.394410447986923,"score_spread":0.07212167363177546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930975310","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041267302,0.001014424,0.22326225,0.0038018092,0.00041001826,0.0005358891,0.000047066198,0.00089691486,0.7287643],"genre_scores_gemma":[0.9460837,0.00018267508,0.04866118,0.00055210793,0.00021700173,3.132532e-8,0.00030639928,0.00035602142,0.0036408817],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806106,0.00060664886,0.00036204638,0.00015802078,0.0005490201,0.000263188],"domain_scores_gemma":[0.99721193,0.0011953581,0.00020607044,0.00056417065,0.00060569344,0.00021677195],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005037096,0.000079566424,0.00011485843,0.0006036774,0.0013799343,0.0012613533,0.0009874632,0.000036374284,0.009888744],"category_scores_gemma":[0.043319706,0.00006758573,0.000022226008,0.0023719769,0.00007658928,0.0013878405,0.0011494055,0.00017637298,0.0044509526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012144989,0.000014497549,0.00037385742,0.0000036246324,0.000005497274,8.8563795e-8,0.00096042297,0.00000900732,0.00006049463,0.008662279,0.24025379,0.7496443],"study_design_scores_gemma":[0.00021441902,0.000030839703,0.025511691,0.0000070072983,0.0000035054295,0.00002768738,0.00056456105,0.0002288858,0.000034320743,0.0025613788,0.9707344,0.00008127514],"about_ca_topic_score_codex":0.000027587113,"about_ca_topic_score_gemma":3.3141944e-7,"teacher_disagreement_score":0.9048164,"about_ca_system_score_codex":0.00004126274,"about_ca_system_score_gemma":0.000002868611,"threshold_uncertainty_score":0.9999201},"labels":[],"label_agreement":null},{"id":"W6931015861","doi":"10.5281/zenodo.3961239","title":"Cygnus X-1 contains a 21-solar mass black hole – implications for massive star winds","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Liquation; Dysgeusia; Diafiltration; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.3166783134647902,"score_gpt":0.40394325449432406,"score_spread":0.08726494102953386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931015861","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021306497,0.0009237041,0.13597633,0.0026219494,0.00048314082,0.0014035158,0.0029048189,0.0009849486,0.85448855],"genre_scores_gemma":[0.0098027205,0.0013940653,0.042303603,0.0010150687,0.0019820754,0.0000016735468,0.008234348,0.015965942,0.9193005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953545,0.0011121634,0.00069960905,0.0012519219,0.00091610075,0.0006657079],"domain_scores_gemma":[0.9932894,0.002357699,0.00073669926,0.0016592642,0.0016369068,0.00031999275],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0036369709,0.00033151172,0.00057641196,0.0012187405,0.0015454916,0.0018322514,0.0030364422,0.00029656375,0.047071245],"category_scores_gemma":[0.06108342,0.00030518102,0.0002303646,0.002740818,0.00031801514,0.0001317846,0.0013622851,0.00045445847,0.0033519403],"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":[0.000024426887,0.00006927781,0.000018961755,0.0000478392,0.000090742426,0.000009141298,0.00019719789,0.000031151652,0.00064855244,0.003227821,0.92423683,0.07139805],"study_design_scores_gemma":[0.000588292,0.00020235026,0.00093486847,0.00007651022,0.00003036289,0.000017926799,0.00079939875,0.00031721764,0.000033779,0.0032112254,0.9934528,0.00033527394],"about_ca_topic_score_codex":0.000026447084,"about_ca_topic_score_gemma":0.0000017062682,"teacher_disagreement_score":0.09367273,"about_ca_system_score_codex":0.00018102754,"about_ca_system_score_gemma":0.000025548932,"threshold_uncertainty_score":0.99994004},"labels":[],"label_agreement":null},{"id":"W6931147657","doi":"10.5281/zenodo.4077866","title":"Regarder Lost Girls &amp; Love Hotels (2020) Film Complet en HD Streaming VF Entier Français jgk","year":2020,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Paraphernalia; Subconscious; Population; Happening; Indignation","score_opus":0.2546335692148976,"score_gpt":0.3652329196868771,"score_spread":0.1105993504719795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931147657","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05927712,0.0062136035,0.19812201,0.030398572,0.0028906062,0.0016447371,0.002439031,0.0012102881,0.69780403],"genre_scores_gemma":[0.79965514,0.0031715068,0.0631997,0.0055704685,0.0040117987,1.3161312e-7,0.0018635427,0.006003335,0.11652435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99169904,0.0030497857,0.0011068371,0.0014313884,0.0016666572,0.0010463062],"domain_scores_gemma":[0.9927138,0.0033761002,0.00052992965,0.0011612253,0.0014287408,0.0007901757],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0048888354,0.00042439753,0.0006453047,0.0005303047,0.0017609758,0.0023882412,0.003483869,0.0002625695,0.29504088],"category_scores_gemma":[0.09075413,0.00042318035,0.00023918295,0.00464713,0.00057613273,0.0006659869,0.0036741463,0.0009782468,0.13779011],"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":[0.00011418127,0.0001621501,0.0002134626,0.00010487638,0.00010586017,0.00008078608,0.010266116,0.00020106867,0.0009780381,0.0008793874,0.6660598,0.3208343],"study_design_scores_gemma":[0.0007451882,0.00037028192,0.006865013,0.00009285267,0.00004208319,0.0001622312,0.0021225002,0.0019375762,0.00016378744,0.0009946581,0.9860534,0.000450427],"about_ca_topic_score_codex":0.00012616145,"about_ca_topic_score_gemma":0.0000013207266,"teacher_disagreement_score":0.740378,"about_ca_system_score_codex":0.00015616539,"about_ca_system_score_gemma":0.000018787654,"threshold_uncertainty_score":0.999822},"labels":[],"label_agreement":null},{"id":"W6931154741","doi":"10.5281/zenodo.5632017","title":"Chaetonotus (Chaetonotus) similis Zelinka 1889","year":2013,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Dorsum; Bog; Anterior surface; Head (geology); Scale (ratio)","score_opus":0.31911160241553505,"score_gpt":0.3806439778287833,"score_spread":0.06153237541324824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931154741","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25190905,0.0005864592,0.050146956,0.006427669,0.0011782874,0.0014669262,0.00018666327,0.0025485952,0.6855494],"genre_scores_gemma":[0.98540336,0.00011122253,0.0066999355,0.00079458486,0.00043500873,1.6970041e-7,0.00021072847,0.0011112674,0.0052337414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953699,0.001094681,0.00073677144,0.0008579964,0.0012809276,0.0006597301],"domain_scores_gemma":[0.99392873,0.0023541565,0.0003273982,0.0012410518,0.0017697267,0.00037895815],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0051901247,0.0002129436,0.00032509942,0.00082450424,0.0023118006,0.0023672718,0.0030067307,0.00011650577,0.07697083],"category_scores_gemma":[0.083669476,0.00017739767,0.00012713386,0.0028969615,0.00026391976,0.0006417235,0.0021589117,0.00039385352,0.04986298],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000145857875,0.00006259361,0.00011613914,0.0000075365383,0.000018022161,0.0000058393666,0.00052417023,0.000064419844,0.0014791967,0.0013905158,0.3323024,0.6640146],"study_design_scores_gemma":[0.00038558556,0.0001800285,0.014342354,0.0000130520675,0.0000064481287,0.000071658775,0.00083033333,0.0018737642,0.0002648247,0.0100548295,0.9717382,0.00023891096],"about_ca_topic_score_codex":0.000064960914,"about_ca_topic_score_gemma":2.8800568e-7,"teacher_disagreement_score":0.7334943,"about_ca_system_score_codex":0.00010649779,"about_ca_system_score_gemma":0.00000588547,"threshold_uncertainty_score":0.9989871},"labels":[],"label_agreement":null},{"id":"W6931214709","doi":"10.5281/zenodo.6046291","title":"iver56/audiomentations: v0.3.0","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alpha Technologies (Canada)","funders":"","keywords":"Python (programming language); Scripting language; Software; Real world data","score_opus":0.3903166133061465,"score_gpt":0.419535393581097,"score_spread":0.029218780274950507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931214709","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005137828,0.00046782554,0.006379478,0.0005559495,0.00058965717,0.00044944262,0.0004715008,0.0012698898,0.98976487],"genre_scores_gemma":[0.0015431129,0.00035791498,0.0044914293,0.00035905873,0.00060625054,1.793092e-7,0.0021421444,0.00869531,0.9818046],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948028,0.0016433154,0.0005141366,0.0008831699,0.0017365614,0.00042003006],"domain_scores_gemma":[0.99610656,0.0014874552,0.00057894527,0.001213854,0.00042051723,0.00019265006],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004478804,0.00021965495,0.00034295206,0.0020318672,0.0022647704,0.0013433581,0.0034127296,0.0001161146,0.60539544],"category_scores_gemma":[0.05222963,0.00020301892,0.00012271079,0.0036666505,0.00018231703,0.00013283337,0.0030080813,0.0004601997,0.023429502],"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":[0.000008991973,0.000044306093,0.000008059619,0.0000105351055,0.00003385332,0.000012149161,0.0002077125,0.000012646715,0.000030011754,0.00126014,0.823169,0.17520258],"study_design_scores_gemma":[0.0003015474,0.0001287311,0.00031238244,0.000016031216,0.0000126557115,0.000060318747,0.00105904,0.000049182396,0.0000038882995,0.0015643956,0.9962725,0.00021930068],"about_ca_topic_score_codex":0.00004109095,"about_ca_topic_score_gemma":4.5048688e-7,"teacher_disagreement_score":0.5819659,"about_ca_system_score_codex":0.00019505121,"about_ca_system_score_gemma":0.0000064462915,"threshold_uncertainty_score":0.99969333},"labels":[],"label_agreement":null},{"id":"W6931355174","doi":"10.5281/zenodo.4371361","title":"Phoenix dactylifera Linnaeus 1753","year":2007,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Phoenix dactylifera; Phoenix; Taxon; Typification; Genus; Nova scotia","score_opus":0.3775126711484734,"score_gpt":0.42142036926180315,"score_spread":0.04390769811332973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931355174","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19473158,0.00021508183,0.13910903,0.0012156192,0.000771067,0.0004137149,0.00008122574,0.0013011368,0.6621615],"genre_scores_gemma":[0.990086,0.000039476676,0.0054906346,0.0004106252,0.00038915168,1.0549764e-8,0.00012125729,0.00071404653,0.002748768],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99618834,0.0006698035,0.0006335762,0.0006463197,0.0012809082,0.0005810548],"domain_scores_gemma":[0.994233,0.0030959602,0.00026956975,0.00092869677,0.001159583,0.00031318763],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013477221,0.0001497181,0.00022923398,0.00085404865,0.0020957277,0.0014152924,0.0024000062,0.00008829169,0.02074698],"category_scores_gemma":[0.108529866,0.00012658178,0.00009237945,0.003284492,0.00017194601,0.00031737838,0.0014128805,0.00035313802,0.012210797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000667368,0.0000817521,0.00019941678,0.0000061462983,0.000016775954,0.000028613797,0.0006778817,0.000024428522,0.002957878,0.0027166929,0.19770531,0.7955184],"study_design_scores_gemma":[0.00033688493,0.00016202692,0.016909618,0.000008915254,0.000004628524,0.00011547616,0.0007000415,0.00017467124,0.00065433996,0.0027320595,0.9780427,0.00015863322],"about_ca_topic_score_codex":0.000011989253,"about_ca_topic_score_gemma":3.190659e-7,"teacher_disagreement_score":0.79535973,"about_ca_system_score_codex":0.00009682956,"about_ca_system_score_gemma":0.000003917222,"threshold_uncertainty_score":0.99962133},"labels":[],"label_agreement":null},{"id":"W6931404941","doi":"10.5281/zenodo.5300636","title":"FIGURES 8–13 in Cybaeus (Araneae: Cybaeidae) in the Nearctic: the devius and tardatus species groups of the Californian clade","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal British Columbia Museum","funders":"","keywords":"Clade; Taxonomy (biology); Phylogenetics; Genus; Species groups","score_opus":0.2554731253318969,"score_gpt":0.3608274452614371,"score_spread":0.1053543199295402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931404941","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013326875,0.0036009809,0.00035757702,0.0048758066,0.00037658363,0.0010177545,0.00032537518,0.000117130876,0.9760019],"genre_scores_gemma":[0.7412008,0.0051198187,0.001915757,0.0021666216,0.0012681318,7.7128635e-7,0.0005267778,0.0055918954,0.24220943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993642,0.0035376179,0.00058835605,0.00056865456,0.0012664772,0.00039694467],"domain_scores_gemma":[0.99468505,0.0032859314,0.00043284261,0.0012773232,0.00025143573,0.000067396104],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005660364,0.00020833954,0.00036778447,0.0005688144,0.00076578086,0.000992131,0.003489438,0.00014884783,0.0145875765],"category_scores_gemma":[0.05175797,0.00010621621,0.00009574035,0.0036223386,0.0006081556,0.00006617647,0.0018602097,0.0007452693,0.00028258775],"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":[0.00003771767,0.00010195974,0.0014612965,0.000094377356,0.000039763214,0.000037863883,0.002949852,0.000049845505,0.00023777274,0.0023456838,0.90569603,0.086947836],"study_design_scores_gemma":[0.00026913334,0.00004465505,0.050240394,0.00013690958,0.000008632952,0.000075029224,0.0027721683,0.00009196604,0.000014778366,0.0010837312,0.94514006,0.00012255345],"about_ca_topic_score_codex":0.00033908777,"about_ca_topic_score_gemma":0.00008731085,"teacher_disagreement_score":0.7337925,"about_ca_system_score_codex":0.00005622687,"about_ca_system_score_gemma":0.000012832018,"threshold_uncertainty_score":0.9863132},"labels":[],"label_agreement":null},{"id":"W6931452755","doi":"10.5281/zenodo.5145832","title":"FIG. 29. — Caudal PVL 4170 in Osteological revision of the holotype of the Middle Jurassic sauropod dinosaur Patagosaurus fariasi Bonaparte, 1979 (Sauropoda: Cetiosauridae)","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Tyrrell Museum","funders":"","keywords":"Osteology; Holotype; Sauropoda; Dorsum; Paratype","score_opus":0.2742973779926121,"score_gpt":0.35394767798408017,"score_spread":0.07965029999146805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931452755","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05921023,0.0033198246,0.0011728591,0.0041598817,0.0023545013,0.0022193738,0.0012647555,0.00046356337,0.925835],"genre_scores_gemma":[0.82734394,0.0012760762,0.0027809863,0.00052054744,0.0007586256,3.1379736e-7,0.00061223365,0.0043657194,0.16234158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99116087,0.0041392827,0.001190595,0.001001393,0.0019803396,0.00052749185],"domain_scores_gemma":[0.9937005,0.0017897377,0.0013863178,0.0022225617,0.0007698348,0.00013102352],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004579152,0.0003481674,0.0007752237,0.0007073675,0.00073221006,0.00035261203,0.0048189587,0.00033519603,0.02893332],"category_scores_gemma":[0.07279683,0.0002077645,0.00031867228,0.00495575,0.00073773746,0.00009206189,0.0047549936,0.00091205566,0.00042840702],"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":[0.00008009176,0.0003523453,0.0015318339,0.00020445885,0.00007383411,0.000029957711,0.0006184661,0.000055037443,0.0019796023,0.002137682,0.80883384,0.18410283],"study_design_scores_gemma":[0.0005292563,0.00017532059,0.042515606,0.0004872959,0.000026098076,0.00005466587,0.0004164688,0.00007231177,0.00022821515,0.000585328,0.95466906,0.00024037207],"about_ca_topic_score_codex":0.00013589513,"about_ca_topic_score_gemma":0.000010854288,"teacher_disagreement_score":0.7681337,"about_ca_system_score_codex":0.00011009917,"about_ca_system_score_gemma":0.000033345477,"threshold_uncertainty_score":0.97195435},"labels":[],"label_agreement":null},{"id":"W6931474524","doi":"10.5281/zenodo.16649769","title":"Creation of data visualization using descriptive analysis","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Earnings; Descriptive statistics; Workforce; Unemployment; Analytics; Quarter (Canadian coin); Frame (networking); State (computer science); Wage; Data analysis","score_opus":0.6245281135109526,"score_gpt":0.4921929228078667,"score_spread":0.13233519070308591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931474524","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012948755,0.0007519707,0.26879886,0.000043726,0.00024942192,0.00028849306,0.0013142048,0.0005476952,0.7278761],"genre_scores_gemma":[0.0891415,0.0011974764,0.07622313,0.0001333667,0.001914732,9.943283e-8,0.025297742,0.023227436,0.7828645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99578124,0.0011440053,0.0006439829,0.0009684006,0.001219373,0.0002430156],"domain_scores_gemma":[0.99607337,0.0006190899,0.0007324127,0.0016832728,0.00078752043,0.00010434939],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0052860607,0.00018441518,0.00045800768,0.0036130762,0.0004108583,0.0010710246,0.0028783327,0.00016004073,0.038586836],"category_scores_gemma":[0.037912562,0.00016059024,0.00011422056,0.008564503,0.00018187938,0.00026803013,0.0026828996,0.00020116928,0.0027288578],"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":[0.000015319638,0.000051820807,0.000018940073,0.000061226,0.00044412792,0.000005047335,0.0004673152,0.000091632064,0.0002507926,0.0021271273,0.8951317,0.10133494],"study_design_scores_gemma":[0.000109079716,0.000055840672,0.00014681854,0.00008471121,0.0003160161,0.0000112258695,0.0006544845,0.013044555,0.000019602694,0.001023793,0.9843731,0.00016075835],"about_ca_topic_score_codex":0.00016385892,"about_ca_topic_score_gemma":0.0000019547915,"teacher_disagreement_score":0.19257572,"about_ca_system_score_codex":0.00009555546,"about_ca_system_score_gemma":0.0000071992135,"threshold_uncertainty_score":0.99996597},"labels":[],"label_agreement":null},{"id":"W6931487531","doi":"10.5281/zenodo.4282826","title":"Cell phone wholesale Supplier","year":2020,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Phone; Mobile phone; GSM; Android (operating system); Bluetooth","score_opus":0.27671437431498436,"score_gpt":0.367958102016373,"score_spread":0.09124372770138867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931487531","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048543836,0.00052085746,0.012285049,0.0007177887,0.000434626,0.00036072466,0.0004870001,0.0013199532,0.98382545],"genre_scores_gemma":[0.0064479164,0.00041702474,0.010584409,0.00066709414,0.0014121523,6.216015e-8,0.0013889164,0.014257652,0.9648248],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99570334,0.0009463129,0.00051147625,0.0009963328,0.0013757194,0.00046682844],"domain_scores_gemma":[0.99680054,0.00096264237,0.00048344786,0.001096408,0.00033592203,0.00032104083],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026113081,0.0002633647,0.00043600402,0.0009897586,0.0009630564,0.0015172418,0.0034220265,0.00020591458,0.23693317],"category_scores_gemma":[0.028226202,0.00022961368,0.0001263081,0.0026960678,0.00019666963,0.000102953294,0.0023509369,0.0005181769,0.08214686],"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":[0.0000135523915,0.00004459291,0.0000040108102,0.000026463656,0.000017090828,0.00001702997,0.00017761055,0.000003589985,0.00032829779,0.00024080121,0.89326274,0.10586423],"study_design_scores_gemma":[0.00035578376,0.00010073879,0.0001266223,0.00002782088,0.000011299819,0.000028603345,0.00029748815,0.000076711134,0.000080795944,0.00057135546,0.99807096,0.00025183702],"about_ca_topic_score_codex":0.000023905064,"about_ca_topic_score_gemma":2.0031625e-7,"teacher_disagreement_score":0.15478632,"about_ca_system_score_codex":0.00006128898,"about_ca_system_score_gemma":0.0000058153564,"threshold_uncertainty_score":0.9995193},"labels":[],"label_agreement":null},{"id":"W6931558491","doi":"10.5281/zenodo.5845537","title":"D4.4 - Predictive Algorithms v2","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian AIDS Treatment Information Exchange","funders":"European Commission","keywords":"Deliverable; Quality (philosophy); Time series; Production (economics); Technology forecasting; Data quality","score_opus":0.4600617377092396,"score_gpt":0.402298141441583,"score_spread":0.05776359626765659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931558491","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024154343,0.0002699003,0.36277032,0.009149255,0.0005373333,0.00069323956,0.00039355687,0.0022619953,0.59977007],"genre_scores_gemma":[0.9821397,0.00008336492,0.012042885,0.0016402096,0.00083263573,5.0044854e-8,0.00026961035,0.0012737106,0.0017178033],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964501,0.00093513704,0.0004433752,0.0006756393,0.00113014,0.0003655801],"domain_scores_gemma":[0.9965055,0.0015053984,0.0002097417,0.000524745,0.00090672786,0.00034788455],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033977828,0.00013016003,0.00021954843,0.00031442472,0.0015902265,0.0012350309,0.0022063416,0.00006314742,0.018840333],"category_scores_gemma":[0.11117177,0.0001098014,0.00007883658,0.0029390864,0.00016545055,0.00033175704,0.0016900632,0.00030884732,0.011568159],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006705231,0.00004740463,0.000064773914,0.000008206287,0.00002524328,0.000017278131,0.0015557944,0.00015087603,0.0008812927,0.0012800089,0.36174017,0.6341619],"study_design_scores_gemma":[0.0003414556,0.0003745663,0.0040150736,0.0000068491254,0.0000062812337,0.00003947043,0.0010825992,0.006921161,0.0001724665,0.0021250085,0.9847807,0.00013432573],"about_ca_topic_score_codex":0.0000060642947,"about_ca_topic_score_gemma":2.2484382e-8,"teacher_disagreement_score":0.9579854,"about_ca_system_score_codex":0.000053638036,"about_ca_system_score_gemma":0.0000039245833,"threshold_uncertainty_score":0.99980175},"labels":[],"label_agreement":null},{"id":"W6931578684","doi":"10.5284/1078666","title":"Archaeological Excavation at Prince Albert School, Perry Barr, Birmingham","year":2019,"lang":"en","type":"article","venue":"Archaeology Data Service","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excavation; Assemblage (archaeology); Period (music); Archaeological science","score_opus":0.40638886031471877,"score_gpt":0.44766721082388133,"score_spread":0.041278350509162565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931578684","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":[0.9699201,0.0004301542,0.0067535928,0.013951404,0.0013630318,0.0004405332,0.000081541344,0.00016575126,0.0068939007],"genre_scores_gemma":[0.8833557,0.00017088761,0.09632965,0.009827496,0.0003289934,0.000028383678,0.00038061794,0.0000361235,0.009542179],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99385214,0.0012270431,0.0010089369,0.001924609,0.0011758695,0.0008114262],"domain_scores_gemma":[0.9640171,0.03013852,0.0005205395,0.004567576,0.00042636506,0.00032991834],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.008784903,0.00030966641,0.0006409136,0.00059382047,0.00023401993,0.0000504684,0.0060694246,0.00029464831,0.005885744],"category_scores_gemma":[0.059001382,0.00022780485,0.00007846303,0.0026187983,0.0004692155,0.0008593606,0.012729961,0.0005425819,0.007128314],"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":[0.0001317744,0.000045965095,0.96826726,0.000020181193,0.000030650812,0.000027135971,0.0006441711,0.0001379345,0.00099618,0.0023300005,0.0043211128,0.023047617],"study_design_scores_gemma":[0.0007526651,0.000179878,0.65457094,0.000022918683,0.000015760503,0.00023978812,0.000596407,0.0111312745,0.00009545211,0.03688448,0.2951232,0.0003872702],"about_ca_topic_score_codex":0.0008330473,"about_ca_topic_score_gemma":0.0013428174,"teacher_disagreement_score":0.31369635,"about_ca_system_score_codex":0.00006950284,"about_ca_system_score_gemma":0.0001307677,"threshold_uncertainty_score":0.9993082},"labels":[],"label_agreement":null},{"id":"W6931600444","doi":"10.5281/zenodo.7399723","title":"Fig. 9 in Revision of Quedius sensu stricto (Coleoptera: Staphylinidae)","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Sensu stricto; Taxonomy (biology); Sensu; Gastropoda; Taxon","score_opus":0.24104761458383148,"score_gpt":0.38270094550570877,"score_spread":0.1416533309218773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931600444","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016559506,0.00078031665,0.0017786586,0.0002044225,0.00038335807,0.0006215716,0.00057407876,0.0004449918,0.9935567],"genre_scores_gemma":[0.21537152,0.0049048727,0.022203619,0.0006705402,0.0017458411,3.2484326e-7,0.004211397,0.025075221,0.72581667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940297,0.0021583252,0.0008836111,0.00084869517,0.0016789691,0.00040067144],"domain_scores_gemma":[0.99557185,0.0017567397,0.00084870594,0.0012141939,0.00046093718,0.00014757233],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0066396412,0.00022922312,0.0005474552,0.002639555,0.00055022456,0.00045841408,0.0026345965,0.00016317777,0.21258284],"category_scores_gemma":[0.061328687,0.00020697872,0.00012677876,0.004631534,0.00014001546,0.000100902966,0.0026324042,0.0005964601,0.002183196],"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":[0.000029729032,0.00008035783,0.00017724837,0.000043724394,0.000017049322,0.000021568041,0.0002293276,0.000031162555,0.000022822716,0.00036635032,0.7277497,0.271231],"study_design_scores_gemma":[0.0004171137,0.00022102162,0.0023063743,0.00008578088,0.000006852647,0.000018710123,0.0005955787,0.00010475479,0.0000069357807,0.00036453558,0.99567616,0.0001961932],"about_ca_topic_score_codex":0.00015326239,"about_ca_topic_score_gemma":0.0000026937598,"teacher_disagreement_score":0.27103478,"about_ca_system_score_codex":0.00014668626,"about_ca_system_score_gemma":0.000009515788,"threshold_uncertainty_score":0.99859375},"labels":[],"label_agreement":null},{"id":"W6931601939","doi":"10.5281/zenodo.6568100","title":"Quantifying phenology and migratory behaviours of hummingbirds using single-site dynamics and mark-detection analyses","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nucleofection; Hyporeflexia; TSG101; Articular cartilage damage; Proteogenomics; Gestational period","score_opus":0.4961460571222674,"score_gpt":0.4358327115638864,"score_spread":0.06031334555838097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931601939","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":[0.56901103,0.0067145117,0.06254249,0.00017546378,0.0011286981,0.0011509228,0.0015842412,0.0015275761,0.35616505],"genre_scores_gemma":[0.90437204,0.0013022519,0.030950274,0.00015688936,0.0005768748,1.9783893e-7,0.0013817145,0.013182275,0.04807746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666137,0.0012281361,0.00047135793,0.0006768775,0.00068418164,0.00027806262],"domain_scores_gemma":[0.99753404,0.00085983414,0.00068179367,0.00052982423,0.0002866153,0.00010788394],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002854416,0.0001908119,0.00040598816,0.00192772,0.0010783013,0.0004785862,0.00073405803,0.00014858536,0.010963816],"category_scores_gemma":[0.015264072,0.0001834191,0.00006190171,0.0018330074,0.00033821794,0.00011000014,0.001675122,0.00034332296,0.000048347898],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086353706,0.00015456926,0.0025972365,0.00015375619,0.00016007655,0.00003534165,0.0008161774,0.000055010372,0.012344046,0.00046323377,0.05385375,0.92928046],"study_design_scores_gemma":[0.00076486,0.00073845737,0.009211137,0.00012878161,0.00018226242,0.0004562668,0.004795306,0.0077170082,0.00026183334,0.00047588267,0.97462666,0.0006415425],"about_ca_topic_score_codex":0.00025503524,"about_ca_topic_score_gemma":0.000020866057,"teacher_disagreement_score":0.92863894,"about_ca_system_score_codex":0.00012496306,"about_ca_system_score_gemma":0.0000041636335,"threshold_uncertainty_score":0.9930308},"labels":[],"label_agreement":null},{"id":"W6931623390","doi":"10.5281/zenodo.5593277","title":"The taxonomic and functional biogeographies of phytoplankton and zooplankton communities across boreal lakes - script","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Zooplankton; Phytoplankton; Boreal; Biomass (ecology); Plankton; Community structure; Community","score_opus":0.2510894746392351,"score_gpt":0.3555392660524237,"score_spread":0.10444979141318861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931623390","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040445246,0.015534996,0.0017053412,0.0006393553,0.0008445304,0.00057640637,0.002255876,0.00047964737,0.9375186],"genre_scores_gemma":[0.6520091,0.04013529,0.0049584685,0.0004716309,0.00165558,8.0986985e-7,0.0070264316,0.009134291,0.28460833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99757653,0.00086778717,0.00036982182,0.00035661357,0.0005522572,0.00027697533],"domain_scores_gemma":[0.9963453,0.0021800974,0.00038779565,0.0006191268,0.00037668244,0.000091040136],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030879679,0.00016840547,0.00030434105,0.0004986929,0.002092154,0.0013601776,0.0008828722,0.000114935276,0.004509243],"category_scores_gemma":[0.008140558,0.000120953715,0.000056153807,0.0009949511,0.0010794079,0.00007652162,0.0016248187,0.00027730543,0.00006494437],"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":[0.000045965313,0.000027095404,0.0009156731,0.000057237015,0.000082709026,0.0000030608867,0.0005196989,0.0000012845502,0.00011937677,0.002060686,0.8268699,0.16929731],"study_design_scores_gemma":[0.00023591994,0.000088802066,0.01268754,0.00007343656,0.000009081242,0.000074730255,0.0050006052,0.000042387164,0.000022691775,0.0006424033,0.980998,0.00012439836],"about_ca_topic_score_codex":0.00020320123,"about_ca_topic_score_gemma":0.000028143393,"teacher_disagreement_score":0.65291023,"about_ca_system_score_codex":0.000015068635,"about_ca_system_score_gemma":0.000004575383,"threshold_uncertainty_score":0.9996765},"labels":[],"label_agreement":null},{"id":"W6931625903","doi":"10.5281/zenodo.7875162","title":"Diploneis duplex Jovanovska & Wilson & Hamilton & Stone 2023, sp. nov.","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Museum of Nature","funders":"","keywords":"Raphe; Bent molecular geometry; Ridge; Apex (geometry); Lateral wall","score_opus":0.39351441434039497,"score_gpt":0.4134727397543485,"score_spread":0.019958325413953537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931625903","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":[0.6620475,0.00039143476,0.032446545,0.004075988,0.0015348059,0.0010041383,0.00041747934,0.004642378,0.29343975],"genre_scores_gemma":[0.9686764,0.00047353248,0.003362543,0.0005072988,0.0006082987,1.5074336e-7,0.0008470586,0.0018576679,0.023667054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99492544,0.0010648314,0.0006793926,0.00091552275,0.0016925604,0.0007222806],"domain_scores_gemma":[0.99480873,0.002403249,0.00030311852,0.0011611345,0.0010296262,0.00029416787],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008354594,0.00021217499,0.00033946952,0.0013436818,0.0025933771,0.001694764,0.0026879583,0.00010687125,0.019840106],"category_scores_gemma":[0.06604685,0.00018520103,0.00012604946,0.008381533,0.00024030214,0.00043587814,0.0019736432,0.00039458965,0.053061403],"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":[0.000056362387,0.00008462869,0.00015762482,0.000016217282,0.000031146934,0.000044748394,0.00084646215,0.00024859776,0.0063205403,0.0017558049,0.6043784,0.38605943],"study_design_scores_gemma":[0.00043836405,0.0001830855,0.022615813,0.000020921025,0.00000821894,0.00006416388,0.00091716816,0.0020481534,0.00024960726,0.0019602943,0.9712688,0.00022543875],"about_ca_topic_score_codex":0.000035320827,"about_ca_topic_score_gemma":6.1840495e-7,"teacher_disagreement_score":0.385834,"about_ca_system_score_codex":0.00011017213,"about_ca_system_score_gemma":0.0000060686766,"threshold_uncertainty_score":0.99934155},"labels":[],"label_agreement":null},{"id":"W6931656224","doi":"10.5281/zenodo.5524281","title":"Future interpretation in Gitksan and reduced clausal complements","year":2021,"lang":"en","type":"book-chapter","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interpretation (philosophy); Focus (optics); Covert; Conjunction (astronomy); Connection (principal bundle); Complement (music); Margin (machine learning); Feature (linguistics); Semantic interpretation","score_opus":0.32325371558040833,"score_gpt":0.39839715171595125,"score_spread":0.07514343613554292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931656224","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035918641,0.00074595626,0.0032349147,0.00093413115,0.0005722612,0.00045341183,0.00022644586,0.0002511464,0.9899899],"genre_scores_gemma":[0.47051376,0.0035672174,0.022605604,0.0016720629,0.0031850145,2.8438188e-7,0.009140994,0.008014655,0.4813004],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99660116,0.00059813936,0.0007016129,0.00083529536,0.000965305,0.0002984995],"domain_scores_gemma":[0.9970461,0.0010149236,0.00038766643,0.00063408975,0.00076496764,0.00015223588],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033752115,0.00021941015,0.00038749565,0.0010009017,0.000809236,0.0013833728,0.0011982739,0.00017160314,0.022494482],"category_scores_gemma":[0.015712447,0.00020545574,0.0000728357,0.00064350216,0.00015250308,0.0002096783,0.0017532723,0.0005514688,0.0012016662],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006901684,0.000030661315,0.000018449304,0.000031775162,0.000039006838,0.000043743392,0.0008619397,0.00000941205,0.00038164412,0.030465292,0.09446966,0.8735794],"study_design_scores_gemma":[0.000375385,0.00013606953,0.0026071302,0.00010682247,0.000009876292,0.00008179872,0.0006207517,0.0002739464,0.000012573929,0.012148691,0.98341066,0.00021627138],"about_ca_topic_score_codex":0.000005738721,"about_ca_topic_score_gemma":0.0000011942925,"teacher_disagreement_score":0.88894105,"about_ca_system_score_codex":0.00012414002,"about_ca_system_score_gemma":0.000007267204,"threshold_uncertainty_score":0.9996533},"labels":[],"label_agreement":null},{"id":"W6931669292","doi":"10.5281/zenodo.6003215","title":"Sphecodes davisii Robertson 1897","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Synonym (taxonomy); George (robot); Taxonomy (biology); Key (lock)","score_opus":0.4448891735767351,"score_gpt":0.43268909944188794,"score_spread":0.012200074134847139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931669292","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08228883,0.00016209284,0.030052949,0.002528405,0.0007021348,0.00034575304,0.00009590075,0.0007748387,0.8830491],"genre_scores_gemma":[0.9879764,0.00006223288,0.0048374543,0.00015318595,0.0002881374,2.034523e-8,0.00006181134,0.00065445155,0.0059663546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967722,0.00068121805,0.00044400527,0.0006570997,0.0010133471,0.00043210541],"domain_scores_gemma":[0.99534047,0.0012896198,0.0004400136,0.0018430678,0.00086575904,0.000221081],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006460468,0.00014134214,0.00023617128,0.00038071087,0.007001261,0.005614598,0.0046243966,0.00007213699,0.028976467],"category_scores_gemma":[0.1549253,0.00011732667,0.00009041691,0.00070531515,0.00028614124,0.0006381304,0.0028529959,0.00025917124,0.009129498],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027537331,0.00005067215,0.00027338148,0.0000063813886,0.000014219947,0.000013618912,0.00027863393,0.000028845077,0.0009074465,0.0038044443,0.24176446,0.7528304],"study_design_scores_gemma":[0.0003088903,0.00011556167,0.030767258,0.000014923031,0.0000051524244,0.000059882404,0.00031455094,0.00065143756,0.00022867126,0.0068683196,0.9605139,0.00015144197],"about_ca_topic_score_codex":0.00004911291,"about_ca_topic_score_gemma":5.412292e-7,"teacher_disagreement_score":0.9056875,"about_ca_system_score_codex":0.000061886916,"about_ca_system_score_gemma":0.0000032485195,"threshold_uncertainty_score":0.99541765},"labels":[],"label_agreement":null},{"id":"W6931670007","doi":"10.5281/zenodo.7971903","title":"Antibody Characterization Report for Valosin-containing protein VCP","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Antibody; Immunoprecipitation; Amyotrophic lateral sclerosis; Protein A; Disease","score_opus":0.37925373569199927,"score_gpt":0.43575054079934095,"score_spread":0.056496805107341674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931670007","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":[0.3160323,0.000021681994,0.6324812,0.0018592142,0.00056098064,0.0014646597,0.00024688477,0.0020673596,0.04526573],"genre_scores_gemma":[0.9507649,0.000038040773,0.0074717076,0.00023688425,0.00075978535,8.065827e-7,0.027769923,0.0017877696,0.011170171],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965416,0.00063777267,0.0006821306,0.00072723866,0.0009276115,0.00048363666],"domain_scores_gemma":[0.9960001,0.0013143274,0.00044412503,0.00074679084,0.0013392351,0.00015543093],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010242363,0.00014434183,0.00025233335,0.00089868566,0.0022861045,0.0014873897,0.0013639033,0.00007981302,0.0026628645],"category_scores_gemma":[0.11996347,0.00012897277,0.00009669368,0.0037887509,0.00009451417,0.0004148955,0.00094703806,0.00017909965,0.003442381],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016196347,0.000087413944,0.00040008858,0.00005116656,0.000043675565,0.00009156256,0.0011565672,0.00005671358,0.544638,0.0039310534,0.020152004,0.4292298],"study_design_scores_gemma":[0.0003878859,0.00025638135,0.02129038,0.000030324765,0.0000064244937,0.00012279295,0.0005065221,0.0026721742,0.000658385,0.0029906675,0.9709011,0.00017696024],"about_ca_topic_score_codex":0.0000056001413,"about_ca_topic_score_gemma":5.5174613e-8,"teacher_disagreement_score":0.9507491,"about_ca_system_score_codex":0.00006717879,"about_ca_system_score_gemma":0.0000074290183,"threshold_uncertainty_score":0.99954915},"labels":[],"label_agreement":null},{"id":"W6931688466","doi":"10.5282/rcc/5646","title":"Removing the People: The Creation of Canada’s Kouchibouguac National Park","year":2018,"lang":"en","type":"article","venue":"Universitätsbibliothek der LMU","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"National park; Government (linguistics); Resistance (ecology); National government; Compensation (psychology)","score_opus":0.1987253379810194,"score_gpt":0.39708381832615786,"score_spread":0.19835848034513845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931688466","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28469905,0.00049552124,0.04518576,0.020427432,0.0017594136,0.00040449327,0.000061882434,0.000058450758,0.646908],"genre_scores_gemma":[0.99122584,0.000022462233,0.0026957125,0.0008403992,0.00021259298,6.741053e-7,0.000001577729,0.000006429838,0.0049943076],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99705637,0.0004709219,0.00032609527,0.00028051846,0.0016275919,0.00023850154],"domain_scores_gemma":[0.9762729,0.021504391,0.00042259658,0.00062644563,0.001108846,0.0000648506],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045500495,0.00010218171,0.00016776017,0.0011914115,0.00074688834,0.00014342454,0.0013588013,0.000044246946,0.0011516763],"category_scores_gemma":[0.026698941,0.000052905463,0.00006830094,0.00959983,0.00026373402,0.00035747554,0.00021526376,0.0001302586,0.000016647451],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120229706,0.00004969141,0.07964337,0.0000074496465,0.0001550757,0.000007383453,0.004817534,0.0005037459,0.00052848615,0.047072552,0.81415564,0.052938838],"study_design_scores_gemma":[0.000393189,0.000069005764,0.5592549,0.000021005482,0.000034904184,0.000029383953,0.010261702,0.004220452,0.00040498207,0.026859118,0.39826092,0.00019045417],"about_ca_topic_score_codex":0.048446894,"about_ca_topic_score_gemma":0.148249,"teacher_disagreement_score":0.70652676,"about_ca_system_score_codex":0.000096794465,"about_ca_system_score_gemma":0.0008383924,"threshold_uncertainty_score":0.9997614},"labels":[],"label_agreement":null},{"id":"W6931845967","doi":"10.5683/sp3/snlokv","title":"UNI-CEN Boundaries (CBF-Original Shorelines) - Province/Territory (PR) - 1861 - File Geodatabase format (WGS84 / EPSG:4326)","year":2023,"lang":"en","type":"dataset","venue":"Borealis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Shapefile; File format; North American Datum of 1927; Documentation; Data file; Web mapping; Geocoding; File Transfer Protocol","score_opus":0.2716714919249668,"score_gpt":0.4333443359490652,"score_spread":0.16167284402409837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931845967","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038638285,0.00062031735,0.0006428541,0.0005325485,0.0045518996,0.0006793626,0.99078405,0.0004214845,0.001728834],"genre_scores_gemma":[0.0000020252182,0.0004950897,0.0066155596,0.0005186992,0.002177072,0.0001711442,0.98761725,0.00008380406,0.0023193578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9895898,0.00095974543,0.0023453531,0.0019272249,0.0037540274,0.0014238526],"domain_scores_gemma":[0.97078097,0.022191793,0.0016145041,0.0042203045,0.000629037,0.0005633698],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008858948,0.00096811255,0.0016167705,0.0021192622,0.0014245093,0.0027068215,0.0049346373,0.000760081,0.0027989638],"category_scores_gemma":[0.084997006,0.0007283113,0.0005226181,0.0028268448,0.00095422886,0.00095143163,0.0017472672,0.0013182855,0.002233691],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008732473,0.00008558286,0.00013835891,0.00010844667,0.000067585584,0.00035591828,0.0000423855,0.000009954069,5.8555275e-7,0.000104258885,0.98335236,0.015647212],"study_design_scores_gemma":[0.00044241053,0.00017603525,0.0013893838,0.00020176198,0.00009744454,0.00008641168,0.00038752705,0.000199398,0.000004525565,0.0028020875,0.993353,0.0008600223],"about_ca_topic_score_codex":0.11208811,"about_ca_topic_score_gemma":0.03923154,"teacher_disagreement_score":0.07613806,"about_ca_system_score_codex":0.0002443253,"about_ca_system_score_gemma":0.0015214448,"threshold_uncertainty_score":0.9998755},"labels":[],"label_agreement":null},{"id":"W6931848984","doi":"10.5281/zenodo.7393746","title":"Dataset for \"Gender and Gender Research in a Research Community: CSTT as a Case Study\"","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Academy of Finland","keywords":"Research methodology; Qualitative research; Research design; Research data; Social research","score_opus":0.8755439207648151,"score_gpt":0.5763696076753153,"score_spread":0.2991743130894998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931848984","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012151075,0.00039923412,0.000100209596,0.00027028203,0.00027405817,0.0031014124,0.9790435,0.00012091005,0.004539332],"genre_scores_gemma":[0.013753717,0.0003025264,0.0003620031,0.00016694704,0.00021742622,0.0000044400463,0.9838289,0.0010128708,0.00035116702],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95679736,0.034245946,0.0012151035,0.0017289858,0.004600666,0.0014119485],"domain_scores_gemma":[0.95901793,0.033065353,0.00040077182,0.0041410583,0.0028452093,0.00052967196],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.12949342,0.0003880529,0.00072801026,0.00641816,0.013246987,0.0041815327,0.007175063,0.00027086836,0.05385879],"category_scores_gemma":[0.21228306,0.00036220643,0.00009529186,0.009806977,0.00083881,0.00041983128,0.020103948,0.0052846973,0.0017434414],"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":[0.00021982857,0.00079335534,0.000018400648,0.00016095994,0.000068007954,0.0014768114,0.0027832065,0.000012227219,0.000008989236,0.00009905469,0.9653541,0.02900509],"study_design_scores_gemma":[0.0011576741,0.0014116827,0.00020013949,0.000022255532,0.00002065481,0.0023420225,0.056467798,0.00006999372,0.0000011275495,0.0055881944,0.9323936,0.00032483257],"about_ca_topic_score_codex":0.0033020556,"about_ca_topic_score_gemma":0.00005473173,"teacher_disagreement_score":0.08278964,"about_ca_system_score_codex":0.0004988433,"about_ca_system_score_gemma":0.00006563032,"threshold_uncertainty_score":0.999883},"labels":[],"label_agreement":null},{"id":"W6931853234","doi":"10.5683/sp3/hiyf3g","title":"Enquête sur la population active, août 2021 [Canada] [Remanié 2025]","year":2023,"lang":"fr","type":"dataset","venue":"Borealis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Population; Research methodology; Publics; Social interest","score_opus":0.24804863310326453,"score_gpt":0.4201734021762265,"score_spread":0.17212476907296198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931853234","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004195093,0.0008517347,0.0003407624,0.0014560332,0.004980302,0.00046512045,0.98405504,0.000069586575,0.0073619024],"genre_scores_gemma":[0.00008469676,0.0020322222,0.002652675,0.00036675643,0.0013344818,0.000056329172,0.9797244,0.00007288203,0.013675524],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903556,0.0023342993,0.0016365339,0.0016190598,0.0030537746,0.0010007096],"domain_scores_gemma":[0.9284769,0.06717219,0.0013159259,0.002049861,0.00057489873,0.00041019716],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006575085,0.00068538287,0.0012829677,0.0010635669,0.00048615818,0.00061912136,0.002300656,0.00076501956,0.0012952666],"category_scores_gemma":[0.15734655,0.0006025051,0.0003387276,0.00471687,0.00017854512,0.0004231205,0.0007828375,0.00096585765,0.0006767079],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003449492,0.000044695284,0.001553146,0.00004773984,0.000080574784,0.00027354894,0.00001940237,0.00009693164,0.0000024014369,0.00020199185,0.7871544,0.21049072],"study_design_scores_gemma":[0.00029351158,0.00005591089,0.1513034,0.00020761907,0.000092427515,0.000029311805,0.00024558452,0.00042953258,0.0000066302773,0.0027746302,0.8440239,0.0005375535],"about_ca_topic_score_codex":0.9845262,"about_ca_topic_score_gemma":0.96802926,"teacher_disagreement_score":0.20995316,"about_ca_system_score_codex":0.00046470083,"about_ca_system_score_gemma":0.0010654543,"threshold_uncertainty_score":0.9996426},"labels":[],"label_agreement":null},{"id":"W6931876920","doi":"10.5441/001/1.d5d912c4","title":"Data from: Study \"Arctic hare Alert - Argos tracking\"","year":2021,"lang":"en","type":"dataset","venue":"Movebank","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"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":"Habitat; Arctic; Settlement (finance); The arctic; Satellite tracking; Satellite","score_opus":0.7802625651926195,"score_gpt":0.5419720276820693,"score_spread":0.23829053751055018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931876920","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022906528,0.0021659543,0.00029003152,0.00015132308,0.004654169,0.0004625061,0.98960274,0.000065393004,0.00031725015],"genre_scores_gemma":[0.00053185545,0.0001371158,0.0025733958,0.00060715165,0.0010996998,0.000028590306,0.9936572,0.000032685573,0.0013323363],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98969954,0.0018538204,0.0016409127,0.0028598905,0.0033344212,0.00061140786],"domain_scores_gemma":[0.9403058,0.046781424,0.0011248474,0.01094659,0.000600628,0.00024068507],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0095424885,0.00054859644,0.0013459382,0.00075952325,0.0002852929,0.0017205074,0.009554674,0.0004183404,0.016840445],"category_scores_gemma":[0.2895418,0.00041225515,0.00021347757,0.0031285982,0.00010020166,0.0005098771,0.0039923484,0.0011323927,0.0020115748],"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":[0.000015043129,0.00036030254,0.012874386,0.000014540256,0.0001257276,0.00041412102,0.000027648712,0.0000058031574,0.0000016057959,3.4220793e-7,0.96936977,0.01679073],"study_design_scores_gemma":[0.00045170754,0.000085572974,0.08071324,0.000085385924,0.000119459844,0.000011746497,0.0005742803,0.00009100434,0.0000021486596,0.00092766527,0.9164976,0.00044021223],"about_ca_topic_score_codex":0.0021225323,"about_ca_topic_score_gemma":0.0007135292,"teacher_disagreement_score":0.27999932,"about_ca_system_score_codex":0.00007261911,"about_ca_system_score_gemma":0.0002301385,"threshold_uncertainty_score":0.9998329},"labels":[],"label_agreement":null},{"id":"W6931878795","doi":"10.5683/sp3/v8ynkc","title":"Perry River (West) British Columbia. 1:50,000. Map Sheet 082M02, ed. 1, 1962","year":2022,"lang":"en","type":"dataset","venue":"Borealis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Georeference; General partnership; Natural (archaeology); Raster graphics; Topographic map (neuroanatomy); Aerial photography; Government (linguistics); Geographic information system","score_opus":0.18635470878354493,"score_gpt":0.39232408106127,"score_spread":0.20596937227772505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931878795","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017561132,0.0023880382,0.00007364372,0.00020771663,0.0033585113,0.0004657602,0.98882186,0.0001526634,0.004356201],"genre_scores_gemma":[0.000008931383,0.0011790129,0.0029039902,0.0013675824,0.00088383263,0.00013839046,0.9864968,0.000055467182,0.0069659967],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898179,0.0016581129,0.0016416295,0.0019899874,0.0038777355,0.0010146231],"domain_scores_gemma":[0.9771218,0.017771613,0.0012049412,0.0030754958,0.00040453416,0.0004216164],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0091575235,0.00046676424,0.0013734899,0.00070092815,0.0009266412,0.0028653443,0.004990187,0.00057320413,0.18330272],"category_scores_gemma":[0.061640725,0.0005850789,0.00054468476,0.0023817313,0.00042025308,0.000298737,0.0020048665,0.0012712043,0.00021957791],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012295396,0.00010476805,0.001909297,0.000031082654,0.00005405797,0.00043158358,0.00004173184,0.000009987713,2.7413557e-7,0.0000029070009,0.9538448,0.043557227],"study_design_scores_gemma":[0.00037957839,0.00014434876,0.045251735,0.000054836983,0.00007867788,0.00019491915,0.0002725001,0.000011265757,1.0419503e-7,0.003129849,0.94982,0.0006621811],"about_ca_topic_score_codex":0.6760199,"about_ca_topic_score_gemma":0.19709723,"teacher_disagreement_score":0.4789227,"about_ca_system_score_codex":0.00027755383,"about_ca_system_score_gemma":0.0004476043,"threshold_uncertainty_score":0.9996601},"labels":[],"label_agreement":null},{"id":"W6931964850","doi":"10.5683/sp3/9y13xp","title":"Fort Frances Ontario. 1:50,000. Map Sheet 052C11, ed. 3, 1994","year":2021,"lang":"en","type":"dataset","venue":"Borealis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Georeference; General partnership; Raster graphics; Natural (archaeology); Aerial photography; Viewshed analysis; Government (linguistics); Topographic map (neuroanatomy)","score_opus":0.26077875975779713,"score_gpt":0.42307144860507606,"score_spread":0.16229268884727893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931964850","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000050498995,0.003517057,0.0006589872,0.00029777962,0.003983148,0.00027437124,0.98376364,0.000078023426,0.0073765074],"genre_scores_gemma":[0.000004062349,0.0007119941,0.012992183,0.0010367524,0.0010892642,0.000055206874,0.9815672,0.000029159326,0.0025141605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99209136,0.0007058762,0.0016398545,0.001700007,0.0030030985,0.00085982704],"domain_scores_gemma":[0.9778356,0.01704686,0.0011181666,0.0033144103,0.00034517987,0.00033976842],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0067874594,0.00062211865,0.001480738,0.0009481726,0.0003563777,0.0009388647,0.0035591293,0.00069442537,0.0072034188],"category_scores_gemma":[0.03777094,0.00045797304,0.00053731527,0.0018023965,0.00020214771,0.0002886819,0.00085291226,0.00096238876,0.00016205189],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020063198,0.000062204555,0.0019091674,0.000029285755,0.000065210166,0.00014732909,0.0000453485,0.000010559658,6.619444e-7,0.000019574009,0.976464,0.021226592],"study_design_scores_gemma":[0.0002551026,0.00008102309,0.010054445,0.00011013019,0.00006909227,0.000036448284,0.00021950612,0.0000063169687,0.000004555362,0.0042607756,0.9843441,0.0005584816],"about_ca_topic_score_codex":0.5268488,"about_ca_topic_score_gemma":0.39999738,"teacher_disagreement_score":0.12685142,"about_ca_system_score_codex":0.00016997253,"about_ca_system_score_gemma":0.0005417743,"threshold_uncertainty_score":0.9997872},"labels":[],"label_agreement":null},{"id":"W6931966748","doi":"10.5285/189900a4-f7a9-41bd-b6f5-eef694209f87","title":"Soil moisture profiles from permafrost in subarctic Canada","year":2016,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Permafrost; Subarctic climate; Black spruce; Peat; Moisture; Taiga; Water content","score_opus":0.33785906224094164,"score_gpt":0.44745951900559405,"score_spread":0.10960045676465241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931966748","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009042541,0.00034140053,0.000007323455,0.00062485563,0.0016668356,0.0003764416,0.98531175,7.601966e-7,0.0026281138],"genre_scores_gemma":[0.00075268396,0.000072986746,0.0036483041,0.0002827661,0.0004752817,0.00004070726,0.99007624,0.000018076193,0.0046329643],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99528736,0.00072178204,0.00092676777,0.0011691196,0.0014389217,0.00045607844],"domain_scores_gemma":[0.97501016,0.022412434,0.00065504207,0.0015950587,0.00015879635,0.00016850805],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040801843,0.00031915426,0.0008181113,0.00038096448,0.00012649706,0.0007540044,0.004857378,0.00030384085,0.024897961],"category_scores_gemma":[0.062193982,0.00019326505,0.00006968349,0.0012151962,0.0000821322,0.00022399316,0.0012735568,0.00050587393,0.00065208325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018862458,0.000017807466,0.0064988458,0.0000024940864,0.000011454696,0.00011965689,0.000019716997,0.0000018379095,0.000009616894,1.7142723e-7,0.91376454,0.07953498],"study_design_scores_gemma":[0.0003220538,0.000018933288,0.023427544,0.00012142513,0.000013339609,0.000005827177,0.00030268158,0.000004921564,0.00004105354,0.0006538088,0.9747946,0.0002937907],"about_ca_topic_score_codex":0.8345827,"about_ca_topic_score_gemma":0.9580215,"teacher_disagreement_score":0.123438835,"about_ca_system_score_codex":0.00020590113,"about_ca_system_score_gemma":0.0016433815,"threshold_uncertainty_score":0.9759934},"labels":[],"label_agreement":null},{"id":"W6939683082","doi":"10.6084/m9.figshare.14881026","title":"Additional file 3 of Assessing the performance of a method for case-mix adjustment in the Korean Diagnosis-Related Groups (KDRG) system and its policy implications","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sample (material); Data collection; Government (linguistics); Table (database)","score_opus":0.36796613395005184,"score_gpt":0.4675532896902662,"score_spread":0.09958715574021437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939683082","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048810923,0.0005044775,0.0000394116,0.00038382565,0.000025171505,0.0003372857,0.99235535,0.000010450572,0.0014629473],"genre_scores_gemma":[0.71098363,0.000020977348,0.048123036,0.00039139084,0.00027156877,0.007529253,0.23237683,0.000026023103,0.00027729844],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99819934,0.0005576007,0.000513578,0.00024585906,0.00033094257,0.00015266644],"domain_scores_gemma":[0.8594598,0.13928352,0.00044946474,0.00034388603,0.00043461143,0.00002869151],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012287714,0.00008423498,0.0002159728,0.00018489332,0.00018677674,0.000068301684,0.00038031559,0.00005706013,0.2473048],"category_scores_gemma":[0.15401952,0.00004618027,0.00008315354,0.0020999522,0.000013315783,0.00013476035,0.0001323757,0.0001045425,0.000014408439],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016816026,0.000035182595,0.00016627631,0.00010763367,0.000014003181,0.0000065363556,0.00029375457,0.00006693247,0.000011185666,0.0004706593,0.945942,0.052884154],"study_design_scores_gemma":[0.00080855354,0.00023315394,0.7042496,0.0060999384,0.000050432354,0.002590432,0.01739062,0.07679025,0.0007411338,0.0031125143,0.18755902,0.00037432712],"about_ca_topic_score_codex":0.000011551127,"about_ca_topic_score_gemma":0.000010230665,"teacher_disagreement_score":0.75997853,"about_ca_system_score_codex":0.000028319388,"about_ca_system_score_gemma":0.00015072606,"threshold_uncertainty_score":0.8531065},"labels":[],"label_agreement":null},{"id":"W6945437321","doi":"10.25384/sage.7105409","title":"Online_Supplement – Supplemental material for The Woodcock-Johnson IV Tests of Achievement Provides Too Many Scores for Clinical Interpretation","year":2018,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Interpretation (philosophy); Test (biology); Stanford–Binet Intelligence Scales; Achievement test; Criterion-referenced test","score_opus":0.5412988342185119,"score_gpt":0.5631800178181421,"score_spread":0.021881183599630205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945437321","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":[0.20463644,0.002483818,0.7454361,0.010583699,0.0063413796,0.0033237175,0.027088847,0.00003583674,0.00007016923],"genre_scores_gemma":[0.6137658,0.001519694,0.3794474,0.00081845623,0.003406361,0.00013083518,0.0006434798,0.00003462018,0.00023337174],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99533397,0.0005183675,0.0021399606,0.0006269544,0.0009790312,0.00040173955],"domain_scores_gemma":[0.9670689,0.02938053,0.001423173,0.0015036983,0.0005166376,0.00010703693],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02738014,0.0001825028,0.0004687978,0.0002585207,0.00038081314,0.00045323133,0.0027627293,0.000067620516,0.002529213],"category_scores_gemma":[0.062170893,0.00010206438,0.00019496786,0.00046743764,0.00020276714,0.0005500749,0.0010620246,0.00013849487,0.000007178061],"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":[0.00071200234,0.00019178432,0.034071848,0.00002027714,0.000120914614,7.5155805e-7,0.00015322304,0.0000030279841,0.0014917232,0.000032572934,0.16292213,0.80027974],"study_design_scores_gemma":[0.0075214067,0.0072449963,0.3044397,0.00086399063,0.00047127318,0.00003863512,0.0056289514,0.047913328,0.008940749,0.03587899,0.5803405,0.00071748166],"about_ca_topic_score_codex":0.000055433935,"about_ca_topic_score_gemma":0.00018356186,"teacher_disagreement_score":0.7995623,"about_ca_system_score_codex":0.000029423412,"about_ca_system_score_gemma":0.000115694806,"threshold_uncertainty_score":0.9983826},"labels":[],"label_agreement":null},{"id":"W6949788110","doi":"10.5281/zenodo.2561625","title":"ERRATUM: The holotype specimen of Trimma putrai Winterbottom, Erdmann &amp; Mambrasar, 2019 has been deposited at the Museum Zoologicum Bogoriense, Cibinong, Java, Indonesia (MZB).","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ontario Museum","funders":"","keywords":"Holotype; Raja; Sargasso sea","score_opus":0.23709615960553448,"score_gpt":0.3497024930766111,"score_spread":0.11260633347107663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949788110","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":[0.9043184,0.00049488863,0.0023936678,0.005006644,0.00074997847,0.001036551,0.00016448296,0.00035606237,0.08547933],"genre_scores_gemma":[0.9827276,0.00007699914,0.0006161257,0.00037888254,0.0001554115,1.2988704e-7,0.00021828977,0.00045782633,0.015368773],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99383897,0.0023681864,0.00087250554,0.0008582593,0.001450279,0.0006118135],"domain_scores_gemma":[0.99278367,0.0034172037,0.0006664178,0.001952267,0.0010136184,0.00016683622],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0076956945,0.00026244248,0.00042229838,0.00052788586,0.0021708761,0.0012529794,0.0040061735,0.00014543762,0.01324305],"category_scores_gemma":[0.01870244,0.00015325566,0.00017910995,0.0033052086,0.00067146873,0.0003101714,0.0030819941,0.00054865575,0.013064468],"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":[0.0003740776,0.00016117738,0.0049124085,0.00002203274,0.00011072871,0.000015258018,0.0016073154,0.00010334256,0.013886961,0.0011418918,0.94239295,0.035271887],"study_design_scores_gemma":[0.00076744956,0.00042953886,0.16054884,0.000024451298,0.000025560603,0.00019772776,0.0007524443,0.0002555401,0.0007690648,0.0009182804,0.8350688,0.00024229514],"about_ca_topic_score_codex":0.000069983726,"about_ca_topic_score_gemma":0.0000024367064,"teacher_disagreement_score":0.15563643,"about_ca_system_score_codex":0.00011443639,"about_ca_system_score_gemma":0.0000140679185,"threshold_uncertainty_score":0.9997838},"labels":[],"label_agreement":null},{"id":"W6950076615","doi":"10.5281/zenodo.16691211","title":"FedIRT: An R package and Shiny app for estimating federated item response theory models","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Toronto","funders":"","keywords":"Item response theory; Measure (data warehouse); Feature (linguistics); Field (mathematics); Key (lock)","score_opus":0.28558736033402776,"score_gpt":0.40319439077753566,"score_spread":0.1176070304435079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950076615","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040058664,0.00035562398,0.5328797,0.00027570597,0.00033063948,0.0007858654,0.000664114,0.0012641138,0.46304363],"genre_scores_gemma":[0.017116204,0.00018619592,0.15750642,0.0006692288,0.0009914135,7.978015e-7,0.0015828991,0.010771146,0.8111757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937074,0.0033081993,0.0005967545,0.0010954659,0.0008078791,0.00048427837],"domain_scores_gemma":[0.98820984,0.009161961,0.0005236649,0.0009789712,0.00086128607,0.00026428292],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014487359,0.00030092776,0.00047870242,0.0013974723,0.0022652235,0.003091774,0.0018311783,0.0002521295,0.008959416],"category_scores_gemma":[0.1657041,0.00025910133,0.000086390675,0.0016518253,0.00022133382,0.0002922474,0.0014217125,0.00037430483,0.00059124595],"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":[0.0003783615,0.000049793303,0.0000017562542,0.000061429484,0.000044888693,0.0000063355596,0.0004068308,0.00009583224,0.00014032741,0.0051590367,0.59212,0.40153542],"study_design_scores_gemma":[0.0006746023,0.00032688293,0.00013558185,0.00017057193,0.000026259795,0.000036831527,0.0009823212,0.03254759,0.000022002925,0.026367985,0.9383522,0.00035714696],"about_ca_topic_score_codex":0.000021352986,"about_ca_topic_score_gemma":6.1862477e-7,"teacher_disagreement_score":0.40117827,"about_ca_system_score_codex":0.00007690372,"about_ca_system_score_gemma":0.000018796614,"threshold_uncertainty_score":0.9999861},"labels":[],"label_agreement":null},{"id":"W6957893313","doi":"10.6084/m9.figshare.14881029.v1","title":"Additional file 4 of Assessing the performance of a method for case-mix adjustment in the Korean Diagnosis-Related Groups (KDRG) system and its policy implications","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Data collection; Sample (material); Government (linguistics); Table (database)","score_opus":0.3697618199718948,"score_gpt":0.46805288057837746,"score_spread":0.09829106060648268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957893313","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004864858,0.0005069124,0.000039705406,0.00038360688,0.00002498099,0.0003379846,0.9923705,0.000010477271,0.0014610012],"genre_scores_gemma":[0.71516776,0.00002066201,0.047449347,0.00038591973,0.00026485123,0.007416622,0.22900537,0.000025625683,0.0002638431],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9981992,0.0005575285,0.0005137583,0.00024588307,0.00033092184,0.00015268335],"domain_scores_gemma":[0.8594671,0.13928595,0.0004488206,0.00034351455,0.0004259934,0.000028647102],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012297407,0.00008424074,0.00021602295,0.0001849779,0.00018686813,0.000068337424,0.00038059065,0.000057064874,0.244228],"category_scores_gemma":[0.15222421,0.0000461889,0.00008315987,0.0020996889,0.000013318136,0.00013477972,0.00013242532,0.00010453931,0.000014119127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017062707,0.000035354806,0.0001673743,0.00010727392,0.0000140649945,0.0000065875465,0.00029533892,0.00006630467,0.000011065524,0.0004896533,0.94572926,0.053076014],"study_design_scores_gemma":[0.0008086723,0.00023802329,0.7101254,0.0061390577,0.000051011688,0.0026274838,0.017513251,0.07736224,0.0007291003,0.0031563267,0.18087353,0.0003759263],"about_ca_topic_score_codex":0.000011450272,"about_ca_topic_score_gemma":0.000010271936,"teacher_disagreement_score":0.76485574,"about_ca_system_score_codex":0.00002821223,"about_ca_system_score_gemma":0.00015017061,"threshold_uncertainty_score":0.85491693},"labels":[],"label_agreement":null},{"id":"W6958224264","doi":"10.6084/m9.figshare.19502442","title":"Additional file 2 of Methodology and experiences of rapid advice guideline development for children with COVID-19: responding to the COVID-19 outbreak quickly and efficiently","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Advice (programming); Guideline; Outbreak; MEDLINE; Data collection","score_opus":0.4260998148817285,"score_gpt":0.4621602636707664,"score_spread":0.03606044878903791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958224264","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027429743,0.0002938483,0.0030396013,0.0011428393,0.000050668397,0.0005972366,0.9919196,0.000028720891,0.00018453151],"genre_scores_gemma":[0.007871332,0.0000015982674,0.74143505,0.011819198,0.00013050328,0.006121542,0.2314076,0.000029214265,0.0011839529],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968617,0.0008728446,0.00069497264,0.0005376258,0.000799163,0.0002337079],"domain_scores_gemma":[0.8593043,0.13906999,0.0007127544,0.00033958838,0.00030183233,0.0002715389],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004436876,0.00013541481,0.0003501796,0.0007447941,0.0006134172,0.00004470064,0.00071055297,0.000040266095,0.789744],"category_scores_gemma":[0.48903,0.00008458247,0.000047195033,0.0022959677,0.000066944354,0.00006324268,0.00068080856,0.00009781026,0.000007009585],"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":[0.00016384084,0.000016067514,0.00007809374,0.000018773328,0.000017482782,0.0000011368631,0.0071379007,0.00051802286,0.000004228016,0.000014185418,0.97784823,0.014182065],"study_design_scores_gemma":[0.00035147727,0.00036742518,0.0026512148,0.000045025055,0.0000045523607,0.00007555195,0.023941347,0.00027665554,0.000033558772,0.0001403632,0.97199124,0.00012158068],"about_ca_topic_score_codex":0.0000152350285,"about_ca_topic_score_gemma":0.000014062618,"teacher_disagreement_score":0.789737,"about_ca_system_score_codex":0.000050490013,"about_ca_system_score_gemma":0.0007148656,"threshold_uncertainty_score":0.5152741},"labels":[],"label_agreement":null},{"id":"W6958324860","doi":"10.6084/m9.figshare.26574448","title":"Additional file 2 of Insights from using an outcomes measurement properties search filter and conducting citation searches to locate psychometric articles of tools used to measure context attributes","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Canadian Agency for Drugs and Technologies in Health; Ottawa Hospital","funders":"","keywords":"Measure (data warehouse); Context (archaeology); Filter (signal processing); Citation; Key (lock)","score_opus":0.9687136184693357,"score_gpt":0.4618653706861401,"score_spread":0.5068482477831956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958324860","genre_codex":"dataset","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":[0.24016032,0.00074334856,0.00029891168,0.00019442319,0.00006998871,0.00039622086,0.7580365,0.000040707517,0.00005957733],"genre_scores_gemma":[0.97421134,3.3618238e-7,0.009824306,0.00007757008,0.00006321511,0.00014307165,0.015620266,0.000016273492,0.000043651413],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99611443,0.0004966552,0.00065023446,0.00054402184,0.0019508898,0.00024378757],"domain_scores_gemma":[0.9674747,0.029942332,0.00017216262,0.00036783653,0.0018423661,0.0002006293],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012805751,0.00016371602,0.00041364387,0.0013233151,0.00011505234,0.00039951876,0.0004017961,0.00007019402,0.37917176],"category_scores_gemma":[0.26498833,0.000112167254,0.00008471365,0.003969317,0.00003063347,0.0005774143,0.00019404117,0.00014012329,0.00019665805],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049687584,0.00008131682,0.0009377421,0.00015126278,0.000102527556,0.0000037978664,0.0031958725,0.00033641292,0.017199798,0.000008474101,0.7720843,0.2058488],"study_design_scores_gemma":[0.0014751732,0.0018253018,0.57929784,0.034958173,0.00008281269,0.000019967865,0.04156047,0.030710207,0.16559498,0.0041754493,0.13847438,0.0018252549],"about_ca_topic_score_codex":0.00005961228,"about_ca_topic_score_gemma":0.000055066066,"teacher_disagreement_score":0.74241626,"about_ca_system_score_codex":0.00006067516,"about_ca_system_score_gemma":0.00016865446,"threshold_uncertainty_score":0.74120295},"labels":[{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W6958456410","doi":"10.6084/m9.figshare.28657184","title":"Additional file 1 of ChIPbinner: an R package for analyzing broad histone marks binned in uniform windows from ChIP-Seq or CUT&amp;RUN/TAG data","year":2025,"lang":"en","type":"dataset","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bristol-Myers Squibb (Canada); McGill University","funders":"","keywords":"R package; Window (computing); Broad spectrum; File format; Data file","score_opus":0.4816619265705861,"score_gpt":0.47560148156037335,"score_spread":0.006060445010212745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958456410","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000339812,0.00022466827,0.000030445432,0.000037717244,0.00032270132,0.0006385823,0.99828905,0.00004602908,0.0004074371],"genre_scores_gemma":[7.4111e-7,0.000017662183,0.021349074,0.00018931592,0.00044596315,0.00066478027,0.9754378,0.00002318806,0.0018714839],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99380714,0.00055810553,0.001797892,0.0018570087,0.0013520267,0.00062782475],"domain_scores_gemma":[0.85281426,0.13967465,0.002061666,0.0047023837,0.0005247819,0.00022224738],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015272581,0.0005543539,0.0013975379,0.0020870634,0.0002251137,0.00029642938,0.0063412003,0.0006612839,0.98198926],"category_scores_gemma":[0.5378801,0.00042751917,0.00026332666,0.0041748816,0.000046445726,0.0006304815,0.002049317,0.00079043495,0.0004189639],"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":[0.00012805747,0.00011820655,0.000006879649,0.00013926635,0.000056320285,0.00001838661,0.000010377258,0.00000629408,0.0000010620029,2.7269505e-7,0.9777703,0.02174455],"study_design_scores_gemma":[0.0005215394,0.00009204868,0.0016505067,0.003964138,0.000033136337,0.0000039952165,0.00008388549,0.00035131452,0.000002778104,0.00049397995,0.99232495,0.00047773434],"about_ca_topic_score_codex":0.00040781862,"about_ca_topic_score_gemma":0.003649785,"teacher_disagreement_score":0.9815703,"about_ca_system_score_codex":0.00013266495,"about_ca_system_score_gemma":0.0009184996,"threshold_uncertainty_score":0.99981767},"labels":[],"label_agreement":null},{"id":"W6958571300","doi":"10.6084/m9.figshare.14091096.v1","title":"Additional file 1 of Gender-related variables for health research","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Table (database); Exploratory factor analysis; Varimax rotation; Factor (programming language); Contingency table; Sample (material)","score_opus":0.8990622923487772,"score_gpt":0.5883637321548894,"score_spread":0.31069856019388786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958571300","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020981179,0.00021316062,0.000040430055,0.00024815934,0.00005211258,0.000116184405,0.97162426,0.000019546003,0.027684055],"genre_scores_gemma":[0.00014190767,0.0000011644836,0.05968689,0.00017946139,0.000089424815,0.000413263,0.93186164,0.000008361542,0.007617895],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972572,0.00058680144,0.0004759395,0.00036508116,0.0010087292,0.0003062745],"domain_scores_gemma":[0.65208685,0.34483105,0.00032363355,0.0004791947,0.0021555515,0.00012370557],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002078692,0.000060328788,0.00021968083,0.00028596958,0.00020799377,0.00007678608,0.0004403131,0.00007510558,0.9985495],"category_scores_gemma":[0.7808486,0.00004851774,0.00009902482,0.0027923398,0.000013814972,0.00007825637,0.00020556492,0.00016148586,0.0012666303],"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":[0.0000026226205,0.000020609868,0.000002464074,0.00002656027,0.0000067027054,0.000002077979,0.0000270496,0.000009086795,0.000002488084,0.00007922345,0.97473264,0.025088487],"study_design_scores_gemma":[0.00008810805,0.000042693606,0.0031716817,0.00042093784,3.5123753e-7,0.000007879139,0.00023272826,0.0005375849,0.000029449246,0.026585942,0.9688358,0.000046880166],"about_ca_topic_score_codex":0.0000019420759,"about_ca_topic_score_gemma":0.0000022729876,"teacher_disagreement_score":0.99728286,"about_ca_system_score_codex":0.00002757401,"about_ca_system_score_gemma":0.0007062343,"threshold_uncertainty_score":0.999511},"labels":[],"label_agreement":null},{"id":"W6958701551","doi":"10.6084/m9.figshare.26994757","title":"Additional file 1 of A scoping review to create a framework for the steps in developing condition-specific preference-based instruments de novo or from an existing non-preference-based instrument: use of item response theory or Rasch analysis","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University Health Network; SickKids Foundation; University of Toronto; Canadian Centre for Applied Research in Cancer Control; Children's Hospital of Eastern Ontario","funders":"","keywords":"Key (lock); Identification (biology); Field (mathematics); Measure (data warehouse); Item response theory; Data collection; Troubleshooting","score_opus":0.7542516777462331,"score_gpt":0.4943969300381246,"score_spread":0.2598547477081085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958701551","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009696587,0.00047507114,0.020713327,0.00013698253,0.000063104344,0.0013041692,0.9675222,0.00004657486,0.000041999865],"genre_scores_gemma":[0.05366568,0.000091503935,0.6076496,0.0016960538,0.000121442215,0.0067638312,0.32970467,0.00006004238,0.0002471395],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9952844,0.0013319516,0.0013516472,0.00076630595,0.0008905053,0.00037519887],"domain_scores_gemma":[0.6557164,0.34224916,0.0006583887,0.00073240243,0.0005250791,0.00011858889],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027581272,0.00026330998,0.00076629524,0.0011995747,0.00018663186,0.00032761748,0.0009890887,0.00015076902,0.76420873],"category_scores_gemma":[0.38408348,0.00016110075,0.0002411611,0.00739459,0.000039866132,0.0003417754,0.00017086363,0.00025708752,0.000055567525],"study_design_candidate":"systematic_review","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":[0.0071723647,0.0002527613,0.0016467241,0.005650815,0.0006591887,0.000060754955,0.0009675237,0.0025504422,0.000054715572,0.0002569175,0.6209412,0.3597866],"study_design_scores_gemma":[0.0011778917,0.00072666584,0.10289534,0.74779713,0.0002192331,0.0000056788876,0.00092270237,0.033888742,0.000940828,0.005564095,0.10496123,0.0009004589],"about_ca_topic_score_codex":0.00001923844,"about_ca_topic_score_gemma":0.00009267777,"teacher_disagreement_score":0.7641532,"about_ca_system_score_codex":0.00014271533,"about_ca_system_score_gemma":0.0015741718,"threshold_uncertainty_score":0.6569498},"labels":[],"label_agreement":null},{"id":"W6958969348","doi":"10.6084/m9.figshare.14091096","title":"Additional file 1 of Gender-related variables for health research","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Table (database); Exploratory factor analysis; Varimax rotation; Factor (programming language); Contingency table; Sample (material)","score_opus":0.8990622923487772,"score_gpt":0.5883637321548894,"score_spread":0.31069856019388786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958969348","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020981179,0.00021316062,0.000040430055,0.00024815934,0.00005211258,0.000116184405,0.97162426,0.000019546003,0.027684055],"genre_scores_gemma":[0.00014190767,0.0000011644836,0.05968689,0.00017946139,0.000089424815,0.000413263,0.93186164,0.000008361542,0.007617895],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972572,0.00058680144,0.0004759395,0.00036508116,0.0010087292,0.0003062745],"domain_scores_gemma":[0.65208685,0.34483105,0.00032363355,0.0004791947,0.0021555515,0.00012370557],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002078692,0.000060328788,0.00021968083,0.00028596958,0.00020799377,0.00007678608,0.0004403131,0.00007510558,0.9985495],"category_scores_gemma":[0.7808486,0.00004851774,0.00009902482,0.0027923398,0.000013814972,0.00007825637,0.00020556492,0.00016148586,0.0012666303],"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":[0.0000026226205,0.000020609868,0.000002464074,0.00002656027,0.0000067027054,0.000002077979,0.0000270496,0.000009086795,0.000002488084,0.00007922345,0.97473264,0.025088487],"study_design_scores_gemma":[0.00008810805,0.000042693606,0.0031716817,0.00042093784,3.5123753e-7,0.000007879139,0.00023272826,0.0005375849,0.000029449246,0.026585942,0.9688358,0.000046880166],"about_ca_topic_score_codex":0.0000019420759,"about_ca_topic_score_gemma":0.0000022729876,"teacher_disagreement_score":0.99728286,"about_ca_system_score_codex":0.00002757401,"about_ca_system_score_gemma":0.0007062343,"threshold_uncertainty_score":0.999511},"labels":[],"label_agreement":null},{"id":"W6961002906","doi":"10.1371/journal.pone.0269691.s037","title":"Meta-regression results and R2 for Newcastle Ottawa Scale score covariate.","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Calibration; Synoptic scale meteorology; Statistical analysis","score_opus":0.8676976750816889,"score_gpt":0.5055886969543592,"score_spread":0.3621089781273298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6961002906","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015615249,0.006567794,0.0010681684,0.003522275,0.0015518354,0.001748295,0.9467488,0.00032274245,0.02285482],"genre_scores_gemma":[0.7666335,0.000017359878,0.124074906,0.003281417,0.0011411768,0.0038235364,0.05920319,0.0001514441,0.041673437],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973363,0.00039021083,0.0005250123,0.0006228861,0.0008458849,0.00027965175],"domain_scores_gemma":[0.97135836,0.027150694,0.0004835583,0.00061618455,0.00025837313,0.0001328227],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031745068,0.00015099805,0.00040220798,0.00028933675,0.0005920906,0.00019549912,0.0006910207,0.00005262205,0.08788974],"category_scores_gemma":[0.12601389,0.00009300753,0.0001871832,0.0013242143,0.00001043965,0.00015142451,0.0006805499,0.00017488166,0.00012687959],"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":[0.00006144269,0.000019657264,0.00020401203,0.000011756033,0.00004026516,0.0000055208493,0.00013847656,0.00015469709,0.00004644381,0.000019470954,0.9567588,0.042539448],"study_design_scores_gemma":[0.000854398,0.00021182364,0.009956784,0.000061215294,0.000052790558,0.000030510915,0.00040816888,0.0025998987,0.0002676315,0.0061673294,0.9791866,0.00020286084],"about_ca_topic_score_codex":0.000016144757,"about_ca_topic_score_gemma":0.0000071928152,"teacher_disagreement_score":0.88754565,"about_ca_system_score_codex":0.000022032089,"about_ca_system_score_gemma":0.00004999157,"threshold_uncertainty_score":0.9129441},"labels":[],"label_agreement":null},{"id":"W6962809226","doi":"10.17605/osf.io/5jq6u","title":"Validation HAIS-Q Spanish","year":2020,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"","score_opus":0.2969481698966023,"score_gpt":0.4098655404164758,"score_spread":0.11291737051987355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6962809226","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19733083,0.0000021698127,0.072730154,0.0031864988,0.0006940241,0.00047727293,0.000010331402,0.00038570064,0.725183],"genre_scores_gemma":[0.90642506,0.000036242425,0.028333375,0.0012607273,0.00029736233,0.000056444038,0.000007525155,0.000035663852,0.06354761],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922408,0.0017923483,0.0011399275,0.002827265,0.0015187875,0.00048086484],"domain_scores_gemma":[0.97723967,0.017247617,0.0006744123,0.003908623,0.0004395757,0.0004901089],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021345539,0.00026670867,0.00053554215,0.00027671584,0.00025945512,0.0005454373,0.002796926,0.0001918483,0.4623236],"category_scores_gemma":[0.34155494,0.00024258834,0.0002628021,0.0020080528,0.0001393684,0.00050704746,0.0020010315,0.00046762396,0.8153708],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016369205,0.00019105135,0.2991751,0.000033818298,0.000097585515,0.000043162658,0.002567052,0.003394608,0.013528007,0.0032520301,0.31764922,0.35990465],"study_design_scores_gemma":[0.0012377832,0.000006254605,0.21181922,0.000044300403,0.000064547145,0.0000539637,0.001329027,0.013084126,0.032227796,0.0776517,0.6615755,0.0009058008],"about_ca_topic_score_codex":0.000068632195,"about_ca_topic_score_gemma":0.0000030916738,"teacher_disagreement_score":0.7090942,"about_ca_system_score_codex":0.00007734438,"about_ca_system_score_gemma":0.000111387206,"threshold_uncertainty_score":0.98924655},"labels":[],"label_agreement":null},{"id":"W6976380693","doi":"10.6084/m9.figshare.14314051","title":"Additional file 2 of Cross-sectional trend analysis of the NCHA II survey data on Canadian post-secondary student mental health and wellbeing from 2013 to 2019","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Trend analysis; Table (database); Mental health; Data collection; Data file; Missing data","score_opus":0.42282885653717595,"score_gpt":0.46926499258703047,"score_spread":0.046436136049854526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976380693","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026507609,0.00023424032,3.2407124e-7,0.0002670231,0.00012009325,0.00007864641,0.97216207,0.0000034675948,0.0006265078],"genre_scores_gemma":[0.01636616,0.0000025515199,0.00073600264,0.00063438417,0.000040964893,0.000013858726,0.98130333,0.000004768696,0.0008979572],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9975476,0.00042949434,0.0004969254,0.00051330746,0.0008316229,0.00018102964],"domain_scores_gemma":[0.9700873,0.028188154,0.0003651845,0.0007837273,0.0003539707,0.0002216747],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079795095,0.000092604445,0.00029935536,0.00046894245,0.0003023937,0.000114662005,0.00087840104,0.00004882892,0.9592244],"category_scores_gemma":[0.08554132,0.0000668176,0.00009138814,0.002336707,0.00001897538,0.00012610512,0.00078495836,0.00012342393,0.000075173324],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066238367,0.000023751509,0.030731196,0.0000022602771,0.000096647826,9.84803e-7,0.00010339238,0.000054301006,0.0000021052126,5.242895e-7,0.9652695,0.0037086916],"study_design_scores_gemma":[0.000062119456,0.000036988098,0.7715835,0.00008731304,0.0000033402578,0.0000011414947,0.00016122316,0.00021569247,0.0000031989177,0.000015529118,0.22778022,0.000049731767],"about_ca_topic_score_codex":0.02375566,"about_ca_topic_score_gemma":0.24677506,"teacher_disagreement_score":0.95914924,"about_ca_system_score_codex":0.00005341296,"about_ca_system_score_gemma":0.00074971275,"threshold_uncertainty_score":0.98274523},"labels":[],"label_agreement":null},{"id":"W6976731003","doi":"10.6084/m9.figshare.12655228.v1","title":"Additional file 3 of On-line virtual patient learning: a pilot study of a new modality in antimicrobial stewardship education for pediatric residents","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Izaak Walton Killam Health Centre; Dalhousie University","funders":"","keywords":"Antimicrobial stewardship; Modality (human–computer interaction); Descriptive statistics; Modalities; Descriptive research; MEDLINE; Data collection","score_opus":0.5776519980496406,"score_gpt":0.4461156805661874,"score_spread":0.13153631748345324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976731003","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10112487,0.000009597428,0.000014105475,0.00008101834,0.000062078194,0.00050954655,0.8979098,0.000014410756,0.00027456207],"genre_scores_gemma":[0.838837,3.4903684e-7,0.0031243793,0.00015120061,0.00030308808,0.00026415937,0.15705368,0.000011735324,0.00025440514],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9978299,0.00030960984,0.00068134884,0.0003673335,0.0006762278,0.00013557276],"domain_scores_gemma":[0.9644458,0.03404533,0.00076735375,0.0002137655,0.00042785885,0.0000998767],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031397966,0.00009822073,0.000284048,0.00033195264,0.0000436089,0.000029257151,0.00038986772,0.00003573006,0.6645836],"category_scores_gemma":[0.40704578,0.00008346793,0.000060879418,0.0016707057,0.0000044824938,0.00008789249,0.00014013606,0.0001433099,0.00011305821],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019029596,0.00066281576,0.0011234365,0.00002728623,0.0000039502065,5.429998e-7,0.00039477885,0.0011190375,0.000004479727,9.926006e-7,0.9816557,0.014816657],"study_design_scores_gemma":[0.0041302033,0.04339896,0.8299841,0.0016689237,0.000026708049,0.0000026568887,0.0070846463,0.0038931258,0.00023722951,0.0018237575,0.10710423,0.00064545334],"about_ca_topic_score_codex":0.000041858497,"about_ca_topic_score_gemma":0.000011035518,"teacher_disagreement_score":0.8745515,"about_ca_system_score_codex":0.00002016792,"about_ca_system_score_gemma":0.00040882372,"threshold_uncertainty_score":0.5979489},"labels":[],"label_agreement":null},{"id":"W6976801847","doi":"10.6084/m9.figshare.20277855.v3","title":"The Reach of Russian Propaganda &amp; Disinformation in Canada","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Disinformation; Politics; Social media; Public opinion; Consumption (sociology); General Social Survey","score_opus":0.47395519935649283,"score_gpt":0.4124652963856675,"score_spread":0.06148990297082535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976801847","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":[0.37817696,0.0029318717,0.00013635935,0.008414141,0.0027021656,0.0022485263,0.31984615,0.000117134696,0.28542668],"genre_scores_gemma":[0.9972134,9.770426e-7,0.00026613704,0.00010725718,0.000015020978,0.00006472849,0.0018526687,0.0000030933704,0.00047672365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982295,0.0002234857,0.00040183825,0.00011110746,0.00089329283,0.00014076507],"domain_scores_gemma":[0.9896268,0.0096055195,0.00031440056,0.00036127956,0.000062079416,0.000029922192],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014746999,0.00004407068,0.00010271052,0.00011455961,0.00021757334,0.00004795546,0.00066420727,0.000009595615,0.034496423],"category_scores_gemma":[0.07290144,0.000025623396,0.000024849533,0.0016018472,0.0000036374513,0.000085369276,0.00024744,0.00013440495,0.000033971635],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001690021,0.000008874506,0.01219306,0.000011740806,0.0000029734435,0.000003832116,0.00041512406,0.0011004185,0.000005478072,0.00013215575,0.7082574,0.27785206],"study_design_scores_gemma":[0.00011513032,0.000016941434,0.23628485,0.000037882593,4.862057e-7,0.0000068515187,0.001706043,0.0012651626,0.000030168212,0.0017808628,0.75868917,0.00006645525],"about_ca_topic_score_codex":0.091758974,"about_ca_topic_score_gemma":0.3219282,"teacher_disagreement_score":0.61903644,"about_ca_system_score_codex":0.00013944834,"about_ca_system_score_gemma":0.00048815805,"threshold_uncertainty_score":0.9663862},"labels":[],"label_agreement":null},{"id":"W6977203271","doi":"10.6084/m9.figshare.16807805.v1","title":"Additional file 1 of Latent class growth modeling of depression and anxiety in older adults: an 8-year follow-up of a population-based study","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Anxiety; Logistic regression; Depression (economics); Confidence interval; Odds ratio; Univariate; Odds","score_opus":0.23387450603794088,"score_gpt":0.3820863154674788,"score_spread":0.1482118094295379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977203271","genre_codex":"dataset","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":[0.2576148,0.000043735945,0.000019098508,0.0000041538337,0.000019793637,0.00013783289,0.7420065,0.0000068034524,0.00014732851],"genre_scores_gemma":[0.87210286,4.4140123e-7,0.0064401105,0.000010003918,0.000011379111,0.000059107446,0.12135555,0.00000520787,0.000015367334],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981255,0.0002571506,0.0005613564,0.00032988781,0.0006251202,0.00010098103],"domain_scores_gemma":[0.9876075,0.011070066,0.00034831275,0.00027590795,0.00065357686,0.00004467615],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035282728,0.00007792451,0.00027516094,0.00024621552,0.000030420442,0.000016983959,0.00019912179,0.00006307372,0.6752954],"category_scores_gemma":[0.10093743,0.00006187659,0.00006460429,0.0010951692,0.000004466109,0.00013159969,0.00011144837,0.000079034275,0.000004668476],"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":[0.00021451376,0.0008723903,0.49579218,0.00022845545,0.000024915094,0.000009201465,0.000756711,0.007837716,0.00003681207,0.000004252202,0.45553124,0.038691606],"study_design_scores_gemma":[0.001006387,0.000079379,0.8682281,0.001895799,0.000003411608,7.711656e-7,0.0011783827,0.127016,0.00006822858,0.00028587793,0.0001544016,0.00008330781],"about_ca_topic_score_codex":0.000052660103,"about_ca_topic_score_gemma":0.00006528271,"teacher_disagreement_score":0.67529076,"about_ca_system_score_codex":0.000009789567,"about_ca_system_score_gemma":0.000073316725,"threshold_uncertainty_score":0.90663576},"labels":[],"label_agreement":null},{"id":"W6980278198","doi":"","title":"Book review of \"The L.M. Montgomery Reader: Volume Two: a critical heritage by Benjamin Lefebvre (ed). Toronto, Canada, University of Toronto Press, 2014. ISBN: 978-1-4426-4492-2","year":2016,"lang":"en","type":"article","venue":"ResearchOnline at James Cook University (James Cook University)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Reading (process); Volume (thermodynamics); Criticism; Performance art","score_opus":0.07163354831821298,"score_gpt":0.33203611347475775,"score_spread":0.2604025651565448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980278198","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021330312,0.78997684,0.007545716,0.040830527,0.001452674,0.003495,0.008309355,0.00038397068,0.12667562],"genre_scores_gemma":[0.0068392158,0.25499246,0.0030846063,0.0011594243,0.000122353,3.4783145e-7,0.00004470193,0.000058598496,0.7336983],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914868,0.0025916744,0.0007360527,0.0013197699,0.0027702013,0.0010955014],"domain_scores_gemma":[0.984147,0.01024437,0.0008404791,0.0022026268,0.0018191962,0.0007463069],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021647885,0.0004973367,0.0012626925,0.00023977786,0.0009850172,0.00005628631,0.004426319,0.0003082086,0.014258474],"category_scores_gemma":[0.0091531975,0.00041573128,0.00060154544,0.0011085465,0.002477492,0.0016146904,0.0027017638,0.0004707449,0.000035342626],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000550294,0.00020198997,0.0039024567,0.0003421644,0.00015207761,0.00024388198,0.00017238031,0.000006610719,0.0007030105,0.00054152776,0.9772062,0.015977459],"study_design_scores_gemma":[0.0017617369,0.00023889501,0.002513629,0.0011792871,0.00013924709,0.000016942027,0.0038425473,0.00015200883,0.00021975355,0.000021040309,0.98944706,0.0004678759],"about_ca_topic_score_codex":0.46858013,"about_ca_topic_score_gemma":0.28338692,"teacher_disagreement_score":0.6070227,"about_ca_system_score_codex":0.0031463946,"about_ca_system_score_gemma":0.002165048,"threshold_uncertainty_score":0.9998295},"labels":[],"label_agreement":null},{"id":"W6980393610","doi":"","title":"Canadian national sport organisationsâ use of the web for relationship marketing in promoting sport participation","year":2009,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Lagging; Sports marketing; The Internet; Sport management; Process (computing); Relationship marketing","score_opus":0.3140924442500151,"score_gpt":0.3769077943748507,"score_spread":0.06281535012483563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980393610","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":[0.9954902,0.000018512445,0.00014323647,0.002296395,0.00014159904,0.00042968598,0.000043799508,0.000017025299,0.0014195752],"genre_scores_gemma":[0.98803914,0.0000022899887,0.011038275,0.00009496504,0.000027651151,6.9466233e-7,0.000013347796,0.0000073625456,0.0007763044],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972912,0.00032280706,0.00059006276,0.00040700196,0.0010548604,0.00033408197],"domain_scores_gemma":[0.992386,0.005453313,0.0007702935,0.0004356849,0.00080373173,0.00015097485],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0122276535,0.00012675006,0.00030143457,0.001027359,0.00058375794,0.00006026251,0.0007531882,0.00017120033,0.00015240142],"category_scores_gemma":[0.058800995,0.00011928093,0.00016339878,0.0030971956,0.00009888341,0.0008955597,0.00009297733,0.00027858547,0.000008385646],"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":[0.00007456366,0.000037556914,0.9943966,0.000006144085,0.0000066255748,0.0000018834438,0.0006599595,0.0003853086,0.0005079085,0.0011471626,0.000119537726,0.0026567017],"study_design_scores_gemma":[0.00046743575,0.00003366915,0.98875076,0.000058422163,0.000014488275,0.0000036060935,0.0006508831,0.0013859193,0.0001455331,0.0068841767,0.0014876327,0.000117499854],"about_ca_topic_score_codex":0.0014454025,"about_ca_topic_score_gemma":0.015604735,"teacher_disagreement_score":0.04657334,"about_ca_system_score_codex":0.00034144192,"about_ca_system_score_gemma":0.00061466213,"threshold_uncertainty_score":0.94912714},"labels":[],"label_agreement":null},{"id":"W6980420914","doi":"","title":"Canada fires: B.C. under state of emergency, wildfires close main highway","year":2023,"lang":"en","type":"other","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"State (computer science); Vegetation (pathology); Poison control; Work (physics); Climate change","score_opus":0.32198287503283124,"score_gpt":0.4341979758447801,"score_spread":0.11221510081194885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980420914","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002152093,0.0019017556,0.002740061,0.0009049171,0.010607151,0.00038732917,0.0012417294,0.00058894325,0.97947603],"genre_scores_gemma":[0.0031109357,0.00078046176,0.0035963585,0.00016258824,0.0001650506,0.000008573664,0.0000061778574,0.00027356096,0.9918963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953651,0.00039635898,0.0010665715,0.00073892804,0.001981119,0.00045193385],"domain_scores_gemma":[0.9834648,0.014210773,0.00091080164,0.0011489692,0.00010658631,0.00015809028],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031216661,0.0003001568,0.00074346614,0.00089238904,0.000057104997,0.000037081612,0.0013354635,0.0001532929,0.015713979],"category_scores_gemma":[0.027647883,0.00019750699,0.00015754381,0.0030157934,0.000066132736,0.00004060624,0.0002725456,0.00018789314,0.0001672227],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003779197,0.0000096556705,0.0024599305,0.000011936295,0.000054723754,0.000016305976,0.000013243937,0.000024126706,0.0000043711584,0.00026659312,0.94290626,0.054229077],"study_design_scores_gemma":[0.00015418802,0.00003435335,0.022250168,0.00006469442,0.000012854172,0.0000015805036,0.00027614972,0.000051698036,0.000029899438,0.027871463,0.94891036,0.00034257924],"about_ca_topic_score_codex":0.915078,"about_ca_topic_score_gemma":0.9595449,"teacher_disagreement_score":0.053886496,"about_ca_system_score_codex":0.00007553186,"about_ca_system_score_gemma":0.0007270905,"threshold_uncertainty_score":0.9851858},"labels":[],"label_agreement":null},{"id":"W6981069200","doi":"","title":"Dialogue summary: Enhancing the delivery of comprehensive care for people living with HIV in Canada","year":2019,"lang":"en","type":"other","venue":"MacSphere (McMaster University)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research; Government of Ontario; McMaster University","keywords":"Human immunodeficiency virus (HIV); Thematic analysis; Key (lock); Stakeholder; Qualitative research","score_opus":0.07575213383587012,"score_gpt":0.27380454807212723,"score_spread":0.1980524142362571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981069200","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059397086,0.0012015257,0.0060729785,0.00006162019,0.0006885616,0.00085966307,0.00026006132,0.00003118483,0.9848847],"genre_scores_gemma":[0.025737183,0.00006835399,0.004331675,0.00009147491,0.00008243396,0.0000022169936,0.000011721908,0.00011060881,0.9695643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997655,0.00042099954,0.00034520967,0.0005845262,0.0006275805,0.0003666822],"domain_scores_gemma":[0.9820218,0.016403526,0.0006372097,0.0006177957,0.00025421492,0.0000654196],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040121112,0.00027290484,0.0007797392,0.0005292604,0.00008711239,0.00004459222,0.0012485976,0.00013897948,0.008749813],"category_scores_gemma":[0.000940015,0.00018709205,0.0001154672,0.001903173,0.00006944798,0.000080870566,0.00036915523,0.0002303461,0.00000986702],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027199308,0.000044268676,0.36391702,0.0008049753,0.0003051035,0.000090400106,0.0035632092,0.0022978804,0.000049939277,0.00037631017,0.23531923,0.39295968],"study_design_scores_gemma":[0.00074587716,0.00008055419,0.012924663,0.0008018637,0.000053989927,0.0000026102016,0.08334969,0.00015578402,0.000016100528,0.000017816967,0.9015137,0.00033736753],"about_ca_topic_score_codex":0.6161361,"about_ca_topic_score_gemma":0.97505724,"teacher_disagreement_score":0.66619444,"about_ca_system_score_codex":0.0003176278,"about_ca_system_score_gemma":0.0009879954,"threshold_uncertainty_score":0.9921563},"labels":[],"label_agreement":null},{"id":"W6981496916","doi":"","title":"Empresários propõem boicote à reunião de Quebec","year":2001,"lang":"pt","type":"article","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.1235636059404153,"score_gpt":0.3426227347088424,"score_spread":0.21905912876842712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981496916","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":[0.37918288,0.0077397786,0.13189034,0.10273321,0.012543457,0.0035297843,0.00028424177,0.0022640044,0.3598323],"genre_scores_gemma":[0.96391207,0.00082259416,0.015473043,0.0008482259,0.0016902438,0.00022303124,0.000067453155,0.00014095164,0.016822416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9846483,0.003658818,0.002788571,0.0026166402,0.0035665508,0.0027211083],"domain_scores_gemma":[0.98196447,0.009870179,0.0018789636,0.0026959495,0.0017547687,0.0018356647],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008882529,0.0012551572,0.0015989225,0.0022970375,0.0021484594,0.0018673862,0.0037585034,0.0016312592,0.00058755255],"category_scores_gemma":[0.053428903,0.0011216606,0.00083871087,0.006695401,0.0001186861,0.001406853,0.0012404388,0.002167574,0.00021313109],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015710592,0.0024896762,0.02878627,0.00026818903,0.000693056,0.002942225,0.008399821,0.0007623573,0.006578991,0.78076315,0.026554532,0.14019068],"study_design_scores_gemma":[0.0019236788,0.00025096585,0.03214983,0.00038619566,0.00017108064,0.0042390064,0.002583573,0.003994015,0.00049227284,0.0024912923,0.95005554,0.0012625322],"about_ca_topic_score_codex":0.00007335519,"about_ca_topic_score_gemma":0.0016898774,"teacher_disagreement_score":0.923501,"about_ca_system_score_codex":0.002012298,"about_ca_system_score_gemma":0.002971625,"threshold_uncertainty_score":0.99966484},"labels":[],"label_agreement":null},{"id":"W6981545595","doi":"","title":"Episode 385 with John Horn, Brandon Rewucki &amp; Moe Khan","year":2022,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Tournament; French horn; Football; Performance art","score_opus":0.06184012000368862,"score_gpt":0.2901171934364049,"score_spread":0.2282770734327163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981545595","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016518141,0.0006927093,0.000027915314,0.00029233826,0.0006476261,0.00056071783,0.00018623951,0.00026560365,0.9971617],"genre_scores_gemma":[0.00029072716,0.00021616908,0.01530741,0.0004209002,0.0001981455,0.00003316801,0.00011604187,0.00013864004,0.9832788],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99455345,0.0006046184,0.00142906,0.0005797734,0.0023083147,0.00052479416],"domain_scores_gemma":[0.9902085,0.0059372424,0.0020080884,0.0013050225,0.0003320526,0.00020906096],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0035343873,0.00049170037,0.00097162975,0.00056569744,0.00021454341,0.00022085916,0.0014817356,0.00037422584,0.7714567],"category_scores_gemma":[0.012958671,0.00036970864,0.00027347577,0.00013488784,0.00022424567,5.710992e-7,0.00037346326,0.0006027971,0.010571388],"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":[0.00019089312,0.00003934341,0.00014658093,0.00009037436,0.00006271516,0.000020653355,0.00012479236,0.0005043597,1.3740213e-7,0.000021600712,0.98417443,0.014624114],"study_design_scores_gemma":[0.0008551461,0.0002444106,0.00010725434,0.00010656618,0.000043310378,0.000157853,0.00025437612,0.000016080883,0.0000015656193,0.00014423176,0.99761605,0.00045316035],"about_ca_topic_score_codex":0.0053457585,"about_ca_topic_score_gemma":0.0026219897,"teacher_disagreement_score":0.76088536,"about_ca_system_score_codex":0.00008714145,"about_ca_system_score_gemma":0.00006220638,"threshold_uncertainty_score":0.9998755},"labels":[],"label_agreement":null},{"id":"W6982927353","doi":"","title":"L'activation plaquettaire et les interactions plaquettes-neutrophiles dans les syndromes coronariens aigus et leur modulation par des agents pharmacologiques","year":2000,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Platelet; Drug; Mechanism of action; Antithrombin; Thromboxane A2","score_opus":0.08967695530601832,"score_gpt":0.3028193982325829,"score_spread":0.2131424429265646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6982927353","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47235668,0.00083091285,0.00375868,0.005847936,0.0007858537,0.00047104232,0.0008702518,0.000053305273,0.5150254],"genre_scores_gemma":[0.87533116,0.002054862,0.008911022,0.0012695355,0.00012482342,0.00002908537,0.00005744359,0.00008977013,0.11213227],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937744,0.0015971356,0.0009243482,0.0007939083,0.0023745284,0.0005356596],"domain_scores_gemma":[0.9854716,0.012843925,0.00095432496,0.00038762204,0.000004339842,0.00033819317],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015304008,0.0005643757,0.00070319907,0.00024230433,0.00069733965,0.00017305021,0.0006741278,0.00016270277,0.002216461],"category_scores_gemma":[0.00043733587,0.00050205196,0.00011269195,0.0004554093,0.0004478221,0.001000647,0.0002540718,0.0006480606,5.1499505e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000883182,0.00026537737,0.3533532,0.0003784871,0.000598228,0.0002879722,0.0013921809,0.009457701,0.019293576,0.032212816,0.01528166,0.5665956],"study_design_scores_gemma":[0.0005062525,0.00024003736,0.7511294,0.0009002553,0.00009046055,0.000064778396,0.004604581,0.009801244,0.012071801,0.005513778,0.21434091,0.00073650223],"about_ca_topic_score_codex":0.021235453,"about_ca_topic_score_gemma":0.070839494,"teacher_disagreement_score":0.5658591,"about_ca_system_score_codex":0.000045954763,"about_ca_system_score_gemma":0.001542256,"threshold_uncertainty_score":0.9997431},"labels":[],"label_agreement":null},{"id":"W6983031126","doi":"","title":"Le package difR, un outil pour l'identification du fonctionnement différentiel d'items dichotomiques","year":2011,"lang":"en","type":"article","venue":"Open Repository and Bibliography (University of Liège)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"R package; Presentation (obstetrics); Process (computing); Differential item functioning; Software package; Package design; Subject (documents)","score_opus":0.201850000355784,"score_gpt":0.3197353875218908,"score_spread":0.1178853871661068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6983031126","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":[0.9087168,0.00034367855,0.04615044,0.00026293015,0.0005302638,0.0002836845,0.000010379978,0.000044396016,0.04365743],"genre_scores_gemma":[0.9816736,0.00071182527,0.016461961,0.000024452811,0.00003268183,0.0000011374291,0.000002301822,0.0000053264125,0.001086697],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99803054,0.00046074207,0.0003685787,0.00051782205,0.00044987357,0.0001724445],"domain_scores_gemma":[0.9973728,0.0010348029,0.00060765335,0.0005346633,0.00031962295,0.0001304477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024883803,0.00012669749,0.00029429057,0.006025328,0.00077481323,0.00032989267,0.0011280312,0.0000896059,0.00015885665],"category_scores_gemma":[0.000037717058,0.000117125455,0.00019401743,0.010572772,0.00020970056,0.0009147026,0.00049290946,0.00010157354,0.0000068106974],"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":[0.00008689515,0.00029434604,0.9766702,0.000008670921,0.00008628702,0.000019582207,0.0007138827,3.9652318e-7,0.0046328306,0.0014235829,0.008758444,0.0073048975],"study_design_scores_gemma":[0.00066878076,0.00011340872,0.97780436,0.00002203088,0.000043489366,0.000013656861,0.006262413,0.000071507486,0.0029034347,0.010760873,0.0011820309,0.0001540029],"about_ca_topic_score_codex":0.004087211,"about_ca_topic_score_gemma":0.000024475634,"teacher_disagreement_score":0.072956815,"about_ca_system_score_codex":0.00000493303,"about_ca_system_score_gemma":0.000032097276,"threshold_uncertainty_score":0.6178668},"labels":[],"label_agreement":null},{"id":"W6983992610","doi":"","title":"Our Contributors","year":2006,"lang":"en","type":"article","venue":"Archivaria","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.4011822789061256,"score_gpt":0.4761489739632225,"score_spread":0.07496669505709685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6983992610","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12134977,0.000120901066,0.22902168,0.0029154534,0.0016992583,0.00014168824,0.000019855524,0.00015955961,0.64457184],"genre_scores_gemma":[0.95917934,0.0000010955604,0.03757354,0.00014964835,0.00030680848,0.0000032536188,0.000002418496,0.0000054330417,0.0027784677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979862,0.0003469304,0.00043207314,0.000327732,0.00061727717,0.00028980328],"domain_scores_gemma":[0.98668236,0.012521925,0.00016157907,0.00048450773,0.00008436969,0.00006527428],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038025645,0.000085888394,0.00020253095,0.00028939257,0.00012986931,0.00015599176,0.0006173105,0.000031468306,0.000120906],"category_scores_gemma":[0.043286476,0.00005761851,0.00008693417,0.0011065031,0.000025232053,0.000086900254,0.00012978932,0.00011005851,0.000405214],"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":[0.00001601842,0.000040303774,0.19194485,7.706735e-7,0.0000069506323,0.000017049248,0.00003827513,0.00012453434,0.0011327898,0.6339452,0.08652035,0.086212866],"study_design_scores_gemma":[0.00016318004,0.00001709884,0.34998232,0.0000015937686,0.000001908407,0.0000072575776,0.00006068255,0.000416833,0.0000955338,0.6136783,0.035515226,0.000060065657],"about_ca_topic_score_codex":0.00023840166,"about_ca_topic_score_gemma":0.000003022463,"teacher_disagreement_score":0.8378296,"about_ca_system_score_codex":0.000009379417,"about_ca_system_score_gemma":0.000025383591,"threshold_uncertainty_score":0.96477234},"labels":[],"label_agreement":null},{"id":"W6985760243","doi":"","title":"SHARP News","year":2006,"lang":"en","type":"other","venue":"UA Campus Repository (The University of Arizona)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Publishing; Exhibition; Modernity; Reading (process); Performance art","score_opus":0.09683292492420903,"score_gpt":0.31353417829238633,"score_spread":0.2167012533681773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6985760243","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000794274,0.0008382781,0.005536862,0.00021717421,0.0017186381,0.00022401115,0.000024913217,0.00015005012,0.9904958],"genre_scores_gemma":[0.002460035,0.000038055638,0.009235537,0.00004284928,0.0003917317,1.8858812e-7,0.0000066227494,0.00007671149,0.98774827],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968927,0.000555411,0.00038026116,0.00068119727,0.0012041487,0.00028630096],"domain_scores_gemma":[0.9920845,0.0049243723,0.0012880655,0.0014295944,0.00017423872,0.000099229495],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011565089,0.0002576076,0.00060046994,0.0007679536,0.00035907046,0.00007566262,0.0022727153,0.00036073098,0.0009366756],"category_scores_gemma":[0.0025980913,0.0001916071,0.00036352052,0.0011485098,0.00055013184,0.000070926806,0.0004156294,0.00035110794,0.00018116758],"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":[0.000016425813,0.000033196902,0.009132683,0.000011077024,0.0000579352,0.000073071635,0.00009622026,0.00003364533,0.000086645436,0.00026835166,0.9721059,0.018084798],"study_design_scores_gemma":[0.00025138908,0.00005562395,0.007355626,0.000059443784,0.000058804984,0.00002431838,0.0006979999,0.00008114095,0.00002373457,0.0009915907,0.99018025,0.00022010204],"about_ca_topic_score_codex":0.0045364904,"about_ca_topic_score_gemma":0.0003226815,"teacher_disagreement_score":0.018074276,"about_ca_system_score_codex":0.000062113664,"about_ca_system_score_gemma":0.00012967555,"threshold_uncertainty_score":0.9999766},"labels":[],"label_agreement":null},{"id":"W6989531188","doi":"","title":"Binom Thue egyenletek kis megoldásainak kiszámítása","year":2014,"lang":"hu","type":"other","venue":"University of Debrecen Electronic Archive (University of Debrecen)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Subject (documents); Government (linguistics); Quarter (Canadian coin)","score_opus":0.05255048620711602,"score_gpt":0.2659230230667864,"score_spread":0.21337253685967036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6989531188","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043740183,0.00493083,0.38511345,0.0032845796,0.0017709249,0.0024387995,0.0012561084,0.00048352368,0.55698156],"genre_scores_gemma":[0.35126683,0.03351911,0.14181858,0.00046567846,0.0006251586,5.327973e-7,0.00059493515,0.00071290677,0.47099623],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886381,0.0032067373,0.0009882782,0.0025647574,0.0022708834,0.0023312508],"domain_scores_gemma":[0.9781287,0.013729609,0.003908596,0.0025105448,0.0009005037,0.00082205946],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041127545,0.0012258235,0.0033070701,0.004150558,0.0011886754,0.00006649325,0.0070629157,0.0011205955,0.027279632],"category_scores_gemma":[0.004166623,0.0014928617,0.0016211173,0.004146262,0.0027963936,0.0006008262,0.002151148,0.0019161324,0.001614172],"study_design_candidate":"not_applicable","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":[0.0051823324,0.0018646619,0.014778916,0.0009496997,0.004950076,0.00040596208,0.012833396,0.0005147251,0.00431591,0.031175137,0.28611016,0.636919],"study_design_scores_gemma":[0.004980539,0.0023677007,0.01460737,0.0008222634,0.0010745049,0.00007080421,0.016130073,0.0073268497,0.000077587894,0.0167866,0.933829,0.0019266971],"about_ca_topic_score_codex":0.007987183,"about_ca_topic_score_gemma":0.010587181,"teacher_disagreement_score":0.64771885,"about_ca_system_score_codex":0.00065310247,"about_ca_system_score_gemma":0.0017785064,"threshold_uncertainty_score":0.99991745},"labels":[],"label_agreement":null},{"id":"W6996612579","doi":"","title":"A standard setting study to establish concordance between the Pearson Test of English Academic (PTE A) and the Canadian Language Benchmarks (CLB)","year":2017,"lang":"en","type":"book","venue":"ePrints Soton (University of Southampton)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Triacetin; Durvalumab; Emperipolesis","score_opus":0.1172114437795707,"score_gpt":0.3592911943946659,"score_spread":0.24207975061509518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996612579","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":[0.68767667,0.0004017344,0.00049056724,0.0011069443,0.00072042487,0.0022917546,0.0012207708,0.000042254087,0.30604887],"genre_scores_gemma":[0.93493146,0.000049869606,0.0016718381,0.00008049567,0.0003072848,0.0000016872472,0.000016717573,0.000026123198,0.06291451],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99577576,0.0007063919,0.00060524134,0.0008479092,0.0015998434,0.00046488253],"domain_scores_gemma":[0.97251755,0.022646733,0.0017490649,0.0017270438,0.0010355004,0.00032411492],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016429858,0.00032202713,0.0011286746,0.00070917525,0.0011970166,0.00021721778,0.003971986,0.00030535713,0.00049992214],"category_scores_gemma":[0.08230607,0.00023149967,0.00022823279,0.0005965071,0.0012665694,0.00024007206,0.0014695538,0.0013372955,0.00001953018],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021139735,0.00002712125,0.7148045,0.000053979184,0.0002450197,0.000047322435,0.16740072,0.00001523871,0.000004247455,0.00034550036,0.027917044,0.08892792],"study_design_scores_gemma":[0.003322441,0.00040953376,0.64894825,0.00061999884,0.00034495795,0.0000035566457,0.2273272,0.00006461477,0.000013704892,0.0084284255,0.109786,0.0007313156],"about_ca_topic_score_codex":0.052764192,"about_ca_topic_score_gemma":0.06004457,"teacher_disagreement_score":0.24725479,"about_ca_system_score_codex":0.00021214728,"about_ca_system_score_gemma":0.0008818077,"threshold_uncertainty_score":0.9571072},"labels":[],"label_agreement":null},{"id":"W6996681271","doi":"","title":"Statistical models for multilevel data with “Don’t know” category: implication for program evaluation","year":2023,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Random effects model; Longitudinal data; Outcome (game theory); Social connectedness; Mental health; Multilevel model; Statistical model","score_opus":0.544237289280577,"score_gpt":0.471941378212588,"score_spread":0.072295911067989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996681271","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":[0.0517302,0.00016944397,0.93767583,0.000461756,0.00070937385,0.006054214,0.0019755217,0.00018286672,0.0010408072],"genre_scores_gemma":[0.097281285,0.00012343875,0.8793665,0.000011367795,0.00018792607,0.0001636784,0.018459309,0.0000989208,0.004307537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679,0.00021842099,0.00031630337,0.0010654096,0.0012805825,0.0003292751],"domain_scores_gemma":[0.9844606,0.011454996,0.0009129524,0.0011713868,0.0019026096,0.00009746952],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0053530866,0.00022861415,0.00052985194,0.00064307166,0.00037387785,0.00010728269,0.0016495195,0.00025918803,0.00001309972],"category_scores_gemma":[0.013394477,0.00021858123,0.000102161175,0.00092321594,0.000086233085,0.00044408994,0.00015897655,0.00015715379,0.00001260415],"study_design_candidate":"design_other","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":[0.0008393888,0.00015306436,0.0014676824,0.00025110968,0.00013434891,0.0000016170304,0.00039827652,0.0013848308,0.000052108393,0.0026590484,0.04873339,0.94392514],"study_design_scores_gemma":[0.0017090647,0.00058594404,0.14897995,0.00010507662,0.0004829813,0.0000013666665,0.046031237,0.7453054,0.000018764904,0.04314858,0.013240956,0.0003906411],"about_ca_topic_score_codex":0.0012477012,"about_ca_topic_score_gemma":0.084492855,"teacher_disagreement_score":0.9435345,"about_ca_system_score_codex":0.0001127175,"about_ca_system_score_gemma":0.0003557371,"threshold_uncertainty_score":0.99491614},"labels":[],"label_agreement":null},{"id":"W6996818687","doi":"","title":"STARD-BLCM: Standards for the Reporting of Diagnostic accuracy studies that use Bayesian Latent Class Models","year":2017,"lang":"en","type":"article","venue":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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 Prince Edward Island; McGill University","funders":"","keywords":"Latent class model; Bayesian probability; Diagnostic accuracy; Class (philosophy); Accuracy and precision","score_opus":0.5114831828999554,"score_gpt":0.43750174133161873,"score_spread":0.07398144156833669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996818687","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":[0.40611577,0.0019348516,0.57259923,0.0052265325,0.0007370173,0.0029024049,0.0009182463,0.0002749994,0.009290979],"genre_scores_gemma":[0.93943745,0.0025560206,0.056566373,0.00003824552,0.000035555564,8.7186606e-7,0.0000046519453,0.000029162122,0.0013316583],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.992213,0.0006491357,0.0020623608,0.0013222285,0.0029211715,0.0008320684],"domain_scores_gemma":[0.8522962,0.12547898,0.012062171,0.0050513935,0.0045844438,0.0005268563],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.014837689,0.0005220023,0.0021715492,0.00073756673,0.0017335886,0.000142035,0.005988522,0.00064021756,0.0003308006],"category_scores_gemma":[0.2589364,0.00044283093,0.0012920441,0.0013088726,0.0035139874,0.001438023,0.0036809654,0.0008855882,0.000008743627],"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":[0.015196696,0.0039956314,0.3875148,0.001757882,0.0049389945,0.0025730268,0.003398264,0.009183503,0.013868758,0.050661836,0.21886249,0.28804815],"study_design_scores_gemma":[0.0128383525,0.0035373773,0.7472622,0.0032363157,0.0033897825,0.00028676394,0.028586337,0.018394861,0.0032467695,0.09997538,0.07586686,0.0033790208],"about_ca_topic_score_codex":0.00091403886,"about_ca_topic_score_gemma":0.00096033205,"teacher_disagreement_score":0.5333217,"about_ca_system_score_codex":0.00044279825,"about_ca_system_score_gemma":0.000510142,"threshold_uncertainty_score":0.99980235},"labels":[],"label_agreement":null},{"id":"W7000352890","doi":"","title":"Fairness In Classroom Assessments at Individual and National Culture Levels: A Cross-Cultural Empirical Examination","year":2025,"lang":"en","type":"article","venue":"University Library (University of Saskatchewan)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Concordia University; University of Alberta; MacEwan University; Canadian Mennonite University; Mount Royal University; University of Lethbridge; Athabasca University; University of Regina; Concordia University of Edmonton","keywords":"Hofstede's cultural dimensions theory; Perception; Multilevel model; Uncertainty avoidance; Cultural diversity; Psychosocial; Immigration; Matching (statistics)","score_opus":0.21103264668414673,"score_gpt":0.39863788377572557,"score_spread":0.18760523709157884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000352890","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":[0.9748667,0.000058397098,0.0030820367,0.00077616255,0.00013772433,0.00012733383,0.00015283858,0.000053791908,0.020745032],"genre_scores_gemma":[0.9526152,0.000020068886,0.014342811,0.000101711375,0.00001274383,3.6365243e-8,0.000034616438,0.0000034210127,0.0328694],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976867,0.0005077523,0.00022137025,0.0005484072,0.0008157148,0.00022005623],"domain_scores_gemma":[0.9965368,0.002646361,0.00024519727,0.00020486851,0.00026979734,0.00009699777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011473759,0.00014992557,0.00032202344,0.0010539534,0.0003949582,0.00013368421,0.0009318009,0.00022719367,0.00037371824],"category_scores_gemma":[0.0010766109,0.00015526386,0.00010029489,0.0028765833,0.00042703812,0.0029845082,0.0011527953,0.00024387891,0.00000935685],"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":[0.00013361416,0.00008853392,0.96746457,0.000018317693,0.000045354547,0.000043242973,0.010322814,0.000051814226,0.00008192617,0.0007504084,0.0045570284,0.016442386],"study_design_scores_gemma":[0.0012724234,0.00004727571,0.8660096,0.000031980504,0.000015509466,0.000003408937,0.117379345,0.00047707997,0.000046217814,0.005899986,0.008674854,0.00014232806],"about_ca_topic_score_codex":0.00013687597,"about_ca_topic_score_gemma":0.00028841302,"teacher_disagreement_score":0.10705653,"about_ca_system_score_codex":0.00016205342,"about_ca_system_score_gemma":0.00026698763,"threshold_uncertainty_score":0.6331476},"labels":[],"label_agreement":null},{"id":"W7001644685","doi":"","title":"Latent variable models for harmonization of test scores:a case study on memory","year":2020,"lang":"en","type":"other","venue":"TU/e Research Portal (Eindhoven University of Technology)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Test (biology); Harmonization; Variable (mathematics); Reliability (semiconductor); Latent variable; Observational study","score_opus":0.4986817858837838,"score_gpt":0.4564420118672449,"score_spread":0.04223977401653889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001644685","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11883727,0.0016604803,0.094123766,0.002700918,0.000874391,0.012131898,0.0023067498,0.0013609488,0.7660036],"genre_scores_gemma":[0.73683614,0.00020574655,0.06625568,0.00001789545,0.0001142844,0.000012026569,0.000032562904,0.00025331136,0.19627237],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99608564,0.00030617055,0.00053881394,0.0009335181,0.0016635191,0.0004723179],"domain_scores_gemma":[0.9909405,0.0060127536,0.0008694867,0.0011931236,0.00084183156,0.00014232278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004861542,0.0002411952,0.0008746739,0.004603336,0.00021869478,0.00002849259,0.001968961,0.00057785783,0.00076993497],"category_scores_gemma":[0.027667155,0.0002233554,0.00016212455,0.0055612028,0.0005238866,0.000102285056,0.00090190314,0.0007124122,0.00002504902],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055957097,0.0038246915,0.03541635,0.000499052,0.0009936477,0.009474341,0.0013141298,0.001227755,0.0013795316,0.008980764,0.8482674,0.08806276],"study_design_scores_gemma":[0.026448954,0.048332628,0.004549034,0.0042167944,0.0012724884,0.0012751868,0.3859752,0.048768055,0.0061208988,0.21015245,0.25785336,0.00503497],"about_ca_topic_score_codex":0.0018584032,"about_ca_topic_score_gemma":0.00017413317,"teacher_disagreement_score":0.61799884,"about_ca_system_score_codex":0.00006330353,"about_ca_system_score_gemma":0.00030770522,"threshold_uncertainty_score":0.9805232},"labels":[],"label_agreement":null},{"id":"W7002025394","doi":"","title":"Measurement invariance of health-related quality of life: a simulation study and numeric example","year":2010,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Manitoba Health","funders":"","keywords":"Intraclass correlation; Measurement invariance; Measure (data warehouse); Sample (material); Quality (philosophy); Sample size determination; Reliability (semiconductor); Cluster analysis; Confirmatory factor analysis","score_opus":0.47488898708810523,"score_gpt":0.41024603547249505,"score_spread":0.06464295161561018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002025394","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":[0.9926253,0.0007046979,0.0049096667,0.000105961015,0.00042485233,0.0005066047,0.000013047456,0.000017313345,0.0006925847],"genre_scores_gemma":[0.9960053,0.00003278342,0.0037861073,0.000004334423,0.000008583395,2.6332893e-7,0.000009294451,0.000008070863,0.00014527144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953064,0.0014259838,0.00085469946,0.000495877,0.001751014,0.00016603305],"domain_scores_gemma":[0.9898122,0.0044793286,0.0038250037,0.0006084432,0.0011863817,0.0000886711],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013005967,0.00016665227,0.0010690313,0.00066481926,0.00018446044,0.000017752947,0.00060322933,0.00020698718,0.000027397025],"category_scores_gemma":[0.021349797,0.00017478908,0.00012002939,0.0015739324,0.00010227902,0.00016346456,0.00011020983,0.00028329168,0.0000027925566],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006459028,0.0007004794,0.90292484,0.0005067922,0.0002531937,0.0000022681647,0.007286192,0.0010007032,0.0014549545,0.00019181277,0.0003483278,0.08468452],"study_design_scores_gemma":[0.00072892307,0.00026243916,0.92025703,0.000080592385,0.000035483525,1.6172234e-7,0.07663586,0.0007855523,0.0000136971485,0.0009735918,0.000106145024,0.00012051717],"about_ca_topic_score_codex":0.030912217,"about_ca_topic_score_gemma":0.16607782,"teacher_disagreement_score":0.1351656,"about_ca_system_score_codex":0.000050859915,"about_ca_system_score_gemma":0.00022911868,"threshold_uncertainty_score":0.9868938},"labels":[],"label_agreement":null},{"id":"W7008870025","doi":"","title":"Contre-validation de données recueillies pour le dépistage des difficultés d’apprentissage chez des élèves francophones du primaire de l’Ontario","year":2005,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Relation (database); Reliability (semiconductor); Test (biology); Validity; Sample (material); Psychometrics","score_opus":0.5359366368808658,"score_gpt":0.5690503036894613,"score_spread":0.03311366680859551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008870025","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":[0.95960736,0.012330621,0.021407764,0.00037924288,0.00062531716,0.000381068,0.000029392848,0.000091633425,0.005147582],"genre_scores_gemma":[0.96240824,0.004484521,0.030989124,0.00013676354,0.00035674087,0.000037362523,0.0000065723334,0.000044589477,0.0015360754],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9933793,0.001909939,0.0017111907,0.0008117201,0.0013710533,0.00081677985],"domain_scores_gemma":[0.9824371,0.013951493,0.0016758725,0.00073725986,0.0007799404,0.00041837426],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013445548,0.0004656438,0.0011519161,0.0012508491,0.0012443183,0.0037789543,0.004350738,0.00021218834,0.010168187],"category_scores_gemma":[0.039947107,0.00036082757,0.00037681076,0.0025267457,0.00060235045,0.0038805206,0.0009559032,0.0005926451,0.000032681644],"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":[0.00014595565,0.0002972922,0.8012305,0.000037084308,0.000094453586,0.00002664869,0.003720653,0.0008433793,0.04132112,0.000033990604,0.015495419,0.13675353],"study_design_scores_gemma":[0.0007876938,0.00001573621,0.9152855,0.0002822585,0.000041500654,0.000058010784,0.002967545,0.00023348576,0.04156197,0.03339688,0.004950478,0.00041888581],"about_ca_topic_score_codex":0.013002066,"about_ca_topic_score_gemma":0.0054695862,"teacher_disagreement_score":0.13633464,"about_ca_system_score_codex":0.00042802157,"about_ca_system_score_gemma":0.0006309117,"threshold_uncertainty_score":0.99988437},"labels":[],"label_agreement":null},{"id":"W7015469619","doi":"","title":"Specifying the random effect structure in linear mixed effect models for analyzing psycholinguistic data","year":2017,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Random effects model; Model selection; Mixed model; Linear model; Psycholinguistics; Generalized linear mixed model; Fixed effects model; Population; Selection (genetic algorithm); Linear regression","score_opus":0.2845167370226674,"score_gpt":0.44902587067123617,"score_spread":0.16450913364856878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015469619","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":[0.9473509,0.002454658,0.00015814659,0.000028851298,0.015995363,0.0039383583,0.0037783466,0.0002047729,0.026090588],"genre_scores_gemma":[0.9872384,0.0002085053,0.007999372,0.00007563673,0.0005489251,0.00019239259,0.0013263832,0.00021453359,0.0021958437],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98592114,0.0044732825,0.002486899,0.0033026051,0.0024911987,0.0013248653],"domain_scores_gemma":[0.9048249,0.0857957,0.0026050324,0.005757419,0.0007226413,0.0002943025],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04071864,0.0012341272,0.002615274,0.0017287476,0.00310894,0.001043327,0.009325667,0.0011341941,0.00012356602],"category_scores_gemma":[0.41149527,0.00079497806,0.000787052,0.0023479227,0.00014112693,0.0011603908,0.00065245334,0.0029476045,0.000051867035],"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":[0.0027785986,0.000057648358,0.0007988504,0.0004090382,0.00030556126,0.000068878726,0.000021586675,0.00199523,0.0025013965,0.0022755903,0.00008632612,0.9887013],"study_design_scores_gemma":[0.028166413,0.0017061359,0.017114474,0.0043444782,0.00221087,0.00014034056,0.00068861013,0.061122093,0.016540125,0.7552378,0.10696879,0.0057598515],"about_ca_topic_score_codex":0.00030085543,"about_ca_topic_score_gemma":0.0016015868,"teacher_disagreement_score":0.98294145,"about_ca_system_score_codex":0.00029301867,"about_ca_system_score_gemma":0.00008217447,"threshold_uncertainty_score":0.9999937},"labels":[],"label_agreement":null},{"id":"W7015700817","doi":"","title":"Tesla deliveries at low-end in 4Q","year":2016,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Quarter (Canadian coin); Car model; Electric cars; General motors","score_opus":0.13960431105707147,"score_gpt":0.38156797331978726,"score_spread":0.2419636622627158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015700817","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054412163,0.00085972983,0.0302527,0.00019287928,0.0025848714,0.00069438963,0.000939503,0.00032851085,0.9587062],"genre_scores_gemma":[0.014624645,0.00035290615,0.009808288,0.0003745966,0.00075653277,0.0000809004,0.00009493126,0.00046090435,0.9734463],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99072444,0.0018470332,0.0019100753,0.0023874615,0.001809913,0.0013210517],"domain_scores_gemma":[0.96861947,0.027507985,0.0014746236,0.0018525932,0.00009179014,0.00045355447],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025476404,0.001048464,0.0016754668,0.0041069575,0.00005343132,0.00035352394,0.004452492,0.00034535173,0.080204576],"category_scores_gemma":[0.016073892,0.0007194034,0.0006822053,0.00075260794,0.0011490536,0.00017925246,0.0035904828,0.00095729035,0.014791726],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028330882,0.00009551341,0.020555777,0.000045197718,0.00013952631,0.00028457344,0.0013512284,0.0000027848723,0.00025469827,0.001599032,0.9625514,0.012836942],"study_design_scores_gemma":[0.0010696849,0.00024810078,0.009250976,0.0015828859,0.000024293231,0.00009944399,0.00014296803,0.0006009007,0.00020227728,0.022763204,0.96308964,0.0009256371],"about_ca_topic_score_codex":0.008906217,"about_ca_topic_score_gemma":0.021741824,"teacher_disagreement_score":0.06541285,"about_ca_system_score_codex":0.00015885218,"about_ca_system_score_gemma":0.00011643822,"threshold_uncertainty_score":0.9995257},"labels":[],"label_agreement":null},{"id":"W7015712427","doi":"","title":"Testing 3 Manitoba Related","year":2015,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Government (linguistics); Data collection; Identification (biology)","score_opus":0.3111599181567599,"score_gpt":0.370092158599887,"score_spread":0.05893224044312706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015712427","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":[0.8252734,0.0005157494,0.0002497947,0.00021274005,0.0020136395,0.00024469927,0.000019673176,0.0001498861,0.17132045],"genre_scores_gemma":[0.8428121,0.00013935292,0.10244278,0.00005889047,0.000413419,0.0000011274955,0.00032448093,0.0001390594,0.053668745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99583524,0.00052546355,0.00047523802,0.0008194843,0.0019443919,0.00040015054],"domain_scores_gemma":[0.9870141,0.008534945,0.0015980195,0.0009066067,0.0017383117,0.00020802545],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0046853987,0.0003146896,0.0008198825,0.0012933934,0.00036425522,0.00010426168,0.0019017652,0.0005164762,0.00006487421],"category_scores_gemma":[0.043969072,0.0003340988,0.00025229272,0.0035941594,0.0001246033,0.00032896895,0.00024839386,0.0005803321,0.00041594755],"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":[0.0003585151,0.00020722517,0.42148468,0.00019216062,0.00027943452,0.00041983117,0.0019190736,0.00028253885,0.0013971238,0.00087856385,0.1556436,0.41693723],"study_design_scores_gemma":[0.0006340035,0.00018263991,0.8045444,0.00020065974,0.000120368066,0.000017934355,0.15010785,0.00076987094,0.00003273215,0.024956295,0.017971665,0.00046158314],"about_ca_topic_score_codex":0.0030085288,"about_ca_topic_score_gemma":0.12371484,"teacher_disagreement_score":0.41647565,"about_ca_system_score_codex":0.00017789815,"about_ca_system_score_gemma":0.0002621996,"threshold_uncertainty_score":0.9999111},"labels":[],"label_agreement":null},{"id":"W7017325486","doi":"","title":"Analysis of multivariate responses in patient reported outcome measures: missing data and auxiliary variables","year":2022,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Missing data; Imputation (statistics); Multivariate statistics; Latent variable model; Latent variable; Item response theory; Type I and type II errors; Multivariate analysis; Odds; Multivariate normal distribution","score_opus":0.4032229500924355,"score_gpt":0.41187548896777343,"score_spread":0.008652538875337956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017325486","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":[0.99485725,0.00060595834,0.0019937812,0.00015159584,0.0003684708,0.00019404046,0.00021889353,0.000021469596,0.0015885542],"genre_scores_gemma":[0.97032166,0.0001871873,0.02770338,0.000014871054,0.000009891643,4.4629874e-7,0.00046670943,0.000017730179,0.0012781522],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99532264,0.0013824679,0.0007565047,0.00089436723,0.0014350237,0.00020901576],"domain_scores_gemma":[0.9825897,0.013200309,0.0022481782,0.0015187507,0.00036392114,0.000079102945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008228502,0.00019877253,0.0010924796,0.0037302794,0.00024469473,0.000045968784,0.001375783,0.00018222604,0.00007339844],"category_scores_gemma":[0.050623015,0.0002093564,0.000172869,0.0054688244,0.00009197555,0.00027643415,0.00070012145,0.00031979522,5.70253e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007126687,0.000118842734,0.9468247,0.000060934693,0.0007025434,0.0001756664,0.0019353727,0.0005301018,0.0005040382,0.00003743723,0.00040851012,0.04798915],"study_design_scores_gemma":[0.00032083393,0.000058300324,0.9023636,0.00005758385,0.00075340184,0.0000025678153,0.08557024,0.0078173205,0.000011773228,0.00034924716,0.002513489,0.00018164494],"about_ca_topic_score_codex":0.011424115,"about_ca_topic_score_gemma":0.10533345,"teacher_disagreement_score":0.09390933,"about_ca_system_score_codex":0.00008410708,"about_ca_system_score_gemma":0.00017153381,"threshold_uncertainty_score":0.9951589},"labels":[],"label_agreement":null},{"id":"W7017887811","doi":"","title":"A cognitive diagnostic assessment of PISA math items: What skills have Canadian student mastered?","year":2022,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Cognition; Test (biology); Cognitive skill; Item response theory; Achievement test; Cognitive development; Educational assessment; Test score","score_opus":0.13565684076695383,"score_gpt":0.39375077427771593,"score_spread":0.2580939335107621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017887811","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":[0.9761295,0.00073666114,0.00064741937,0.000294359,0.0018361416,0.0006675292,0.00030291383,0.000023191473,0.019362302],"genre_scores_gemma":[0.98854846,0.0009825886,0.003490813,0.00006313167,0.00005081716,0.0000036818178,0.00029427232,0.000031021107,0.00653522],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99560195,0.0007399835,0.00044123255,0.0007397398,0.0020719005,0.00040517194],"domain_scores_gemma":[0.97675467,0.02022618,0.0014087758,0.0005944909,0.00076341844,0.00025244092],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027298594,0.0002926349,0.0008652681,0.0019389153,0.00041147973,0.00017396324,0.0015185318,0.00021861459,0.00058773934],"category_scores_gemma":[0.010143098,0.00032357624,0.00029648145,0.0014166903,0.00012378518,0.00045162629,0.00030097354,0.0004703725,0.000026040412],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093615425,0.00048073893,0.9103199,0.00019042892,0.00046370755,0.0006045528,0.00825029,0.00018336897,0.000036522804,0.0006073465,0.005517901,0.073251635],"study_design_scores_gemma":[0.00034833202,0.0001753252,0.5887398,0.00026522006,0.000106260944,0.0000035628573,0.40778357,0.00012119836,0.0000072056564,0.0002890372,0.0019799152,0.00018055346],"about_ca_topic_score_codex":0.07530356,"about_ca_topic_score_gemma":0.9046521,"teacher_disagreement_score":0.82934856,"about_ca_system_score_codex":0.00042156316,"about_ca_system_score_gemma":0.0006304525,"threshold_uncertainty_score":0.9999216},"labels":[],"label_agreement":null},{"id":"W7018493324","doi":"","title":"Education Policy Analysis Archives 15/20","year":2007,"lang":"en","type":"article","venue":"Digital Commons - University of South Florida (University of South Florida)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"H2020 European Research Council; Wisconsin Center for Education Research, School of Education, University of Wisconsin-Madison; University of North Carolina at Greensboro; Kentucky Science and Technology Corporation; National Academy of Education; Social Sciences and Humanities Research Council of Canada; Fordham University; Center for Advanced Study in the Behavioral Sciences, Stanford University; University of Texas at Arlington; University of North Texas; University of South Florida; University of Texas at Austin; Annie E. Casey Foundation; University of Pittsburgh; Helsingin Yliopisto; American Psychological Association; Institute of Education Sciences; Educational Testing Service; University of Wisconsin-Madison; Arizona State University; Northwestern University; Abell Foundation; American Educational Research Association; Ball State University; U.S. Department of Education; Center for Advanced Study, University of Illinois at Urbana-Champaign; University of Washington; National Science Foundation","keywords":"Policy analysis; Public policy; Education policy; Government (linguistics); Discourse analysis","score_opus":0.125746460189541,"score_gpt":0.32539894979799244,"score_spread":0.19965248960845144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018493324","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":[0.8031275,0.00007509942,0.1265352,0.00033286258,0.00037065518,0.00018609788,0.0005266695,0.000098650235,0.068747215],"genre_scores_gemma":[0.9867157,0.000009979355,0.009012894,0.000023062224,0.00013258097,2.7577089e-8,0.00006273685,0.000013784731,0.004029235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99644005,0.00019980392,0.0005428339,0.00082622765,0.001388144,0.0006029366],"domain_scores_gemma":[0.99195564,0.004553488,0.001150027,0.0012541197,0.00059878064,0.00048795968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017066088,0.0003270996,0.0009796203,0.0049067726,0.00068227196,0.000114513365,0.0024175805,0.0002076408,0.00027619005],"category_scores_gemma":[0.003598219,0.00038545596,0.00092994765,0.009257945,0.0010761797,0.0010263968,0.0008931462,0.00037238435,0.00009325247],"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":[0.00078737125,0.00023677238,0.89935696,0.00003861037,0.0007814477,0.00004961445,0.029469632,0.00064393046,0.000095431256,0.003981663,0.0009904255,0.06356812],"study_design_scores_gemma":[0.0012895493,0.00022601217,0.72757196,0.0000576923,0.0005224237,0.00000578978,0.2520391,0.00087367615,0.00005805549,0.005191071,0.011550257,0.000614407],"about_ca_topic_score_codex":0.00070946093,"about_ca_topic_score_gemma":0.00030762592,"teacher_disagreement_score":0.22256948,"about_ca_system_score_codex":0.00010825454,"about_ca_system_score_gemma":0.00042207053,"threshold_uncertainty_score":0.99985975},"labels":[],"label_agreement":null},{"id":"W7020581204","doi":"","title":"Limits of generalizing in education research: Why criteria for research generalization should include population heterogeneity and users of knowledge claims","year":2014,"lang":"en","type":"article","venue":"Griffith Research Online (Griffith University, Queensland, Australia)","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 Victoria","funders":"","keywords":"Generalization; Representativeness heuristic; Population; Probabilistic logic; Sample (material); Essentialism; Neglect","score_opus":0.8487840553327511,"score_gpt":0.6255744716843369,"score_spread":0.22320958364841426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020581204","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":[0.9944676,0.00028025062,0.0016948775,0.0014379559,0.00036076497,0.0011569296,0.00019735223,0.000027472151,0.00037676658],"genre_scores_gemma":[0.97728753,0.0004120639,0.02051569,0.000020535825,0.00035460637,0.0000116190495,0.00015203426,0.000032736338,0.0012131928],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9828774,0.010198806,0.0011954742,0.0012319307,0.0032482436,0.0012481675],"domain_scores_gemma":[0.970736,0.020640241,0.00045845823,0.0011098337,0.006620318,0.00043513626],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046147585,0.0002783956,0.0007946583,0.0069355723,0.0007323537,0.00018899576,0.0015692718,0.00047681716,0.000044658056],"category_scores_gemma":[0.03693874,0.0002546378,0.00014946632,0.009014958,0.0008975002,0.0006115451,0.00087683235,0.001179776,0.0000052425353],"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":[0.0009784754,0.0010614599,0.90442234,0.00048072348,0.000054825363,0.0000060222833,0.0015224284,0.00089737517,0.013903807,0.012300234,0.020565439,0.04380686],"study_design_scores_gemma":[0.0019156074,0.0010526193,0.9488707,0.0004023008,0.000018267976,0.000007368241,0.0041245567,0.007949149,0.0024204315,0.019302435,0.013593394,0.00034312924],"about_ca_topic_score_codex":0.00806083,"about_ca_topic_score_gemma":0.014271529,"teacher_disagreement_score":0.04444839,"about_ca_system_score_codex":0.0003718606,"about_ca_system_score_gemma":0.00045985304,"threshold_uncertainty_score":0.9999906},"labels":[],"label_agreement":null},{"id":"W7024336930","doi":"","title":"Reliability and Validity of a Short Version of the General Functioning Subscale of the McMaster Family Assessment Device","year":2015,"lang":"en","type":"article","venue":"UWA Profiles and Research Repository (University of Western Australia)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Reliability (semiconductor); Measure (data warehouse); Validity; Psychometrics; Predictive validity","score_opus":0.5645375956801061,"score_gpt":0.46699719821217484,"score_spread":0.09754039746793125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024336930","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":[0.9980858,0.000056362198,0.000246039,0.00015782657,0.000217338,0.00025038357,0.000015421774,0.0000036055058,0.00096721784],"genre_scores_gemma":[0.9942046,0.000014598164,0.0022934913,0.0000022903528,0.00001992379,3.1618106e-7,3.7876484e-7,0.0000027619838,0.0034616704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962341,0.0014912667,0.00034365512,0.0003070302,0.0014512382,0.00017269538],"domain_scores_gemma":[0.9959658,0.0021202357,0.0003458533,0.00051619613,0.0009565632,0.00009538297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006887109,0.00007935573,0.0002922867,0.00013654462,0.00026949312,0.000028603683,0.0006389134,0.000094813644,0.000012158493],"category_scores_gemma":[0.0016427737,0.000048158887,0.00010645702,0.0007996436,0.001005765,0.00019842497,0.0008032661,0.00024961543,3.065385e-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":[0.00007813655,0.000050499933,0.96231633,0.0000745013,0.000015590504,0.0000010890487,0.00047947236,0.00006118503,0.035259932,0.000034899826,0.00053341145,0.0010949224],"study_design_scores_gemma":[0.0002829026,0.00021114494,0.9756381,0.00008702247,0.000021068778,0.0000061696005,0.0073009636,0.0004594996,0.015306345,0.0002983421,0.00034122245,0.00004721631],"about_ca_topic_score_codex":0.0015222051,"about_ca_topic_score_gemma":0.000013667325,"teacher_disagreement_score":0.019953588,"about_ca_system_score_codex":0.000038581624,"about_ca_system_score_gemma":0.00012091033,"threshold_uncertainty_score":0.37057835},"labels":[],"label_agreement":null},{"id":"W7025246185","doi":"","title":"What we're hearing : World Federation of Technical Assessment Organizations one step closer to worldwide assessments","year":2003,"lang":"en","type":"article","venue":"NPARC","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Impact assessment; Technical report; Russian federation","score_opus":0.36883711575669703,"score_gpt":0.495146292731972,"score_spread":0.126309176975275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025246185","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":[0.08518063,0.0000980482,0.75400007,0.0056061284,0.0015809699,0.0006459137,0.0000052607415,0.00012433725,0.15275864],"genre_scores_gemma":[0.5765505,0.000023300296,0.4204883,0.0002548653,0.00003497067,0.000015724427,0.0000018803944,0.0000120874665,0.0026184125],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962782,0.0006107983,0.00086256774,0.00052925665,0.0014080823,0.00031106317],"domain_scores_gemma":[0.9907397,0.007510921,0.0003039418,0.0006864181,0.000597131,0.0001618657],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0049871686,0.00014835657,0.00038576388,0.0007974861,0.00025119304,0.00064139784,0.000506487,0.000069346184,0.0021394473],"category_scores_gemma":[0.02445885,0.0001242693,0.0000645416,0.006552542,0.00003981082,0.00055579614,0.00019327771,0.0002288534,0.00005126845],"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":[0.00004144779,0.0009818011,0.2702709,0.000034211313,0.00009249966,0.000010206331,0.00043690743,0.0014101714,0.16573505,0.07907553,0.037728548,0.44418272],"study_design_scores_gemma":[0.0018521814,0.00068647834,0.5302642,0.00065408455,0.000091796195,0.000019863232,0.006738972,0.0037338927,0.029166816,0.32796803,0.09770223,0.0011214829],"about_ca_topic_score_codex":0.000009994284,"about_ca_topic_score_gemma":0.00018385307,"teacher_disagreement_score":0.49136984,"about_ca_system_score_codex":0.00013215157,"about_ca_system_score_gemma":0.000162493,"threshold_uncertainty_score":0.99877274},"labels":[],"label_agreement":null},{"id":"W7030339015","doi":"","title":"A Multi-Group Investigation of the CES-D's Measurement Structure Across Adolescents, Young Adults and Middle-Aged Adults","year":2004,"lang":"fr","type":"article","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Validation test; Young adult; Age groups; Statistical analysis; Age structure","score_opus":0.10469238556732223,"score_gpt":0.3005064928588521,"score_spread":0.19581410729152987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030339015","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":[0.98106235,0.0124943005,0.0011252299,0.00070322864,0.0019357965,0.00081673876,0.001713532,0.000029991295,0.000118837364],"genre_scores_gemma":[0.9901637,0.0024558005,0.006628469,0.000043796474,0.00009228998,6.8079305e-7,0.000047367645,0.000017071576,0.00055086624],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99452865,0.00089244556,0.0010221715,0.0013735251,0.0016352374,0.00054797204],"domain_scores_gemma":[0.99431986,0.00096049416,0.001875979,0.0018392369,0.0006495896,0.00035482485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002261875,0.00043885663,0.000764205,0.00020748646,0.0010769502,0.0001708189,0.0017958365,0.0003214613,0.000020494828],"category_scores_gemma":[0.004086719,0.00036619796,0.00014901636,0.00087584683,0.0016195981,0.0011790935,0.001774881,0.00042422203,0.0000016475933],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015618633,0.0005148664,0.8952234,0.0013280769,0.00054473965,0.00022560533,0.005376951,0.00015433252,0.005063552,0.0001346585,0.0020723986,0.08779955],"study_design_scores_gemma":[0.008130798,0.0002694107,0.97335327,0.004640722,0.0003627705,0.00015735737,0.007975197,0.00061245175,0.0008168892,0.0006249587,0.0025915785,0.00046457455],"about_ca_topic_score_codex":0.041720476,"about_ca_topic_score_gemma":0.050822027,"teacher_disagreement_score":0.087334976,"about_ca_system_score_codex":0.00037384775,"about_ca_system_score_gemma":0.00021095428,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W7036602812","doi":"","title":"Céreste-en-Luberon – Le village","year":2025,"lang":"fr","type":"other","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Prospection; Quarter (Canadian coin); Context (archaeology); Period (music)","score_opus":0.1461411809619255,"score_gpt":0.35365160653772104,"score_spread":0.20751042557579555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036602812","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034296163,0.0025487186,0.013751287,0.030598298,0.0049880827,0.0008748113,0.00027988563,0.00035750624,0.9431718],"genre_scores_gemma":[0.011459582,0.00035205673,0.012801221,0.0007834765,0.0011127532,0.000013035644,0.000057754067,0.0001444902,0.9732756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905665,0.0030605437,0.0011352071,0.0020594918,0.0016331159,0.0015451419],"domain_scores_gemma":[0.9695738,0.02583014,0.0014067512,0.0018062649,0.0006484191,0.0007346375],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.0042787725,0.0010710855,0.0016675487,0.0026172835,0.0008665056,0.0009292439,0.004003816,0.003342447,0.030309416],"category_scores_gemma":[0.06705511,0.0009878406,0.00075965957,0.008139877,0.00065306394,0.000652884,0.0011813396,0.0024834408,0.0020949093],"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":[0.00008563689,0.00019276318,0.0022704322,0.00005417628,0.0003882267,0.00047479072,0.0007608546,0.00032397042,0.0006926752,0.049657986,0.61404485,0.33105364],"study_design_scores_gemma":[0.0021875429,0.0001833838,0.055994403,0.00079965295,0.00022162261,0.00010612356,0.009130345,0.0004899279,0.00022841567,0.0033621257,0.92620814,0.0010882965],"about_ca_topic_score_codex":0.0063656904,"about_ca_topic_score_gemma":0.00061821507,"teacher_disagreement_score":0.32996535,"about_ca_system_score_codex":0.00090796885,"about_ca_system_score_gemma":0.0021518322,"threshold_uncertainty_score":0.99981785},"labels":[],"label_agreement":null},{"id":"W7039717170","doi":"","title":"New Approaches to the Study of Religion:Volume 2: Textual, Comparative, Sociological, and Cognitive Approaches","year":2008,"lang":"en","type":"book","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Saint Vincent University","funders":"","keywords":"Cognition; Cognitive systems; Cognitive computing; Perception","score_opus":0.8728096561840504,"score_gpt":0.46185357025560586,"score_spread":0.4109560859284445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039717170","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022243114,0.0039810506,0.032461133,0.0010621342,0.00023734807,0.0028540946,0.00004392616,0.00009385713,0.93702334],"genre_scores_gemma":[0.23161474,0.00031434337,0.02775049,0.00040121208,0.00047663515,0.00009439915,0.000017138778,0.000033394375,0.7392976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99366534,0.001485228,0.0013771979,0.00141512,0.0016672969,0.00038980923],"domain_scores_gemma":[0.9485865,0.049089838,0.0009766483,0.00088449597,0.00021984859,0.00024265127],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0054160105,0.0005090898,0.0016451171,0.0006107795,0.0004259324,0.00021521884,0.0015865543,0.0003886046,0.0001947809],"category_scores_gemma":[0.018627536,0.00025103107,0.0002139713,0.0013038506,0.0005995119,0.0001107344,0.0009711711,0.00070864265,0.00014380449],"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":[0.00013008207,0.00033342058,0.00643346,0.000010149936,0.0002849057,0.000008161762,0.010781648,0.000092954186,3.3893332e-7,0.010783832,0.8858657,0.08527536],"study_design_scores_gemma":[0.004253083,0.011681679,0.112318456,0.00030087316,0.0006959287,0.0001889652,0.23169719,0.0017752909,0.00001732088,0.24159916,0.3925225,0.0029495193],"about_ca_topic_score_codex":0.00012946899,"about_ca_topic_score_gemma":0.00006363647,"teacher_disagreement_score":0.49334317,"about_ca_system_score_codex":0.000033977278,"about_ca_system_score_gemma":0.000306787,"threshold_uncertainty_score":0.9999942},"labels":[],"label_agreement":null},{"id":"W7042390486","doi":"","title":"Online_Supplement – Supplemental material for The Woodcock-Johnson IV Tests of Achievement Provides Too Many Scores for Clinical Interpretation","year":2018,"lang":"en","type":"article","venue":"W&M Publish (College of William & Mary)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Interpretation (philosophy); Test (biology); Stanford–Binet Intelligence Scales; Achievement test; Criterion-referenced test","score_opus":0.22357030516516774,"score_gpt":0.45936746835693915,"score_spread":0.2357971631917714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042390486","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":[0.8453491,0.00033201903,0.10204602,0.014774193,0.012146701,0.008675901,0.015347877,0.000106848674,0.0012213858],"genre_scores_gemma":[0.8040252,0.00005925411,0.19206446,0.00045400835,0.0014248282,0.00046391273,0.00022319007,0.000040800034,0.001244379],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99432516,0.0004340123,0.0026203806,0.00081126974,0.0012523833,0.00055677554],"domain_scores_gemma":[0.9733208,0.022684878,0.0015235065,0.00094638666,0.0013936557,0.00013077857],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013330764,0.00029164788,0.00077963015,0.000534495,0.00030392554,0.0002523902,0.0017943041,0.0001412169,0.0010379127],"category_scores_gemma":[0.046475623,0.00018331177,0.00047139125,0.0011700224,0.0005477538,0.000767906,0.00057045993,0.0001289083,0.0000038785506],"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":[0.0017344682,0.0005724455,0.06368154,0.00010027547,0.0001828531,8.2725654e-7,0.00019787798,0.0000068513145,0.00070200505,0.0018262421,0.83297944,0.09801518],"study_design_scores_gemma":[0.0059834737,0.007844818,0.24553041,0.00016086263,0.0002222053,0.00000509575,0.0030233671,0.008597123,0.006379896,0.025010798,0.69668037,0.00056155486],"about_ca_topic_score_codex":0.00010844913,"about_ca_topic_score_gemma":0.00022743137,"teacher_disagreement_score":0.18184887,"about_ca_system_score_codex":0.0000645967,"about_ca_system_score_gemma":0.00023358245,"threshold_uncertainty_score":0.99987525},"labels":[],"label_agreement":null},{"id":"W7066432708","doi":"","title":"Ion channel remodeling in response to variations in heart rate","year":2011,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Stimulation; Electrophysiology; Transient (computer programming); Downregulation and upregulation; Heart cells; Heart rate; Amplitude; Ion channel","score_opus":0.2683277867854637,"score_gpt":0.40294865249613576,"score_spread":0.13462086571067206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066432708","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":[0.96783555,0.00016924129,0.000025077643,0.000117923344,0.0032130694,0.0009348743,0.00021799422,0.00014185593,0.027344428],"genre_scores_gemma":[0.9764448,0.000065270695,0.015120732,0.00050624076,0.00005639666,0.00018296385,0.00007571778,0.00011958543,0.007428302],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9868162,0.005466829,0.002735068,0.0021758103,0.0016996475,0.0011064268],"domain_scores_gemma":[0.9757939,0.020544836,0.0009160203,0.0015176579,0.0008132676,0.0004143057],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04010319,0.0006943454,0.0013059734,0.006233078,0.00066503836,0.00024215785,0.0017945237,0.0009286288,0.00028413857],"category_scores_gemma":[0.23580557,0.0006660681,0.00032623456,0.008926983,0.000030387222,0.0009132283,0.00030085648,0.0018761713,0.0006675229],"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":[0.01336315,0.0012356396,0.0029160057,0.0001889367,0.00012234891,0.0003817973,0.00069610844,0.008693044,0.22084735,0.038620573,0.00010721835,0.71282786],"study_design_scores_gemma":[0.0025787533,0.0005787363,0.3444978,0.001529278,0.00006109689,0.000039837363,0.0028873978,0.0023130628,0.010716006,0.5970214,0.035214096,0.0025625275],"about_ca_topic_score_codex":0.0013894166,"about_ca_topic_score_gemma":0.0037294864,"teacher_disagreement_score":0.7102653,"about_ca_system_score_codex":0.00062389876,"about_ca_system_score_gemma":0.00014629193,"threshold_uncertainty_score":0.9995791},"labels":[],"label_agreement":null},{"id":"W7066507071","doi":"","title":"Is Timing Everything? The Effects of Measurement Timing on the Performance of Nonlinear Longitudinal Models","year":2023,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Sample size determination; Sample (material); Observational error; Longitudinal data; Longitudinal study; Nonlinear system; Value (mathematics); Accuracy and precision","score_opus":0.33744927238579137,"score_gpt":0.3644046808633851,"score_spread":0.026955408477593756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066507071","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":[0.99504465,0.0004095156,0.000801848,0.0006065245,0.00079290563,0.00039471232,0.000014272597,0.000021422653,0.0019141203],"genre_scores_gemma":[0.99620265,0.00027590207,0.0010362775,0.000031687458,0.00005326035,5.926949e-7,0.0000047557132,0.0000150619135,0.0023798058],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99596435,0.00053984567,0.0004606016,0.00037699105,0.00241387,0.00024432456],"domain_scores_gemma":[0.97768587,0.018922754,0.0014512355,0.0010334803,0.0008715251,0.000035117697],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009282149,0.00021098826,0.00054659764,0.00043741436,0.00056044455,0.00002808322,0.0024586695,0.000144029,0.00005998613],"category_scores_gemma":[0.009923166,0.0001153201,0.000380431,0.0019756258,0.00021089564,0.00015309644,0.00026509602,0.0004398837,0.000023077326],"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":[0.007282496,0.0010914544,0.032343082,0.007832011,0.0049083387,0.00008607563,0.2564212,0.064770326,0.1369335,0.003926898,0.076462485,0.40794212],"study_design_scores_gemma":[0.0012722732,0.0012500571,0.73357314,0.0031180754,0.0011174293,0.000007343165,0.08356639,0.1549901,0.012420951,0.0074000186,0.00057260704,0.00071163283],"about_ca_topic_score_codex":0.00047680564,"about_ca_topic_score_gemma":0.000068151894,"teacher_disagreement_score":0.70123005,"about_ca_system_score_codex":0.00005236419,"about_ca_system_score_gemma":0.00012914678,"threshold_uncertainty_score":0.99841666},"labels":[],"label_agreement":null},{"id":"W7067262971","doi":"","title":"A Longitudinal Multilevel Extension of the Linear Logistic Test Model to Predict the Instructional Sensitivity of Test Items","year":2019,"lang":"en","type":"article","venue":"Das Repository der Padagogischen Hoschule St. Gallen (Padagogischen Hoschule St. Gallen)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Extension (predicate logic); Test (biology); Item response theory; Sensitivity (control systems); Multilevel model; Logistic regression; Educational testing; Relation (database)","score_opus":0.2688678884034303,"score_gpt":0.4102798062908345,"score_spread":0.1414119178874042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067262971","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":[0.9087688,0.0015703638,0.06677471,0.0022326394,0.0041120322,0.003597547,0.0013656794,0.00033651252,0.011241767],"genre_scores_gemma":[0.9557068,0.0000895509,0.0358064,0.00031146468,0.00066876214,0.00012894186,0.00003770755,0.00015361715,0.0070967823],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9824062,0.0026405915,0.004099605,0.0030944573,0.0060928822,0.0016662937],"domain_scores_gemma":[0.9486621,0.038276155,0.0033901348,0.0057329,0.0032425486,0.0006961559],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.013023091,0.0013739008,0.002361385,0.0010065478,0.001199791,0.00037711798,0.0041354722,0.0008134578,0.00025503652],"category_scores_gemma":[0.0790456,0.0008579351,0.0012197045,0.0031688933,0.0014532724,0.0010235521,0.0028485612,0.0019793315,0.00012367006],"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":[0.0009795355,0.0023612187,0.7202883,0.00039423673,0.0008636742,0.00011455023,0.0024928118,0.07611034,0.16019933,0.0011460381,0.02230725,0.012742727],"study_design_scores_gemma":[0.0028754356,0.0015182727,0.6573104,0.0007769024,0.000525176,0.00058202696,0.0038172454,0.29582036,0.019859586,0.0017927819,0.013187545,0.0019342229],"about_ca_topic_score_codex":0.00086896133,"about_ca_topic_score_gemma":0.00024063673,"teacher_disagreement_score":0.21971002,"about_ca_system_score_codex":0.000241893,"about_ca_system_score_gemma":0.0012534682,"threshold_uncertainty_score":0.9999012},"labels":[],"label_agreement":null},{"id":"W7084123791","doi":"10.64628/aap.v5rgnvwfe","title":"Les Canadiens satisfaits de leurs médias mais peu nombreux à payer pour s’informer en ligne","year":2019,"lang":"fr","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Government (linguistics); Context (archaeology); Power (physics); Test (biology); The Internet","score_opus":0.44543213436488616,"score_gpt":0.4554850446592479,"score_spread":0.010052910294361728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084123791","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":[0.61689234,0.002892381,0.011797737,0.007850999,0.003864052,0.00031607316,0.000047345122,0.000080800826,0.35625827],"genre_scores_gemma":[0.5109477,0.00039807404,0.11611605,0.0025599573,0.00038264706,0.000008906107,0.0000025049358,0.000036260484,0.36954787],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947218,0.0007950415,0.0010534358,0.00086830417,0.001097373,0.0014640985],"domain_scores_gemma":[0.9633914,0.034196053,0.00040067956,0.00099161,0.0004017143,0.0006185466],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00811412,0.00041262468,0.0007012616,0.0007987731,0.00025815933,0.0004885513,0.0013800041,0.00043087773,0.031710796],"category_scores_gemma":[0.042862274,0.0003160539,0.00028576827,0.0024496973,0.00016622154,0.0006024923,0.0002889115,0.00051151804,0.005159184],"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":[0.000011630606,0.00002996855,0.37580338,0.000020857731,0.000041000247,0.000026253172,0.00094507483,0.00016077604,0.00025633545,0.006949458,0.05706568,0.5586896],"study_design_scores_gemma":[0.000744565,0.00024398985,0.66623724,0.00009297094,0.00004452444,0.00019534295,0.008530098,0.003906052,0.00036683574,0.008372277,0.31067628,0.00058984954],"about_ca_topic_score_codex":0.07059981,"about_ca_topic_score_gemma":0.0075856727,"teacher_disagreement_score":0.55809975,"about_ca_system_score_codex":0.00037014144,"about_ca_system_score_gemma":0.0007978375,"threshold_uncertainty_score":0.99992913},"labels":[],"label_agreement":null},{"id":"W7095516206","doi":"","title":"Canadian Journal of Experimental Psychology (in press, 2003). This is a pre-publication version.","year":2007,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Experimental psychology; Range (aeronautics); Null hypothesis; Presentation (obstetrics); Factorial; Natural (archaeology); Statistical hypothesis testing; Confidence interval","score_opus":0.37218936847887996,"score_gpt":0.5065173126039412,"score_spread":0.13432794412506122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095516206","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46719745,0.0036855435,0.026110064,0.004201483,0.0032216827,0.00028131178,0.000011647844,0.000021968057,0.49526885],"genre_scores_gemma":[0.94322157,0.000025263103,0.046540543,0.001954058,0.0001162247,0.0000018490559,0.0000010323658,0.0000066965804,0.00813277],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790806,0.00018449449,0.00077734125,0.00025370633,0.0005632001,0.00031317348],"domain_scores_gemma":[0.99578434,0.0024229577,0.0003561452,0.00036399966,0.00082247827,0.0002500841],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0091180885,0.00007771193,0.00019578011,0.0011155157,0.00008060389,0.00010662647,0.0007649451,0.00010508903,0.0077840355],"category_scores_gemma":[0.038186967,0.000054567343,0.000049187773,0.0027448735,0.00006383124,0.00028474708,0.00003547311,0.00016002827,0.00007557045],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005064982,0.000060966067,0.15809685,5.915582e-7,0.0000069534717,0.00001529468,0.0010837902,0.0000027749447,0.0007593936,0.0005697264,0.78091425,0.05843875],"study_design_scores_gemma":[0.0009044265,0.00023885326,0.38858765,0.000009707488,0.0000033715744,0.000094880255,0.0014139416,0.0002430153,0.0068175625,0.0025681893,0.59896964,0.00014875087],"about_ca_topic_score_codex":0.014077845,"about_ca_topic_score_gemma":0.0032745183,"teacher_disagreement_score":0.4871361,"about_ca_system_score_codex":0.00009677857,"about_ca_system_score_gemma":0.0002455841,"threshold_uncertainty_score":0.993123},"labels":[],"label_agreement":null},{"id":"W7096040788","doi":"","title":"RESEARCH ARTICLE Introducing Computer-Based Testing in High- Stakes Exams in Higher Education: Results of a Field Experiment","year":2016,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Test (biology); Quarter (Canadian coin); Sample (material); Sample size determination; Student achievement; Research design; Higher education","score_opus":0.7312558407360974,"score_gpt":0.5363079835911067,"score_spread":0.19494785714499074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096040788","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":[0.9770925,0.00009481504,0.005464356,0.009930975,0.00058799394,0.00017547759,0.0000013174973,0.00002488663,0.006627658],"genre_scores_gemma":[0.8845589,0.0000012326575,0.11435682,0.00018288475,0.00016557258,0.00001855064,1.972939e-7,0.000004933737,0.0007108787],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959951,0.0010207756,0.0010288839,0.00060069526,0.0009732498,0.00038129714],"domain_scores_gemma":[0.9086093,0.08995135,0.00020309008,0.0007486544,0.0004093647,0.00007825415],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014981154,0.00009400176,0.00027545672,0.0011653196,0.000051465275,0.00007633074,0.0005590285,0.00006554406,0.00045768256],"category_scores_gemma":[0.07021046,0.00005482994,0.000028091827,0.004486549,0.0000826951,0.00017123623,0.00016499677,0.00015901933,0.000020527163],"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":[0.00014984704,0.00035603112,0.25892937,0.0000065674,0.0000022250283,0.000005341642,0.0003376983,0.0004498616,0.01741533,0.0011282447,0.008074255,0.7131452],"study_design_scores_gemma":[0.0024925547,0.0006942733,0.89041543,0.0004002338,0.0000010343995,0.0000014825603,0.001931105,0.0028725443,0.08510581,0.014448169,0.0014309201,0.00020645827],"about_ca_topic_score_codex":0.0017707889,"about_ca_topic_score_gemma":0.00008117689,"teacher_disagreement_score":0.7129388,"about_ca_system_score_codex":0.000094681694,"about_ca_system_score_gemma":0.00015331504,"threshold_uncertainty_score":0.93762153},"labels":[],"label_agreement":null},{"id":"W7096144025","doi":"","title":"The Service and Outcome Measurement","year":2002,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Service (business); Outcome (game theory); Best practice; Human services; Information system; Training (meteorology)","score_opus":0.9107738055954878,"score_gpt":0.5105348807184698,"score_spread":0.40023892487701807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096144025","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2535457,0.0057786023,0.026355451,0.065413654,0.0018291129,0.00030096967,0.000001176641,0.00017392907,0.6466014],"genre_scores_gemma":[0.9839043,0.000052972922,0.009042338,0.0014655653,0.00004200161,0.0000032419466,1.01549595e-8,0.0000028449747,0.005486723],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981884,0.00017758625,0.0003065901,0.00018579641,0.000995563,0.00014609257],"domain_scores_gemma":[0.9853522,0.013890589,0.0000803611,0.00037287947,0.00024928502,0.00005464178],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009551528,0.000050336723,0.00009477021,0.00006446225,0.00025281732,0.00024495588,0.0004134835,0.00001890775,0.00050503266],"category_scores_gemma":[0.063518256,0.000021036909,0.000022987404,0.0009375795,0.00002743488,0.00006062424,0.00010999085,0.00005579155,0.00022062742],"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":[0.0000019554022,0.000009822965,0.1574141,0.0000010514223,0.000005796876,8.8112716e-7,0.000111683636,0.0000036236145,0.00006873904,0.0025137286,0.026506657,0.81336194],"study_design_scores_gemma":[0.00032113836,0.000043639873,0.4852798,0.0000035997864,0.0000056290132,0.000016355309,0.001659746,0.010734639,0.00006595882,0.045044802,0.4566734,0.00015127248],"about_ca_topic_score_codex":0.000028119988,"about_ca_topic_score_gemma":0.000047117792,"teacher_disagreement_score":0.81321067,"about_ca_system_score_codex":0.000008464601,"about_ca_system_score_gemma":0.0000021834096,"threshold_uncertainty_score":0.94437015},"labels":[],"label_agreement":null},{"id":"W7096244888","doi":"","title":"An Experiment in the Use of Gamma Measure and of the Guttman Scale *","year":2016,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Guttman scale; Scale (ratio); Measure (data warehouse); Promotion (chess)","score_opus":0.7517426509178944,"score_gpt":0.49438228826336184,"score_spread":0.25736036265453255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096244888","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":[0.99264956,0.00008400467,0.004238652,0.0008269018,0.00008078477,0.000098891804,0.000002126178,0.0000034212662,0.0020156775],"genre_scores_gemma":[0.98748696,0.0000071397703,0.012150346,0.00008927393,0.0000075270664,0.0000024168191,1.1421865e-8,0.0000015147609,0.00025480957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981974,0.0006423262,0.0003136829,0.00015834546,0.0005999107,0.00008834641],"domain_scores_gemma":[0.98747104,0.011673799,0.00014243448,0.0006079113,0.00008412604,0.000020684878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0048103384,0.00004515683,0.00012978092,0.00010024321,0.000031396048,0.000030316214,0.0005710381,0.000025481486,0.00009623922],"category_scores_gemma":[0.015863774,0.000012975175,0.000034095763,0.0007008989,0.000115276685,0.00012424754,0.00008029519,0.00002947052,0.000001041423],"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":[0.00001997453,0.00007231395,0.65540534,0.0000014036415,0.0000031348548,3.1028276e-7,0.0014995601,0.0000064013425,0.04469068,0.0014785649,0.0021886213,0.2946337],"study_design_scores_gemma":[0.00027553574,0.00009175732,0.9630089,0.000025288426,0.0000021330986,0.000003095441,0.002716405,0.00013697566,0.025189754,0.0060601803,0.002443908,0.000046109395],"about_ca_topic_score_codex":0.00011804137,"about_ca_topic_score_gemma":0.00006204212,"teacher_disagreement_score":0.3076035,"about_ca_system_score_codex":0.0000038901553,"about_ca_system_score_gemma":0.000010881906,"threshold_uncertainty_score":0.99242604},"labels":[],"label_agreement":null},{"id":"W7096557082","doi":"","title":"Copyright © Canadian Academy of Oriental and Occidental Culture The Modification of Dichotomous and Polytomous Item Response Theory to Structural Equation Modeling Analysis","year":2012,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Item response theory; Polytomous Rasch model; Structural equation modeling; Structural approach; Differential item functioning; Rasch model","score_opus":0.3426074438237303,"score_gpt":0.4646583327438969,"score_spread":0.12205088892016658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096557082","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":[0.9573807,0.0005225953,0.041251298,0.00029195627,0.00007087095,0.00017555508,0.00002935138,0.000008225156,0.0002694513],"genre_scores_gemma":[0.9928266,0.000008706831,0.006840995,0.00013320602,0.000028451395,0.0000035900568,0.0000025406443,0.0000038374387,0.00015209346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977462,0.0007262276,0.0005077141,0.00025225594,0.0005472086,0.00022036636],"domain_scores_gemma":[0.9926549,0.006565821,0.00023378785,0.00020983216,0.00011782481,0.00021778974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074192896,0.0001023734,0.0002525114,0.0008186191,0.00018482585,0.00006155362,0.00029375072,0.00008845344,0.00007912871],"category_scores_gemma":[0.013825936,0.0000547553,0.00006097889,0.0023227588,0.00009807517,0.00027036475,0.00007654707,0.00010330146,0.0000013795823],"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":[0.000957276,0.000025542377,0.8861269,0.000008365372,0.00024776673,6.453479e-7,0.021894721,0.0046683387,0.018697442,0.01616322,0.00024878417,0.050961006],"study_design_scores_gemma":[0.00024379896,0.000069240705,0.7255166,0.0000068357595,0.0001607818,0.00001931198,0.013878985,0.24570705,0.0030256382,0.011126032,0.000082785285,0.0001629186],"about_ca_topic_score_codex":0.0052363225,"about_ca_topic_score_gemma":0.00077877095,"teacher_disagreement_score":0.24103871,"about_ca_system_score_codex":0.000040494735,"about_ca_system_score_gemma":0.00002770329,"threshold_uncertainty_score":0.994481},"labels":[],"label_agreement":null},{"id":"W7096568579","doi":"","title":"The Service and Outcome Measurement","year":2015,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Service (business); Outcome (game theory); Best practice; Human services; Information system; Training (meteorology)","score_opus":0.9474566104784713,"score_gpt":0.5675963466922874,"score_spread":0.37986026378618387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096568579","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41823524,0.0031569616,0.05825474,0.050829057,0.0029983057,0.00030675446,0.0000011072149,0.00016680398,0.46605104],"genre_scores_gemma":[0.97844136,0.000007930026,0.017631754,0.0013319474,0.000057117373,0.0000034702246,2.7091692e-8,0.0000030339568,0.002523349],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979261,0.00022611397,0.000287993,0.00016872984,0.0012599026,0.00013114713],"domain_scores_gemma":[0.9881224,0.010658583,0.000087448316,0.00038190436,0.0006334693,0.0001161893],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023770267,0.000046864352,0.0000955777,0.000058909136,0.00013135122,0.0002444335,0.00042197618,0.00001829538,0.000028602753],"category_scores_gemma":[0.13411069,0.0000190226,0.000016599768,0.0008531212,0.000026621348,0.00006676624,0.00015647194,0.000048989925,0.00010693581],"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":[0.000014012278,0.000009888789,0.4500192,0.000001070971,0.0000080830505,0.0000012439601,0.00024345012,0.00001364876,0.00004931475,0.0058151684,0.04433174,0.49949318],"study_design_scores_gemma":[0.00045781065,0.000060080565,0.3575153,0.0000026747705,0.0000049485766,0.000014126916,0.006097939,0.0021831682,0.00006797945,0.17569932,0.45776942,0.00012722755],"about_ca_topic_score_codex":0.00007804056,"about_ca_topic_score_gemma":0.00009198977,"teacher_disagreement_score":0.5602061,"about_ca_system_score_codex":0.000014329536,"about_ca_system_score_gemma":0.000023289556,"threshold_uncertainty_score":0.8731831},"labels":[],"label_agreement":null},{"id":"W7096779003","doi":"","title":"LSAC RESEARCH REPORT SERIES � Constraining Item Exposure in Computerized Adaptive Testing with Shadow Tests","year":2005,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Government (linguistics); Shadow (psychology); Agency (philosophy); Voting; Corporation; Test (biology)","score_opus":0.775064766779053,"score_gpt":0.5371735166305188,"score_spread":0.23789125014853418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096779003","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":[0.78317785,0.00016895508,0.027142825,0.00091932336,0.00020165626,0.0004371955,0.0000035053292,0.00022483931,0.18772386],"genre_scores_gemma":[0.57303494,0.0000016465275,0.42561296,0.00006971756,0.00011044932,0.000014026862,7.688949e-7,0.000009946549,0.0011455402],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939892,0.0010480154,0.0012006974,0.0009803434,0.0020266594,0.00075506716],"domain_scores_gemma":[0.9115848,0.08504241,0.00054132123,0.0009933773,0.0016027658,0.00023535533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022275154,0.00021859749,0.0005617376,0.0011940335,0.00031228072,0.0004347218,0.00080665667,0.0001166,0.0003074023],"category_scores_gemma":[0.14923888,0.00014137727,0.000050981766,0.0072578443,0.00045909075,0.00066018547,0.00034892783,0.0005984136,0.000044224802],"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":[0.00011546708,0.000063299936,0.5353638,0.0000036775245,0.000009402373,0.0006760696,0.0006150355,0.00055559224,0.00071202783,0.0011021221,0.000876207,0.4599073],"study_design_scores_gemma":[0.002170976,0.0016209207,0.9263983,0.00034926253,0.000006374308,0.0036918677,0.01862245,0.026021415,0.00056865,0.0131520135,0.006714337,0.00068348274],"about_ca_topic_score_codex":0.00018022624,"about_ca_topic_score_gemma":0.00038634753,"teacher_disagreement_score":0.4592238,"about_ca_system_score_codex":0.00007812521,"about_ca_system_score_gemma":0.00023204205,"threshold_uncertainty_score":0.85792744},"labels":[],"label_agreement":null},{"id":"W7096938795","doi":"","title":"ADoes Mother or Father Know Best? An Assessment of Parent/Child Agreement","year":2000,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Agreement; Affect (linguistics); Socioeconomic status; Set (abstract data type); Test (biology); Vocabulary; National Longitudinal Surveys","score_opus":0.5049940278846808,"score_gpt":0.5501600343407549,"score_spread":0.04516600645607405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096938795","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47651476,0.00019293133,0.018804088,0.00047467148,0.0002899469,0.00022769265,0.00001049207,0.000050570263,0.50343484],"genre_scores_gemma":[0.7952268,0.00015703781,0.15137185,0.00043682748,0.00010754227,0.000012774297,0.0000012975032,0.000014236105,0.05267164],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99697405,0.00042592234,0.00070294406,0.00048121827,0.0011420555,0.00027381425],"domain_scores_gemma":[0.9947371,0.0039595203,0.00021736322,0.00082195265,0.00014356589,0.00012052962],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003686372,0.00014766934,0.00034399328,0.00026735652,0.000100575955,0.00010779577,0.0008001434,0.00005860048,0.08431121],"category_scores_gemma":[0.003064497,0.00007489287,0.00009997337,0.0012210334,0.0000726958,0.00019611536,0.000072383824,0.000097634795,0.00020035],"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":[0.00002329647,0.00029876994,0.07060549,0.000002611639,0.000018374283,0.000002710437,0.000121331075,0.00019567978,0.00006333562,0.00060881564,0.002189171,0.9258704],"study_design_scores_gemma":[0.001567552,0.0022080005,0.62872297,0.00012763908,0.000042992095,0.000022306602,0.0064368336,0.011512443,0.000830175,0.021066472,0.32680094,0.0006616911],"about_ca_topic_score_codex":0.00015953468,"about_ca_topic_score_gemma":0.00007205477,"teacher_disagreement_score":0.92520875,"about_ca_system_score_codex":0.00001984197,"about_ca_system_score_gemma":0.000041331838,"threshold_uncertainty_score":0.91652584},"labels":[],"label_agreement":null},{"id":"W7097092499","doi":"","title":"Moderated DIF 1 Running head: MODERATED DDF METHODOLOGY Differential Domain Functioning on the Numeracy Component of the Foundation Skills Assessment: Bringing the Context into Picture by Investigating Sociological / Community Moderated Test and Item","year":2003,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Differential item functioning; Test (biology); Numeracy; Context (archaeology); Matching (statistics); Item response theory; Contrast (vision); Differential (mechanical device)","score_opus":0.3317731146178872,"score_gpt":0.4374428462040095,"score_spread":0.10566973158612225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097092499","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":[0.71273136,0.000077426324,0.28331608,0.002084566,0.0003175333,0.0004454514,0.000005737004,0.00006953354,0.0009523364],"genre_scores_gemma":[0.9734608,0.000009040532,0.024676224,0.0016102945,0.00003961084,0.000039135313,0.000017929795,0.00002284803,0.0001241091],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9805132,0.016079588,0.001308981,0.00062480813,0.000961977,0.00051144685],"domain_scores_gemma":[0.8774567,0.11957752,0.0011994661,0.00103481,0.000601603,0.00012987654],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.017022274,0.00042110746,0.00076070696,0.00018726691,0.004484431,0.00075010874,0.0009939894,0.0002633807,0.00027126318],"category_scores_gemma":[0.083911836,0.00018563218,0.00016302707,0.0016283263,0.0008554303,0.00025634756,0.0004470929,0.001845777,0.0000031924321],"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":[0.00026381147,0.0013045908,0.45458597,0.00006188858,0.00064836047,0.0000025866605,0.045683064,0.044547677,0.3301221,0.07299415,0.003396236,0.046389572],"study_design_scores_gemma":[0.0017267171,0.0003408367,0.17884222,0.00017204718,0.00006675455,0.000048428425,0.036452975,0.574028,0.0071031535,0.20051414,0.00018336753,0.0005213684],"about_ca_topic_score_codex":0.0005965679,"about_ca_topic_score_gemma":0.000049818358,"teacher_disagreement_score":0.52948034,"about_ca_system_score_codex":0.000119718236,"about_ca_system_score_gemma":0.00010901286,"threshold_uncertainty_score":0.99681157},"labels":[],"label_agreement":null},{"id":"W7097173925","doi":"","title":"LSAC RESEARCH REPORT SERIES � Predictive Control of Speededness in Adaptive Testing","year":2007,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Discretion; Government (linguistics); Agency (philosophy); Accreditation; Common law; Public law","score_opus":0.7946350243075865,"score_gpt":0.579686668911813,"score_spread":0.2149483553957735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097173925","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":[0.40618116,0.00012326012,0.3086938,0.00013820743,0.00039958538,0.00035395756,0.0000052208757,0.000047231202,0.2840576],"genre_scores_gemma":[0.91906875,0.0000017617987,0.07883384,0.000021889547,0.00008564385,0.000005739611,2.8731796e-7,0.000006995411,0.0019750604],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943586,0.0008417951,0.0014056517,0.00060139154,0.0022207603,0.0005718143],"domain_scores_gemma":[0.80129975,0.19322692,0.000759044,0.00096772716,0.0035590155,0.00018755496],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.078054525,0.00011592894,0.0004672374,0.0015186467,0.00012090221,0.00006257626,0.000661962,0.000105719686,0.00017978117],"category_scores_gemma":[0.43029976,0.0000791518,0.000060653158,0.008179464,0.00039757878,0.00033105983,0.000207393,0.00037542934,0.000014263287],"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":[0.0004979239,0.00010618159,0.880334,0.000004927667,0.000016678896,0.00047042043,0.00057026214,0.00036373627,0.0018770596,0.0035875507,0.0006822252,0.11148899],"study_design_scores_gemma":[0.0006569717,0.00061866466,0.89296764,0.00005432472,0.0000036666845,0.00017537769,0.021377852,0.004286257,0.0032459823,0.07598779,0.00048649512,0.00013895232],"about_ca_topic_score_codex":0.0006107961,"about_ca_topic_score_gemma":0.00016348825,"teacher_disagreement_score":0.5128876,"about_ca_system_score_codex":0.00006747883,"about_ca_system_score_gemma":0.00015675608,"threshold_uncertainty_score":0.9493369},"labels":[],"label_agreement":null},{"id":"W7097530823","doi":"","title":"� Balanced Item Pool Assembly in Computerized Adaptive Testing","year":2007,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Discretion; Government (linguistics); Accreditation; Agency (philosophy); Common law; Public law","score_opus":0.5907761345273238,"score_gpt":0.4859520636099765,"score_spread":0.1048240709173473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097530823","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":[0.48839,0.000031641906,0.44241902,0.000075574346,0.0003866283,0.00011185863,7.471853e-7,0.00009205363,0.06849248],"genre_scores_gemma":[0.6380063,6.774219e-7,0.36126152,0.00026864308,0.000068069494,0.0000016553661,2.338572e-7,0.000005170177,0.00038768753],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99688035,0.00031768612,0.00090434786,0.00054277375,0.00085659826,0.00049822114],"domain_scores_gemma":[0.888386,0.11047326,0.00030342094,0.00042093094,0.00029015777,0.00012621921],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015406469,0.00014349158,0.00039263957,0.00078883406,0.00008711765,0.00014558474,0.00070694846,0.00008406613,0.00012286546],"category_scores_gemma":[0.11813106,0.000099274446,0.00006463092,0.005383525,0.000043857865,0.00021093391,0.00020764988,0.0001947468,0.000092875605],"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":[0.000058491016,0.00004156254,0.30087098,0.0000012422067,0.0000048063143,0.00005450479,0.00009304747,0.00015396238,0.004555739,0.0010367426,0.0008317635,0.69229716],"study_design_scores_gemma":[0.0007422497,0.000117716474,0.9259498,0.000023532131,0.0000014725341,0.00001934827,0.00087027706,0.06219151,0.0008028782,0.008379167,0.0007188177,0.00018323078],"about_ca_topic_score_codex":0.00015743187,"about_ca_topic_score_gemma":0.000049464456,"teacher_disagreement_score":0.69211394,"about_ca_system_score_codex":0.000048139653,"about_ca_system_score_gemma":0.000036952304,"threshold_uncertainty_score":0.8892973},"labels":[],"label_agreement":null},{"id":"W7097913826","doi":"","title":"LSAC RESEARCH REPORT SERIES � Robustness of Person-Fit Decisions in Computerized Adaptive Testing","year":2005,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Government (linguistics); Robustness (evolution); Voting; Corporation; Agency (philosophy); Legal research; Work (physics); Commercial law","score_opus":0.880449482829345,"score_gpt":0.5643384276428418,"score_spread":0.3161110551865032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097913826","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":[0.7657923,0.00017080823,0.17794949,0.0009140379,0.00041227302,0.00030866516,0.000004047749,0.000073859395,0.054374494],"genre_scores_gemma":[0.49381307,0.000007082492,0.50421834,0.000016565495,0.00010111708,0.000008309865,4.175437e-7,0.000007206978,0.0018279055],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99392956,0.0011812549,0.0013374963,0.00077059044,0.0022285788,0.0005525409],"domain_scores_gemma":[0.86843103,0.12765823,0.00053987093,0.0011236711,0.0020735122,0.00017370105],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029919414,0.00015640525,0.0005979401,0.0016753107,0.00023087002,0.00015480627,0.0011213874,0.00011331048,0.0004216962],"category_scores_gemma":[0.29203245,0.00010886754,0.00010082696,0.009029555,0.00030717935,0.0004933449,0.0004634586,0.00040518405,0.0000316067],"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":[0.00018482565,0.00022837409,0.06878909,0.000003987038,0.000016808206,0.0001839217,0.0007372438,0.025942933,0.0012949419,0.0014139926,0.007416405,0.8937875],"study_design_scores_gemma":[0.0017968304,0.00070860476,0.5204166,0.00031050868,0.000008754672,0.00093870086,0.025077298,0.42541978,0.001545402,0.014128831,0.00902648,0.0006222081],"about_ca_topic_score_codex":0.00026122062,"about_ca_topic_score_gemma":0.00019162091,"teacher_disagreement_score":0.8931653,"about_ca_system_score_codex":0.0000719511,"about_ca_system_score_gemma":0.00019069269,"threshold_uncertainty_score":0.9989021},"labels":[],"label_agreement":null},{"id":"W7097965712","doi":"","title":"TITLE Differential Domain Functioning on the Numeracy Component of the Foundation Skills Assessment: Bringing the Context into","year":2016,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Numeracy; Differential item functioning; Matching (statistics); Context (archaeology); Test (biology); Differential (mechanical device); Contrast (vision); Interpretation (philosophy)","score_opus":0.1806498618922558,"score_gpt":0.41977572630881843,"score_spread":0.23912586441656264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097965712","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":[0.552923,0.000014687856,0.31927216,0.008235777,0.0019383865,0.00018256869,0.0000011086755,0.000023178687,0.11740908],"genre_scores_gemma":[0.99467075,0.000002870162,0.001260508,0.00019710431,0.00007516688,0.0000038415515,1.4953478e-7,0.000003303282,0.0037862929],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986274,0.0003822057,0.00024181562,0.00013910148,0.00051717745,0.0000922996],"domain_scores_gemma":[0.98375565,0.015566702,0.00019614668,0.0003957718,0.000072344636,0.000013386111],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002126603,0.00005497241,0.000088921726,0.000057023033,0.00028740865,0.000099755394,0.00044464105,0.00001811717,0.0056688217],"category_scores_gemma":[0.006222266,0.000015514968,0.00007109362,0.00037003896,0.000084420746,0.000055494787,0.00012467272,0.000073850635,0.00017315429],"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":[0.0000087596345,0.000041891213,0.017358957,0.0000013024538,0.000025100366,1.5825972e-7,0.00033263123,0.000007647142,0.005539855,0.0860315,0.0131347,0.8775175],"study_design_scores_gemma":[0.0007222273,0.00008514003,0.6768757,0.00014646763,0.000019534527,0.0000066952834,0.003374525,0.002835163,0.004425449,0.19521995,0.11609083,0.000198287],"about_ca_topic_score_codex":0.00003322143,"about_ca_topic_score_gemma":0.000005569407,"teacher_disagreement_score":0.8773192,"about_ca_system_score_codex":0.000025919153,"about_ca_system_score_gemma":0.000017292312,"threshold_uncertainty_score":0.99524015},"labels":[],"label_agreement":null},{"id":"W7098460734","doi":"","title":"6.14. PBDES, PCBS, AND DDE IN SNAPPING TURTLE EGGS FROM CANADIAN AREAS OF CONCERN ON THE LOWER GREAT LAKES","year":2015,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Fish <Actinopterygii>; Turtle (robot); Wildlife; Polychlorinated biphenyl; Drainage basin; Range (aeronautics); Fishing","score_opus":0.5477033195028663,"score_gpt":0.44060912670057933,"score_spread":0.10709419280228699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098460734","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":[0.9112896,0.0004665744,0.00024697214,0.001967964,0.00040144825,0.0001064153,0.000019821642,0.000012327513,0.08548892],"genre_scores_gemma":[0.9960951,0.000013436227,0.0019269205,0.00067455886,0.000050941006,0.000002752483,0.0000012754027,0.000004872452,0.0012301115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982646,0.00029248852,0.00035683127,0.00031707805,0.0005310408,0.000237959],"domain_scores_gemma":[0.9831955,0.015899897,0.00012474436,0.00043040808,0.00014410885,0.00020534976],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038177986,0.000102080936,0.00025427985,0.00032897235,0.00006092284,0.000108166816,0.0004767551,0.00006939038,0.00081483275],"category_scores_gemma":[0.043406397,0.000053700685,0.000033959797,0.0009968551,0.000121057084,0.00009082703,0.00007441422,0.00012918985,0.000034369583],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053641914,0.000033988792,0.7985684,0.000001771562,0.000023603567,0.00003282475,0.0017599838,0.000104411614,0.000091430564,0.004100332,0.053986087,0.14124349],"study_design_scores_gemma":[0.0013852267,0.00033081337,0.66610277,0.00014459244,0.00001473238,0.00001163714,0.01624938,0.0037879006,0.00071995275,0.1405931,0.17019953,0.00046040295],"about_ca_topic_score_codex":0.17401855,"about_ca_topic_score_gemma":0.16304782,"teacher_disagreement_score":0.14078309,"about_ca_system_score_codex":0.000045299766,"about_ca_system_score_gemma":0.000139444,"threshold_uncertainty_score":0.9646514},"labels":[],"label_agreement":null},{"id":"W7099231579","doi":"","title":"LSAC RESEARCH REPORT SERIES � Adaptive Testing With Equated Number-Correct Scoring","year":2006,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Government (linguistics); Agency (philosophy); Corporation; Voting; Common law; Legal research; Public law","score_opus":0.7940409670834562,"score_gpt":0.5486190145520123,"score_spread":0.24542195253144383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099231579","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3817394,0.00004965376,0.077145144,0.00017559399,0.00038306185,0.00022154488,0.0000014295472,0.0002607066,0.54002345],"genre_scores_gemma":[0.71008885,0.0000011496429,0.26903686,0.000017556284,0.00019997418,0.000017623235,0.0000013507677,0.000016911958,0.020619702],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937513,0.0008706601,0.00094356376,0.0009726424,0.002691568,0.0007702789],"domain_scores_gemma":[0.928006,0.067638814,0.0005005896,0.0011255961,0.0025748494,0.00015412975],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022937847,0.0001993386,0.00041491538,0.0006556391,0.0006094639,0.000522201,0.0007600184,0.00008903111,0.0005512987],"category_scores_gemma":[0.15487053,0.00012163116,0.000060837763,0.010541735,0.0002948165,0.000559938,0.00031989807,0.0004599355,0.00023630018],"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":[0.00013135344,0.00006902038,0.86357486,0.0000043398663,0.000016529397,0.00085887534,0.00008536449,0.0008287284,0.00094664097,0.0039311014,0.010215398,0.11933777],"study_design_scores_gemma":[0.0011741,0.0014729185,0.6738272,0.0003111149,0.000025431838,0.0057827714,0.012607684,0.012480635,0.01178238,0.2649874,0.014297775,0.0012506385],"about_ca_topic_score_codex":0.0038050087,"about_ca_topic_score_gemma":0.00034625243,"teacher_disagreement_score":0.51940376,"about_ca_system_score_codex":0.000077160075,"about_ca_system_score_gemma":0.00020570027,"threshold_uncertainty_score":0.8522484},"labels":[],"label_agreement":null},{"id":"W7099247932","doi":"","title":"Send Correspondence to:","year":2015,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Comparability; Construct (python library); Confirmatory factor analysis; Exploratory factor analysis; Complement (music); Context (archaeology)","score_opus":0.923610221665222,"score_gpt":0.6216770368815122,"score_spread":0.3019331847837098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099247932","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31366727,0.00006278577,0.2556011,0.0019287512,0.0018955737,0.000085682455,0.0000013533153,0.00009745292,0.42666003],"genre_scores_gemma":[0.6986344,7.7106034e-7,0.21628168,0.0018726224,0.000118453514,0.0000034310058,1.2285449e-7,0.0000044708536,0.083084084],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799645,0.00022429625,0.00027222798,0.00029656908,0.0010284572,0.00018202617],"domain_scores_gemma":[0.9815269,0.017312678,0.000063534644,0.00048990763,0.00030709236,0.0002999004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008835018,0.000056871297,0.00013548262,0.00033498975,0.000038247905,0.00014259285,0.0006848426,0.000028083516,0.0012127949],"category_scores_gemma":[0.29771712,0.00003411084,0.000030417017,0.0026847247,0.000022347936,0.00011664246,0.00019515095,0.000054490196,0.0046622436],"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":[0.000029303243,0.000012267402,0.06778546,1.8829661e-7,0.0000015287612,0.000010343978,0.0002709871,0.00016033955,0.00017918601,0.002561034,0.64606905,0.2829203],"study_design_scores_gemma":[0.00031840964,0.0002295671,0.09876824,0.000004828419,0.0000018746329,0.000040536714,0.0035271167,0.0023750796,0.0007191849,0.12970747,0.7640955,0.000212188],"about_ca_topic_score_codex":0.00004384575,"about_ca_topic_score_gemma":0.0000063795383,"teacher_disagreement_score":0.3849671,"about_ca_system_score_codex":0.000015310734,"about_ca_system_score_gemma":0.000048289032,"threshold_uncertainty_score":0.99970025},"labels":[{"model":"gemma","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W7099755004","doi":"","title":"Parameter Estimation in Item Response Theory.......","year":2011,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Estimation; Process (computing); Corporation; Estimation theory; Work (physics)","score_opus":0.6566548490055042,"score_gpt":0.490133015937672,"score_spread":0.1665218330678322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099755004","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":[0.7024764,0.00003623179,0.24190171,0.000105731975,0.0002575288,0.000091127644,7.3242245e-7,0.00005911346,0.055071425],"genre_scores_gemma":[0.75438595,0.0000014417266,0.2428618,0.00021417541,0.000006963243,0.00000759036,1.6076999e-7,0.0000047776807,0.002517141],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963002,0.0019280743,0.0006009202,0.00038686726,0.0005379306,0.00024600048],"domain_scores_gemma":[0.88893586,0.11008208,0.00017619447,0.0006339786,0.0000975262,0.00007435376],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025485711,0.00009914093,0.00021226602,0.00084280095,0.000049885566,0.000081868915,0.0005797665,0.000073573705,0.002699368],"category_scores_gemma":[0.36104,0.000062128034,0.00006403472,0.0021622668,0.000064999425,0.00027059845,0.00010321101,0.00011739332,0.00041305443],"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":[0.0011783559,0.000094001545,0.2259636,0.0000015179633,0.0000072206053,0.000029933886,0.0018732002,0.00006913456,0.00023018298,0.02978951,0.0018216964,0.7389416],"study_design_scores_gemma":[0.00018328849,0.000068196045,0.54836416,0.000004910042,0.0000014328692,0.0000073411215,0.0006366367,0.00687419,0.00049325504,0.4427552,0.00052672555,0.00008468589],"about_ca_topic_score_codex":0.00004979439,"about_ca_topic_score_gemma":0.0000071755444,"teacher_disagreement_score":0.738857,"about_ca_system_score_codex":0.000024791778,"about_ca_system_score_gemma":0.000026907677,"threshold_uncertainty_score":0.9982123},"labels":[],"label_agreement":null},{"id":"W7100390059","doi":"","title":"CERA 2014: Using HLM to Examine Reading Achievement Using Hierarchy Linear Modeling to Examine Factors Predicting Students&amp;apos; Reading Achievement","year":2014,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Reading (process); Multilevel model; Hierarchy; Class (philosophy); Extensive reading; English language; Identification (biology)","score_opus":0.707461260734264,"score_gpt":0.5334731989359244,"score_spread":0.1739880617983396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100390059","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":[0.52681196,0.00002480404,0.4704257,0.0001976578,0.0010583347,0.00061836146,0.000008478497,0.00017875839,0.0006759424],"genre_scores_gemma":[0.6514637,0.000008396021,0.34610048,0.000657905,0.00063528586,0.00001666846,0.000010096947,0.000081372345,0.0010261063],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98715276,0.0013539136,0.0029214958,0.0023491208,0.0044044377,0.0018182829],"domain_scores_gemma":[0.9822443,0.013038569,0.00082803174,0.001990996,0.0007536221,0.0011444661],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.024260348,0.000853228,0.0013812195,0.0030021868,0.0012897701,0.0011254192,0.0026005493,0.0002473727,0.0003515184],"category_scores_gemma":[0.049286705,0.00066913286,0.00029010748,0.004383421,0.00006549396,0.00079038163,0.002495963,0.0006460919,0.00015240653],"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":[0.00009546493,0.00029698483,0.49277982,0.0000324041,0.00014686231,0.000007881855,0.0033864297,0.39892277,0.06353862,0.00018447136,0.00045878626,0.040149502],"study_design_scores_gemma":[0.0013135965,0.00071485236,0.027608095,0.00050923653,0.00012966113,0.000022642655,0.0056899325,0.95171034,0.0034200603,0.0009173352,0.0064183553,0.001545895],"about_ca_topic_score_codex":0.0020484817,"about_ca_topic_score_gemma":0.00009462857,"teacher_disagreement_score":0.55278754,"about_ca_system_score_codex":0.00067923515,"about_ca_system_score_gemma":0.00008936733,"threshold_uncertainty_score":0.9999115},"labels":[],"label_agreement":null},{"id":"W7100596586","doi":"","title":"66.1 Overview","year":2015,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Data collection; International comparisons; Tracking (education); Survey instrument; Quality (philosophy); Statistics education; Data quality; Survey methodology","score_opus":0.9629429949705253,"score_gpt":0.6341146351319277,"score_spread":0.3288283598385976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100596586","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050408244,0.0020015093,0.0590086,0.002183365,0.00140358,0.00006625096,9.312777e-7,0.00012377379,0.8848038],"genre_scores_gemma":[0.73469645,0.00004518294,0.2267871,0.0025094873,0.0002453955,0.0000042645897,4.3027134e-7,0.000008230547,0.03570346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831915,0.00021750922,0.0002789915,0.00021787087,0.0008251263,0.00014136947],"domain_scores_gemma":[0.9883428,0.010745861,0.0000853546,0.000452324,0.00022159285,0.00015204331],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0085232295,0.000049547692,0.00014485589,0.00017498192,0.000030369363,0.0001145723,0.00051689066,0.0000277706,0.0012226582],"category_scores_gemma":[0.15534143,0.000027417103,0.000045655685,0.0016848681,0.000022958184,0.00012420723,0.0001316932,0.000047793405,0.0013877067],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044647295,0.000015942076,0.054830737,6.828529e-7,0.0000030241245,0.000004601093,0.00008813858,0.000019732037,0.000015589269,0.021122102,0.36643258,0.5574624],"study_design_scores_gemma":[0.00020363364,0.000048659633,0.035934344,0.0000025970796,0.000001533446,0.000011846623,0.0007367955,0.00073067093,0.00006039372,0.36794168,0.59424376,0.00008406014],"about_ca_topic_score_codex":0.00003704434,"about_ca_topic_score_gemma":0.000003391454,"teacher_disagreement_score":0.8491003,"about_ca_system_score_codex":0.0000103848715,"about_ca_system_score_gemma":0.000032170716,"threshold_uncertainty_score":0.99969035},"labels":[],"label_agreement":null},{"id":"W7100609564","doi":"","title":"16Copyright © Canadian Research &amp;amp; Development Center of Sciences and Cultures 17","year":2011,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Test (biology); Construct (python library); Affect (linguistics); Construct validity; Language proficiency; Language assessment; Center (category theory)","score_opus":0.8884788864428674,"score_gpt":0.5808004734848119,"score_spread":0.30767841295805554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100609564","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":[0.5100008,0.00024476022,0.0010309011,0.00027043352,0.00017015354,0.00010716923,0.0000045982333,0.000013611683,0.48815754],"genre_scores_gemma":[0.6596979,0.000025061956,0.3253862,0.00015964326,0.000024972764,0.0000048822753,7.908187e-7,0.0000034757759,0.014697091],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971188,0.00035165224,0.00044021738,0.00043580533,0.001194939,0.0004586175],"domain_scores_gemma":[0.994009,0.0048463526,0.000100146346,0.000287104,0.0004776356,0.00027973295],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014887321,0.00008603478,0.00018896408,0.0011562497,0.0005084925,0.00014602754,0.00088961166,0.000060472124,0.003025682],"category_scores_gemma":[0.023773242,0.000047042908,0.00002787499,0.002405447,0.00056257565,0.000161714,0.00020431932,0.00012707639,0.00020524256],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013246313,0.000049596994,0.6731874,0.0000055870637,0.000013702714,0.0000024998787,0.004953618,8.663688e-7,0.0002724322,0.0055794665,0.25166953,0.06425207],"study_design_scores_gemma":[0.00013644525,0.00003623117,0.3692464,0.000017986165,0.000001126379,0.000011511396,0.0016575827,0.000012192517,0.0012678675,0.029693037,0.59779143,0.00012819156],"about_ca_topic_score_codex":0.03480064,"about_ca_topic_score_gemma":0.12124636,"teacher_disagreement_score":0.47346044,"about_ca_system_score_codex":0.000030523453,"about_ca_system_score_gemma":0.00026643256,"threshold_uncertainty_score":0.9978857},"labels":[],"label_agreement":null},{"id":"W7100966490","doi":"","title":"EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT THOMPSON AND COOK STABILITY OF THE RELIABILITY OF LibQUAL+ ™ SCORES: A RELIABILITY GENERALIZATION META-ANALYSIS STUDY","year":2016,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Generalization; Reliability (semiconductor); Stability (learning theory); Scale (ratio); Reliability theory; Invariant (physics)","score_opus":0.7702951878084472,"score_gpt":0.5073866717896546,"score_spread":0.2629085160187926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100966490","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":[0.9796758,0.00033281554,0.016171962,0.002564263,0.00010584084,0.0006068064,0.00002357479,0.000011659046,0.0005072739],"genre_scores_gemma":[0.99023134,0.000017487924,0.009546447,0.00004419539,0.000012650933,0.000028589546,2.717732e-7,0.0000031648046,0.00011588104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9917067,0.0038261185,0.0014398698,0.0009222602,0.0019421612,0.00016288488],"domain_scores_gemma":[0.97219265,0.023213632,0.00086365256,0.0018003543,0.0018274206,0.0001023161],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03411946,0.00016256401,0.00096476404,0.0002390767,0.00011888919,0.000041601023,0.00054146623,0.00007475419,0.0012943553],"category_scores_gemma":[0.14433442,0.00006043214,0.00041433144,0.002622709,0.0005806409,0.00016206701,0.00028477123,0.00007588535,7.277654e-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":[0.000051049155,0.00075578084,0.99425346,0.000008114797,0.0009420821,2.530317e-8,0.00023752316,0.000036030477,0.0007355579,0.00043374347,0.00013317894,0.0024134435],"study_design_scores_gemma":[0.00027953272,0.00022402906,0.96611327,0.0000019354268,0.003413936,5.250412e-7,0.0004161907,0.00015881701,0.00050318055,0.028780913,0.000027518083,0.00008017118],"about_ca_topic_score_codex":0.00017928045,"about_ca_topic_score_gemma":0.00012208475,"teacher_disagreement_score":0.110214956,"about_ca_system_score_codex":0.000041403815,"about_ca_system_score_gemma":0.00006255265,"threshold_uncertainty_score":0.9996186},"labels":[],"label_agreement":null},{"id":"W7101107143","doi":"","title":"LSAC RESEARCH REPORT SERIES � Evaluating Equating Error in Observed-Score Equating","year":2006,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Equating; Government (linguistics); Agency (philosophy); Corporation; Voting; Public law; Common law","score_opus":0.9515921373360537,"score_gpt":0.6538690167211358,"score_spread":0.2977231206149179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101107143","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":[0.86222243,0.00028703894,0.016003907,0.0008107229,0.0005501695,0.00038766096,0.0000016412428,0.00014801213,0.11958844],"genre_scores_gemma":[0.7652855,0.0000019851952,0.22470385,0.000049328948,0.00029130725,0.00004535393,0.000005348669,0.000022884984,0.009594442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98637563,0.0032450978,0.002865326,0.0013758383,0.0049053463,0.0012327384],"domain_scores_gemma":[0.86202765,0.13196394,0.0014026217,0.0021400524,0.0022582337,0.00020752492],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12088117,0.0002557616,0.000622314,0.0015205012,0.0006785666,0.0007238944,0.0012790471,0.00017355364,0.0010227794],"category_scores_gemma":[0.5230862,0.00018958985,0.00014959252,0.009422479,0.00021280335,0.0008086254,0.0007643854,0.00077253283,0.0001226451],"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":[0.000036810216,0.00008202647,0.780817,0.00001841116,0.000006473225,0.0003114229,0.0004293335,0.003997255,0.0060903844,0.007599984,0.0022393833,0.19837156],"study_design_scores_gemma":[0.00071696873,0.00035415488,0.51832783,0.00019330284,0.000006364006,0.00021987701,0.012219588,0.08284442,0.0016163522,0.38170952,0.0012556893,0.00053593214],"about_ca_topic_score_codex":0.0033739093,"about_ca_topic_score_gemma":0.0013177366,"teacher_disagreement_score":0.40220502,"about_ca_system_score_codex":0.00016218203,"about_ca_system_score_gemma":0.0002666641,"threshold_uncertainty_score":0.99989045},"labels":[],"label_agreement":null},{"id":"W7110779789","doi":"10.1371/journal.pmen.0000431.s001","title":"Comparison of principal components and item loadings across Ontario and Manitoba samples.","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Principal component analysis; Principal (computer security); Component (thermodynamics); Identification (biology); Sample (material)","score_opus":0.6297237702356006,"score_gpt":0.5078864264031873,"score_spread":0.12183734383241329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110779789","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":[0.9434014,0.0065230243,0.000062725885,0.00011242953,0.00054594927,0.00048427223,0.044960923,0.00003412562,0.0038751762],"genre_scores_gemma":[0.99421144,0.00004300814,0.0030678373,0.00014048986,0.000044603028,0.000021700464,0.0015093356,0.000012536651,0.00094905385],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99596196,0.00027902913,0.0013704983,0.0009686082,0.00081590883,0.00060400134],"domain_scores_gemma":[0.9682318,0.02934232,0.0009520684,0.0006662892,0.00056537095,0.00024215067],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014208207,0.00034830548,0.00108625,0.00041716368,0.0005013082,0.0006232786,0.00088984147,0.00027552733,0.027514944],"category_scores_gemma":[0.08011189,0.00030659212,0.00010970258,0.0017815959,0.00012172594,0.00027791038,0.0018817278,0.00050369784,0.00007711207],"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":[0.000073016614,0.00010461157,0.773427,0.00031887263,0.00006173597,0.0000066327807,0.0027533688,0.000006831057,0.00013655463,0.000031901127,0.033284433,0.18979502],"study_design_scores_gemma":[0.00067213725,0.00011058067,0.80825996,0.0021114137,0.000020142208,0.00000841168,0.0022508004,0.0012113348,0.00044082254,0.00053627376,0.18415046,0.00022767532],"about_ca_topic_score_codex":0.003616021,"about_ca_topic_score_gemma":0.007867822,"teacher_disagreement_score":0.18956734,"about_ca_system_score_codex":0.00012844145,"about_ca_system_score_gemma":0.00019419992,"threshold_uncertainty_score":0.9999386},"labels":[],"label_agreement":null},{"id":"W7111049705","doi":"10.1371/journal.pone.0319591.s004","title":"Quality assessment using New Castle - Ottawa Scale for case-control studies.","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Quality assessment; Scale (ratio); Quality (philosophy); Impact assessment; Risk assessment","score_opus":0.8146296236628118,"score_gpt":0.6158871059265558,"score_spread":0.19874251773625595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111049705","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0100470595,0.051418375,0.114112444,0.0035330078,0.010645154,0.0065753567,0.780124,0.00032531997,0.02321927],"genre_scores_gemma":[0.5775883,0.00006890315,0.38585964,0.004544241,0.0027286257,0.0008471541,0.0038062623,0.00013378507,0.024423087],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927973,0.0014370839,0.002187775,0.0015041425,0.001074042,0.0009996564],"domain_scores_gemma":[0.8307274,0.1631599,0.0016514185,0.0018066153,0.0022081323,0.00044652537],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0073615066,0.0005077274,0.0014725166,0.0007557414,0.0011835137,0.00076895853,0.0012025322,0.00033863602,0.07310178],"category_scores_gemma":[0.38017285,0.000426571,0.0006222221,0.0040237224,0.000047957332,0.00043030648,0.000682709,0.00045651794,0.0001990747],"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":[0.000043337972,0.00008483069,0.002487969,0.00040976555,0.00027581208,0.00012883246,0.00024403405,0.0004999024,0.000049396767,0.00006793497,0.7026527,0.29305547],"study_design_scores_gemma":[0.011737575,0.0006926388,0.060380682,0.009774482,0.0007339942,0.0006373877,0.019368095,0.11381157,0.00029401437,0.033576455,0.7466134,0.002379703],"about_ca_topic_score_codex":0.00026549684,"about_ca_topic_score_gemma":0.0001827271,"teacher_disagreement_score":0.7763178,"about_ca_system_score_codex":0.00046361182,"about_ca_system_score_gemma":0.0015541804,"threshold_uncertainty_score":0.9998186},"labels":[],"label_agreement":null},{"id":"W7115033889","doi":"","title":"Modern type error localization in education","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Haskell; Functional programming; Compiler; Context (archaeology); Set (abstract data type); Source code; Type inference; Satisfiability modulo theories; Focus (optics)","score_opus":0.21600670076461734,"score_gpt":0.4233298324420958,"score_spread":0.20732313167747848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115033889","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":[0.66986257,0.0017143822,0.000030598418,0.00004326323,0.010188255,0.000859526,0.00018463224,0.00022356924,0.3168932],"genre_scores_gemma":[0.94328254,0.00036025266,0.005389341,0.00065537926,0.000086973865,0.00012513225,0.0007459711,0.00010347492,0.049250912],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923462,0.0013970385,0.0019542791,0.0017372675,0.0019140568,0.00065114646],"domain_scores_gemma":[0.9887605,0.0068613817,0.0011666107,0.0013630376,0.0016248355,0.00022367785],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0063995523,0.0006151538,0.0009858187,0.0031673962,0.0006920092,0.00028002777,0.00171702,0.0009758101,0.00044919056],"category_scores_gemma":[0.11892104,0.00057465147,0.00027127427,0.008069284,0.000036983092,0.00080201915,0.00019506678,0.0012865377,0.00031666967],"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":[0.00015407118,0.00022232968,0.00081451004,0.00010728946,0.000031958196,0.000008814792,0.000016367063,0.00078065775,0.0010323088,0.021821804,0.00014813028,0.97486174],"study_design_scores_gemma":[0.0008402584,0.00016512176,0.014468798,0.0010598904,0.00011409201,0.000011969758,0.0019822272,0.0041083456,0.00382677,0.79275274,0.17931294,0.0013568447],"about_ca_topic_score_codex":0.0004930216,"about_ca_topic_score_gemma":0.0018436947,"teacher_disagreement_score":0.9735049,"about_ca_system_score_codex":0.0006919723,"about_ca_system_score_gemma":0.00042335805,"threshold_uncertainty_score":0.9996705},"labels":[],"label_agreement":null},{"id":"W7115807625","doi":"","title":"Individual factors","year":2008,"lang":"en","type":"article","venue":"VU Research Portal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Movement Disorders","funders":"","keywords":"","score_opus":0.9138576848911839,"score_gpt":0.6198049403714594,"score_spread":0.2940527445197245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115807625","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":[0.88716143,0.00015577368,0.0003400899,0.00019182156,0.00035661683,0.00011244083,0.000016624972,0.000053161875,0.11161201],"genre_scores_gemma":[0.99174577,0.000030466772,0.0029518872,0.000031718802,0.00016693001,0.0000066054668,0.000004950701,0.000009098181,0.0050525535],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99247795,0.0009020893,0.00048719236,0.00052197586,0.0049243355,0.0006864762],"domain_scores_gemma":[0.9643494,0.03402232,0.00011205543,0.00069786323,0.00052690646,0.0002914711],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017107727,0.000103032435,0.00023622978,0.0012991857,0.00059642666,0.00017459858,0.0014218679,0.000091428075,0.003907827],"category_scores_gemma":[0.21048051,0.000065568136,0.0001070586,0.004562314,0.00043592782,0.00024485053,0.00045758917,0.00053681404,0.0005279178],"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":[0.000008058678,0.000050804,0.8093855,9.917718e-7,0.000012673874,0.00024386236,0.0005711192,0.000004134899,0.00013103252,0.0011837257,0.16555288,0.02285523],"study_design_scores_gemma":[0.00016777495,0.00013973785,0.9397856,0.0000033454492,0.0000010251432,0.00006732058,0.0022123223,0.00004178078,0.0004250131,0.010232791,0.046814963,0.00010831395],"about_ca_topic_score_codex":0.00011838663,"about_ca_topic_score_gemma":0.000009724793,"teacher_disagreement_score":0.19337279,"about_ca_system_score_codex":0.000012377171,"about_ca_system_score_gemma":0.00018797356,"threshold_uncertainty_score":0.9970027},"labels":[],"label_agreement":null},{"id":"W7116213154","doi":"","title":"Creation and validation of the LEVANTE core tasks: Internationalized measures of learning and development for children ages 5-12 years","year":2025,"lang":"","type":"preprint","venue":"PsyArXiv (OSF Preprints)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Set (abstract data type); Reliability (semiconductor); Core (optical fiber); Sample (material); Measure (data warehouse); Cognition; Selection (genetic algorithm)","score_opus":0.2953755882102296,"score_gpt":0.4220356792820552,"score_spread":0.12666009107182563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116213154","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":[0.9006387,0.00033564767,0.09402455,0.0001666445,0.0007728367,0.0017194707,0.00006156061,0.000033677155,0.0022469384],"genre_scores_gemma":[0.9520697,0.0010912287,0.04276565,0.000017111468,0.00004529951,0.00011039045,0.000021197991,0.000020124144,0.003859319],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940706,0.0011700438,0.0018617079,0.0015101976,0.0011183695,0.00026911433],"domain_scores_gemma":[0.9782906,0.017306795,0.0024876099,0.0009164047,0.0009173373,0.000081249054],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.017366428,0.00034963182,0.00087529374,0.0007141945,0.00030493378,0.00018715029,0.0010982944,0.00030409344,0.0007338956],"category_scores_gemma":[0.107315876,0.00028147586,0.00022543412,0.00065258215,0.0004341561,0.00015497915,0.002262209,0.00047644,0.000026954762],"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":[0.00019384047,0.00007871418,0.70748323,0.00020758907,0.00033695245,1.3902388e-7,0.0024572758,0.0020578322,0.0010883551,0.0004573658,0.00012472655,0.28551397],"study_design_scores_gemma":[0.0012873722,0.000017800572,0.96506447,0.0010340057,0.00016664395,0.0000071453483,0.0007019473,0.0027004415,0.01033155,0.014935369,0.0034415731,0.00031169504],"about_ca_topic_score_codex":0.00014234686,"about_ca_topic_score_gemma":0.000012711118,"teacher_disagreement_score":0.28520226,"about_ca_system_score_codex":0.00007802524,"about_ca_system_score_gemma":0.00032533967,"threshold_uncertainty_score":0.99996376},"labels":[],"label_agreement":null},{"id":"W7120158765","doi":"10.1353/jip.00031","title":"Examining the Psychometric Properties of an English Translation of the Shortened Inferiority and Superiority Complex Scales","year":2025,"lang":"en","type":"article","venue":"˜The œjournal of individual psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Adlerian; Facet (psychology); Scale (ratio); Set (abstract data type); Personality; Confirmatory factor analysis; Psychometrics","score_opus":0.5000975150483505,"score_gpt":0.44926253465386123,"score_spread":0.050834980394489304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7120158765","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":[0.99068356,0.002367585,0.0034413263,0.0008257493,0.0013986373,0.00024289824,0.000014911716,0.000007783836,0.0010175706],"genre_scores_gemma":[0.99610925,0.00011855334,0.0032480853,0.00038932366,0.0001143497,0.00000213796,3.8122604e-7,0.0000065227873,0.0000114190325],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941423,0.002668597,0.0015680166,0.00026652036,0.0011117583,0.00024280635],"domain_scores_gemma":[0.9871691,0.009894897,0.0012015075,0.0007962178,0.0008788529,0.00005944046],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01871694,0.00017054907,0.0006141439,0.00084048125,0.00030348438,0.000098740595,0.0023157508,0.0001347888,0.00002782056],"category_scores_gemma":[0.0107986415,0.00007248925,0.00015095194,0.0039452813,0.0010802152,0.00024361449,0.00018642833,0.000531356,2.9257117e-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":[0.00030795785,0.00017947616,0.6258621,0.000019292956,0.00014235356,6.247969e-7,0.005494093,0.00007512305,0.007639938,0.00013170748,0.00038880217,0.35975853],"study_design_scores_gemma":[0.000752993,0.0004044455,0.98709786,0.000047035595,0.00007799967,0.00005956985,0.0048119393,0.00012246854,0.0002779276,0.005224044,0.001048158,0.00007558177],"about_ca_topic_score_codex":0.000025319461,"about_ca_topic_score_gemma":0.000056750883,"teacher_disagreement_score":0.36123574,"about_ca_system_score_codex":0.000010849704,"about_ca_system_score_gemma":0.00008536149,"threshold_uncertainty_score":0.9975338},"labels":[],"label_agreement":null},{"id":"W7125387411","doi":"10.59463/rjas.2025.3.52","title":"COMPARATIVE BEHAVIORAL ASSESSMENT OF LABRADOR RETRIEVER, GERMAN SHEPHERD, AND BEAGLE USING THE C-BARQ STANDARDIZED QUESTIONNAIRE","year":2025,"lang":"","type":"article","venue":"Research Journal of Agricultural Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"German; Beagle; Standardized test; German Shepherd Dog; Psychometrics","score_opus":0.4826594608628143,"score_gpt":0.6195198917305447,"score_spread":0.13686043086773036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125387411","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":[0.9864186,0.005272062,0.0040513943,0.0019339175,0.0011260073,0.00050784985,0.000017294231,0.000005337697,0.00066751684],"genre_scores_gemma":[0.9791274,0.00070783496,0.019734528,0.000018787343,0.00012355893,0.0000019265767,1.7642297e-7,0.000003180424,0.00028259042],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.98524284,0.0036648226,0.0019453709,0.000650707,0.0075616124,0.00093462627],"domain_scores_gemma":[0.97056866,0.015062048,0.0017496732,0.00054557144,0.011597977,0.00047608605],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.06377802,0.0002715703,0.0010154226,0.0013569648,0.002504337,0.0015406694,0.0031480698,0.00012891108,0.00007514583],"category_scores_gemma":[0.031363696,0.00012242481,0.00024762613,0.019461839,0.0056961803,0.0017890867,0.0012283432,0.0016036942,8.764873e-7],"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":[0.0008397706,0.0013729004,0.24178033,0.00019473098,0.0003483855,0.00010644525,0.012305701,0.003041785,0.5385176,0.00942307,0.008356222,0.18371306],"study_design_scores_gemma":[0.0009834572,0.0012244234,0.9638606,0.0011499687,0.00007233944,0.00017830842,0.019173346,0.0023073065,0.007947178,0.0025212876,0.00038485613,0.00019698487],"about_ca_topic_score_codex":0.00032234986,"about_ca_topic_score_gemma":0.000025909461,"teacher_disagreement_score":0.72208023,"about_ca_system_score_codex":0.0007534474,"about_ca_system_score_gemma":0.0032073143,"threshold_uncertainty_score":0.9994958},"labels":[],"label_agreement":null},{"id":"W7126460285","doi":"10.18653/v1/2022.wmt-1.8","title":"Test Set Sampling Affects System Rankings: Expanded Human Evaluation of WMT20 English-Inuktitut Systems","year":2022,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Set (abstract data type); Sampling (signal processing); Test (biology); Data set; Test set","score_opus":0.6765852235668929,"score_gpt":0.5162689098489014,"score_spread":0.1603163137179915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126460285","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":[0.9223695,0.0008882277,0.014616546,0.000023943145,0.003865074,0.0010787138,0.0000446767,0.00028469012,0.05682866],"genre_scores_gemma":[0.9968523,0.000001048796,0.0023710201,0.0000195353,0.00020524456,0.00015572178,0.000010462111,0.000015039993,0.0003696419],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9904903,0.0026793187,0.0011116805,0.00068527675,0.0046822242,0.00035120538],"domain_scores_gemma":[0.96139735,0.03514149,0.0010749442,0.0009896714,0.0012952484,0.0001012811],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05598568,0.00018662357,0.0006133663,0.0009417773,0.00068374624,0.00026014884,0.0010765204,0.00006782817,0.0005595408],"category_scores_gemma":[0.10722324,0.00014101465,0.00015405894,0.0032346207,0.000054084187,0.00022499135,0.00042387095,0.00023073143,0.000012438971],"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":[0.00019508376,0.00083628827,0.486095,0.00094806636,0.00033942182,0.000041892872,0.01629245,0.23102833,0.04103941,0.053418867,0.042908367,0.12685682],"study_design_scores_gemma":[0.01386065,0.0027803953,0.11734839,0.0007515063,0.0007067552,0.00035059208,0.31869477,0.4971745,0.0052143317,0.0174744,0.02311965,0.0025240402],"about_ca_topic_score_codex":0.00021217215,"about_ca_topic_score_gemma":0.000007867199,"teacher_disagreement_score":0.36874664,"about_ca_system_score_codex":0.00030036975,"about_ca_system_score_gemma":0.00013130186,"threshold_uncertainty_score":0.9720614},"labels":[],"label_agreement":null},{"id":"W7132902964","doi":"","title":"IRT parameter estimation: can the jackknife improve accuracy?","year":2004,"lang":"","type":"dissertation","venue":"TSpace","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadians Living with HIV; Bibliographical Society of Canada","funders":"","keywords":"Jackknife resampling; Item response theory; Curse of dimensionality; Differential item functioning; Estimation theory; Sampling (signal processing); Sample (material); Sample size determination","score_opus":0.2948268767087249,"score_gpt":0.5090436512276972,"score_spread":0.2142167745189723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132902964","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":[0.7314602,0.00881958,0.12893285,0.022947626,0.03506844,0.005182976,0.00011880038,0.00047153316,0.06699797],"genre_scores_gemma":[0.81053114,0.00070158666,0.11759769,0.0016393054,0.0010941906,0.00027914316,0.00017048276,0.00015090751,0.06783556],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99027497,0.0012703651,0.0020902008,0.0019634545,0.003198448,0.0012025768],"domain_scores_gemma":[0.8954535,0.09727907,0.0030419305,0.002732607,0.0011072409,0.00038563806],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009230564,0.0009876468,0.0012950484,0.00086131593,0.0014431966,0.0019071096,0.0035838627,0.00081396074,0.0030977007],"category_scores_gemma":[0.32189474,0.00061627646,0.0006887326,0.0055033197,0.00041786273,0.00040970827,0.00032557896,0.001650482,0.0009095893],"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":[0.00023400603,0.00015480365,0.0007461398,0.00014144323,0.00019408258,0.000042063664,0.026168125,0.004043576,0.0005014655,0.0017692499,0.005065531,0.9609395],"study_design_scores_gemma":[0.0060064103,0.0025982326,0.118467525,0.0023401082,0.0015185833,0.00033017097,0.32237172,0.09984547,0.012411972,0.36087132,0.06627639,0.0069620977],"about_ca_topic_score_codex":0.0022468488,"about_ca_topic_score_gemma":0.00024963557,"teacher_disagreement_score":0.9539774,"about_ca_system_score_codex":0.00030781538,"about_ca_system_score_gemma":0.0013938565,"threshold_uncertainty_score":0.99986833},"labels":[],"label_agreement":null},{"id":"W7132987028","doi":"","title":"Test Validation and Complex, Dynamic Systems: The Case of the Pedagogical Content Knowledge for Supporting English Learners Test (PeCKSELT)","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Test (biology); Thematic analysis; Interpretation (philosophy); Item response theory; Test validity; Variety (cybernetics)","score_opus":0.6593913137566458,"score_gpt":0.5615762568738744,"score_spread":0.09781505688277148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132987028","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":[0.98218334,0.0020099329,0.0024224387,0.00066393893,0.006570548,0.00330983,0.00017985895,0.00012166358,0.0025384799],"genre_scores_gemma":[0.9709359,0.0001951036,0.00080653053,0.000020486968,0.0002681128,0.00018407237,0.00008737812,0.000067355664,0.02743505],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9930873,0.0015287886,0.0023878599,0.0012583123,0.0009550906,0.00078267686],"domain_scores_gemma":[0.76688623,0.22497167,0.004050802,0.0012588393,0.002626639,0.00020582319],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.017265989,0.0006008199,0.0012337341,0.0005284145,0.0015630854,0.00074733724,0.0014121445,0.0004449971,0.00009060526],"category_scores_gemma":[0.4701907,0.00033204546,0.0004725112,0.0035171825,0.0005321378,0.00016008207,0.0003979616,0.0007497986,0.000017036939],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005570049,0.0013869129,0.11306971,0.005405774,0.0006547728,0.00020876089,0.5322995,0.0023920622,0.013158751,0.00425467,0.015047097,0.31156498],"study_design_scores_gemma":[0.0009340195,0.0005023218,0.025284545,0.0005982049,0.00031852545,0.00022843336,0.8832712,0.08579254,0.00016973911,0.00043551743,0.0019873958,0.0004775114],"about_ca_topic_score_codex":0.0010416177,"about_ca_topic_score_gemma":0.0006169307,"teacher_disagreement_score":0.45292473,"about_ca_system_score_codex":0.00013262093,"about_ca_system_score_gemma":0.00037627204,"threshold_uncertainty_score":0.99991316},"labels":[],"label_agreement":null},{"id":"W7133053492","doi":"","title":"Examining group differences in omission rates in a mathematics assessment","year":2005,"lang":"","type":"dissertation","venue":"TSpace","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reliability (semiconductor); Demographics; Relation (database); Group (periodic table); Psychometrics","score_opus":0.5414990327988992,"score_gpt":0.5495456717362989,"score_spread":0.008046638937399653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133053492","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":[0.9524335,0.0019662431,0.003951585,0.00022065754,0.0015236766,0.000761159,0.000002825074,0.00004542932,0.039094906],"genre_scores_gemma":[0.88265955,0.0012730293,0.10756925,0.000032160864,0.00014454922,0.00008829192,0.00002660463,0.00004442974,0.008162123],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99056756,0.0016736175,0.0028094093,0.0016477066,0.0022751687,0.0010265252],"domain_scores_gemma":[0.94626355,0.050403446,0.0019920901,0.00090614165,0.00020313538,0.0002316118],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014682529,0.00079475576,0.0019753336,0.003381507,0.00023908573,0.0006661692,0.001677331,0.0007358066,0.001865807],"category_scores_gemma":[0.05341484,0.00062234467,0.00017863775,0.006504458,0.0001084886,0.00039111718,0.00027091673,0.0014194924,0.00006812483],"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":[0.00010994139,0.0009343773,0.6782515,0.00028022847,0.000029203904,0.00007701747,0.039871715,0.00016408224,0.0024191237,0.0008489843,0.00013506469,0.27687874],"study_design_scores_gemma":[0.0009474245,0.00025750903,0.73983943,0.0020525265,0.000020782723,0.000005990939,0.22055784,0.028944172,0.00010702406,0.0065294197,0.00012759127,0.00061029044],"about_ca_topic_score_codex":0.00060835475,"about_ca_topic_score_gemma":0.0012202761,"teacher_disagreement_score":0.27626845,"about_ca_system_score_codex":0.00034096127,"about_ca_system_score_gemma":0.00033900072,"threshold_uncertainty_score":0.99962276},"labels":[],"label_agreement":null},{"id":"W7133087936","doi":"","title":"Individual factors","year":2008,"lang":"en","type":"article","venue":"Pure Amsterdam UMC","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pediatric Oncology Group","funders":"","keywords":"","score_opus":0.5852990207753377,"score_gpt":0.4508653784334021,"score_spread":0.1344336423419356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133087936","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":[0.9616823,0.00032170909,0.0040127197,0.00029438297,0.00096903363,0.00009972145,0.00001558527,0.00011480466,0.032489695],"genre_scores_gemma":[0.9909508,0.000015314496,0.0053497073,0.00030139912,0.00018372724,0.000004541279,0.0000038457347,0.000011028441,0.00317961],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968651,0.00030760295,0.0005281338,0.00049023743,0.0014320784,0.00037687467],"domain_scores_gemma":[0.9864713,0.01233571,0.00024029506,0.00065578445,0.00013810646,0.00015879587],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024554455,0.0001608746,0.0003231026,0.00045987542,0.00031783115,0.00014333783,0.0011493914,0.00010003962,0.00080799626],"category_scores_gemma":[0.037467804,0.000103301194,0.00014484162,0.0018820594,0.00013829218,0.00025912304,0.00027261747,0.00020542523,0.00038636365],"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":[0.0000063286534,0.00003236437,0.86150795,0.0000014067236,0.000014118255,0.000027125703,0.00080579,0.000019196626,0.00004593743,0.00017669989,0.041510418,0.09585266],"study_design_scores_gemma":[0.00022150493,0.00008070368,0.94626856,0.0000036610788,0.000006482517,0.000063557156,0.00055327144,0.000046888148,0.00019473565,0.009282067,0.04310855,0.00017004403],"about_ca_topic_score_codex":0.000018313021,"about_ca_topic_score_gemma":0.0000035069606,"teacher_disagreement_score":0.09568261,"about_ca_system_score_codex":0.000015554844,"about_ca_system_score_gemma":0.000039452974,"threshold_uncertainty_score":0.97064},"labels":[],"label_agreement":null},{"id":"W7133188988","doi":"10.2310/derm.1.2004.2000","title":"Self-Assessment","year":2004,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.2631226708143088,"score_gpt":0.459013350376797,"score_spread":0.19589067956248823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133188988","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":[0.36264253,0.00030615978,0.36403474,0.012726905,0.0016803275,0.0002102704,0.00000946511,0.00037089238,0.2580187],"genre_scores_gemma":[0.7053549,0.000024421981,0.2927654,0.0016989673,0.000053051288,0.0000059628856,6.800345e-7,0.000003882426,0.0000927205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982892,0.0001425414,0.00037900673,0.00022952312,0.00076680863,0.00019286617],"domain_scores_gemma":[0.9952355,0.004034238,0.00013949953,0.00040248793,0.00010995306,0.000078321435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018352681,0.000074146614,0.00016408556,0.00023771412,0.00012868649,0.00019550683,0.00047075996,0.00003791223,0.00034982894],"category_scores_gemma":[0.0059393463,0.000053163636,0.00006373563,0.001185129,0.000021964253,0.00019646206,0.00009023461,0.00009061801,0.00048040654],"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":[9.917359e-7,0.0002162653,0.27806926,0.000019518084,0.000046623543,0.00016247176,0.0014808237,0.0007462832,0.00009332333,0.08533864,0.09742337,0.5364024],"study_design_scores_gemma":[0.00036251312,0.00002874523,0.68248993,0.000007154354,0.0000032389978,0.000059243615,0.00023073863,0.00038675952,0.0001707143,0.18731116,0.12884943,0.00010034669],"about_ca_topic_score_codex":0.000031970863,"about_ca_topic_score_gemma":0.0000057195552,"teacher_disagreement_score":0.5363021,"about_ca_system_score_codex":0.0000653473,"about_ca_system_score_gemma":0.000069021786,"threshold_uncertainty_score":0.7110381},"labels":[],"label_agreement":null},{"id":"W7133198034","doi":"10.2310/derm.1.2004.2014","title":"Self-Assessment","year":2004,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.2631226708143088,"score_gpt":0.459013350376797,"score_spread":0.19589067956248823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133198034","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":[0.36264253,0.00030615978,0.36403474,0.012726905,0.0016803275,0.0002102704,0.00000946511,0.00037089238,0.2580187],"genre_scores_gemma":[0.7053549,0.000024421981,0.2927654,0.0016989673,0.000053051288,0.0000059628856,6.800345e-7,0.000003882426,0.0000927205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982892,0.0001425414,0.00037900673,0.00022952312,0.00076680863,0.00019286617],"domain_scores_gemma":[0.9952355,0.004034238,0.00013949953,0.00040248793,0.00010995306,0.000078321435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018352681,0.000074146614,0.00016408556,0.00023771412,0.00012868649,0.00019550683,0.00047075996,0.00003791223,0.00034982894],"category_scores_gemma":[0.0059393463,0.000053163636,0.00006373563,0.001185129,0.000021964253,0.00019646206,0.00009023461,0.00009061801,0.00048040654],"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":[9.917359e-7,0.0002162653,0.27806926,0.000019518084,0.000046623543,0.00016247176,0.0014808237,0.0007462832,0.00009332333,0.08533864,0.09742337,0.5364024],"study_design_scores_gemma":[0.00036251312,0.00002874523,0.68248993,0.000007154354,0.0000032389978,0.000059243615,0.00023073863,0.00038675952,0.0001707143,0.18731116,0.12884943,0.00010034669],"about_ca_topic_score_codex":0.000031970863,"about_ca_topic_score_gemma":0.0000057195552,"teacher_disagreement_score":0.5363021,"about_ca_system_score_codex":0.0000653473,"about_ca_system_score_gemma":0.000069021786,"threshold_uncertainty_score":0.7110381},"labels":[],"label_agreement":null},{"id":"W7133221914","doi":"10.2310/derm.1.2004.2028","title":"Self-Assessment","year":2004,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.2631226708143088,"score_gpt":0.459013350376797,"score_spread":0.19589067956248823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133221914","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":[0.36264253,0.00030615978,0.36403474,0.012726905,0.0016803275,0.0002102704,0.00000946511,0.00037089238,0.2580187],"genre_scores_gemma":[0.7053549,0.000024421981,0.2927654,0.0016989673,0.000053051288,0.0000059628856,6.800345e-7,0.000003882426,0.0000927205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982892,0.0001425414,0.00037900673,0.00022952312,0.00076680863,0.00019286617],"domain_scores_gemma":[0.9952355,0.004034238,0.00013949953,0.00040248793,0.00010995306,0.000078321435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018352681,0.000074146614,0.00016408556,0.00023771412,0.00012868649,0.00019550683,0.00047075996,0.00003791223,0.00034982894],"category_scores_gemma":[0.0059393463,0.000053163636,0.00006373563,0.001185129,0.000021964253,0.00019646206,0.00009023461,0.00009061801,0.00048040654],"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":[9.917359e-7,0.0002162653,0.27806926,0.000019518084,0.000046623543,0.00016247176,0.0014808237,0.0007462832,0.00009332333,0.08533864,0.09742337,0.5364024],"study_design_scores_gemma":[0.00036251312,0.00002874523,0.68248993,0.000007154354,0.0000032389978,0.000059243615,0.00023073863,0.00038675952,0.0001707143,0.18731116,0.12884943,0.00010034669],"about_ca_topic_score_codex":0.000031970863,"about_ca_topic_score_gemma":0.0000057195552,"teacher_disagreement_score":0.5363021,"about_ca_system_score_codex":0.0000653473,"about_ca_system_score_gemma":0.000069021786,"threshold_uncertainty_score":0.7110381},"labels":[],"label_agreement":null},{"id":"W7133253692","doi":"10.2310/derm.1.2005.2116","title":"Self-Assessment","year":2005,"lang":"en","type":"article","venue":"Dermatitis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.2643819910732367,"score_gpt":0.4650700633162458,"score_spread":0.2006880722430091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133253692","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25252798,0.00056659675,0.15457904,0.024906505,0.0012393056,0.00021702913,0.000010968722,0.0004264164,0.5655262],"genre_scores_gemma":[0.6462914,0.000030074116,0.35041234,0.0026751128,0.00013883266,0.000005815103,6.210713e-7,0.000003806457,0.0004420411],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981848,0.00022528463,0.00041539432,0.0002242593,0.00075395516,0.00019630369],"domain_scores_gemma":[0.99239993,0.0068623447,0.00014515863,0.00040646485,0.000108282926,0.00007781727],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002267097,0.00007331788,0.00016261965,0.00023958307,0.00011848282,0.00019668089,0.00048412138,0.000037037764,0.0012306295],"category_scores_gemma":[0.005307587,0.00005269055,0.00006206395,0.00095250783,0.00001777023,0.00025782222,0.00009335802,0.00009023031,0.0008829108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7639904e-7,0.000035151763,0.08572191,0.0000023757364,0.000007961226,0.0000071053764,0.0002177607,0.0000476945,0.000012007181,0.0038454295,0.1938609,0.71624154],"study_design_scores_gemma":[0.000121231096,0.000010466204,0.40636688,0.0000022934194,0.0000020458979,0.000025446121,0.00009486122,0.00663043,0.00007153742,0.0077008503,0.5789098,0.000064157546],"about_ca_topic_score_codex":0.000007775549,"about_ca_topic_score_gemma":0.0000064316355,"teacher_disagreement_score":0.71617734,"about_ca_system_score_codex":0.000046647077,"about_ca_system_score_gemma":0.00003455648,"threshold_uncertainty_score":0.99989504},"labels":[],"label_agreement":null},{"id":"W7133447372","doi":"","title":"Optimal testing situations for the automated analysis of cognitive components in natural language : a systematic literature review.","year":2025,"lang":"en","type":"preprint","venue":"ORBi UMONS","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Cognition; Natural language; Component (thermodynamics); Systematic review","score_opus":0.30932643831224904,"score_gpt":0.48529538350686263,"score_spread":0.1759689451946136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133447372","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":[0.3266215,0.55177593,0.09002365,0.0032568225,0.003813672,0.014413516,0.0060253,0.00071562873,0.003353967],"genre_scores_gemma":[0.9467613,0.002091687,0.049177445,0.0002647896,0.00004567092,0.00065039494,0.00037875195,0.000013773454,0.0006161929],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955506,0.0012566929,0.0015483517,0.0006131092,0.00077505107,0.0002562271],"domain_scores_gemma":[0.8327456,0.16367121,0.0014623244,0.0008981025,0.0011810391,0.0000417102],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008623844,0.00025335688,0.0015479674,0.0019997025,0.00015298596,0.00021592322,0.0012145188,0.00016161171,0.000015650905],"category_scores_gemma":[0.37603635,0.00014627069,0.00054713286,0.012886698,0.00006997264,0.000065321394,0.0006373876,0.0005740628,0.0000022397119],"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":[0.00045067398,0.00209714,0.12637413,0.3483494,0.031855643,0.00039924562,0.0709633,0.23635927,0.0019798698,0.0010612315,0.033479806,0.14663032],"study_design_scores_gemma":[0.00022956781,0.000018819237,0.066642426,0.09946434,0.002919903,0.0000048732754,0.0020919614,0.8281705,0.000009349585,0.00024934806,0.0000058205405,0.00019313097],"about_ca_topic_score_codex":0.000114212744,"about_ca_topic_score_gemma":0.00008158526,"teacher_disagreement_score":0.6201398,"about_ca_system_score_codex":0.000055205972,"about_ca_system_score_gemma":0.00012078884,"threshold_uncertainty_score":0.6292196},"labels":[],"label_agreement":null},{"id":"W7134100976","doi":"","title":"Individual factors","year":2013,"lang":"en","type":"article","venue":"Pure Amsterdam UMC","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pediatric Oncology Group","funders":"","keywords":"","score_opus":0.43659310840151466,"score_gpt":0.4379181088045906,"score_spread":0.0013250004030759266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134100976","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":[0.9553616,0.0002129344,0.0035012593,0.0007525322,0.0009961596,0.00020051254,0.0000095455525,0.00011162373,0.038853813],"genre_scores_gemma":[0.9901175,0.0000037294885,0.005984522,0.00042483382,0.00016042324,0.000016162221,0.00000344688,0.000011152494,0.0032782687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99707663,0.0003060141,0.0005315446,0.0004726333,0.0012129453,0.00040025054],"domain_scores_gemma":[0.9851359,0.01354174,0.0002490868,0.0006908776,0.00020069239,0.00018170604],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024001081,0.00016069034,0.00029627015,0.0004221566,0.00016383316,0.0006066167,0.001233536,0.00010100124,0.003924195],"category_scores_gemma":[0.035911873,0.000098045784,0.00012466057,0.001569904,0.00008040655,0.00044502996,0.00031669773,0.00019327519,0.0017743241],"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":[0.0000016809506,0.000023986417,0.5406492,0.0000018543627,0.0000136880035,0.000002163636,0.0003528757,0.000009756023,0.00010974261,0.0002566307,0.0704261,0.38815233],"study_design_scores_gemma":[0.00016236708,0.00006653289,0.9295833,0.0000044590406,0.0000065777313,0.0000069569237,0.0010968113,0.00011347741,0.00015105984,0.045297988,0.023346877,0.00016360369],"about_ca_topic_score_codex":0.00006862246,"about_ca_topic_score_gemma":0.000004211506,"teacher_disagreement_score":0.38893408,"about_ca_system_score_codex":0.00001415427,"about_ca_system_score_gemma":0.00002112251,"threshold_uncertainty_score":0.99900293},"labels":[],"label_agreement":null},{"id":"W7161949349","doi":"10.82308/31018","title":"A quantitative social systems approach to mentalizing among bilingual adults","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Mentalization; Social relation; Social relationship; Social environment","score_opus":0.5042222347103535,"score_gpt":0.5199148070236046,"score_spread":0.015692572313251052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161949349","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":[0.70116293,0.00078715355,0.0092577655,0.000019255185,0.0038474482,0.00059899053,0.000028092209,0.00010171926,0.28419665],"genre_scores_gemma":[0.8119386,0.000020273043,0.10888866,0.00011913158,0.0007344993,0.0001764981,0.0006014819,0.00008664323,0.07743421],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9936459,0.00097469374,0.0013111554,0.0013593204,0.0022532318,0.000455705],"domain_scores_gemma":[0.9859913,0.01152273,0.0008232247,0.0004780926,0.0010147542,0.00016991804],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005878635,0.000364253,0.000996721,0.0011626189,0.00039287115,0.00088899233,0.001007969,0.00037787695,0.00014977965],"category_scores_gemma":[0.06929092,0.00026846904,0.0003054243,0.0043788943,0.00004134774,0.00017266738,0.00013699706,0.00037520693,0.00007805055],"study_design_candidate":"qualitative","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":[0.0023989116,0.001744693,0.03783035,0.0018251374,0.0014547568,0.00020174928,0.2906691,0.0017816783,0.0028325948,0.11649419,0.14359377,0.39917305],"study_design_scores_gemma":[0.0005040339,0.00020129548,0.03643342,0.0003909683,0.000056114506,0.000008582571,0.9523124,0.0059887837,0.0002609947,0.0011622049,0.0018308475,0.0008503381],"about_ca_topic_score_codex":0.0011063158,"about_ca_topic_score_gemma":0.00034584902,"teacher_disagreement_score":0.66164327,"about_ca_system_score_codex":0.00009147606,"about_ca_system_score_gemma":0.00022892896,"threshold_uncertainty_score":0.99997675},"labels":[],"label_agreement":null},{"id":"W7162019789","doi":"10.82308/834","title":"Bayesian construct validation leveraging expert knowledge for questionnaire instruments used in primary care research and practice","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Construct (python library); Bayesian probability; Inference; Domain (mathematical analysis); Subject-matter expert; Bayesian inference; Process (computing); Bayesian network","score_opus":0.5363131275926621,"score_gpt":0.5747210984084848,"score_spread":0.0384079708158227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162019789","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":[0.72912467,0.02007711,0.010336291,0.00086744525,0.007713153,0.0028944842,0.000035889527,0.00022767796,0.22872329],"genre_scores_gemma":[0.9364627,0.00033075712,0.054485787,0.000059662936,0.00024126646,0.00025524624,0.00034350625,0.000053607204,0.007767468],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99470085,0.0013996351,0.0009674346,0.0011629044,0.0013495235,0.0004196584],"domain_scores_gemma":[0.9607738,0.036755178,0.00031271408,0.00045236872,0.0015966092,0.000109316854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0131016,0.00026446875,0.00050719146,0.0026118588,0.00031779706,0.0009425877,0.0005229184,0.00035731177,0.000041590523],"category_scores_gemma":[0.10114623,0.00021134397,0.00008215093,0.0029664286,0.00009466523,0.0006202081,0.0001443546,0.00061056466,0.000022847145],"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":[0.00026253288,0.00006386837,0.015984975,0.0006147077,0.00003591831,0.000010163799,0.020986207,0.0000033137478,0.00038097837,0.0016582696,0.0028776017,0.9571215],"study_design_scores_gemma":[0.00397943,0.0009077475,0.113944165,0.0071946685,0.00010726919,0.00013509307,0.6385959,0.003913026,0.0041587865,0.18433473,0.04085,0.0018792084],"about_ca_topic_score_codex":0.00027327042,"about_ca_topic_score_gemma":0.00024747715,"teacher_disagreement_score":0.9552423,"about_ca_system_score_codex":0.0003961171,"about_ca_system_score_gemma":0.0006234552,"threshold_uncertainty_score":0.9089395},"labels":[],"label_agreement":null},{"id":"W7165194727","doi":"10.2196/83563","title":"Measurement Properties of the European Portuguese Michigan Hand Outcomes Questionnaire (MHQ) in Paper and Electronic Formats: An Instrument Validation Study (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Rehabilitation and Assistive Technologies","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Portuguese; European Portuguese; European union; Measure (data warehouse); Data collection","score_opus":0.14466295524795564,"score_gpt":0.37783401254336824,"score_spread":0.2331710572954126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7165194727","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":[0.9944176,0.00068646023,0.0004832359,0.0028439397,0.000076468576,0.001150313,0.0000012308035,0.000112243055,0.00022848658],"genre_scores_gemma":[0.99912596,0.000023587783,0.0006516379,0.000027692207,0.0000020913242,0.00014284224,2.1009653e-7,0.0000045052893,0.000021467467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970688,0.0010712917,0.00069959596,0.00045034362,0.000538203,0.00017175816],"domain_scores_gemma":[0.99800885,0.0008197769,0.00030314428,0.0005245492,0.000326603,0.000017086555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0071481154,0.00014738108,0.00028806514,0.00054914807,0.0001923949,0.00011803542,0.00037787374,0.00005833299,0.0000013521984],"category_scores_gemma":[0.043053534,0.00008186976,0.00004451966,0.0010987138,0.0004476898,0.0003530656,0.00034069456,0.00018540981,5.329114e-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":[0.000022992515,0.00017612339,0.7163921,0.000025540305,0.0000127690855,1.4743674e-7,0.0012149697,0.000007870496,0.001888762,0.0011799753,0.0000059044505,0.27907285],"study_design_scores_gemma":[0.00049809966,0.00033690227,0.9377965,0.0002149504,0.000007982316,6.1034666e-7,0.04102215,0.000050262628,0.0013760973,0.018559055,0.000053585005,0.00008382934],"about_ca_topic_score_codex":0.000054059226,"about_ca_topic_score_gemma":0.00028684663,"teacher_disagreement_score":0.27898902,"about_ca_system_score_codex":0.000078693905,"about_ca_system_score_gemma":0.000055970984,"threshold_uncertainty_score":0.96500725},"labels":[],"label_agreement":null},{"id":"W72030968","doi":"","title":"Differential Item Functioning: The Consequence of Language, Curriculum, or Culture?","year":2010,"lang":"en","type":"book-chapter","venue":"eScholarship (California Digital Library)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"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":"Hong Kong Institute of Education","keywords":"Differential item functioning; Equivalence (formal languages); Multinomial logistic regression; Psychology; Curriculum; Item bank; Item response theory; Mainland China; Differential (mechanical device); Social psychology; Statistics; Geography; Mathematics; Developmental psychology; Psychometrics; Pedagogy; China","score_opus":0.1306020648954044,"score_gpt":0.3381048616861991,"score_spread":0.20750279679079467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W72030968","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07148144,0.0016577783,0.0021889568,0.00074031745,0.0026754804,0.00089758344,0.0058861603,0.0005065439,0.91396576],"genre_scores_gemma":[0.2865643,0.00011637933,0.0048937774,0.00056848425,0.0011123838,0.000024648985,0.0004498235,0.00018267496,0.7060875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946674,0.00021447618,0.0015833697,0.0010355416,0.001992158,0.00050704903],"domain_scores_gemma":[0.9824175,0.013955083,0.0015018252,0.0015336097,0.00028636577,0.00030558472],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012064935,0.0006434179,0.00096546,0.0005743386,0.00034088746,0.0025649783,0.0027369075,0.0007309363,0.011842802],"category_scores_gemma":[0.04645939,0.0003242709,0.00063355523,0.00082255155,0.0007160478,0.001529262,0.00090302207,0.0020713853,0.0016685651],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015859703,0.00076484407,0.14124036,0.0004278647,0.0011786247,0.0017755213,0.000666908,0.000012445584,0.0034520829,0.12995233,0.1329479,0.58599514],"study_design_scores_gemma":[0.00042094025,0.0001939544,0.0015070322,0.00025201406,0.000072276256,0.00023302602,0.00021590019,0.000027337403,0.001021776,0.1326293,0.8627343,0.00069210987],"about_ca_topic_score_codex":0.000004979532,"about_ca_topic_score_gemma":0.0000032591925,"teacher_disagreement_score":0.7297864,"about_ca_system_score_codex":0.000022854765,"about_ca_system_score_gemma":0.00023455892,"threshold_uncertainty_score":0.99992096},"labels":[],"label_agreement":null},{"id":"W752406994","doi":"","title":"Assessment of a Master of Education Counselling Application Selection Process Using Rasch Analysis and Generalizability Theory/évaluation D'un Processus De Sélection De Candidats Pour Un Programme De Maîtrise En éDucation En Counseling En Utilisant L'analyse Rasch et la Théorie De la Généralisabilité","year":2014,"lang":"fr","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Psychology; Valuation (finance); Selection (genetic algorithm); Medical education; Interpersonal communication; Process (computing); Quality (philosophy); Social psychology; Medicine; Computer science; Business","score_opus":0.08809648160733467,"score_gpt":0.4449385157504484,"score_spread":0.3568420341431137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W752406994","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":[0.49889717,0.0033538477,0.49709454,0.0002787591,0.000119065124,0.00021182552,0.0000076162,0.000005685505,0.000031499756],"genre_scores_gemma":[0.9067234,0.019271255,0.07352921,0.00012014449,0.0002609078,0.000024838271,0.000007088576,0.00003067895,0.000032464606],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98813057,0.008876401,0.0013168426,0.00049902487,0.0006526796,0.00052449293],"domain_scores_gemma":[0.9841652,0.011635465,0.0017392695,0.00030102258,0.0016741338,0.00048489042],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.06304754,0.00029425512,0.0006733446,0.0013255614,0.00032818448,0.000382114,0.00033020947,0.0004074384,0.00006047535],"category_scores_gemma":[0.0013944969,0.0002837062,0.00019281455,0.0027031156,0.00024078958,0.0003741283,9.4946904e-7,0.00052955246,1.7511408e-7],"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":[0.00027247446,0.00034727494,0.4514891,0.00037130038,0.00064195384,0.0000011825705,0.06641053,0.09037047,0.01256206,0.0020165625,0.000017616398,0.3754995],"study_design_scores_gemma":[0.0009762198,0.00027976354,0.028816883,0.00033228818,0.0011064005,0.0002802727,0.0040609958,0.45704794,0.0031203,0.50297505,0.0006985421,0.0003053556],"about_ca_topic_score_codex":0.002819464,"about_ca_topic_score_gemma":0.0015581676,"teacher_disagreement_score":0.50095844,"about_ca_system_score_codex":0.00044300244,"about_ca_system_score_gemma":0.0049817148,"threshold_uncertainty_score":0.9999615},"labels":[],"label_agreement":null},{"id":"W78882529","doi":"10.55016/ojs/ajer.v55i4.55343","title":"Robustness of Lord’s Formulas for Item Difficulty and Discrimination Conversions Between Classical and Item Response Theory Models","year":2010,"lang":"en","type":"article","venue":"Alberta Journal of Educational 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":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Robustness (evolution); Item response theory; Statistics; Psychology; Range (aeronautics); Econometrics; Computer science; Mathematics; Psychometrics; Engineering","score_opus":0.5762851965354135,"score_gpt":0.549076653154242,"score_spread":0.027208543381171513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W78882529","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":[0.98223597,0.00015534958,0.0056823078,0.010512293,0.00032226017,0.00017742006,0.000014538655,4.424326e-7,0.0008994411],"genre_scores_gemma":[0.9880298,0.000033305303,0.0072090565,0.000013754744,0.00025778875,0.000007451124,0.0000029352566,0.000007613821,0.004438327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99667174,0.0009979557,0.00070617755,0.00024737796,0.0011281496,0.00024862864],"domain_scores_gemma":[0.5221022,0.47576326,0.00030807857,0.00017086508,0.0014702646,0.00018535019],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01753926,0.000091397145,0.000301259,0.0009177646,0.00028905424,0.00012641112,0.00050896424,0.00010703278,0.00030904752],"category_scores_gemma":[0.5444324,0.000059405276,0.000088577974,0.0007739673,0.00044022212,0.00049133145,0.0001502149,0.0004478019,0.0000014030105],"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":[0.0064590275,0.0009383971,0.46178025,0.00017121836,0.0002467993,0.0000011157706,0.006995497,0.0007411487,0.01565275,0.36919913,0.02997805,0.10783662],"study_design_scores_gemma":[0.0011509096,0.0005938016,0.81894076,0.00009814307,0.00004594782,0.000080330254,0.0051415246,0.018287204,0.0004521246,0.15244009,0.0026147023,0.00015448841],"about_ca_topic_score_codex":0.000022736014,"about_ca_topic_score_gemma":0.000043385306,"teacher_disagreement_score":0.52689314,"about_ca_system_score_codex":0.0000325109,"about_ca_system_score_gemma":0.0004425931,"threshold_uncertainty_score":0.6078793},"labels":[],"label_agreement":null},{"id":"W843694097","doi":"10.1007/978-4-431-66996-8_24","title":"Construct Comparability in International Assessments: Comparability of English and French versions of TIMSS","year":2003,"lang":"en","type":"book-chapter","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Comparability; Differential item functioning; Construct (python library); Item response theory; Construct validity; Statistics; Psychology; Test (biology); International comparisons; Econometrics; Mathematics; Mathematics education; Psychometrics; Computer science; Economics","score_opus":0.42293170621114673,"score_gpt":0.47448355252794233,"score_spread":0.0515518463167956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W843694097","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09640087,0.00018640926,0.0019392024,0.00004007748,0.0015522402,0.0002726914,0.00017288105,0.000015361144,0.89942026],"genre_scores_gemma":[0.9191457,0.00008010124,0.06445149,0.00005823577,0.000050932933,0.0000034121176,0.000018329818,0.000012392662,0.01617939],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959136,0.0003241782,0.0017155065,0.00068587495,0.0011962984,0.00016454146],"domain_scores_gemma":[0.97068876,0.02598642,0.0009935581,0.0007462201,0.001496264,0.00008876219],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006139217,0.00022734878,0.001089739,0.0007475629,0.000033453853,0.000037241076,0.0007717273,0.00022482636,0.0037485824],"category_scores_gemma":[0.042719115,0.00017656466,0.00016510366,0.00034460824,0.00076622,0.00013757641,0.0003122157,0.0003609451,0.0000038313074],"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":[0.000053550444,0.00018691384,0.9013714,0.000052449243,0.00010439434,0.0000023809737,0.0002922293,0.00005763237,0.0000149748885,0.06611574,0.0050502717,0.02669802],"study_design_scores_gemma":[0.0021303832,0.00027921743,0.45097172,0.00026467995,0.00005281882,0.00000802871,0.0014332628,0.0013082258,0.00010292688,0.47705308,0.065801024,0.00059462065],"about_ca_topic_score_codex":0.00016580688,"about_ca_topic_score_gemma":0.00005422111,"teacher_disagreement_score":0.8832409,"about_ca_system_score_codex":0.000074090516,"about_ca_system_score_gemma":0.00010422011,"threshold_uncertainty_score":0.9971621},"labels":[],"label_agreement":null},{"id":"W98422573","doi":"10.55016/ojs/ajer.v51i3.55148","title":"The Use of One-, Two-, and Three-Parameter and Nominal Item Response Scoring in Place of Number-Right Scoring in the Presence of Test-Wiseness","year":2005,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Item response theory; Test (biology); Psychology; Mathematics; Econometrics; Psychometrics","score_opus":0.6230280355567007,"score_gpt":0.5439208949779503,"score_spread":0.07910714057875046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W98422573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.992271,0.0010160808,0.00002489643,0.0058989865,0.00008517859,0.00015861618,0.0000019703966,1.3292802e-7,0.0005431337],"genre_scores_gemma":[0.9929065,0.00016981467,0.0061935936,0.0000128488,0.000074423624,0.0000058561227,7.636751e-8,0.000004972829,0.00063187565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99483615,0.0019031742,0.0011508722,0.00022357148,0.0016011,0.0002851402],"domain_scores_gemma":[0.47662494,0.5220063,0.00044191963,0.0002693188,0.0005993835,0.00005819757],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026175175,0.000088702756,0.00032063897,0.0008114602,0.0001276986,0.00013567334,0.00091846194,0.000042941596,0.00013843396],"category_scores_gemma":[0.56132686,0.000049463408,0.00005188298,0.0020385657,0.0005418081,0.00049407326,0.00020154672,0.0004544512,0.0000017275779],"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":[0.0008829656,0.00019631824,0.979346,0.000015529313,0.000012471525,0.0000011629729,0.0013286199,0.0003696717,0.0023322867,0.0010873969,0.00019198886,0.014235599],"study_design_scores_gemma":[0.0004569267,0.00016829964,0.98969907,0.0003171013,0.0000052522787,0.000102668586,0.0011571796,0.0016000598,0.0010548234,0.0045121606,0.00087275816,0.00005370222],"about_ca_topic_score_codex":0.001587924,"about_ca_topic_score_gemma":0.0021810653,"teacher_disagreement_score":0.5351517,"about_ca_system_score_codex":0.000056506084,"about_ca_system_score_gemma":0.00056960917,"threshold_uncertainty_score":0.90718454},"labels":[],"label_agreement":null},{"id":"W997115915","doi":"10.1017/cbo9780511804632.009","title":"Designing Studies to Avoid Confounds","year":2006,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Psychology","score_opus":0.4474015997285752,"score_gpt":0.3891586258714473,"score_spread":0.0582429738571279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W997115915","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002608288,0.0006446175,0.025803998,0.000044555756,0.0009699999,0.00039465682,0.000099266625,0.00017546363,0.9716066],"genre_scores_gemma":[0.00080826983,0.00005042065,0.008145925,0.00018520298,0.00024785934,8.722861e-7,0.0000058753158,0.0000369737,0.9905186],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99632066,0.00025521652,0.000609024,0.0011102848,0.0012364741,0.00046834795],"domain_scores_gemma":[0.98452926,0.012623432,0.00062082487,0.0010859381,0.0009354595,0.0002051138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025215715,0.0004740469,0.0009915797,0.0011766339,0.0004634697,0.00021509657,0.0016656495,0.00033779576,0.000012372199],"category_scores_gemma":[0.007382413,0.00044037943,0.00033011503,0.000107080275,0.0003302402,0.00011720642,0.0011444326,0.0005111623,0.00009736284],"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":[0.00006905262,0.0000058888654,0.000034549685,0.000029988874,0.00017423206,0.000333437,0.00010147109,0.00006495543,0.00008630727,0.39574775,0.59095347,0.012398883],"study_design_scores_gemma":[0.00031840891,0.000094816765,0.00007986286,0.00017432375,0.00010562434,0.00001592751,0.0003859126,0.000024648298,0.00020427736,0.0005438026,0.9975263,0.0005261],"about_ca_topic_score_codex":0.00010594385,"about_ca_topic_score_gemma":0.0000028174236,"teacher_disagreement_score":0.40657282,"about_ca_system_score_codex":0.00025576673,"about_ca_system_score_gemma":0.000109379,"threshold_uncertainty_score":0.9998048},"labels":[],"label_agreement":null}]}