{"meta":{"query_hash":"8e83b7261a16","filters":{"venue":"Methodology"},"cohort_total":15,"direct_labels_cover":1,"predictions_cover":15,"exported":15,"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/8e83b7261a16","api":"https://metacan.xera.ac/api/v1/cohort?venue=Methodology"},"results":[{"id":"W1898119662","doi":"10.1027/1614-2241/a000012","title":"Accentuating the Negative?","year":2010,"lang":"en","type":"article","venue":"Methodology","topic":"Electoral Systems and Political Participation","field":"Social Sciences","cited_by":22,"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":"Acquiescence; Framing (construction); Politics; Psychology; Social psychology; Survey data collection; Attribution; Political science; Law; Engineering; Statistics","score_opus":0.32215961902123946,"score_gpt":0.5012206608623628,"score_spread":0.17906104184112337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898119662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9071701,0.000013263654,0.008815078,0.022573818,0.0018064362,0.00019194503,7.049099e-7,0.000057431047,0.059371207],"genre_scores_gemma":[0.98908454,5.87421e-7,0.0087393215,0.00042931148,0.0006883007,0.000014515938,2.2415603e-7,0.0000028124507,0.0010403835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977454,0.0017735445,0.000095829026,0.000073866555,0.000088786524,0.0002225897],"domain_scores_gemma":[0.996806,0.0029675486,0.000038546215,0.00009041641,0.000045423145,0.00005206986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032485723,0.000031754953,0.000069373535,0.000011601752,0.0003777627,0.00002334808,0.00012767744,0.000069743524,0.0005925342],"category_scores_gemma":[0.0061306576,0.000020269586,0.000024548053,0.00010693002,0.00024418434,0.00004277917,0.000015439206,0.00017748537,0.00007408096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027331337,0.000005633027,0.013439828,9.2834875e-7,0.000003765402,2.8972315e-7,0.005000781,5.619527e-7,0.008571108,0.95566773,0.00048240105,0.016824262],"study_design_scores_gemma":[0.0002125203,0.000056823428,0.12734696,0.000003993869,0.000023001103,0.000002543212,0.0022133947,0.00010897894,0.008870789,0.53753614,0.32343853,0.00018631051],"about_ca_topic_score_codex":0.012655051,"about_ca_topic_score_gemma":0.023815192,"teacher_disagreement_score":0.41813153,"about_ca_system_score_codex":0.000009475472,"about_ca_system_score_gemma":0.000042431042,"threshold_uncertainty_score":0.99399763},"labels":[],"label_agreement":null},{"id":"W2110497623","doi":"10.1027/1614-1881.1.2.71","title":"Modelling Behaviour with Multivariate Multilevel Growth Curves","year":2005,"lang":"en","type":"article","venue":"Methodology","topic":"Income, Poverty, and Inequality","field":"Social Sciences","cited_by":13,"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":"Multivariate statistics; Multilevel model; Multivariate analysis; Econometrics; Longitudinal data; Multilevel modelling; Measure (data warehouse); Psychology; Set (abstract data type); Statistics; Mathematics; Demography; Computer science; Sociology; Data mining","score_opus":0.29716268945923674,"score_gpt":0.42785576713879614,"score_spread":0.1306930776795594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110497623","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":[0.11374011,0.00041053467,0.86308503,0.0041908897,0.0004774403,0.00031657843,0.00001604538,0.00017240888,0.017590942],"genre_scores_gemma":[0.55707943,0.0002500455,0.43878576,0.0015067279,0.0004829808,0.000020839881,0.00000544353,0.000017195815,0.0018515505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99609524,0.0025956726,0.00026423702,0.00031089102,0.0002643555,0.00046961333],"domain_scores_gemma":[0.9982981,0.0010821068,0.00012505749,0.00019092097,0.00018599063,0.000117802025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004583595,0.00014012952,0.0003131785,0.00006629583,0.00038191187,0.000020442934,0.00027864322,0.00016718531,0.0002894436],"category_scores_gemma":[0.00080463727,0.00011425423,0.000067052526,0.00014597338,0.00026657176,0.00023499377,0.00004405657,0.00022984498,0.000051455772],"study_design_candidate":"theoretical_or_conceptual","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":[0.00073408295,0.0012558998,0.12037753,0.000295069,0.00027561592,0.00005609649,0.14793095,0.014599928,0.0014155393,0.65500915,0.0064025274,0.051647615],"study_design_scores_gemma":[0.01659568,0.002096855,0.17718667,0.0011854752,0.0014277735,0.000103572456,0.03024892,0.23671527,0.022257231,0.18321873,0.32037625,0.0085875625],"about_ca_topic_score_codex":0.020776521,"about_ca_topic_score_gemma":0.0021352137,"teacher_disagreement_score":0.4717904,"about_ca_system_score_codex":0.00008393996,"about_ca_system_score_gemma":0.00012105411,"threshold_uncertainty_score":0.98574424},"labels":[],"label_agreement":null},{"id":"W2126367292","doi":"10.1027/1614-2241/a000032","title":"Two-Part Modeling of Semicontinuous Longitudinal Variables","year":2011,"lang":"en","type":"article","venue":"Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","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":"York University","funders":"","keywords":"Covariate; Outcome (game theory); Zero (linguistics); Mathematics; Statistics; Variable (mathematics); Interpretation (philosophy); Econometrics; Range (aeronautics); Latent variable; Growth curve (statistics); Maximum likelihood; Continuous variable; Computer science; Mathematical economics; Engineering; Mathematical analysis","score_opus":0.48186026290138945,"score_gpt":0.43865334274944784,"score_spread":0.04320692015194161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126367292","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":[0.011868321,0.000051137526,0.96589303,0.00001581234,0.00031308012,0.00009260372,0.000011862779,0.00004534656,0.02170878],"genre_scores_gemma":[0.062934786,0.00000789823,0.9368554,0.00002554776,0.00007742034,0.00001169712,8.413728e-7,0.00001690918,0.00006952935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774665,0.001134164,0.0004798247,0.0002559623,0.0001038591,0.00027955574],"domain_scores_gemma":[0.9953585,0.0039681448,0.00015984711,0.00032158938,0.0001274188,0.00006445565],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023086998,0.0001365482,0.0005451566,0.000075723205,0.000036612244,0.0000044140916,0.00020770762,0.00011045461,0.0010936573],"category_scores_gemma":[0.005719258,0.000115124014,0.00007232241,0.00011771932,0.00011970972,0.00003801406,0.00008276656,0.00016344847,0.0000095712685],"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":[0.000060907427,0.00007173358,0.0012470847,0.000065936416,0.000044963694,0.000015728101,0.00048164063,0.0000034444804,0.0021393439,0.9849444,0.00009583669,0.010828964],"study_design_scores_gemma":[0.00023317065,0.00009424124,0.00012705364,0.000033072796,0.00008391097,0.000052737436,0.00009685526,0.0057925265,0.0057307486,0.98760486,0.000026284251,0.0001245427],"about_ca_topic_score_codex":0.00021418995,"about_ca_topic_score_gemma":0.000014614518,"teacher_disagreement_score":0.051066466,"about_ca_system_score_codex":0.000010210601,"about_ca_system_score_gemma":0.00003549875,"threshold_uncertainty_score":0.99981946},"labels":[],"label_agreement":null},{"id":"W2157428947","doi":"10.1027/1614-2241/a000051","title":"Non-Graphical Solutions for Cattell’s Scree Test","year":2012,"lang":"en","type":"article","venue":"Methodology","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":355,"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 de Montréal; Université du Québec à Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Principal component analysis; Eigenvalues and eigenvectors; Plot (graphics); Test (biology); Computer science; Matrix (chemical analysis); Factor (programming language); Mathematics; Statistics; Artificial intelligence; Geology","score_opus":0.35031273622427517,"score_gpt":0.39547294823846263,"score_spread":0.04516021201418746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157428947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62277937,0.00051793165,0.36556807,0.0070708683,0.0008058523,0.0004735937,0.00023856823,0.0001079074,0.0024378784],"genre_scores_gemma":[0.65338606,0.000015868118,0.34439868,0.00090265553,0.0008636914,0.000054761913,0.000046571997,0.0000012471994,0.00033048348],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99823624,0.00062360236,0.00022310828,0.00022297828,0.00008206394,0.00061198],"domain_scores_gemma":[0.98686236,0.012771136,0.000057666384,0.000065786575,0.0000640379,0.00017902347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003037456,0.00011349565,0.0002968053,0.000017038745,0.0003111228,0.000013971988,0.00015791404,0.00015347627,0.00063178997],"category_scores_gemma":[0.0034239832,0.000042276126,0.00017943485,0.00027754484,0.0001355163,0.00004971498,0.000051880543,0.00012116002,0.000040016388],"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":[0.00006123901,0.00036835225,0.07771004,0.000010052738,0.00006323646,0.0000014059239,0.000088629284,0.000003885361,0.5149571,0.05765131,0.0043636365,0.34472117],"study_design_scores_gemma":[0.00021637083,0.0005496203,0.8642509,0.0000044575927,0.00016956466,0.000026631376,0.00031331723,0.00087381504,0.004771578,0.05540409,0.073053256,0.00036640774],"about_ca_topic_score_codex":0.000113505695,"about_ca_topic_score_gemma":0.00015271599,"teacher_disagreement_score":0.78654087,"about_ca_system_score_codex":0.000008765314,"about_ca_system_score_gemma":0.0000031386448,"threshold_uncertainty_score":0.69176567},"labels":[],"label_agreement":null},{"id":"W2166565928","doi":"10.1027/1614-2241/a000061","title":"A Multiple-Process Latent Transition Model of Poverty and Health","year":2012,"lang":"en","type":"article","venue":"Methodology","topic":"Global Health Care Issues","field":"Health Professions","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":"Public Health Ontario; University of Toronto","funders":"Economic and Social Research Council","keywords":"Poverty; British Household Panel Survey; Covariate; Longitudinal data; Longitudinal study; Psychology; Latent growth modeling; Econometrics; Demographic economics; Developmental psychology; Economics; Demography; Statistics; Mathematics; Sociology; Economic growth","score_opus":0.5234643545063861,"score_gpt":0.570236664049345,"score_spread":0.04677230954295897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166565928","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8103251,0.0037541804,0.168768,0.013669613,0.0011249194,0.0011485256,0.00010063776,0.00012072364,0.0009882799],"genre_scores_gemma":[0.8961152,0.00018794769,0.09319218,0.010219251,0.00012713006,0.0000493813,0.000014334998,0.000017168844,0.000077434604],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959462,0.002481227,0.00056442095,0.00019154485,0.00013457918,0.0006820088],"domain_scores_gemma":[0.99799615,0.0011599491,0.00025811404,0.00018598046,0.00013717767,0.00026260279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046092523,0.00012030299,0.0004998417,0.00008415584,0.00021521788,6.560579e-7,0.00007675887,0.00024144285,0.000066829714],"category_scores_gemma":[0.0004228741,0.00010265138,0.000037040507,0.00011151661,0.000058890055,0.00009986081,0.000040249888,0.00034618747,0.00002958227],"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":[0.0018360103,0.00073145225,0.54625726,0.0135782305,0.0001440913,0.0000029632095,0.32984972,0.0018401787,0.0074476455,0.038772006,0.030917043,0.028623398],"study_design_scores_gemma":[0.010488929,0.0016520743,0.8088602,0.0012915543,0.00019785753,0.0000592313,0.029209342,0.077282816,0.002714336,0.057424504,0.009600065,0.0012190829],"about_ca_topic_score_codex":0.0011513662,"about_ca_topic_score_gemma":0.00024908723,"teacher_disagreement_score":0.30064037,"about_ca_system_score_codex":0.00010869742,"about_ca_system_score_gemma":0.0002048582,"threshold_uncertainty_score":0.41860017},"labels":[],"label_agreement":null},{"id":"W2171914249","doi":"10.1027/1614-2241/a000041","title":"An Improved Model for Evaluating Change in Randomized Pretest, Posttest, Follow-Up Designs","year":2011,"lang":"en","type":"article","venue":"Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"York University","funders":"","keywords":"Treatment and control groups; Research design; Monte Carlo method; Randomized controlled trial; Randomized experiment; Treatment effect; Computer science; Psychology; Mathematics education; Statistics; Mathematics; Medicine","score_opus":0.8674030637400533,"score_gpt":0.5803188037493868,"score_spread":0.28708425999066645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171914249","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":[0.058230028,0.000056894267,0.9377424,0.000042353706,0.00012145474,0.0031638958,0.00001032868,0.00033448578,0.00029815643],"genre_scores_gemma":[0.13895085,0.000009193798,0.8572371,0.00025785793,0.000045724228,0.003312486,0.000007613034,0.000061897685,0.00011726277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951114,0.0031056777,0.0006955754,0.0004575245,0.00011018079,0.000519657],"domain_scores_gemma":[0.9880812,0.010729972,0.00035578955,0.00054331427,0.00020678733,0.00008291464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013419516,0.00026851604,0.0011637508,0.00021341463,0.000056333145,0.000009516426,0.0003468302,0.0002845224,0.00006018556],"category_scores_gemma":[0.01987813,0.00023412019,0.00017652444,0.00013641462,0.00013389197,0.00028114155,0.00007115976,0.00023291913,0.0000017139885],"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":[0.07496352,0.0005553251,0.0005048416,0.000401363,0.00018539376,0.000011082412,0.054166075,0.00006615729,0.39477432,0.4008765,0.00009144522,0.07340399],"study_design_scores_gemma":[0.017240375,0.00039369075,0.00001427324,0.000022484806,0.000074112846,0.000004155736,0.00005906547,0.3422239,0.018578254,0.62121147,5.7731125e-7,0.00017763318],"about_ca_topic_score_codex":0.00015749726,"about_ca_topic_score_gemma":0.00020396298,"teacher_disagreement_score":0.37619606,"about_ca_system_score_codex":0.00006853769,"about_ca_system_score_gemma":0.00007013648,"threshold_uncertainty_score":0.98837787},"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":"W2601443004","doi":"10.1027/1614-2241/a000122","title":"Using the Errors-in-Variables Method in Two-Group Pretest-Posttest Designs","year":2017,"lang":"en","type":"article","venue":"Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","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":"York University","funders":"","keywords":"Analysis of covariance; Covariate; Statistics; Reliability (semiconductor); Covariance; Mathematics; Econometrics; Observational error; Sample size determination; Psychology; Power (physics)","score_opus":0.918746052008132,"score_gpt":0.6893558059739121,"score_spread":0.22939024603421987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601443004","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":[0.019684441,0.00006100656,0.9745602,0.00093818794,0.0012795521,0.0008113489,0.000018068584,0.000049915692,0.0025972626],"genre_scores_gemma":[0.011537647,0.000012488499,0.9874957,0.0003922417,0.0003236956,0.00008618701,5.414395e-7,0.00006075435,0.00009074742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96869993,0.027970333,0.0014699107,0.0007637896,0.00029260822,0.000803408],"domain_scores_gemma":[0.7083924,0.28918856,0.0006824357,0.0015651174,0.000075968375,0.00009553904],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057018254,0.00032289018,0.0013902866,0.00016759479,0.0003006976,0.00009650548,0.0013363241,0.00033581755,0.00026299374],"category_scores_gemma":[0.5003332,0.0002321059,0.0001619683,0.00023338845,0.0005796097,0.00012472279,0.00050940766,0.00091876456,0.00001241675],"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":[0.00049298967,0.00037697793,0.027431192,0.00017323527,0.00012281492,0.00020868666,0.00096596166,0.00033186714,0.037690688,0.89356923,0.0002013432,0.038435023],"study_design_scores_gemma":[0.0015061626,0.00009365105,0.0062399125,0.00010506544,0.00011257035,0.000041325904,0.00013001563,0.0067690844,0.003294202,0.98130476,0.00013677073,0.00026646644],"about_ca_topic_score_codex":0.00092512276,"about_ca_topic_score_gemma":0.0007141522,"teacher_disagreement_score":0.4433149,"about_ca_system_score_codex":0.000112645575,"about_ca_system_score_gemma":0.00010154634,"threshold_uncertainty_score":0.97099817},"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":"W3149010529","doi":"10.5964/meth.4495","title":"Analytic and bootstrap confidence intervals for the common-language effect size estimate","year":2021,"lang":"en","type":"article","venue":"Methodology","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","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":"University of Manitoba","funders":"University of Manitoba","keywords":"Estimator; Confidence interval; Statistics; Parametric statistics; Type I and type II errors; Mathematics; Standard error; Econometrics; Computer science","score_opus":0.12452210094722825,"score_gpt":0.4010031702919732,"score_spread":0.2764810693447449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149010529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9517555,0.002261617,0.040539656,0.002664508,0.000713452,0.00039393344,0.000004137106,0.00008008211,0.0015870904],"genre_scores_gemma":[0.9916721,0.00001578242,0.005490911,0.0020979517,0.00020386733,0.000048458074,0.000008095149,0.000017802176,0.00044503],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99903977,0.00022849716,0.00019472027,0.00024512786,0.00006718051,0.00022467827],"domain_scores_gemma":[0.9888704,0.010676284,0.00010031388,0.00025691418,0.000086555316,0.000009557861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026892389,0.00013247243,0.0003218354,0.00005379704,0.00016738256,0.00015716472,0.00016400377,0.000056555105,0.00038713528],"category_scores_gemma":[0.0037158371,0.00009455805,0.00009462005,0.00016922908,0.00010057451,0.00013728694,0.00019200768,0.00012989291,0.0000126392115],"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":[0.00053607335,0.000055113123,0.18181852,0.0012692957,0.00031603067,0.00023107315,0.00077478774,0.000031176525,0.06632981,0.009081541,0.0019672576,0.7375893],"study_design_scores_gemma":[0.003785398,0.00014763339,0.90983564,0.0002503907,0.003511968,0.00028582115,0.0024565693,0.019293405,0.012885257,0.018153895,0.028331915,0.0010621026],"about_ca_topic_score_codex":0.0006429005,"about_ca_topic_score_gemma":0.000432175,"teacher_disagreement_score":0.7365272,"about_ca_system_score_codex":0.0000052476394,"about_ca_system_score_gemma":0.000012553061,"threshold_uncertainty_score":0.44484726},"labels":[],"label_agreement":null},{"id":"W4221124934","doi":"10.5964/meth.8575","title":"Welcome message from the new editors-in-chief","year":2022,"lang":"en","type":"article","venue":"Methodology","topic":"Mental Health Research Topics","field":"Psychology","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":"Citation; License; Library science; XML; Download; Computer science; Editor in chief; World Wide Web; Management; Operating system","score_opus":0.3201864956255316,"score_gpt":0.5072122021254595,"score_spread":0.1870257064999279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221124934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40961343,0.011007624,0.023393698,0.23113927,0.1804482,0.0033548435,0.0004842853,0.0003551493,0.14020349],"genre_scores_gemma":[0.3972133,0.00024965766,0.18323818,0.07278691,0.10475297,0.0034829576,0.0004907636,0.0004357506,0.23734948],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98802483,0.010315011,0.0003352985,0.00041289176,0.0003088098,0.00060318655],"domain_scores_gemma":[0.99257654,0.0065127024,0.000086677916,0.0006765496,0.000010647655,0.00013688467],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004762717,0.0001212695,0.0002893494,0.00010646989,0.00023763854,0.000009026984,0.00075465435,0.00010401431,0.050261892],"category_scores_gemma":[0.0005230467,0.00009680606,0.00006394231,0.0003343084,0.000098767036,0.000025508389,0.0004939364,0.0011177367,0.00034299245],"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":[0.0005363534,0.00020024019,0.024392039,0.000009758016,0.00006552187,0.00025287934,0.008154105,0.00001917073,0.0004669454,0.026951373,0.85573137,0.08322026],"study_design_scores_gemma":[0.00091129576,0.00022173037,0.11103968,0.0000021409385,0.0000064342385,0.00002527844,0.0018249335,0.000012309174,0.00006103613,0.027119085,0.85867655,0.00009950606],"about_ca_topic_score_codex":0.0098008355,"about_ca_topic_score_gemma":0.00047422407,"teacher_disagreement_score":0.15984449,"about_ca_system_score_codex":0.00016240697,"about_ca_system_score_gemma":0.00012508805,"threshold_uncertainty_score":0.996793},"labels":[],"label_agreement":null},{"id":"W4283719121","doi":"10.5964/meth.8467","title":"Bootstrap confidence intervals for 11 robust correlations in the presence of outliers and leverage observations","year":2022,"lang":"en","type":"article","venue":"Methodology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Outlier; Confidence interval; Leverage (statistics); Statistics; Bivariate analysis; Percentile; Correlation; Robust confidence intervals; Standard deviation; Econometrics; Statistic; Mathematics","score_opus":0.7145503611330684,"score_gpt":0.5126216750297369,"score_spread":0.20192868610333148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283719121","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":[0.019954044,0.00006225411,0.97813994,0.00094934757,0.00014097721,0.0005074946,0.00011633459,0.000009870957,0.000119764605],"genre_scores_gemma":[0.10865198,0.0000065300533,0.8905954,0.00021111328,0.000010543923,0.00027440858,0.000004784199,0.000008317439,0.00023693657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973303,0.0018835643,0.0003421588,0.00018337843,0.00010528728,0.00015528982],"domain_scores_gemma":[0.96903497,0.030543132,0.00014158162,0.00020660897,0.000051962146,0.000021761012],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037922924,0.000075267104,0.00025798823,0.000056452907,0.00014098371,0.0000053463978,0.0001994249,0.00003593941,0.000045530185],"category_scores_gemma":[0.010713711,0.00006085554,0.00004052739,0.00014032303,0.00014631131,0.00005167042,0.00008858777,0.00018019143,7.922734e-8],"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":[0.000030288236,0.000048068818,0.0006539764,0.000046937213,0.000008890033,0.0000018276374,0.0035539262,0.0038129939,0.0005673649,0.9890217,0.00035785342,0.0018961518],"study_design_scores_gemma":[0.00028914507,0.00012094441,0.0027745096,0.000008726473,0.000030449619,0.0000135761775,0.0025278127,0.015501559,0.000078654884,0.977871,0.00071691355,0.000066704946],"about_ca_topic_score_codex":0.00005194895,"about_ca_topic_score_gemma":0.00010344598,"teacher_disagreement_score":0.08869793,"about_ca_system_score_codex":0.000015444451,"about_ca_system_score_gemma":0.000028489456,"threshold_uncertainty_score":0.99761945},"labels":[],"label_agreement":null},{"id":"W4382393838","doi":"10.5964/meth.10863","title":"The logics of and strategies to enhance generalization of mixed methods research findings","year":2023,"lang":"en","type":"article","venue":"Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Generalization; Context (archaeology); Computer science; Interpretation (philosophy); Management science; Artificial intelligence; Psychology; Epistemology; Engineering; Biology","score_opus":0.9500912121363324,"score_gpt":0.8438520423046605,"score_spread":0.10623916983167192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382393838","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":[0.6849713,0.000038340433,0.29994982,0.013413847,0.00038062737,0.0005752487,0.000013534323,0.000025859083,0.00063143624],"genre_scores_gemma":[0.19231601,0.000488012,0.8031741,0.0019141352,0.00011583973,0.0003168438,0.000004372834,0.000018149909,0.0016525491],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.97069937,0.027441718,0.00076150603,0.00022481864,0.0002845697,0.0005880395],"domain_scores_gemma":[0.9509223,0.048049826,0.00019094098,0.00025775825,0.0004916784,0.00008749812],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06531996,0.000058811678,0.00024407098,0.00029816077,0.0006159256,0.000005658528,0.00025754684,0.000108524924,0.000057121524],"category_scores_gemma":[0.028556854,0.000041614127,0.000015655107,0.0015796183,0.00033039047,0.000059492264,0.00027821385,0.00025814856,0.000028779503],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011378874,0.000009144315,0.00971146,0.0006126165,0.000020042437,8.114279e-7,0.081084915,0.00016343534,0.4738549,0.3253349,0.034358304,0.07473566],"study_design_scores_gemma":[0.00057644275,0.0007854533,0.28369144,0.00010852286,0.000016177059,0.000002264245,0.10383505,0.0009868292,0.1774094,0.2481913,0.18416229,0.00023484607],"about_ca_topic_score_codex":0.00062453316,"about_ca_topic_score_gemma":0.0005270321,"teacher_disagreement_score":0.50322425,"about_ca_system_score_codex":0.00003703755,"about_ca_system_score_gemma":0.0004562851,"threshold_uncertainty_score":0.979626},"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":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4390021842","doi":"10.5964/meth.8285","title":"Which robust regression technique is appropriate under violated assumptions? A simulation study","year":2023,"lang":"en","type":"article","venue":"Methodology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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 Manitoba","funders":"","keywords":"Robust regression; Statistics; Ordinary least squares; Regression; Regression analysis; Heteroscedasticity; Outlier; Mathematics; Mean squared error; Regression diagnostic; Econometrics; Monte Carlo method; Linear regression; Polynomial regression","score_opus":0.590566386328184,"score_gpt":0.5569675912452756,"score_spread":0.03359879508290842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390021842","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":[0.026177032,0.000009731539,0.9714647,0.0003186409,0.00021058456,0.001054824,0.000014561531,0.00048170242,0.00026821584],"genre_scores_gemma":[0.12690604,0.000009848021,0.8719631,0.000081116144,0.00005646415,0.00022247889,0.000010968017,0.000048037993,0.00070194155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99507934,0.003327881,0.00049176853,0.0005133205,0.00022131945,0.0003663686],"domain_scores_gemma":[0.9904819,0.008521454,0.00019132454,0.0004977162,0.00022412623,0.00008344464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049124323,0.00021685705,0.0005165929,0.0002325119,0.00018319167,0.000016562572,0.00016228318,0.00026397902,0.00015864594],"category_scores_gemma":[0.006655393,0.00017038942,0.00006224562,0.0007921765,0.000044143093,0.0000821286,0.00015063271,0.00036306962,0.000056166777],"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":[0.0013388898,0.0029014337,0.0021607212,0.0007104059,0.0007941312,0.00013951388,0.012117605,0.35063007,0.11000979,0.34107935,0.0037809832,0.17433709],"study_design_scores_gemma":[0.00046493293,0.00019277356,0.0012620684,0.00003320118,0.0000761073,0.0000054892207,0.00042564177,0.092764735,0.0012526943,0.9031906,0.00012949291,0.00020224671],"about_ca_topic_score_codex":0.000018842466,"about_ca_topic_score_gemma":0.00002538476,"teacher_disagreement_score":0.56211126,"about_ca_system_score_codex":0.00005053949,"about_ca_system_score_gemma":0.000028501081,"threshold_uncertainty_score":0.7967608},"labels":[],"label_agreement":null},{"id":"W4411809104","doi":"10.5964/meth.14733","title":"A practical guide to conducting dose-response meta-analyses in epidemiology","year":2025,"lang":"en","type":"article","venue":"Methodology","topic":"Alcohol Consumption and Health Effects","field":"Medicine","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":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health","keywords":"Epidemiology; Meta-analysis; Medicine; Internal medicine","score_opus":0.9429413618181373,"score_gpt":0.7269228172101364,"score_spread":0.21601854460800085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411809104","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":[0.37626138,0.00267173,0.30542395,0.30962595,0.0009033732,0.0013795694,0.0000034782265,0.00014007249,0.0035904865],"genre_scores_gemma":[0.076320834,0.000034145658,0.83699507,0.08135121,0.00008044067,0.0002221371,0.000004383465,0.0000157626,0.004976],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.97876525,0.019163383,0.00092662167,0.00051977194,0.00009041589,0.0005345867],"domain_scores_gemma":[0.94487363,0.054177765,0.00015035504,0.0004479415,0.00012696855,0.00022331536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026075553,0.00017600796,0.0016805278,0.00069312257,0.00006167182,0.0000033264196,0.000082970306,0.0002684876,0.00082547346],"category_scores_gemma":[0.15553476,0.00013210317,0.0002496402,0.000552477,0.000119035925,0.000035164612,0.00009758919,0.0005401062,0.00018561403],"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":[0.048007123,0.00095100136,0.07708868,0.0011380109,0.011451267,0.0017980296,0.002896726,0.00036141256,0.5423359,0.09453091,0.19057095,0.028869985],"study_design_scores_gemma":[0.0084472,0.0020235253,0.4251207,0.00015594417,0.012640165,0.0014003782,0.0020001743,0.0010108525,0.020474996,0.007917729,0.51811045,0.00069788157],"about_ca_topic_score_codex":0.00043378194,"about_ca_topic_score_gemma":0.0001363408,"teacher_disagreement_score":0.5315711,"about_ca_system_score_codex":0.00013743319,"about_ca_system_score_gemma":0.0004916231,"threshold_uncertainty_score":0.90383554},"labels":[],"label_agreement":null}]}