{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":15,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":15,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"8e83b7261a16","filters":{"venue":"Methodology"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3503127362242752,"gpt":0.3954729482384626,"spread":0.04516021201418746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003037456,0.0001134956,0.0002968053,0.00001703874,0.0003111228,0.00001397199,0.000157914,0.0001534763,0.00063179],"category_scores_gemma":[0.003423983,0.00004227613,0.0001794348,0.0002775448,0.0001355163,0.00004971498,0.00005188054,0.00012116,0.00004001639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008765314,"about_ca_system_score_gemma":0.000003138645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001135057,"about_ca_topic_score_gemma":0.000152716,"domain_scores_codex":[0.9982362,0.0006236024,0.0002231083,0.0002229783,0.00008206394,0.00061198],"domain_scores_gemma":[0.9868624,0.01277114,0.00005766638,0.00006578657,0.0000640379,0.0001790235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00006123901,0.0003683523,0.07771004,0.00001005274,0.00006323646,0.000001405924,0.00008862928,0.000003885361,0.5149571,0.05765131,0.004363636,0.3447212],"study_design_scores_gemma":[0.0002163708,0.0005496203,0.8642509,0.000004457593,0.0001695647,0.00002663138,0.0003133172,0.000873815,0.004771578,0.05540409,0.07305326,0.0003664077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6227794,0.0005179317,0.3655681,0.007070868,0.0008058523,0.0004735937,0.0002385682,0.0001079074,0.002437878],"genre_scores_gemma":[0.6533861,0.00001586812,0.3443987,0.0009026555,0.0008636914,0.00005476191,0.000046572,0.000001247199,0.0003304835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7865409,"threshold_uncertainty_score":0.6917657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Acquiescence; Framing (construction); Politics; Psychology; Social psychology; Survey data collection; Attribution; Political science; Law; Engineering; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3221596190212395,"gpt":0.5012206608623628,"spread":0.1790610418411234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003248572,0.00003175495,0.00006937353,0.00001160175,0.0003777627,0.00002334808,0.0001276774,0.00006974352,0.0005925342],"category_scores_gemma":[0.006130658,0.00002026959,0.00002454805,0.00010693,0.0002441843,0.00004277917,0.00001543921,0.0001774854,0.00007408096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009475472,"about_ca_system_score_gemma":0.00004243104,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01265505,"about_ca_topic_score_gemma":0.02381519,"domain_scores_codex":[0.9977454,0.001773544,0.00009582903,0.00007386655,0.00008878652,0.0002225897],"domain_scores_gemma":[0.996806,0.002967549,0.00003854622,0.00009041641,0.00004542314,0.00005206986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002733134,0.000005633027,0.01343983,9.283488e-7,0.000003765402,2.897231e-7,0.005000781,5.619527e-7,0.008571108,0.9556677,0.0004824011,0.01682426],"study_design_scores_gemma":[0.0002125203,0.00005682343,0.127347,0.000003993869,0.0000230011,0.000002543212,0.002213395,0.0001089789,0.008870789,0.5375361,0.3234385,0.0001863105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9071701,0.00001326365,0.008815078,0.02257382,0.001806436,0.000191945,7.049099e-7,0.00005743105,0.05937121],"genre_scores_gemma":[0.9890845,5.87421e-7,0.008739321,0.0004293115,0.0006883007,0.00001451594,2.24156e-7,0.000002812451,0.001040383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4181315,"threshold_uncertainty_score":0.9939976,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8674030637400533,"gpt":0.5803188037493868,"spread":0.2870842599906664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01341952,0.000268516,0.001163751,0.0002134146,0.00005633315,0.000009516426,0.0003468302,0.0002845224,0.00006018556],"category_scores_gemma":[0.01987813,0.0002341202,0.0001765244,0.0001364146,0.000133892,0.0002811415,0.00007115976,0.0002329191,0.000001713988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006853769,"about_ca_system_score_gemma":0.00007013648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001574973,"about_ca_topic_score_gemma":0.000203963,"domain_scores_codex":[0.9951114,0.003105678,0.0006955754,0.0004575245,0.0001101808,0.000519657],"domain_scores_gemma":[0.9880812,0.01072997,0.0003557896,0.0005433143,0.0002067873,0.00008291464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.07496352,0.0005553251,0.0005048416,0.000401363,0.0001853938,0.00001108241,0.05416607,0.00006615729,0.3947743,0.4008765,0.00009144522,0.07340399],"study_design_scores_gemma":[0.01724038,0.0003936907,0.00001427324,0.00002248481,0.00007411285,0.000004155736,0.00005906547,0.3422239,0.01857825,0.6212115,5.773113e-7,0.0001776332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05823003,0.00005689427,0.9377424,0.00004235371,0.0001214547,0.003163896,0.00001032868,0.0003344858,0.0002981564],"genre_scores_gemma":[0.1389509,0.000009193798,0.8572371,0.0002578579,0.00004572423,0.003312486,0.000007613034,0.00006189768,0.0001172628],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3761961,"threshold_uncertainty_score":0.9883779,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9500912121363324,"gpt":0.8438520423046605,"spread":0.1062391698316719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06531996,0.00005881168,0.000244071,0.0002981608,0.0006159256,0.000005658528,0.0002575468,0.0001085249,0.00005712152],"category_scores_gemma":[0.02855685,0.00004161413,0.00001565511,0.001579618,0.0003303905,0.00005949226,0.0002782138,0.0002581486,0.0000287795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003703755,"about_ca_system_score_gemma":0.0004562851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006245332,"about_ca_topic_score_gemma":0.0005270321,"domain_scores_codex":[0.9706994,0.02744172,0.000761506,0.0002248186,0.0002845697,0.0005880395],"domain_scores_gemma":[0.9509223,0.04804983,0.000190941,0.0002577582,0.0004916784,0.00008749812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001137887,0.000009144315,0.00971146,0.0006126165,0.00002004244,8.114279e-7,0.08108491,0.0001634353,0.4738549,0.3253349,0.0343583,0.07473566],"study_design_scores_gemma":[0.0005764427,0.0007854533,0.2836914,0.0001085229,0.00001617706,0.000002264245,0.103835,0.0009868292,0.1774094,0.2481913,0.1841623,0.0002348461],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6849713,0.00003834043,0.2999498,0.01341385,0.0003806274,0.0005752487,0.00001353432,0.00002585908,0.0006314362],"genre_scores_gemma":[0.192316,0.000488012,0.8031741,0.001914135,0.0001158397,0.0003168438,0.000004372834,0.00001814991,0.001652549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5032243,"threshold_uncertainty_score":0.979626,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2971626894592367,"gpt":0.4278557671387961,"spread":0.1306930776795594,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004583595,0.0001401295,0.0003131785,0.00006629583,0.0003819119,0.00002044293,0.0002786432,0.0001671853,0.0002894436],"category_scores_gemma":[0.0008046373,0.0001142542,0.00006705253,0.0001459734,0.0002665718,0.0002349938,0.00004405657,0.000229845,0.00005145577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008393996,"about_ca_system_score_gemma":0.0001210541,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02077652,"about_ca_topic_score_gemma":0.002135214,"domain_scores_codex":[0.9960952,0.002595673,0.000264237,0.000310891,0.0002643555,0.0004696133],"domain_scores_gemma":[0.9982981,0.001082107,0.0001250575,0.000190921,0.0001859906,0.000117802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007340829,0.0012559,0.1203775,0.000295069,0.0002756159,0.00005609649,0.1479309,0.01459993,0.001415539,0.6550092,0.006402527,0.05164761],"study_design_scores_gemma":[0.01659568,0.002096855,0.1771867,0.001185475,0.001427774,0.0001035725,0.03024892,0.2367153,0.02225723,0.1832187,0.3203762,0.008587562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1137401,0.0004105347,0.863085,0.00419089,0.0004774403,0.0003165784,0.00001604538,0.0001724089,0.01759094],"genre_scores_gemma":[0.5570794,0.0002500455,0.4387858,0.001506728,0.0004829808,0.00002083988,0.00000544353,0.00001719581,0.001851551],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4717904,"threshold_uncertainty_score":0.9857442,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.590566386328184,"gpt":0.5569675912452756,"spread":0.03359879508290842,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004912432,0.000216857,0.0005165929,0.0002325119,0.0001831917,0.00001656257,0.0001622832,0.000263979,0.0001586459],"category_scores_gemma":[0.006655393,0.0001703894,0.00006224562,0.0007921765,0.00004414309,0.0000821286,0.0001506327,0.0003630696,0.00005616678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005053949,"about_ca_system_score_gemma":0.00002850108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001884247,"about_ca_topic_score_gemma":0.00002538476,"domain_scores_codex":[0.9950793,0.003327881,0.0004917685,0.0005133205,0.0002213195,0.0003663686],"domain_scores_gemma":[0.9904819,0.008521454,0.0001913245,0.0004977162,0.0002241262,0.00008344464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00133889,0.002901434,0.002160721,0.0007104059,0.0007941312,0.0001395139,0.0121176,0.3506301,0.1100098,0.3410794,0.003780983,0.1743371],"study_design_scores_gemma":[0.0004649329,0.0001927736,0.001262068,0.00003320118,0.0000761073,0.000005489221,0.0004256418,0.09276474,0.001252694,0.9031906,0.0001294929,0.0002022467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02617703,0.000009731539,0.9714647,0.0003186409,0.0002105846,0.001054824,0.00001456153,0.0004817024,0.0002682158],"genre_scores_gemma":[0.126906,0.000009848021,0.8719631,0.00008111614,0.00005646415,0.0002224789,0.00001096802,0.00004803799,0.0007019415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5621113,"threshold_uncertainty_score":0.7967608,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9393714709572591,"gpt":0.5778324970126306,"spread":0.3615389739446285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05156149,0.0002279295,0.0009014422,0.0008195868,0.0003480022,0.00009529106,0.000900591,0.0002271698,0.0006947915],"category_scores_gemma":[0.5043761,0.000171873,0.00017548,0.002282435,0.0003997112,0.0002990212,0.0004542281,0.0002758148,0.00002395948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000569484,"about_ca_system_score_gemma":0.0001397633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001858269,"about_ca_topic_score_gemma":0.00001392827,"domain_scores_codex":[0.9859024,0.009768643,0.001537847,0.0009564214,0.001321845,0.000512843],"domain_scores_gemma":[0.775876,0.2188537,0.001913433,0.001506146,0.001672162,0.0001786298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001911295,0.00005864094,0.7453701,0.00002386914,0.00009969637,0.00004224344,0.001017094,0.00009423086,0.1364369,0.0003007706,0.0003963793,0.115969],"study_design_scores_gemma":[0.0006944019,0.001380992,0.8828159,0.0001967093,0.0002653912,0.001274401,0.001993847,0.01093573,0.0599493,0.03718641,0.00266003,0.0006468682],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5052119,0.0001647395,0.491093,0.00002890183,0.002678838,0.00007176885,7.065198e-7,0.00006462595,0.0006854945],"genre_scores_gemma":[0.5563092,0.000007816942,0.4430392,0.00003427243,0.0004841175,0.000003038115,2.830139e-7,0.0000102538,0.0001118861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4528145,"threshold_uncertainty_score":0.976617,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Citation; Library science; Psychology; Delphi method; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.941291787059819,"gpt":0.6278904871636637,"spread":0.3134012998961553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.04755716,0.0001181584,0.0004278084,0.0004846188,0.0002035311,0.00007132936,0.001047632,0.0001380676,0.003784645],"category_scores_gemma":[0.4936381,0.00007947515,0.0001159629,0.002118074,0.0004049923,0.00009915588,0.0002873243,0.0001672712,0.001489931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001553558,"about_ca_system_score_gemma":0.00003466592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003721664,"about_ca_topic_score_gemma":0.00001183183,"domain_scores_codex":[0.9902833,0.007542993,0.0005822259,0.0006052071,0.000585832,0.0004004407],"domain_scores_gemma":[0.8135408,0.1841775,0.000351239,0.001204391,0.0005760671,0.0001500151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007346075,0.00003418076,0.1507413,0.000001721036,0.0000135475,0.00001288172,0.0004608099,0.000002943489,0.004947691,0.01556367,0.05446554,0.7736822],"study_design_scores_gemma":[0.0001833545,0.0002898594,0.1603021,0.000001469697,0.000006593572,0.00005797685,0.0002361149,0.0002298137,0.004700651,0.6241308,0.2097283,0.0001329133],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2472934,0.00005522275,0.6842728,0.0008383212,0.003315046,0.00005947176,0.000002087389,0.00009184612,0.06407186],"genre_scores_gemma":[0.248033,0.000004494736,0.7476125,0.0009526432,0.0007933952,0.000004453466,3.654056e-7,0.000007812525,0.002591416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7735493,"threshold_uncertainty_score":0.9992875,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1245221009472283,"gpt":0.4010031702919732,"spread":0.2764810693447449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002689239,0.0001324724,0.0003218354,0.00005379704,0.0001673826,0.0001571647,0.0001640038,0.00005655511,0.0003871353],"category_scores_gemma":[0.003715837,0.00009455805,0.00009462005,0.0001692291,0.0001005745,0.0001372869,0.0001920077,0.0001298929,0.00001263921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005247639,"about_ca_system_score_gemma":0.00001255306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006429005,"about_ca_topic_score_gemma":0.000432175,"domain_scores_codex":[0.9990398,0.0002284972,0.0001947203,0.0002451279,0.00006718051,0.0002246783],"domain_scores_gemma":[0.9888704,0.01067628,0.0001003139,0.0002569142,0.00008655532,0.000009557861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005360733,0.00005511312,0.1818185,0.001269296,0.0003160307,0.0002310732,0.0007747877,0.00003117653,0.06632981,0.009081541,0.001967258,0.7375893],"study_design_scores_gemma":[0.003785398,0.0001476334,0.9098356,0.0002503907,0.003511968,0.0002858212,0.002456569,0.01929341,0.01288526,0.01815389,0.02833191,0.001062103],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9517555,0.002261617,0.04053966,0.002664508,0.000713452,0.0003939334,0.000004137106,0.00008008211,0.00158709],"genre_scores_gemma":[0.9916721,0.00001578242,0.005490911,0.002097952,0.0002038673,0.00004845807,0.000008095149,0.00001780218,0.00044503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7365272,"threshold_uncertainty_score":0.4448473,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4818602629013894,"gpt":0.4386533427494478,"spread":0.04320692015194161,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023087,0.0001365482,0.0005451566,0.0000757232,0.00003661224,0.000004414092,0.0002077076,0.0001104546,0.001093657],"category_scores_gemma":[0.005719258,0.000115124,0.00007232241,0.0001177193,0.0001197097,0.00003801406,0.00008276656,0.0001634485,0.000009571268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000102106,"about_ca_system_score_gemma":0.00003549875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002141899,"about_ca_topic_score_gemma":0.00001461452,"domain_scores_codex":[0.9977466,0.001134164,0.0004798247,0.0002559623,0.0001038591,0.0002795557],"domain_scores_gemma":[0.9953585,0.003968145,0.0001598471,0.0003215894,0.0001274188,0.00006445565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006090743,0.00007173358,0.001247085,0.00006593642,0.00004496369,0.0000157281,0.0004816406,0.00000344448,0.002139344,0.9849444,0.00009583669,0.01082896],"study_design_scores_gemma":[0.0002331706,0.00009424124,0.0001270536,0.0000330728,0.00008391097,0.00005273744,0.00009685526,0.005792527,0.005730749,0.9876049,0.00002628425,0.0001245427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01186832,0.00005113753,0.965893,0.00001581234,0.0003130801,0.00009260372,0.00001186278,0.00004534656,0.02170878],"genre_scores_gemma":[0.06293479,0.00000789823,0.9368554,0.00002554776,0.00007742034,0.00001169712,8.413728e-7,0.00001690918,0.00006952935],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05106647,"threshold_uncertainty_score":0.9998195,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.918746052008132,"gpt":0.6893558059739121,"spread":0.2293902460342199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05701825,0.0003228902,0.001390287,0.0001675948,0.0003006976,0.00009650548,0.001336324,0.0003358175,0.0002629937],"category_scores_gemma":[0.5003332,0.0002321059,0.0001619683,0.0002333884,0.0005796097,0.0001247228,0.0005094077,0.0009187646,0.00001241675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001126456,"about_ca_system_score_gemma":0.0001015463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009251228,"about_ca_topic_score_gemma":0.0007141522,"domain_scores_codex":[0.9686999,0.02797033,0.001469911,0.0007637896,0.0002926082,0.000803408],"domain_scores_gemma":[0.7083924,0.2891886,0.0006824357,0.001565117,0.00007596838,0.00009553904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004929897,0.0003769779,0.02743119,0.0001732353,0.0001228149,0.0002086867,0.0009659617,0.0003318671,0.03769069,0.8935692,0.0002013432,0.03843502],"study_design_scores_gemma":[0.001506163,0.00009365105,0.006239912,0.0001050654,0.0001125703,0.0000413259,0.0001300156,0.006769084,0.003294202,0.9813048,0.0001367707,0.0002664664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01968444,0.00006100656,0.9745602,0.0009381879,0.001279552,0.0008113489,0.00001806858,0.00004991569,0.002597263],"genre_scores_gemma":[0.01153765,0.0000124885,0.9874957,0.0003922417,0.0003236956,0.00008618701,5.414395e-7,0.00006075435,0.00009074742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4433149,"threshold_uncertainty_score":0.9709982,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5234643545063861,"gpt":0.570236664049345,"spread":0.04677230954295897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004609252,0.000120303,0.0004998417,0.00008415584,0.0002152179,6.560579e-7,0.00007675887,0.0002414428,0.00006682971],"category_scores_gemma":[0.0004228741,0.0001026514,0.00003704051,0.0001115166,0.00005889005,0.00009986081,0.00004024989,0.0003461875,0.00002958227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001086974,"about_ca_system_score_gemma":0.0002048582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001151366,"about_ca_topic_score_gemma":0.0002490872,"domain_scores_codex":[0.9959462,0.002481227,0.0005644209,0.0001915449,0.0001345792,0.0006820088],"domain_scores_gemma":[0.9979962,0.001159949,0.000258114,0.0001859805,0.0001371777,0.0002626028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00183601,0.0007314523,0.5462573,0.01357823,0.0001440913,0.000002963209,0.3298497,0.001840179,0.007447646,0.03877201,0.03091704,0.0286234],"study_design_scores_gemma":[0.01048893,0.001652074,0.8088602,0.001291554,0.0001978575,0.0000592313,0.02920934,0.07728282,0.002714336,0.0574245,0.009600065,0.001219083],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8103251,0.00375418,0.168768,0.01366961,0.001124919,0.001148526,0.0001006378,0.0001207236,0.0009882799],"genre_scores_gemma":[0.8961152,0.0001879477,0.09319218,0.01021925,0.0001271301,0.0000493813,0.000014335,0.00001716884,0.0000774346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3006404,"threshold_uncertainty_score":0.4186002,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7145503611330684,"gpt":0.5126216750297369,"spread":0.2019286861033315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003792292,0.0000752671,0.0002579882,0.00005645291,0.0001409837,0.000005346398,0.0001994249,0.00003593941,0.00004553019],"category_scores_gemma":[0.01071371,0.00006085554,0.00004052739,0.000140323,0.0001463113,0.00005167042,0.00008858777,0.0001801914,7.922734e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001544445,"about_ca_system_score_gemma":0.00002848946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005194895,"about_ca_topic_score_gemma":0.000103446,"domain_scores_codex":[0.9973303,0.001883564,0.0003421588,0.0001833784,0.0001052873,0.0001552898],"domain_scores_gemma":[0.969035,0.03054313,0.0001415816,0.000206609,0.00005196215,0.00002176101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003028824,0.00004806882,0.0006539764,0.00004693721,0.000008890033,0.000001827637,0.003553926,0.003812994,0.0005673649,0.9890217,0.0003578534,0.001896152],"study_design_scores_gemma":[0.0002891451,0.0001209444,0.00277451,0.000008726473,0.00003044962,0.00001357618,0.002527813,0.01550156,0.00007865488,0.977871,0.0007169135,0.00006670495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01995404,0.00006225411,0.9781399,0.0009493476,0.0001409772,0.0005074946,0.0001163346,0.000009870957,0.0001197646],"genre_scores_gemma":[0.108652,0.000006530053,0.8905954,0.0002111133,0.00001054392,0.0002744086,0.000004784199,0.000008317439,0.0002369366],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08869793,"threshold_uncertainty_score":0.9976195,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9429413618181373,"gpt":0.7269228172101364,"spread":0.2160185446080009,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02607555,0.000176008,0.001680528,0.0006931226,0.00006167182,0.00000332642,0.00008297031,0.0002684876,0.0008254735],"category_scores_gemma":[0.1555348,0.0001321032,0.0002496402,0.000552477,0.0001190359,0.00003516461,0.00009758919,0.0005401062,0.000185614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001374332,"about_ca_system_score_gemma":0.0004916231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004337819,"about_ca_topic_score_gemma":0.0001363408,"domain_scores_codex":[0.9787652,0.01916338,0.0009266217,0.0005197719,0.00009041589,0.0005345867],"domain_scores_gemma":[0.9448736,0.05417776,0.000150355,0.0004479415,0.0001269685,0.0002233154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.04800712,0.0009510014,0.07708868,0.001138011,0.01145127,0.00179803,0.002896726,0.0003614126,0.5423359,0.09453091,0.190571,0.02886998],"study_design_scores_gemma":[0.0084472,0.002023525,0.4251207,0.0001559442,0.01264017,0.001400378,0.002000174,0.001010853,0.020475,0.007917729,0.5181105,0.0006978816],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3762614,0.00267173,0.3054239,0.309626,0.0009033732,0.001379569,0.000003478227,0.0001400725,0.003590486],"genre_scores_gemma":[0.07632083,0.00003414566,0.8369951,0.08135121,0.00008044067,0.0002221371,0.000004383465,0.0000157626,0.004976],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5315711,"threshold_uncertainty_score":0.9038355,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Citation; License; Library science; XML; Download; Computer science; Editor in chief; World Wide Web; Management; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.3201864956255316,"gpt":0.5072122021254595,"spread":0.1870257064999279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004762717,0.0001212695,0.0002893494,0.0001064699,0.0002376385,0.000009026984,0.0007546543,0.0001040143,0.05026189],"category_scores_gemma":[0.0005230467,0.00009680606,0.00006394231,0.0003343084,0.00009876704,0.00002550839,0.0004939364,0.001117737,0.0003429925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000162407,"about_ca_system_score_gemma":0.000125088,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009800836,"about_ca_topic_score_gemma":0.0004742241,"domain_scores_codex":[0.9880248,0.01031501,0.0003352985,0.0004128918,0.0003088098,0.0006031865],"domain_scores_gemma":[0.9925765,0.006512702,0.00008667792,0.0006765496,0.00001064765,0.0001368847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005363534,0.0002002402,0.02439204,0.000009758016,0.00006552187,0.0002528793,0.008154105,0.00001917073,0.0004669454,0.02695137,0.8557314,0.08322026],"study_design_scores_gemma":[0.0009112958,0.0002217304,0.1110397,0.000002140938,0.000006434238,0.00002527844,0.001824933,0.00001230917,0.00006103613,0.02711909,0.8586766,0.00009950606],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4096134,0.01100762,0.0233937,0.2311393,0.1804482,0.003354843,0.0004842853,0.0003551493,0.1402035],"genre_scores_gemma":[0.3972133,0.0002496577,0.1832382,0.07278691,0.104753,0.003482958,0.0004907636,0.0004357506,0.2373495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1598445,"threshold_uncertainty_score":0.996793,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}