{"meta":{"query_hash":"59d05407f7d7","filters":{"venue":"Meta-Psychology"},"cohort_total":15,"direct_labels_cover":0,"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/59d05407f7d7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Meta-Psychology"},"results":[{"id":"W2915455637","doi":"10.15626/mp.2018.843","title":"A Brief Guide to Evaluate Replications","year":2019,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Meta-analysis and systematic reviews","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":"Western University","funders":"","keywords":"Replication (statistics); Transparency (behavior); Independence (probability theory); Computer science; Similarity (geometry); Research design; Psychology; Statistics; Artificial intelligence; Mathematics; Computer security","score_opus":0.8534897186781798,"score_gpt":0.6528829468946589,"score_spread":0.20060677178352093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915455637","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":[0.09121804,0.0023284242,0.11871169,0.058060788,0.0018580362,0.0032266367,0.000043202966,0.000037357655,0.7245158],"genre_scores_gemma":[0.32583946,0.000040373525,0.06468218,0.063923724,0.0002390996,0.00083229924,0.000019220177,0.000050829218,0.54437286],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97541493,0.0101677235,0.00841983,0.0021484017,0.003450798,0.0003983247],"domain_scores_gemma":[0.98158437,0.0021090202,0.0023815334,0.012371964,0.0013091109,0.00024401267],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.1272678,0.00030358677,0.0042167874,0.00054755283,0.00009063977,0.000318553,0.002883065,0.00011461753,0.1438041],"category_scores_gemma":[0.028392956,0.00014377806,0.002519505,0.0020941086,0.000044685814,0.00013254647,0.00018854285,0.00015289609,0.18515998],"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":[0.0000066191237,0.000053884836,0.004139873,0.0000043980817,0.0010769329,0.000002185167,0.00012230543,0.00004975092,0.0010911335,0.004553144,0.9656626,0.023237167],"study_design_scores_gemma":[0.00019002997,0.000061591294,0.03375987,0.0000018868533,0.001091104,0.000026722388,0.000025499241,0.0002413702,0.000020471607,0.0071664522,0.9572689,0.0001460868],"about_ca_topic_score_codex":0.00001586258,"about_ca_topic_score_gemma":0.00002709265,"teacher_disagreement_score":0.2346214,"about_ca_system_score_codex":0.000017831915,"about_ca_system_score_gemma":0.000044587287,"threshold_uncertainty_score":0.9797913},"labels":[],"label_agreement":null},{"id":"W3030972095","doi":"10.15626/mp.2018.874","title":"Estimating Population Mean Power Under Conditions of Heterogeneity and Selection for Significance","year":2020,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":81,"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","funders":"University of Toronto Mississauga; University of Toronto","keywords":"Statistics; Sample size determination; Mathematics; Population; Statistical power; Replication (statistics); Statistical significance; Power (physics); Selection (genetic algorithm); Statistical hypothesis testing; Econometrics; Sample (material); Set (abstract data type); Demography; Computer science","score_opus":0.8026212016523445,"score_gpt":0.5861197031220517,"score_spread":0.21650149853029277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030972095","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":[0.42990923,0.00034001653,0.5658498,0.0026284943,0.00015174809,0.00059970154,0.000041062736,0.000007145998,0.00047281187],"genre_scores_gemma":[0.9592785,0.0000020215007,0.03873875,0.0017517898,0.000041949508,0.00007240704,0.000013439066,0.000008069647,0.00009305381],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99242324,0.0026068953,0.0033289948,0.00072652026,0.0007742422,0.00014008838],"domain_scores_gemma":[0.99539006,0.0012376562,0.0021995553,0.0006162267,0.000463979,0.000092549075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015197067,0.00016233999,0.002011152,0.00013709425,0.000109363165,0.00008827395,0.00033870962,0.00007721407,0.0022981619],"category_scores_gemma":[0.006050619,0.000090949005,0.0008094744,0.0006045742,0.000055511096,0.00012964956,0.000026828093,0.00007237101,0.000087069544],"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":[0.00025676348,0.0007831965,0.47532922,0.0006746714,0.019095298,0.000004246079,0.004327067,0.0290678,0.1376724,0.071895614,0.205902,0.054991733],"study_design_scores_gemma":[0.0014107991,0.000702395,0.7059123,0.000017052676,0.006877794,0.000047290472,0.0003158118,0.14215577,0.0011323041,0.108329244,0.03244835,0.0006508935],"about_ca_topic_score_codex":0.000009053762,"about_ca_topic_score_gemma":0.000038618884,"teacher_disagreement_score":0.5293693,"about_ca_system_score_codex":0.000006554323,"about_ca_system_score_gemma":0.000010046381,"threshold_uncertainty_score":0.9986139},"labels":[],"label_agreement":null},{"id":"W3039001205","doi":"10.15626/mp.2019.1992","title":"Multiplicity Control vs Replication","year":2020,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Probability and Risk Models","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":"York University","funders":"","keywords":"Multiplicity (mathematics); Replication (statistics); Multiplicity of infection; Computer science; Mathematics; Biology; Statistics; Genetics; In vitro; Geometry","score_opus":0.5084974778146327,"score_gpt":0.49536236048173293,"score_spread":0.013135117332899793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039001205","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":[0.10152991,0.00077473256,0.67997,0.20547706,0.00051636895,0.00072515535,0.00007194364,0.00021266982,0.01072214],"genre_scores_gemma":[0.950846,0.000020533544,0.002844457,0.04582332,0.00013159007,0.00006949522,0.0000032675698,0.0000088713505,0.00025243344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964249,0.0007450539,0.000778068,0.00121408,0.0005666148,0.00027127005],"domain_scores_gemma":[0.996685,0.00081647164,0.00026617738,0.0017868858,0.00024366517,0.00020174492],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003748457,0.0001578532,0.00066361506,0.00008356468,0.00012221611,0.000060041577,0.0010731849,0.00017125289,0.0013646361],"category_scores_gemma":[0.0056901583,0.00010077135,0.00034211832,0.0005534536,0.00018292651,0.00019545408,0.00008985644,0.00024470562,0.0023971836],"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":[0.003041605,0.0012069902,0.04601913,0.00002085766,0.0019298685,0.00004599281,0.0037098199,0.0028767346,0.037801452,0.037995595,0.35670194,0.50865],"study_design_scores_gemma":[0.002036,0.00034323882,0.0954628,7.6341416e-7,0.00035495815,0.000016508855,0.000023289924,0.015511844,0.0006978235,0.18023008,0.7050272,0.00029544331],"about_ca_topic_score_codex":0.000016640452,"about_ca_topic_score_gemma":0.000014834525,"teacher_disagreement_score":0.8493161,"about_ca_system_score_codex":0.000009657638,"about_ca_system_score_gemma":0.0000246619,"threshold_uncertainty_score":0.99954826},"labels":[],"label_agreement":null},{"id":"W3135512811","doi":"10.15626/mp.2019.1645","title":"The Validation Crisis in Psychology","year":2021,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; University of Toronto Mississauga; University of Toronto","keywords":"Nomological network; Construct (python library); Construct validity; Cronbach's alpha; Psychology; Criterion validity; External validity; Metatheory; Predictive validity; Incremental validity; Psychometrics; Structural equation modeling; Social psychology; Computer science; Developmental psychology; Machine learning","score_opus":0.3490952054780505,"score_gpt":0.5715458269845495,"score_spread":0.22245062150649897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135512811","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":[0.15735136,0.04168805,0.00397775,0.31777626,0.01597501,0.0019238825,0.00007296463,0.00027521304,0.46095952],"genre_scores_gemma":[0.8507349,0.0063041453,0.0038997997,0.10713864,0.0011621288,0.0026262503,0.00020320038,0.00020069882,0.027730277],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99351835,0.0030614259,0.0008945133,0.0010313564,0.00036314927,0.0011312052],"domain_scores_gemma":[0.99695516,0.00060961826,0.0001838156,0.0018900195,0.00015865504,0.00020274082],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026829904,0.00027322094,0.000600559,0.00025676156,0.00024634527,0.000046475405,0.0007062502,0.00039858156,0.012600689],"category_scores_gemma":[0.00031630255,0.00020606311,0.00023837903,0.0009354934,0.0002432322,0.00008549315,0.00014229836,0.00090883276,0.0030122148],"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":[0.00075208704,0.0017071101,0.013090516,0.000048125497,0.0016515341,0.0012897694,0.0014978317,0.0000032187631,0.0016607264,0.043830115,0.61277217,0.3216968],"study_design_scores_gemma":[0.0017394931,0.00022862814,0.10528322,0.0000032409932,0.00012969408,0.00026831895,0.00030444606,0.0000039773336,0.0003047508,0.018107537,0.8734129,0.00021380937],"about_ca_topic_score_codex":0.00014139648,"about_ca_topic_score_gemma":0.00046171498,"teacher_disagreement_score":0.6933835,"about_ca_system_score_codex":0.00006502139,"about_ca_system_score_gemma":0.00008001326,"threshold_uncertainty_score":0.99776405},"labels":[],"label_agreement":null},{"id":"W3198867954","doi":"10.15626/mp.2020.2506","title":"What to make of equivalence testing with a post-specified margin?","year":2021,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","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":"Margin (machine learning); Equivalence (formal languages); Frequentist inference; Post hoc; Statistical hypothesis testing; Computer science; Econometrics; Mathematics; Statistics; Machine learning; Artificial intelligence; Bayesian probability; Medicine; Bayesian inference","score_opus":0.8258386333211938,"score_gpt":0.6156700248907838,"score_spread":0.21016860843040996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198867954","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":[0.09944557,0.0013887373,0.84288526,0.021668922,0.004187721,0.0016496319,0.00022473492,0.0002600442,0.028289411],"genre_scores_gemma":[0.012488746,0.000050853498,0.9814989,0.0047565624,0.00016582172,0.00008772543,0.000001480232,0.00004990491,0.00090001913],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596673,0.001346258,0.0010957182,0.000740532,0.00040719786,0.0004435752],"domain_scores_gemma":[0.962277,0.035305165,0.00035598417,0.001203404,0.00067236705,0.00018609011],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003040569,0.00025817228,0.001420514,0.00009937153,0.000042168227,0.00004431875,0.00042107547,0.00018257693,0.0022243904],"category_scores_gemma":[0.08739571,0.00019023131,0.00020505025,0.0007113859,0.00021781893,0.00006997745,0.00019644374,0.00032229995,0.00010080415],"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":[0.0038513313,0.003917559,0.0023804868,0.0011941895,0.0074361516,0.0023722912,0.0015742136,0.000019569445,0.09283659,0.33029857,0.012714991,0.54140407],"study_design_scores_gemma":[0.002188158,0.0015713755,0.011870046,0.00024967632,0.0022157212,0.00025877106,0.00026842186,0.000014153516,0.0089241695,0.963473,0.008414783,0.00055169594],"about_ca_topic_score_codex":0.0000036473375,"about_ca_topic_score_gemma":0.000016717337,"teacher_disagreement_score":0.6331744,"about_ca_system_score_codex":0.000014530268,"about_ca_system_score_gemma":0.00006747173,"threshold_uncertainty_score":0.9986877},"labels":[],"label_agreement":null},{"id":"W4226236655","doi":"10.15626/mp.2020.2595","title":"Tutorial in Longitudinal Measurement Invariance and Cross-lagged Panel Models Using Lavaan","year":2022,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Psychological Well-being and Life Satisfaction","field":"Psychology","cited_by":76,"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; Dalhousie University","funders":"","keywords":"Structural equation modeling; Measurement invariance; Latent variable; Computer science; Panel data; Syntax; Econometrics; Process (computing); Test (biology); Interpretation (philosophy); Mathematics; Confirmatory factor analysis; Artificial intelligence; Machine learning; Programming language","score_opus":0.5074782751927323,"score_gpt":0.4361204782108346,"score_spread":0.07135779698189765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226236655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9397391,0.0037189107,0.008113062,0.0013206506,0.010570213,0.0007233852,0.000055639077,0.0001844276,0.035574604],"genre_scores_gemma":[0.9960282,0.000037909103,0.0006900579,0.0020586394,0.00042728658,0.00032955283,0.000011067671,0.000042820557,0.00037445655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995099,0.0015794951,0.0007602516,0.001256011,0.0005687669,0.00073646376],"domain_scores_gemma":[0.99859565,0.00013619948,0.00028048584,0.0007552091,0.00008197362,0.00015048275],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003176819,0.00036831014,0.0007644524,0.00032273598,0.0003886387,0.000054946937,0.0003993866,0.00026841386,0.0043984246],"category_scores_gemma":[0.00010716762,0.00034844165,0.00019139353,0.0005304298,0.00023002387,0.0001641403,0.00017054996,0.00097183266,0.000058494257],"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":[0.019969614,0.011194583,0.58251953,0.00016473384,0.012525804,0.0036759083,0.017649908,0.034758534,0.05596066,0.13623178,0.0523241,0.073024824],"study_design_scores_gemma":[0.009542273,0.0011602234,0.87982166,0.000012844637,0.0008044144,0.0009580481,0.0002781312,0.0012785089,0.000041200205,0.049666405,0.055300925,0.0011353479],"about_ca_topic_score_codex":0.0009671885,"about_ca_topic_score_gemma":0.00010366881,"teacher_disagreement_score":0.29730213,"about_ca_system_score_codex":0.00017359521,"about_ca_system_score_gemma":0.00003876567,"threshold_uncertainty_score":0.99989676},"labels":[],"label_agreement":null},{"id":"W4294233607","doi":"10.15626/mp.2021.2720","title":"Z-curve 2.0: Estimating Replication Rates and Discovery Rates","year":2022,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","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":"University of Toronto","funders":"","keywords":"Replication (statistics); Confidence interval; False discovery rate; Statistics; Selection (genetic algorithm); False positive paradox; Multiple comparisons problem; Computer science; Range (aeronautics); Extension (predicate logic); Statistical power; Econometrics; Mathematics; Artificial intelligence; Biology; Engineering","score_opus":0.7276317683307449,"score_gpt":0.64387429511749,"score_spread":0.083757473213255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294233607","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":[0.06307341,0.0007893696,0.9164829,0.011457492,0.002408108,0.0011095864,0.000275743,0.00024594093,0.0041574053],"genre_scores_gemma":[0.051939037,0.00002354443,0.9439685,0.0024910863,0.00022301392,0.0005782188,0.000010888531,0.00004708385,0.0007186732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951055,0.0026026706,0.0009406981,0.00079952495,0.00025420057,0.00029741292],"domain_scores_gemma":[0.9731434,0.025206797,0.00045622478,0.0010559376,0.00005755076,0.00008010906],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007435662,0.0002077712,0.0008794412,0.00008822545,0.00024692246,0.000053718173,0.0003175724,0.00009464981,0.0013654961],"category_scores_gemma":[0.06030139,0.0001702773,0.00016392922,0.000266899,0.00021237647,0.000099410674,0.00029144812,0.00043430118,0.000022454076],"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":[0.00092316774,0.0018143227,0.008078642,0.0003717468,0.004676923,0.00011548242,0.0011167035,0.00007334703,0.0095647955,0.7168034,0.10273095,0.15373056],"study_design_scores_gemma":[0.0006487608,0.00023095231,0.002684729,0.000003819187,0.0007278182,0.000045088378,0.000029889849,0.0006837421,0.0003296986,0.9889766,0.0054431427,0.00019574638],"about_ca_topic_score_codex":0.000008719313,"about_ca_topic_score_gemma":0.000001840573,"teacher_disagreement_score":0.27217326,"about_ca_system_score_codex":0.000023151057,"about_ca_system_score_gemma":0.000020624444,"threshold_uncertainty_score":0.99954736},"labels":[],"label_agreement":null},{"id":"W4308725914","doi":"10.15626/mp.2021.2803","title":"Meta-Analytic Findings of the Self-Controlled Motor Learning Literature: Underpowered, Biased, and Lacking Evidential Value","year":2022,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Ottawa","funders":"","keywords":"Moderation; Psychology; Selection bias; Robustness (evolution); Publication bias; Meta-analysis; Statistics; Social psychology; Medicine; Mathematics; Internal medicine","score_opus":0.3099148603923441,"score_gpt":0.382829465661358,"score_spread":0.07291460526901389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308725914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90097266,0.06380782,0.00019615419,0.014300954,0.0048474274,0.0020436717,0.00014411451,0.00025880066,0.013428381],"genre_scores_gemma":[0.9879964,0.00014201624,0.0002125563,0.004071607,0.000118455544,0.0006041008,0.000009872935,0.000043078104,0.006801935],"study_design_codex":"meta_analysis","study_design_gemma":"observational","domain_scores_codex":[0.9936996,0.003131375,0.0009856711,0.0010358001,0.00051968946,0.00062782486],"domain_scores_gemma":[0.9977656,0.00063250324,0.00057421013,0.0008204072,0.00009875677,0.00010854041],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024022153,0.00048945163,0.0020678802,0.00025517205,0.0006836542,0.00006344779,0.0007929711,0.00024532684,0.011567736],"category_scores_gemma":[0.000164446,0.00028416968,0.0017848816,0.0009208495,0.00037166986,0.00008405006,0.00047231303,0.0013104811,0.00006055085],"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":[0.021221826,0.012313168,0.14501481,0.00029132012,0.5487448,0.0013974984,0.033892117,0.00055834744,0.02690221,0.08916464,0.1023322,0.01816707],"study_design_scores_gemma":[0.026836285,0.0053898487,0.4294201,0.00002385674,0.19573338,0.001176626,0.0013142151,0.000074721625,0.00012591654,0.018225519,0.3196614,0.0020181173],"about_ca_topic_score_codex":0.00008331549,"about_ca_topic_score_gemma":0.000011330751,"teacher_disagreement_score":0.35301143,"about_ca_system_score_codex":0.00003671083,"about_ca_system_score_gemma":0.000016437476,"threshold_uncertainty_score":0.999961},"labels":[],"label_agreement":null},{"id":"W4383908607","doi":"10.15626/mp.2021.2938","title":"A critical re-analysis of six implicit learning papers","year":2023,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Innovative Teaching and Learning Methods","field":"Psychology","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":"McMaster University","funders":"","keywords":"Pairwise comparison; Contrast (vision); Statistics; Psychology; Mathematics; Computer science; Econometrics; Artificial intelligence","score_opus":0.19468294443366635,"score_gpt":0.5180829281699013,"score_spread":0.32339998373623496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383908607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51120216,0.0006817307,0.021561781,0.008209346,0.0023578964,0.0002551428,0.000038433085,0.0009512055,0.4547423],"genre_scores_gemma":[0.98583996,0.000011684295,0.0027564138,0.0023699047,0.00012644312,0.00009033915,0.00006094445,0.00005748184,0.008686846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.992562,0.0047777286,0.0007869974,0.000852397,0.0002800937,0.0007408064],"domain_scores_gemma":[0.9961832,0.0023575497,0.000268991,0.00090487325,0.0001848245,0.00010053542],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006625067,0.0002983583,0.0013720058,0.0015623254,0.00017369179,0.000016547583,0.00043297908,0.0003477466,0.016214935],"category_scores_gemma":[0.0029764557,0.00025585946,0.00082096976,0.0045499476,0.00036105764,0.00004358906,0.000086289045,0.0011890857,0.0009506562],"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":[0.0011587194,0.0014609423,0.18222459,0.00011658627,0.1559225,0.00064245,0.034695107,0.0025188287,0.1418988,0.20653822,0.07105106,0.20177221],"study_design_scores_gemma":[0.00059829315,0.00042960214,0.7303863,0.00000405883,0.01087194,0.00001849719,0.0007940551,0.00015867068,0.00007343597,0.0011482225,0.25515044,0.00036649941],"about_ca_topic_score_codex":0.00013921045,"about_ca_topic_score_gemma":0.00001467908,"teacher_disagreement_score":0.5481617,"about_ca_system_score_codex":0.000017628501,"about_ca_system_score_gemma":0.000018044446,"threshold_uncertainty_score":0.9999894},"labels":[],"label_agreement":null},{"id":"W4387116974","doi":"10.15626/mp.2023.4020","title":"A Plea to Psychology Professional Societies that Publish Journals: Assess Computational Reproducibility","year":2023,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"scientometrics and bibliometrics research","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 Victoria","funders":"","keywords":"Plea; Publication; Reproducibility; Psychology; Applied psychology; Political science; Law; Mathematics; Statistics","score_opus":0.9415478893122667,"score_gpt":0.728999741796331,"score_spread":0.21254814751593576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387116974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61224556,0.0019720092,0.046274543,0.30572176,0.012533411,0.0012701368,0.00029407878,0.00035047726,0.019338042],"genre_scores_gemma":[0.9314603,0.00032473187,0.014513681,0.03094783,0.0006617408,0.0003560936,0.00007481842,0.000061990504,0.021598773],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9793342,0.0027436146,0.0017683737,0.0040859315,0.010566524,0.0015013589],"domain_scores_gemma":[0.98288405,0.007389652,0.0005935253,0.003422389,0.0049312357,0.00077915326],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","insufficient_payload"],"category_scores_codex":[0.11937234,0.00034800058,0.001125819,0.041367635,0.0006105331,0.001987144,0.004528896,0.00041979208,0.009483469],"category_scores_gemma":[0.08018442,0.00023159389,0.0006321585,0.14779978,0.0005005564,0.00092605554,0.0015373698,0.0010005754,0.0042569917],"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":[0.000068243215,0.00033669043,0.08249592,0.0000043348236,0.00025121338,0.00003557392,0.00020511782,0.00014916093,0.00031217915,0.00040086466,0.8735426,0.0421981],"study_design_scores_gemma":[0.0005116293,0.00014778701,0.687478,0.0000028452964,0.00003824623,0.000050178343,0.00020198499,0.00035021093,0.00004318396,0.09205174,0.21890283,0.00022139077],"about_ca_topic_score_codex":0.000011356379,"about_ca_topic_score_gemma":0.000011474239,"teacher_disagreement_score":0.6546398,"about_ca_system_score_codex":0.000078450066,"about_ca_system_score_gemma":0.00033289773,"threshold_uncertainty_score":0.9990489},"labels":[],"label_agreement":null},{"id":"W4394955471","doi":"10.15626/mp.2021.2918","title":"Associations between Goal Orientation and Self-Regulated Learning Strategies are Stable across Course Types, Underrepresented Minority Status, and Gender","year":2024,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Innovative Teaching and Learning Methods","field":"Psychology","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":"Goal orientation; Psychology; Underrepresented Minority; Orientation (vector space); Future orientation; Social psychology; Medical education; Mathematics; Medicine","score_opus":0.13543207344279207,"score_gpt":0.4753749570623645,"score_spread":0.3399428836195724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394955471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96711373,0.0055703116,0.014795432,0.0007306794,0.0009779978,0.00024648747,0.00014568283,0.0005598537,0.009859835],"genre_scores_gemma":[0.9948059,0.0000512114,0.0021195915,0.00015802988,0.00021430802,0.00003081833,0.00026432323,0.00004334102,0.002312493],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99523693,0.0026787936,0.00043840765,0.00082484697,0.00019662481,0.000624385],"domain_scores_gemma":[0.99850136,0.000685197,0.00023590661,0.00031518057,0.00015700105,0.00010537275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029886947,0.00028485028,0.0005822243,0.00017203133,0.00042835585,0.00022531925,0.00010946934,0.0003473815,0.00040422849],"category_scores_gemma":[0.00020627647,0.00025860895,0.000082754406,0.0005877947,0.00020879552,0.00023212073,0.0000655633,0.0011314828,0.000058556536],"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":[0.00007291733,0.00030036434,0.91899407,0.000080931706,0.008890096,0.00005601568,0.03090991,0.00008871355,0.0004786456,0.014828428,0.0053107617,0.019989131],"study_design_scores_gemma":[0.0006484341,0.00012218299,0.96526164,0.0000055471255,0.0010669649,0.0000187965,0.0019787857,0.000096348886,0.000006973162,0.0032570034,0.027291477,0.00024582684],"about_ca_topic_score_codex":0.00045829391,"about_ca_topic_score_gemma":0.00006252159,"teacher_disagreement_score":0.046267577,"about_ca_system_score_codex":0.000053833068,"about_ca_system_score_gemma":0.000058965357,"threshold_uncertainty_score":0.9999866},"labels":[],"label_agreement":null},{"id":"W4398239542","doi":"10.15626/mp.2018.1479","title":"How Close to the Mark Might Published Heritability Estimates Be?","year":2024,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Heritability; Genealogy; Econometrics; History; Evolutionary biology; Biology; Mathematics","score_opus":0.10560242464394395,"score_gpt":0.3824294459025446,"score_spread":0.2768270212586006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398239542","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":[0.28388944,0.017659413,0.0039639566,0.5056866,0.010932195,0.0017774208,0.00034319088,0.0010400255,0.17470774],"genre_scores_gemma":[0.9701037,0.0000129411,0.0020920122,0.014758974,0.0007449023,0.00093201327,0.00003914463,0.000083904604,0.011232425],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964503,0.0006656881,0.00047971625,0.001345479,0.0002458708,0.0008129677],"domain_scores_gemma":[0.9959289,0.0021040328,0.00007613881,0.0015138028,0.00018823153,0.00018891424],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020207858,0.0004037001,0.0006450255,0.00019663575,0.00020490782,0.00048964185,0.0006938156,0.00022500545,0.0146172345],"category_scores_gemma":[0.0019088851,0.00025398022,0.00046793962,0.0008185837,0.00033081527,0.00023852079,0.00021541039,0.0006247551,0.0010174512],"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":[0.00025868136,0.00059296674,0.009611666,0.00012001677,0.004094529,0.00035555146,0.0049750176,0.0000014393108,0.00080298533,0.034420103,0.723352,0.22141501],"study_design_scores_gemma":[0.00031248035,0.00025413293,0.089323156,0.00001030562,0.0007447978,0.00017011187,0.0004945659,0.000020443054,0.00004056695,0.017736472,0.89057475,0.0003181989],"about_ca_topic_score_codex":0.00016913249,"about_ca_topic_score_gemma":0.00024927518,"teacher_disagreement_score":0.6862142,"about_ca_system_score_codex":0.000037602764,"about_ca_system_score_gemma":0.00003512723,"threshold_uncertainty_score":0.99999124},"labels":[],"label_agreement":null},{"id":"W4406183016","doi":"10.15626/mp.2021.2757","title":"The Devil is Mainly in the Nuisance Parameters: Performance of Structural Fit Indices Under Misspecified Structural Models in SEM","year":2024,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Multi-Criteria Decision Making","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":"Nuisance; Structural equation modeling; Econometrics; Nuisance parameter; Statistics; Mathematics; Economics; Political science; Law","score_opus":0.5075904091821208,"score_gpt":0.5103925816882979,"score_spread":0.002802172506177092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406183016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98522246,0.0050314106,0.0006887632,0.0061622625,0.0013764802,0.00039676705,0.000035296776,0.000023619705,0.0010629393],"genre_scores_gemma":[0.9935976,0.00011799193,0.002474198,0.003467675,0.00006616281,0.000047069883,0.0000019083375,0.000022298318,0.00020507569],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99399614,0.0012413365,0.0016507313,0.0010109781,0.0014890282,0.0006117947],"domain_scores_gemma":[0.99325705,0.004688425,0.0002917951,0.0015634851,0.00013855199,0.000060717615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005876569,0.0003483044,0.0007766191,0.0006238572,0.00018085452,0.00054037414,0.0028760293,0.00020028072,0.00085284107],"category_scores_gemma":[0.00056074746,0.00016389613,0.00029993337,0.0019594848,0.0004882704,0.0006704945,0.00022142363,0.0006736026,0.00010602396],"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":[0.0028264083,0.00020182629,0.03875948,0.00014464604,0.0017095424,0.0005105162,0.05985721,0.045181714,0.005234692,0.046623394,0.043230698,0.7557199],"study_design_scores_gemma":[0.0013526895,0.00020591829,0.44393915,0.000078899786,0.00014830807,0.00023682672,0.002623424,0.21457805,0.00045287993,0.31565687,0.02014486,0.000582121],"about_ca_topic_score_codex":0.00004949495,"about_ca_topic_score_gemma":0.00031648544,"teacher_disagreement_score":0.75513774,"about_ca_system_score_codex":0.000045220906,"about_ca_system_score_gemma":0.00006188781,"threshold_uncertainty_score":0.9338012},"labels":[],"label_agreement":null},{"id":"W4409214529","doi":"10.15626/mp.2025.4708","title":"Reality Television Shows Focusing on Sexual Relationships and College Students Engagement in One-Night Stands: A Replication Report","year":2025,"lang":"en","type":"preprint","venue":"Meta-Psychology","topic":"Asian Culture and Media Studies","field":"Social 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":"Replication (statistics); Psychology; Reality television; Sociology; Media studies; Medicine","score_opus":0.34444033996682266,"score_gpt":0.48760139579806927,"score_spread":0.1431610558312466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409214529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.529823,0.0070634587,0.0041046455,0.082560904,0.004860833,0.009272752,0.00055180915,0.00043660335,0.36132598],"genre_scores_gemma":[0.98338246,0.0017366436,0.001847969,0.0012038236,0.00045542815,0.0007867201,0.00013556435,0.000018770452,0.010432601],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943678,0.0024394384,0.0008266006,0.0013318062,0.00069111807,0.00034327485],"domain_scores_gemma":[0.99765044,0.00046324584,0.0004923513,0.0011141686,0.00017798261,0.00010181356],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009454237,0.0002819882,0.0008275418,0.00028004096,0.0006875523,0.000059216898,0.00039189568,0.00056081597,0.000057778154],"category_scores_gemma":[0.0028812776,0.00024726545,0.000113139984,0.00036264208,0.00024987658,0.00007567108,0.00045456341,0.0011847267,0.0000062569425],"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":[0.0011583507,0.00426579,0.32543823,0.00067186996,0.008096906,0.00087788317,0.34903792,0.000058295263,0.0002173615,0.04790333,0.16234879,0.099925295],"study_design_scores_gemma":[0.0011638597,0.00018499642,0.41130507,0.00021108278,0.0016909264,0.0000071880804,0.018043676,0.0000031887957,0.000031515225,0.012203617,0.5545492,0.0006056797],"about_ca_topic_score_codex":0.00044036203,"about_ca_topic_score_gemma":0.009340819,"teacher_disagreement_score":0.4535595,"about_ca_system_score_codex":0.00025794248,"about_ca_system_score_gemma":0.00020458987,"threshold_uncertainty_score":0.999998},"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}]}