{"meta":{"query_hash":"b6f3f6bdb720","filters":{"venue":"Psychological Methods"},"cohort_total":95,"direct_labels_cover":1,"predictions_cover":95,"exported":95,"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/b6f3f6bdb720","api":"https://metacan.xera.ac/api/v1/cohort?venue=Psychological+Methods"},"results":[{"id":"W1964275428","doi":"10.1037/1082-989x.7.2.210","title":"When constraints interact: A caution about reference variables, identification constraints, and scale dependencies in structural equation modeling.","year":2002,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structural equation modeling; Latent variable; Identification (biology); Variable (mathematics); Computer science; Econometrics; Scale (ratio); Latent variable model; Instrumental variable; Mathematical optimization; Software; Mathematics; Artificial intelligence; Machine learning","score_opus":0.21359218176728356,"score_gpt":0.4363520711109367,"score_spread":0.22275988934365315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964275428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6879764,0.0006155782,0.27930024,0.0002556262,0.00048703398,0.00037046155,0.00003082097,0.00009291408,0.030870881],"genre_scores_gemma":[0.9271901,0.000036747137,0.07218887,0.00021781182,0.00005724237,0.00008074833,0.000021597896,0.0000116092,0.00019522617],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970094,0.001064941,0.0006539257,0.0007252779,0.0001568846,0.00038954735],"domain_scores_gemma":[0.99817455,0.0011063501,0.00018450522,0.00029016368,0.00014158453,0.00010285018],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017354569,0.00021411754,0.00029838693,0.00014377068,0.00012394265,0.00009365268,0.00017386021,0.00025822752,0.006912554],"category_scores_gemma":[0.0014948703,0.00019105188,0.000048071215,0.00020165778,0.0005214209,0.0001922347,0.00006119823,0.000481488,0.000053032792],"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":[0.0000601223,0.00016093155,0.011295036,0.000020164296,0.00002189249,0.000012187354,0.0048728515,0.000027016677,0.0030707375,0.018881105,0.000049703547,0.96152824],"study_design_scores_gemma":[0.0032757742,0.0004885889,0.46756223,0.00028206478,0.000096134136,0.0006371076,0.0099329995,0.24773178,0.00020619242,0.26844716,0.0002606507,0.0010793302],"about_ca_topic_score_codex":0.00020696818,"about_ca_topic_score_gemma":0.0000352251,"teacher_disagreement_score":0.9604489,"about_ca_system_score_codex":0.000071701055,"about_ca_system_score_gemma":0.000006351414,"threshold_uncertainty_score":0.99399525},"labels":[],"label_agreement":null},{"id":"W1966359789","doi":"10.1037/1082-989x.12.4.399","title":"Toward using confidence intervals to compare correlations.","year":2007,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":758,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Statistics; Robust confidence intervals; Mathematics; Sample size determination; Dependency (UML); Correlation; Nominal level; Sampling (signal processing); Confidence distribution; Sample (material); Econometrics; Computer science; Artificial intelligence","score_opus":0.915936087266207,"score_gpt":0.7443180110581955,"score_spread":0.1716180762080115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966359789","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":[0.025327602,0.000040201518,0.96075314,0.0005206976,0.0022221082,0.00066844875,0.000017511495,0.0002341467,0.010216124],"genre_scores_gemma":[0.11708707,0.000003497593,0.88051605,0.0018735718,0.00035021623,0.00002039245,4.9654824e-7,0.000030880656,0.00011783004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934767,0.0030960476,0.001614716,0.00076377584,0.00041256886,0.000636223],"domain_scores_gemma":[0.9027226,0.09551849,0.00031949137,0.0007088883,0.00022989554,0.00050063705],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020980999,0.0002963858,0.0009653323,0.00014665945,0.000113243135,0.000057130732,0.0006240472,0.00022841204,0.001776686],"category_scores_gemma":[0.2010913,0.00023161687,0.00024217005,0.00069476746,0.00027161004,0.0000603097,0.00022242389,0.00061522936,0.00017105369],"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":[0.00068876316,0.0008721092,0.001881923,0.00008779249,0.000102728285,0.00010208923,0.0006326517,0.000023606652,0.010619191,0.6164291,0.0042761047,0.36428395],"study_design_scores_gemma":[0.00050044677,0.00023077152,0.010091083,0.000107650616,0.00007127367,0.00004729715,0.00014804886,0.00041338635,0.0024274606,0.9839951,0.0016230403,0.00034444628],"about_ca_topic_score_codex":0.000009550187,"about_ca_topic_score_gemma":0.0000017086537,"teacher_disagreement_score":0.367566,"about_ca_system_score_codex":0.000084305844,"about_ca_system_score_gemma":0.000012575534,"threshold_uncertainty_score":0.99913585},"labels":[],"label_agreement":null},{"id":"W1966967512","doi":"10.1037/1082-989x.13.2.110","title":"A generally robust approach for testing hypotheses and setting confidence intervals for effect sizes.","year":2008,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Manitoba Health; University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada; Canadian Institutes of Health Research; Manitoba Health Research Council","keywords":"Nonparametric statistics; Type I and type II errors; Heteroscedasticity; Statistics; Statistical hypothesis testing; Normality; Confidence interval; Robust statistics; Robustness (evolution); Mathematics; Statistic; Statistical power; Standard error; Variance (accounting); Nominal level; Econometrics; Sample size determination; Degrees of freedom (physics and chemistry); Multiple comparisons problem; Outlier","score_opus":0.5411151333206106,"score_gpt":0.547425561088569,"score_spread":0.006310427767958426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966967512","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":[0.00776591,0.00021134275,0.98844165,0.00008291318,0.000116026764,0.0015055166,0.00003834583,0.00014924607,0.0016890505],"genre_scores_gemma":[0.008586347,0.000015959871,0.9896419,0.00045288546,0.00017572398,0.0008983618,0.0000028824081,0.000045507724,0.00018042975],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972206,0.0009268325,0.0005150828,0.00072404207,0.00012524766,0.00048821548],"domain_scores_gemma":[0.9556491,0.04356828,0.0002021671,0.00027565775,0.00014713891,0.00015769],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00435891,0.00028981201,0.00071276055,0.00004483339,0.00028359785,0.000033440458,0.0002147478,0.0001809838,0.000009214931],"category_scores_gemma":[0.055150427,0.00020240291,0.00014994993,0.00012435995,0.00025016113,0.00007609108,0.000074397685,0.00021387033,3.732478e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005138004,0.00034975,0.00020152738,0.0008451164,0.000081321894,0.000010788584,0.00033700262,0.000249116,0.029377237,0.10796296,0.00083041674,0.85924095],"study_design_scores_gemma":[0.00133607,0.0015090721,0.00040736867,0.00007297299,0.000087612105,0.00016027257,0.00002863443,0.06755658,0.0028251836,0.9252364,0.00037553743,0.0004043111],"about_ca_topic_score_codex":0.0000013969942,"about_ca_topic_score_gemma":9.977197e-8,"teacher_disagreement_score":0.85883665,"about_ca_system_score_codex":0.000017989369,"about_ca_system_score_gemma":0.000008821974,"threshold_uncertainty_score":0.95280844},"labels":[],"label_agreement":null},{"id":"W1970325005","doi":"10.1037/a0029315","title":"When can categorical variables be treated as continuous? A comparison of robust continuous and categorical SEM estimation methods under suboptimal conditions.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":2534,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Categorical variable; Statistics; Mathematics; Normality; Continuous variable; Sample size determination; Ordinal data; Sample (material); Latent variable; Confirmatory factor analysis; Econometrics; Structural equation modeling","score_opus":0.35917610160414,"score_gpt":0.5393551820295689,"score_spread":0.1801790804254289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970325005","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":[0.2184741,0.00065069646,0.7715866,0.0029581173,0.0006295535,0.00063354237,0.000019847663,0.00009562784,0.004951901],"genre_scores_gemma":[0.56340086,0.000014651143,0.4358103,0.00038298056,0.00006637195,0.000059472026,0.00001744137,0.000012116294,0.00023578166],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9880808,0.0070522563,0.0018335215,0.0009840264,0.0012995218,0.00074986217],"domain_scores_gemma":[0.9887494,0.008602803,0.0007382056,0.0008331003,0.0005398568,0.0005366234],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019853534,0.00043089868,0.0014159856,0.00026614405,0.0002947318,0.00021130822,0.0006962457,0.00049215835,0.0017594387],"category_scores_gemma":[0.0092919925,0.0002864,0.00024615735,0.00089918356,0.0006933506,0.0003313724,0.00020047076,0.0005656711,0.00003739318],"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":[0.0008796751,0.008410262,0.2674582,0.000064654996,0.00044051534,0.000015965497,0.0049694953,0.004061446,0.03602914,0.15476674,0.027018527,0.49588537],"study_design_scores_gemma":[0.0034362245,0.0029654999,0.22082315,0.00004391505,0.00059820956,0.00021336961,0.0058752955,0.028391765,0.014317865,0.70704544,0.014880322,0.0014089294],"about_ca_topic_score_codex":0.0002334369,"about_ca_topic_score_gemma":0.000006330643,"teacher_disagreement_score":0.5522787,"about_ca_system_score_codex":0.00012126773,"about_ca_system_score_gemma":0.0000365577,"threshold_uncertainty_score":0.9999588},"labels":[],"label_agreement":null},{"id":"W1973926374","doi":"10.1037/a0016955","title":"Killeen's (2005) prep coefficient: Logical and mathematical problems.","year":2010,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Null hypothesis; Replication (statistics); Statistical hypothesis testing; Sign (mathematics); Statistical inference; Statistics; Statistical power; p-value; Noise (video); Psychology; Mathematics; Computer science; Artificial intelligence","score_opus":0.06215015672492949,"score_gpt":0.44347826398017864,"score_spread":0.3813281072552491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973926374","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":[0.0022101263,0.000057710564,0.98797077,0.0013342664,0.00028463904,0.00036432577,0.0000027154529,0.0009084618,0.0068669864],"genre_scores_gemma":[0.09738292,0.00001927983,0.9017059,0.00065249536,0.00004919358,0.00008398124,8.1286703e-7,0.000012591366,0.000092811344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732393,0.00039838132,0.00044632293,0.00095536327,0.00028076954,0.00059520855],"domain_scores_gemma":[0.99715364,0.001393731,0.00009694391,0.0008931049,0.00008357835,0.00037900064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002125714,0.00025485273,0.00038281697,0.000074906675,0.00013899624,0.00013797835,0.0009838126,0.00029928985,0.00019704842],"category_scores_gemma":[0.0024661934,0.000174937,0.00007011734,0.00025508457,0.00043921286,0.00016481885,0.0005336886,0.0008025214,0.000049323695],"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":[0.00000832975,0.00035500972,0.00002797777,0.000013804945,0.000004667508,0.000015293755,0.000054987322,0.000020448058,0.0066118627,0.74975663,0.00024448583,0.24288648],"study_design_scores_gemma":[0.00020930516,0.00026722264,0.00078958017,0.0000137950365,0.000006066223,0.00015775523,0.0000020544533,0.08287548,0.00068660406,0.90934855,0.0053639445,0.00027963668],"about_ca_topic_score_codex":8.03518e-7,"about_ca_topic_score_gemma":3.5680867e-7,"teacher_disagreement_score":0.24260685,"about_ca_system_score_codex":0.000013187489,"about_ca_system_score_gemma":0.000008359564,"threshold_uncertainty_score":0.71337235},"labels":[],"label_agreement":null},{"id":"W1976410238","doi":"10.1037/a0029314","title":"Asking sensitive questions: A statistical power analysis of randomized response models.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Randomized response; Statistical power; Statistics; Statistical model; Sample size determination; Wald test; Goodness of fit; Statistical hypothesis testing; Power (physics); Item response theory; Sample (material); Econometrics; Computer science; Statistical analysis; Mathematics; Psychology; Psychometrics","score_opus":0.2830794992700697,"score_gpt":0.5610199716537944,"score_spread":0.27794047238372466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976410238","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":[0.05282803,0.000086228894,0.94409263,0.0001264345,0.0001164802,0.0002723632,0.000043314278,0.00023270099,0.0022018391],"genre_scores_gemma":[0.43644235,0.000008866628,0.56336564,0.00008824457,0.000010782266,0.000043783664,0.000006551431,0.000008405446,0.00002539527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886039,0.009971418,0.00065153086,0.00025230984,0.00023786213,0.00028300233],"domain_scores_gemma":[0.9624132,0.036602624,0.00028085613,0.00037957996,0.00019799623,0.00012576257],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027639676,0.0001685913,0.0011387313,0.00037615505,0.000058660473,0.00001660254,0.00011582134,0.0001874217,0.00026839395],"category_scores_gemma":[0.038702965,0.00012022997,0.0003038017,0.00075516995,0.00025650303,0.00008071489,0.000041437193,0.00021574268,0.000004522795],"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":[0.07299909,0.0018053869,0.00044198736,0.000037099115,0.0027995573,0.000007961973,0.0038929696,0.00029438062,0.0043854057,0.8743543,0.0010581181,0.03792374],"study_design_scores_gemma":[0.009072223,0.00019497452,0.009526278,0.000059189282,0.0023666895,0.000018103596,0.00018799152,0.03295132,0.0021910246,0.94290966,0.00011617439,0.00040636488],"about_ca_topic_score_codex":0.00001398473,"about_ca_topic_score_gemma":4.90843e-7,"teacher_disagreement_score":0.3836143,"about_ca_system_score_codex":0.00003082035,"about_ca_system_score_gemma":0.0000074174877,"threshold_uncertainty_score":0.96939445},"labels":[],"label_agreement":null},{"id":"W1980718559","doi":"10.1037/1082-989x.10.3.317","title":"An Alternative to Cohen's Standardized Mean Difference Effect Size: A Robust Parameter and Confidence Interval in the Two Independent Groups Case.","year":2005,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":292,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Percentile; Confidence interval; Mathematics; Robust confidence intervals; Coverage probability; Truncated mean; Confidence distribution; CDF-based nonparametric confidence interval; Population; Standard deviation; Tolerance interval; Range (aeronautics); Measure (data warehouse); Medicine","score_opus":0.4903035578928938,"score_gpt":0.6284214039490661,"score_spread":0.13811784605617228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980718559","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":[0.44307768,0.000023700744,0.5545641,0.000553954,0.00029144678,0.0010104905,0.000032706947,0.000056651003,0.00038925238],"genre_scores_gemma":[0.44892904,0.00000814065,0.54934686,0.0013043007,0.00017859357,0.00020374995,2.6889282e-7,0.000018109502,0.000010933414],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9742556,0.022199819,0.0012045504,0.0011254514,0.0006137919,0.00060075935],"domain_scores_gemma":[0.8201193,0.17839383,0.0002463637,0.0008293131,0.000091615344,0.00031955543],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.026773086,0.00045225644,0.0013050082,0.00009353076,0.00011614824,0.00020056138,0.0008736,0.00027046105,0.00038627323],"category_scores_gemma":[0.1349491,0.00025806503,0.00017693975,0.0003736835,0.00045336227,0.0001029205,0.00023170176,0.0011182677,0.000012608806],"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":[0.0032487724,0.0014827785,0.0017536893,0.00007883898,0.00014937049,0.0014133097,0.0047373143,0.000045636087,0.0025381504,0.084259026,0.00017656518,0.90011656],"study_design_scores_gemma":[0.004365852,0.003428238,0.011922998,0.00013246314,0.0001408336,0.0007971115,0.0004047396,0.002135997,0.001445774,0.9746147,0.00007682775,0.00053448294],"about_ca_topic_score_codex":0.000043074226,"about_ca_topic_score_gemma":0.00006777177,"teacher_disagreement_score":0.8995821,"about_ca_system_score_codex":0.00008788912,"about_ca_system_score_gemma":0.000009799477,"threshold_uncertainty_score":0.9999872},"labels":[],"label_agreement":null},{"id":"W1987144197","doi":"10.1037/1082-989x.10.2.139","title":"Structural Equation Models for Interchangeable Dyads: Being the Same Makes a Difference.","year":2005,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Attachment and Relationship Dynamics","field":"Psychology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Structural equation modeling; Psychology; Latent variable; Personality; Social psychology; Range (aeronautics); Latent variable model; Econometrics; Cognitive psychology; Developmental psychology; Statistics; Mathematics","score_opus":0.27351794498441073,"score_gpt":0.540779147405514,"score_spread":0.2672612024211033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987144197","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":[0.12136886,0.00037526616,0.8555405,0.0044384156,0.0010941043,0.0006296801,0.000009184184,0.00012094367,0.016423032],"genre_scores_gemma":[0.6946618,0.000012677588,0.2987975,0.0011600092,0.00044167993,0.00029263017,0.000021546253,0.000018225142,0.0045939176],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979442,0.0007313739,0.00036073185,0.00043012906,0.00012755448,0.00040605906],"domain_scores_gemma":[0.9978332,0.0015116193,0.00013605098,0.00039330998,0.000056645687,0.000069178415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012254202,0.00019788383,0.00023308217,0.00007159091,0.0002721649,0.000054694705,0.00037620953,0.000281406,0.0006433034],"category_scores_gemma":[0.00017955355,0.00011356521,0.00015959938,0.00018682754,0.00014795364,0.000102809485,0.000053943986,0.00038042667,0.000046852896],"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":[0.00021393021,0.0001285527,0.0032670898,0.000007671706,0.000086223736,8.5314855e-7,0.0051523712,0.0009327582,0.00035949124,0.36994433,0.0005770717,0.61932963],"study_design_scores_gemma":[0.00090880267,0.00032111505,0.037202075,0.00001542084,0.00007669351,0.000019815616,0.00080748275,0.30159104,0.000025872594,0.65625936,0.0024716305,0.00030067874],"about_ca_topic_score_codex":0.000008866518,"about_ca_topic_score_gemma":0.000007625552,"teacher_disagreement_score":0.619029,"about_ca_system_score_codex":0.000050845352,"about_ca_system_score_gemma":0.000003992267,"threshold_uncertainty_score":0.7043721},"labels":[],"label_agreement":null},{"id":"W1993260957","doi":"10.1037/a0024918","title":"Marginal mean weighting through stratification: A generalized method for evaluating multivalued and multiple treatments with nonexperimental data.","year":2011,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Academy of Education; Spencer Foundation; Social Sciences and Humanities Research Council of Canada; William T. Grant Foundation","keywords":"Causal inference; Covariate; Propensity score matching; Weighting; Average treatment effect; Inverse probability weighting; Statistics; Mathematics; Randomized experiment; Econometrics; Nonparametric statistics; Inference; Binary data; Computer science; Artificial intelligence; Binary number","score_opus":0.793516695385926,"score_gpt":0.6567447400249953,"score_spread":0.13677195536093067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993260957","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":[0.055552408,0.00010061974,0.93977046,0.000041340958,0.000059313516,0.0013898439,0.00004010181,0.00030705836,0.002738848],"genre_scores_gemma":[0.04467795,0.000013844708,0.9545158,0.000104221996,0.000052983753,0.0004797073,0.000046534307,0.0000446073,0.00006430633],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968522,0.0011141576,0.0005100788,0.00093308307,0.00021680062,0.00037368244],"domain_scores_gemma":[0.9957712,0.0027786104,0.00034252685,0.00088895037,0.00011563128,0.0001030773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024881833,0.000336573,0.0005060565,0.000043078522,0.00021146671,0.00003807781,0.0004030967,0.00015935888,0.00014720214],"category_scores_gemma":[0.0015793359,0.00022557011,0.00005791933,0.00015420164,0.00016019389,0.00034105263,0.00014563592,0.00019111189,0.0000014423022],"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":[0.0021797845,0.002014185,0.0010881376,0.00010603667,0.00043603455,0.00001695605,0.0070400042,0.0000021860787,0.5194012,0.1545401,0.00014543705,0.31302997],"study_design_scores_gemma":[0.004305995,0.0024574334,0.0010569615,0.00008293605,0.0003035872,0.00011158451,0.0011811375,0.028153807,0.1842142,0.77735406,0.00012908266,0.0006492066],"about_ca_topic_score_codex":0.000034635505,"about_ca_topic_score_gemma":0.000003858791,"teacher_disagreement_score":0.62281394,"about_ca_system_score_codex":0.00004910014,"about_ca_system_score_gemma":0.000012464101,"threshold_uncertainty_score":0.9198482},"labels":[],"label_agreement":null},{"id":"W1995508717","doi":"10.1037/1082-989x.6.3.258","title":"Testing parameters in structural equation modeling: Every \"one\" matters.","year":2001,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":152,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structural equation modeling; Identification (biology); Standard error; Statistical model; Statistics; Set (abstract data type); Statistical hypothesis testing; Mathematics; Invariant (physics); Econometrics; Likelihood-ratio test; Scale (ratio); Applied mathematics; Computer science; Physics","score_opus":0.8579973400321181,"score_gpt":0.6038590198508541,"score_spread":0.25413832018126403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995508717","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5084123,0.00012180033,0.48437968,0.0011194292,0.0006797996,0.00015245266,9.662311e-7,0.00009172027,0.0050418647],"genre_scores_gemma":[0.43951422,0.000007896851,0.55903125,0.0013050131,0.00006788973,0.000016939623,8.6682786e-7,0.000009510721,0.00004641654],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99153066,0.004141248,0.0014255969,0.001205868,0.0009830421,0.00071357394],"domain_scores_gemma":[0.94016427,0.058072023,0.0004330042,0.00089727726,0.00023417712,0.00019927244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021676723,0.00027952713,0.0006644564,0.00082453404,0.00016015391,0.00026304123,0.0011775229,0.0002628037,0.0003658529],"category_scores_gemma":[0.207381,0.0001954142,0.00016612916,0.0052808733,0.00012607974,0.00033510942,0.00020783723,0.0005720123,0.00007996628],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090252644,0.000074251286,0.11348211,0.0000025004206,0.000008132305,0.000024096471,0.000120997014,0.014303021,0.001891585,0.0003249657,0.0001356508,0.8695424],"study_design_scores_gemma":[0.0004569567,0.0001744599,0.24195577,0.000021205109,0.0000072069306,0.00006641295,0.00028170637,0.37058863,0.000049574224,0.38587466,0.0002359724,0.0002874693],"about_ca_topic_score_codex":0.00008028478,"about_ca_topic_score_gemma":0.0000018992379,"teacher_disagreement_score":0.86925495,"about_ca_system_score_codex":0.000066822766,"about_ca_system_score_gemma":0.000012266654,"threshold_uncertainty_score":0.79929554},"labels":[],"label_agreement":null},{"id":"W2004921315","doi":"10.1037/1082-989x.8.3.254","title":"Modern Robust Data Analysis Methods: Measures of Central Tendency.","year":2003,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":504,"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":"Contrast (vision); Computer science; Variance (accounting); Econometrics; Range (aeronautics); Statistical hypothesis testing; Statistical power; Statistics; Value (mathematics); Mathematics; Artificial intelligence; Machine learning; Engineering","score_opus":0.6806927522206976,"score_gpt":0.6148759361173601,"score_spread":0.06581681610333745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004921315","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":[0.00034999967,0.00067807036,0.9859085,0.000066036766,0.00029616273,0.0002885507,0.00011185837,0.000106525884,0.012194279],"genre_scores_gemma":[0.009860176,0.000107929576,0.9895853,0.00013513194,0.000043808483,0.000026743259,0.000013325369,0.000034747005,0.00019288232],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895346,0.00713883,0.0010253201,0.0011679467,0.00043452656,0.00069875363],"domain_scores_gemma":[0.9892493,0.00764826,0.000377939,0.002224093,0.00018025245,0.00032015977],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010382013,0.00035791422,0.0012739233,0.0001956431,0.00009962252,0.000026159452,0.0009711917,0.00029232132,0.00060302473],"category_scores_gemma":[0.028660113,0.00025623362,0.0003359905,0.0010760552,0.00028111326,0.00014841437,0.00019384573,0.00047760253,0.0000025819493],"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":[0.0000803362,0.0007753448,0.00026779104,0.00005370139,0.0007495502,0.000011900672,0.00019061808,0.0007983838,0.005542077,0.39972883,0.00022951355,0.591572],"study_design_scores_gemma":[0.0003691258,0.000120979654,0.0009236678,0.000012375777,0.0010787691,0.000012783082,0.00007672164,0.021114565,0.0017506124,0.97261274,0.0015932737,0.00033435767],"about_ca_topic_score_codex":0.000007209667,"about_ca_topic_score_gemma":0.0000041457974,"teacher_disagreement_score":0.5912376,"about_ca_system_score_codex":0.000032499556,"about_ca_system_score_gemma":0.000023474619,"threshold_uncertainty_score":0.999989},"labels":[],"label_agreement":null},{"id":"W2005615110","doi":"10.1037/1082-989x.11.1.112","title":"Paper and plastic in daily diary research: Comment on Green, Rafaeli, Bolger, Shrout, and Reis (2006).","year":2006,"lang":"en","type":"letter","venue":"Psychological Methods","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Mental Health; National Institute on Alcohol Abuse and Alcoholism; Social Sciences and Humanities Research Council of Canada; Arthritis Foundation","keywords":"Psychology","score_opus":0.2598997714356185,"score_gpt":0.5457960284064142,"score_spread":0.2858962569707957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005615110","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069706356,0.0047467495,0.0014326226,0.874505,0.00424537,0.00188224,0.00046532913,0.00019784053,0.10555425],"genre_scores_gemma":[0.009451824,0.000117396405,0.015814217,0.9541165,0.0016578233,0.0013157415,0.00027562713,0.00018385235,0.017067008],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867843,0.008017768,0.0012501534,0.0018618582,0.0006045148,0.0014814554],"domain_scores_gemma":[0.9891134,0.00924009,0.0002568186,0.001028525,0.00007246816,0.00028871393],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0053910213,0.0006537495,0.000998188,0.00097428204,0.00019729223,0.00014119966,0.0005715602,0.0017112771,0.0013866817],"category_scores_gemma":[0.0005655438,0.0005438282,0.00019283502,0.0006713007,0.00093356747,0.00011904115,0.0003775021,0.0053690416,0.00044645526],"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":[0.0002400654,0.00100053,0.00051859283,0.00019624594,0.000053527063,0.0008611915,0.000093935574,1.3451009e-7,0.00000800016,0.0015738215,0.85288894,0.14256501],"study_design_scores_gemma":[0.0015013228,0.0027764589,0.049276296,0.00048407319,0.000032085252,0.00011266973,0.00004167428,0.000005411436,0.0000042649694,0.040300727,0.9049223,0.00054272613],"about_ca_topic_score_codex":0.0009293159,"about_ca_topic_score_gemma":0.000041417796,"teacher_disagreement_score":0.1420223,"about_ca_system_score_codex":0.0002191856,"about_ca_system_score_gemma":0.000013636945,"threshold_uncertainty_score":0.9997013},"labels":[],"label_agreement":null},{"id":"W2011619587","doi":"10.1037/a0029250","title":"Qualitative research as methodical hermeneutics.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":200,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Hermeneutics; Epistemology; Qualitative research; Exegesis; Demonstrative; Credibility; Conversation; Meaning (existential); Mainstream; Thematic analysis; Generality; Rhetoric; Sociology; Psychology; Verstehen; Interpretation (philosophy); Social psychology; Linguistics; Philosophy; Social science","score_opus":0.7749174545978643,"score_gpt":0.7295370932943747,"score_spread":0.04538036130348966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011619587","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04799064,0.0015532835,0.0039850357,0.0030564289,0.00082069455,0.0002705078,0.000010401034,0.00020186634,0.94211113],"genre_scores_gemma":[0.7349944,0.0000778373,0.25430143,0.0011988187,0.00089745235,0.00015341227,0.00000921057,0.00002749505,0.008339923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98335016,0.014690889,0.0004000427,0.0003354269,0.00047661996,0.0007468342],"domain_scores_gemma":[0.99310154,0.005465877,0.00009884203,0.00080446433,0.00025623667,0.00027303895],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016242275,0.00019650738,0.00032560117,0.00014937809,0.000563105,0.00023564727,0.00070231326,0.00015383364,0.0136684375],"category_scores_gemma":[0.0022800518,0.00013401173,0.00013314927,0.00017097063,0.0018105643,0.0003290134,0.00022592398,0.0009241936,0.0013191687],"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":[0.000033791526,0.00039128854,0.000015428612,0.0000064982855,0.00002944941,0.0000018586063,0.18598422,1.0345004e-7,0.0003928709,0.77571523,0.0031293116,0.03429993],"study_design_scores_gemma":[0.0002514466,0.0002308796,0.00050305144,0.000012448382,0.00002007548,0.000011603279,0.2189571,0.0000039945166,0.0004612461,0.41657758,0.36272094,0.00024964032],"about_ca_topic_score_codex":0.00007519836,"about_ca_topic_score_gemma":0.000011227786,"teacher_disagreement_score":0.9337712,"about_ca_system_score_codex":0.00004600981,"about_ca_system_score_gemma":0.000021483687,"threshold_uncertainty_score":0.99945843},"labels":[],"label_agreement":null},{"id":"W2011843009","doi":"10.1037/1082-989x.6.1.3","title":"Empirical and hermeneutic approaches to phenomenological research in psychology: A comparison.","year":2001,"lang":"en","type":"review","venue":"Psychological Methods","topic":"Counseling, Therapy, and Family Dynamics","field":"Psychology","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Intuition; Phenomenology (philosophy); Psychology; Epistemology; Similarity (geometry); Social psychology; Meaning (existential); Empirical research; Cognitive psychology; Psychotherapist; Cognitive science; Philosophy; Artificial intelligence","score_opus":0.870865608223874,"score_gpt":0.6743232721351252,"score_spread":0.19654233608874883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011843009","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075924693,0.94163805,0.010356683,0.0007123545,0.0014927925,0.0026064126,0.00002346594,0.00022365856,0.042187326],"genre_scores_gemma":[0.00023063987,0.90866333,0.0864697,0.0015090863,0.00053026114,0.0018615007,0.00003388155,0.00014139307,0.00056021055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.975926,0.01560702,0.0021709555,0.0035334777,0.0005498569,0.0022127002],"domain_scores_gemma":[0.9917994,0.005021506,0.00037055512,0.002005221,0.000078245015,0.0007250493],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.012176758,0.001179553,0.0045271595,0.0015952132,0.00024153687,0.00014419721,0.0017920028,0.0030786544,0.0008800317],"category_scores_gemma":[0.00042207478,0.00087526283,0.0005589266,0.004121989,0.0011212294,0.000049286988,0.0004764472,0.0053041717,0.00076596136],"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":[0.0002595849,0.0022262314,0.00046892682,0.0004703638,0.00017124355,0.00020513879,0.0036277822,9.883996e-7,4.1590712e-7,0.0025633501,0.0023366609,0.9876693],"study_design_scores_gemma":[0.00084138074,0.0015439142,0.0019314128,0.0007778058,0.00014857839,0.00042714333,0.0015032076,0.000015431448,1.7398056e-9,0.022146353,0.9697053,0.00095945754],"about_ca_topic_score_codex":0.000024093973,"about_ca_topic_score_gemma":0.000020102487,"teacher_disagreement_score":0.98670983,"about_ca_system_score_codex":0.0002725062,"about_ca_system_score_gemma":0.00005513729,"threshold_uncertainty_score":0.9993698},"labels":[],"label_agreement":null},{"id":"W2029286738","doi":"10.1037/1082-989x.13.2.150","title":"Constrained versus unconstrained estimation in structural equation modeling.","year":2008,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"National Institute on Drug Abuse; U.S. Social Security Administration","keywords":"Constraint (computer-aided design); Structural equation modeling; Estimation; Computer science; Boundary (topology); Estimation theory; Mathematics; Mathematical optimization; Applied mathematics; Algorithm; Econometrics; Statistics","score_opus":0.6554148748889531,"score_gpt":0.6096974645123965,"score_spread":0.04571741037655663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029286738","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":[0.4397911,0.000031757256,0.55499196,0.00026835178,0.0010239668,0.00018682111,0.000004575991,0.00006459491,0.003636825],"genre_scores_gemma":[0.5335121,0.00000226017,0.46626765,0.00012460361,0.00003872325,0.000012802598,0.000003833339,0.0000066106913,0.00003140785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99384046,0.0021238236,0.0014399218,0.0009766935,0.0011897137,0.00042939922],"domain_scores_gemma":[0.99150705,0.0069902344,0.00030462572,0.0007338606,0.00028856675,0.00017563421],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007636446,0.00025968498,0.00054116215,0.0005264911,0.00019588614,0.00014506924,0.0007918479,0.00027026876,0.0016878631],"category_scores_gemma":[0.03416156,0.00018458499,0.0001657412,0.0013717967,0.00032090477,0.0004007941,0.00011964126,0.00037912437,0.00017962551],"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":[0.0008760173,0.00010306718,0.0018029845,0.0000017479068,0.000010751939,0.00007536702,0.00084730407,0.05169168,0.00356106,0.005189164,0.0001233351,0.9357175],"study_design_scores_gemma":[0.002118427,0.00013931499,0.011210625,0.000008775013,0.0000041495255,0.00006923822,0.00020121937,0.8742181,0.00007922377,0.11167734,0.000060102222,0.00021347044],"about_ca_topic_score_codex":0.000018282033,"about_ca_topic_score_gemma":0.000007140306,"teacher_disagreement_score":0.935504,"about_ca_system_score_codex":0.00009166955,"about_ca_system_score_gemma":0.000041218325,"threshold_uncertainty_score":0.9992247},"labels":[],"label_agreement":null},{"id":"W2030382769","doi":"10.1037/1082-989x.9.4.453","title":"Comparative Judgments as an Alternative to Ratings: Identifying the Scale Origin.","year":2004,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Psychology; Scale (ratio); Interpretation (philosophy); Value (mathematics); Econometrics; Social psychology; Cognitive psychology; Statistics; Computer science; Mathematics","score_opus":0.6618471505924736,"score_gpt":0.6779126136633634,"score_spread":0.01606546307088985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030382769","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":[0.46056476,0.000041481842,0.5281514,0.0011709839,0.0014575078,0.00044957444,0.0000059749077,0.0000650953,0.008093214],"genre_scores_gemma":[0.47289392,0.000002597412,0.52287614,0.0036275247,0.00018241786,0.00006387738,8.737822e-7,0.0000111493955,0.00034149011],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9911693,0.0037255788,0.0011496996,0.0014886975,0.0019113756,0.00055538863],"domain_scores_gemma":[0.99269265,0.0045467787,0.00042737546,0.0014420574,0.0004664177,0.00042473243],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013477592,0.00033376578,0.0006768568,0.00030488742,0.00055846776,0.0011018347,0.002857445,0.00014051136,0.0016464243],"category_scores_gemma":[0.007767005,0.00017805056,0.00020592962,0.0016839193,0.00028430184,0.00056793366,0.00052619533,0.0004990406,0.0025656007],"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":[0.0007568128,0.0013528174,0.001688309,0.0000031215718,0.000070776754,0.00010732661,0.03135582,0.004122863,0.09762065,0.019401936,0.003975362,0.8395442],"study_design_scores_gemma":[0.0017559719,0.00094297307,0.04518883,0.00007206838,0.00002312989,0.00009646344,0.0070682764,0.0020197476,0.019397723,0.89643896,0.026352143,0.0006437136],"about_ca_topic_score_codex":0.000054232067,"about_ca_topic_score_gemma":0.000017086717,"teacher_disagreement_score":0.87703705,"about_ca_system_score_codex":0.0001008768,"about_ca_system_score_gemma":0.000024516366,"threshold_uncertainty_score":0.9999351},"labels":[],"label_agreement":null},{"id":"W2040991114","doi":"10.1037/a0017737","title":"Testing multiple outcomes in repeated measures designs.","year":2010,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"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 Saskatchewan","funders":"Canadian Institutes of Health Research; Manitoba Health Research Council","keywords":"Bonferroni correction; Multiple comparisons problem; Type I and type II errors; Statistics; Statistical power; Permutation (music); Monte Carlo method; Mathematics; Outcome (game theory); Variable (mathematics); Statistical hypothesis testing; Repeated measures design; Computer science","score_opus":0.8871628882891909,"score_gpt":0.695675757748921,"score_spread":0.1914871305402699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040991114","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":[0.23679656,0.000014951533,0.7484806,0.00043215454,0.002014949,0.00077010726,0.000013227229,0.00046027754,0.011017137],"genre_scores_gemma":[0.13614382,0.0000021915382,0.86303675,0.000403986,0.00016170317,0.00012123603,3.5828074e-7,0.000040328785,0.000089645364],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9909475,0.0056214933,0.0015259075,0.0008765792,0.00039293154,0.0006355746],"domain_scores_gemma":[0.76781654,0.23050685,0.0003227081,0.0009273684,0.00016816508,0.0002583422],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021954468,0.0003471878,0.0011759442,0.00014027834,0.00008924834,0.00005350847,0.0006302576,0.0006050398,0.00057962694],"category_scores_gemma":[0.7586523,0.00023952386,0.00020957628,0.00069487194,0.00033403825,0.0000580514,0.00014111829,0.0015617388,0.000048399706],"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":[0.00020978248,0.0014157537,0.13758561,0.000032683714,0.000051342657,0.00007605069,0.000072618255,0.0000015932296,0.13295756,0.027750133,0.00032641878,0.69952047],"study_design_scores_gemma":[0.0011773857,0.0001947154,0.18683285,0.000023619748,0.000029313638,0.0000152155835,0.000013300533,0.00026088726,0.0030266535,0.8078861,0.00024788213,0.0002920512],"about_ca_topic_score_codex":0.000018355,"about_ca_topic_score_gemma":0.000012779107,"teacher_disagreement_score":0.780136,"about_ca_system_score_codex":0.000025770132,"about_ca_system_score_gemma":0.00001541619,"threshold_uncertainty_score":0.97674996},"labels":[],"label_agreement":null},{"id":"W2042003034","doi":"10.1037/a0025810","title":"Many tests of significance: New methods for controlling type I errors.","year":2011,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"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":"Multiple comparisons problem; Control (management); Computer science; Mathematics; Statistics; False discovery rate; Artificial intelligence","score_opus":0.8514252015725781,"score_gpt":0.7047830235817717,"score_spread":0.14664217799080637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042003034","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":[0.0011177775,0.0002858948,0.98372865,0.00014795459,0.0022284791,0.0014237679,0.000024074832,0.00019120506,0.010852195],"genre_scores_gemma":[0.0021159016,0.000046376725,0.9961085,0.00042772284,0.00041203303,0.00014392106,8.442401e-7,0.00006932189,0.00067537813],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99035716,0.005887685,0.0019578296,0.0008972952,0.00025333712,0.0006466775],"domain_scores_gemma":[0.866086,0.13142188,0.0007961415,0.00094896415,0.0003605051,0.00038652506],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021005796,0.00039688873,0.0018206182,0.00011477494,0.000077671284,0.000018241513,0.00080556964,0.0005889914,0.0018985223],"category_scores_gemma":[0.28623438,0.00029065288,0.0004995556,0.00056979794,0.0004063963,0.000057469628,0.000115275376,0.0005260089,0.000020609847],"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":[0.0017543568,0.000748754,0.00014847577,0.00013367283,0.00017280594,0.0000040569244,0.00019753778,6.4664437e-7,0.027907142,0.3135695,0.001739751,0.65362334],"study_design_scores_gemma":[0.002012898,0.0015762842,0.0017832353,0.00005641779,0.00027079633,0.000006008866,0.00003957027,0.00026920944,0.017872458,0.97311485,0.0026504367,0.00034785407],"about_ca_topic_score_codex":0.0000130482895,"about_ca_topic_score_gemma":4.7419002e-7,"teacher_disagreement_score":0.65954536,"about_ca_system_score_codex":0.000027520557,"about_ca_system_score_gemma":0.000055553737,"threshold_uncertainty_score":0.9999546},"labels":[],"label_agreement":null},{"id":"W2042334535","doi":"10.1037/a0014269","title":"A proposed framework for conducting data-based test analysis.","year":2008,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Extant taxon; Computer science; Test theory; Test data; Data mining; Psychometrics; Statistics; Mathematics; Software engineering","score_opus":0.9565826883810709,"score_gpt":0.7111345330937316,"score_spread":0.2454481552873392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042334535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038662445,0.00037057645,0.9553593,0.0013298559,0.0010498825,0.0005131687,0.000065770706,0.00023619308,0.0024128202],"genre_scores_gemma":[0.18635736,0.000010968673,0.81178796,0.001327331,0.0002629391,0.000039529157,0.000019146188,0.000015936912,0.00017884946],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9914123,0.0033479927,0.001419141,0.002070588,0.0010346805,0.00071532116],"domain_scores_gemma":[0.6658209,0.32879803,0.00091378624,0.0036056393,0.00054292893,0.00031874626],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03781359,0.0003193908,0.0011721522,0.00093750894,0.00057515263,0.00018469113,0.0034264436,0.00037883018,0.0008598824],"category_scores_gemma":[0.69519436,0.00019689795,0.00048519467,0.010056076,0.00043950006,0.00021868784,0.00035424382,0.0005752073,0.00004839182],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018209228,0.00080795796,0.19245046,0.000009683715,0.00022818682,0.000035102446,0.00013149505,0.00030971918,0.0015427574,0.0024691774,0.006091946,0.79574144],"study_design_scores_gemma":[0.0018177568,0.0014009337,0.3585839,0.000025352625,0.00051126746,0.00006721015,0.0005433851,0.06759359,0.0017669871,0.51951885,0.047070842,0.0010999043],"about_ca_topic_score_codex":0.000007286564,"about_ca_topic_score_gemma":6.1420224e-7,"teacher_disagreement_score":0.7946415,"about_ca_system_score_codex":0.000024965513,"about_ca_system_score_gemma":0.00004560177,"threshold_uncertainty_score":0.9907734},"labels":[],"label_agreement":null},{"id":"W2048699385","doi":"10.1037/1082-989x.5.3.370","title":"How important is transient error in estimating reliability? Going beyond simulation studies.","year":2000,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"","keywords":"Reliability (semiconductor); Transient (computer programming); Observational error; Statistics; Standard error; Range (aeronautics); Error analysis; Reliability engineering; Mathematics; Computer science; Algorithm; Applied mathematics; Engineering","score_opus":0.3949998641647077,"score_gpt":0.6121051813343663,"score_spread":0.21710531716965858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048699385","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":[0.47230467,0.0015148126,0.51456267,0.0029976415,0.0009272154,0.00070611306,0.0000075537855,0.00012263612,0.006856704],"genre_scores_gemma":[0.29604083,0.000024570772,0.70199835,0.0010388419,0.0000708488,0.000051591865,7.5041095e-7,0.000017202756,0.00075703685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9902726,0.004620101,0.0016888035,0.0016005272,0.001193172,0.0006247857],"domain_scores_gemma":[0.9881411,0.01004401,0.00034193808,0.0010491578,0.00019670077,0.00022709269],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023291713,0.00037578234,0.0009214871,0.00026292045,0.00018118665,0.0002739564,0.0007994767,0.0002686549,0.00205451],"category_scores_gemma":[0.017181449,0.000254636,0.00029362578,0.0017651089,0.00035516635,0.0005637128,0.000091065114,0.00050563086,0.000081246995],"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":[0.00026605456,0.000391252,0.0025553815,0.000008725655,0.000016835626,0.000036148816,0.003024217,0.017020822,0.008320876,0.000102117374,0.000377097,0.9678805],"study_design_scores_gemma":[0.0012837817,0.0008190936,0.014884049,0.000056538884,0.000024990159,0.000025064164,0.0018673532,0.78964794,0.0030351207,0.17761946,0.010060064,0.0006765568],"about_ca_topic_score_codex":0.0000050794647,"about_ca_topic_score_gemma":9.944565e-7,"teacher_disagreement_score":0.9672039,"about_ca_system_score_codex":0.00014700013,"about_ca_system_score_gemma":0.000015383775,"threshold_uncertainty_score":0.9999906},"labels":[],"label_agreement":null},{"id":"W2052567024","doi":"10.1037/1082-989x.12.3.247","title":"Combining propensity score matching and group-based trajectory analysis in an observational study.","year":2007,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":285,"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":"National Institute of Mental Health","keywords":"Propensity score matching; Covariate; Observational study; Matching (statistics); Mahalanobis distance; Statistics; Trajectory; Mathematics; Econometrics","score_opus":0.7505569186862165,"score_gpt":0.6029601374272204,"score_spread":0.1475967812589961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052567024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53224874,0.000008115736,0.46711665,0.000018491732,0.000020585596,0.0002803985,0.000001146544,0.00014043052,0.00016540561],"genre_scores_gemma":[0.51991904,5.851282e-7,0.4798669,0.00016659955,0.000009833866,0.000023662134,0.0000045982624,0.000006699965,0.0000020826403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973857,0.0010480005,0.0005275923,0.00052029284,0.0002229732,0.00029545047],"domain_scores_gemma":[0.9964577,0.0028170345,0.00016705121,0.00037771137,0.000068456044,0.00011207951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071391575,0.00019653807,0.00052360696,0.00028343173,0.00008469209,0.000035924266,0.00021048693,0.00014730004,0.000056194614],"category_scores_gemma":[0.001111004,0.00015566885,0.00006999222,0.00086318987,0.0001068295,0.00018244417,0.00005779812,0.0004400316,5.900721e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018829828,0.0020710246,0.92895716,0.000020964879,0.00006376801,0.00005678197,0.00073295145,0.000044860226,0.011234982,0.017358858,0.0000035778921,0.03926678],"study_design_scores_gemma":[0.00034023804,0.00044387815,0.7458445,0.000011814829,0.00006288737,0.0000019154754,0.00020856019,0.00022907305,0.00030403188,0.25238758,0.000002279458,0.00016325148],"about_ca_topic_score_codex":0.000022235577,"about_ca_topic_score_gemma":0.00018574718,"teacher_disagreement_score":0.23502871,"about_ca_system_score_codex":0.000052018342,"about_ca_system_score_gemma":0.0000061425344,"threshold_uncertainty_score":0.6347992},"labels":[],"label_agreement":null},{"id":"W2064765903","doi":"10.1037/1082-989x.8.4.468","title":"Bidimensional Regression: Assessing the Configural Similarity and Accuracy of Cognitive Maps and Other Two-Dimensional Data Sets.","year":2003,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":180,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Similarity (geometry); Regression; Fidelity; Regression analysis; Euclidean distance; Distortion (music); Euclidean geometry; Artificial intelligence; Mathematics; Cognition; Cognitive map; Linear regression; Pattern recognition (psychology); Statistics; Psychology; Computer science; Image (mathematics)","score_opus":0.18311456404649293,"score_gpt":0.48913956596141756,"score_spread":0.30602500191492465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064765903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96658033,0.0018218824,0.021759044,0.00033144088,0.0004434157,0.0003080413,0.00014505288,0.00010128685,0.008509502],"genre_scores_gemma":[0.913358,0.000027607393,0.085688725,0.0008263775,0.000029766645,0.000007380861,0.000044302,0.000011857324,0.000005994079],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99856865,0.0006585645,0.0002242935,0.00026750387,0.00014551984,0.00013543763],"domain_scores_gemma":[0.9972932,0.0022992592,0.00007015236,0.0002056889,0.000060063812,0.000071653005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012775651,0.00013518357,0.00018650471,0.000032419015,0.0001032315,0.00003263217,0.00009233538,0.00010011756,0.00028552482],"category_scores_gemma":[0.0014516631,0.00008217872,0.000023364393,0.00013319524,0.00021446659,0.00013311322,0.000057434852,0.0002620024,0.0000026915973],"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":[0.00026051453,0.000433503,0.011405004,0.00011614897,0.0002702776,0.00003188686,0.000624444,0.00020543984,0.11374113,0.007875967,0.004154506,0.8608812],"study_design_scores_gemma":[0.015924398,0.0008711083,0.52089095,0.0021248998,0.00075885723,0.001494368,0.0021537237,0.12680222,0.12417662,0.17327157,0.028676996,0.002854308],"about_ca_topic_score_codex":0.0000041358553,"about_ca_topic_score_gemma":6.785435e-7,"teacher_disagreement_score":0.85802686,"about_ca_system_score_codex":0.000004719174,"about_ca_system_score_gemma":0.000006512183,"threshold_uncertainty_score":0.33511508},"labels":[],"label_agreement":null},{"id":"W2079540101","doi":"10.1037/1082-989x.10.1.65","title":"A Latent Markov Model for the Analysis of Longitudinal Data Collected in Continuous Time: States, Durations, and Transitions.","year":2005,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Generalization; Markov chain; Markov model; Computer science; Markov process; Econometrics; Latent variable; Variable-order Markov model; Sampling (signal processing); Statistics; Observable; Duration (music); Artificial intelligence; Machine learning; Mathematics","score_opus":0.2726942149715341,"score_gpt":0.5589278597371689,"score_spread":0.28623364476563473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079540101","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":[0.19744392,0.002588252,0.78366315,0.011659079,0.00011835218,0.0020239681,0.0010845982,0.000045444933,0.0013732472],"genre_scores_gemma":[0.33612505,0.0004491977,0.65915954,0.0008776171,0.000056074798,0.0004939532,0.00037893333,0.000017909666,0.0024417606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973749,0.001051726,0.0005592515,0.00050680235,0.0001572657,0.0003500639],"domain_scores_gemma":[0.9971133,0.0018737921,0.00010930763,0.0007223659,0.00007841051,0.00010282476],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033132995,0.00012349377,0.00041400932,0.00023812342,0.000112734655,0.000019765423,0.00039477856,0.0001318675,0.0010273773],"category_scores_gemma":[0.00031522958,0.000083289044,0.0000728941,0.00091817026,0.00018742787,0.00006278337,0.00007068909,0.00024996453,0.0000055544774],"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":[0.0024619463,0.002362958,0.009131422,0.00005886374,0.0012826385,0.000012219549,0.0022768804,0.0020914928,0.00076211325,0.0028832818,0.0131770605,0.9634991],"study_design_scores_gemma":[0.0011311935,0.00018925073,0.28007174,0.0000065204254,0.00026157097,0.0000071867253,0.00009878391,0.7159494,0.000008088348,0.0008322265,0.0013467416,0.00009725459],"about_ca_topic_score_codex":0.0000712807,"about_ca_topic_score_gemma":0.00022672667,"teacher_disagreement_score":0.96340185,"about_ca_system_score_codex":0.000039635852,"about_ca_system_score_gemma":0.000017940347,"threshold_uncertainty_score":0.9998858},"labels":[],"label_agreement":null},{"id":"W2082558248","doi":"10.1037/a0020143","title":"Expected versus observed information in SEM with incomplete normal and nonnormal data.","year":2010,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Statistic; Standard error; Fisher information; Test statistic; Missing data; Computation; Mathematics; Maximum likelihood; Information Criteria; Structural equation modeling; Computer science; Econometrics; Statistical hypothesis testing; Algorithm; Model selection","score_opus":0.6072341590302414,"score_gpt":0.5821967672574048,"score_spread":0.025037391772836592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082558248","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8486754,0.000015658798,0.14556262,0.0004140571,0.0012740445,0.0002535127,0.000029722407,0.00007061865,0.0037044126],"genre_scores_gemma":[0.48906735,0.0000021058847,0.5105693,0.00025129094,0.000060931263,0.000013396112,0.000014879699,0.0000055255364,0.000015268171],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99566793,0.0011363862,0.0010443139,0.00075898226,0.0009765965,0.00041579158],"domain_scores_gemma":[0.9921781,0.005349973,0.0003426155,0.0016734478,0.00024226255,0.00021364285],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008079202,0.00023589877,0.0004487175,0.0004149023,0.00013747915,0.0005350451,0.001718948,0.00023667324,0.0009342424],"category_scores_gemma":[0.013132661,0.00014604212,0.000040721345,0.0012303266,0.00024137128,0.0020371713,0.00083091867,0.0006975914,0.00012549006],"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":[0.0021290376,0.00012934131,0.018403687,0.00000367781,0.000011003836,0.000028488259,0.00064729166,0.00003368076,0.008162059,0.0009224271,0.0005392443,0.9689901],"study_design_scores_gemma":[0.00468612,0.00041915427,0.919892,0.000014898937,0.000009596782,0.00008750171,0.0005767593,0.02791485,0.00018456094,0.0043046894,0.04149216,0.00041766476],"about_ca_topic_score_codex":0.000034167726,"about_ca_topic_score_gemma":0.0001352569,"teacher_disagreement_score":0.9685724,"about_ca_system_score_codex":0.000013240666,"about_ca_system_score_gemma":0.000019668321,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W2086012744","doi":"10.1037/a0029253","title":"Individual influence on model selection.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Akaike information criterion; Bayesian information criterion; Model selection; Selection (genetic algorithm); Ranking (information retrieval); Generality; Information Criteria; Computer science; Bayesian probability; Deviance information criterion; Multilevel model; Econometrics; Bayesian inference; Statistics; Data mining; Machine learning; Artificial intelligence; Psychology; Mathematics","score_opus":0.3007814790311631,"score_gpt":0.5548223446057223,"score_spread":0.25404086557455924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086012744","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":[0.0388746,0.000028104365,0.9396348,0.00013587295,0.00023469131,0.00016411698,0.0000123835325,0.00017174492,0.020743694],"genre_scores_gemma":[0.13956173,0.0000052586993,0.8589538,0.0011633821,0.00014404202,0.00005823425,7.146034e-7,0.000016873953,0.00009600716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99741906,0.0010519848,0.00035700324,0.00034389598,0.00028183314,0.0005462039],"domain_scores_gemma":[0.99529797,0.0039519966,0.00010837585,0.00030678685,0.000063417276,0.00027148242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028960814,0.00021498611,0.00032593883,0.00007510257,0.00011992914,0.00003749284,0.00028969496,0.00021995792,0.0005567313],"category_scores_gemma":[0.00749286,0.00015033325,0.00008643939,0.00031675198,0.00012615185,0.00011634442,0.00006309574,0.00048486932,0.00009950767],"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":[0.00003337928,0.00043358488,0.0010708305,0.000010670409,0.000015342699,7.598328e-7,0.00011670874,0.000008711759,0.0010497435,0.7773663,0.001164341,0.21872966],"study_design_scores_gemma":[0.00019337639,0.00022777353,0.027063476,0.000015751839,0.000033301818,0.000019191646,0.000011865013,0.0013834347,0.0010829702,0.96922874,0.0005073441,0.00023276989],"about_ca_topic_score_codex":0.0000010975532,"about_ca_topic_score_gemma":8.7836995e-8,"teacher_disagreement_score":0.21849689,"about_ca_system_score_codex":0.00002759632,"about_ca_system_score_gemma":0.000007872993,"threshold_uncertainty_score":0.8970194},"labels":[],"label_agreement":null},{"id":"W2093491439","doi":"10.1037/1082-989x.7.1.126","title":"The role of qualitative research in psychological journals.","year":2002,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":183,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"PsycINFO; Qualitative research; Qualitative analysis; Psychology; Content analysis; Applied psychology; Social psychology; MEDLINE; Social science; Sociology","score_opus":0.9375029604873701,"score_gpt":0.8324841901757505,"score_spread":0.10501877031161966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093491439","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50292,0.0072844955,0.017661711,0.021316176,0.0008823148,0.0006068209,0.000005238865,0.000033845365,0.44928944],"genre_scores_gemma":[0.9168964,0.00074873446,0.080959834,0.00033712183,0.00007302813,0.000056732246,1.9364079e-7,0.000004920134,0.00092303375],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9704429,0.02457314,0.0013574505,0.00058196485,0.0025336088,0.0005109739],"domain_scores_gemma":[0.9730021,0.025203196,0.0002902099,0.00074874086,0.0006247978,0.00013099024],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12530676,0.00011892806,0.00034813493,0.00036046666,0.00028038124,0.00016704907,0.0013761608,0.00017204358,0.0073454836],"category_scores_gemma":[0.015197282,0.000054971217,0.00014088675,0.002592566,0.0006824816,0.00016050425,0.00013593676,0.0009031989,0.0005211517],"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":[0.0000738244,0.0004253943,0.0032949324,5.34131e-7,0.000005033755,0.0000021725252,0.0034991915,0.0000127130725,0.0013213303,0.02033557,0.0023585174,0.9686708],"study_design_scores_gemma":[0.0004234338,0.00059199013,0.09659927,0.000012834333,0.0000016088486,0.000010713997,0.01230831,0.0026390464,0.00027371864,0.83308357,0.0539583,0.000097227006],"about_ca_topic_score_codex":0.000004991409,"about_ca_topic_score_gemma":0.0000053681483,"teacher_disagreement_score":0.9685736,"about_ca_system_score_codex":0.00003620322,"about_ca_system_score_gemma":0.000008418303,"threshold_uncertainty_score":0.9935619},"labels":[],"label_agreement":null},{"id":"W2094893424","doi":"10.1037/a0029316","title":"A multilevel simultaneous equations model for within-cluster dynamic effects, with an application to reciprocal parent–child and sibling effects.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychological and Temporal Perspectives Research","field":"Psychology","cited_by":22,"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":"Economic and Social Research Council; Medical Research Council; Social Sciences and Humanities Research Council; Wellcome Trust","keywords":"Reciprocal; Multilevel model; Psychology; Sibling; Developmental psychology; Set (abstract data type); Social psychology; Peer group; Cluster (spacecraft); Statistics; Computer science; Mathematics","score_opus":0.11546710169619348,"score_gpt":0.517022654787798,"score_spread":0.4015555530916045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094893424","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":[0.12913595,0.00038945355,0.86325055,0.00069472054,0.00033464664,0.002983585,0.000025078929,0.00021720881,0.002968821],"genre_scores_gemma":[0.632534,0.0000048899074,0.36375907,0.0012786897,0.0001334969,0.0018929878,0.00002006154,0.000040348536,0.00033643868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958125,0.0012110814,0.00044565657,0.0012706213,0.0002821813,0.0009780067],"domain_scores_gemma":[0.9926331,0.005579558,0.00014800322,0.00071177445,0.00014946373,0.00077806757],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020420311,0.00042816365,0.0005426281,0.00023789008,0.0003454766,0.000072362505,0.00041795895,0.0004206365,0.00004722929],"category_scores_gemma":[0.0020582518,0.0002877451,0.00011140509,0.00052163866,0.00025667474,0.00020113176,0.0001085246,0.0006387264,0.00007125065],"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":[0.0072126593,0.0058483607,0.0015616955,0.00019485688,0.0002560665,0.000014455003,0.007978676,0.004450415,0.009838246,0.023220036,0.00014804793,0.9392765],"study_design_scores_gemma":[0.005921002,0.007989575,0.032044433,0.000113407565,0.00016415291,0.00010968848,0.00068115094,0.9200753,0.0002835291,0.030264512,0.0010457836,0.0013074732],"about_ca_topic_score_codex":0.000014374492,"about_ca_topic_score_gemma":0.000007995586,"teacher_disagreement_score":0.937969,"about_ca_system_score_codex":0.00007905976,"about_ca_system_score_gemma":0.000007715638,"threshold_uncertainty_score":0.99995744},"labels":[],"label_agreement":null},{"id":"W2097789390","doi":"10.1037/a0033266","title":"Why the items versus parcels controversy needn’t be one.","year":2013,"lang":"en","type":"review","venue":"Psychological Methods","topic":"Financial Reporting and Valuation Research","field":"Business, Management and Accounting","cited_by":1553,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Sciences and Humanities Research Council of Canada; University of Kansas; National Science Foundation","keywords":"Statistics; Econometrics; Psychology; Environmental science; Mathematics","score_opus":0.6121447167284271,"score_gpt":0.5685405495960681,"score_spread":0.04360416713235893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097789390","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011746686,0.90560853,0.0051338845,0.0031005444,0.003498897,0.0019063755,0.0000046031123,0.00021265823,0.08052275],"genre_scores_gemma":[0.0000056764084,0.9772628,0.009726796,0.0060917586,0.0038171983,0.00090662955,0.000059270846,0.00007690225,0.0020529898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602497,0.00075437955,0.0010446421,0.00079257844,0.00069443,0.00068900065],"domain_scores_gemma":[0.99453115,0.0031222582,0.001083972,0.0009079917,0.0003101102,0.000044536875],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0068735196,0.0004909632,0.0014698822,0.00024789048,0.00036690524,0.0006971173,0.0010442662,0.00056122855,0.0027147718],"category_scores_gemma":[0.010812265,0.00027254134,0.0007494809,0.001081407,0.00023815104,0.00024895056,0.00035815465,0.0011600967,0.0011876328],"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":[0.000022805023,0.00009063909,0.0000031237225,0.00085635786,0.00008005278,0.000005546101,0.000003904137,3.906762e-7,0.0000013869624,0.005978693,0.06520374,0.9277533],"study_design_scores_gemma":[0.0003853623,0.000046950714,0.000054500226,0.00051856425,0.00038906356,0.0000031910547,0.000021574328,0.00006266874,1.3245685e-7,0.002654998,0.99551624,0.00034673582],"about_ca_topic_score_codex":0.0003252051,"about_ca_topic_score_gemma":0.000004473362,"teacher_disagreement_score":0.9303125,"about_ca_system_score_codex":0.000058622565,"about_ca_system_score_gemma":0.000040296858,"threshold_uncertainty_score":0.9999727},"labels":[],"label_agreement":null},{"id":"W2101928545","doi":"10.1037/1082-989x.10.3.285","title":"Structural Equation Modeling of Paired-Comparison and Ranking Data.","year":2005,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Thurstone scale; Structural equation modeling; Covariance; Ranking (information retrieval); Statistical model; Factor analysis; Econometrics; Model selection; Statistics; Computer science; Factor (programming language); Mathematics; Artificial intelligence","score_opus":0.6611313861810452,"score_gpt":0.43620183126280326,"score_spread":0.2249295549182419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101928545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62179035,0.0012019753,0.3731237,0.00017458378,0.00010536307,0.00006837844,0.000013375619,0.000011983238,0.0035103022],"genre_scores_gemma":[0.7235739,0.00007729197,0.276156,0.00008881899,0.000059368504,0.000003378569,0.000019803472,0.000005265963,0.000016156078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988627,0.000065333166,0.0005563676,0.00037257202,0.00002017892,0.0001228574],"domain_scores_gemma":[0.99933755,0.00009543962,0.00022806558,0.00029858304,0.000004022787,0.00003634385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017028105,0.000084202984,0.00027321515,0.00005354157,0.00004821011,0.000016931532,0.0001729606,0.000085045234,0.00035153495],"category_scores_gemma":[0.00015179139,0.000084167994,0.000032150776,0.00005011305,0.00004633862,0.0002530654,0.00008448076,0.000096481206,0.000039406033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044853827,0.00012383067,0.40236595,0.00001923858,0.000045004686,1.7025758e-7,0.0007534541,0.03620291,0.00040335025,0.056723587,0.00006427623,0.5032534],"study_design_scores_gemma":[0.00029643803,0.000037770325,0.10060914,0.0000032429361,0.0000048552097,0.000001427582,0.00004551791,0.8565396,0.00003693696,0.04197979,0.0003469187,0.00009837323],"about_ca_topic_score_codex":0.000019079387,"about_ca_topic_score_gemma":0.0000012366909,"teacher_disagreement_score":0.8203367,"about_ca_system_score_codex":0.000029506973,"about_ca_system_score_gemma":8.822103e-7,"threshold_uncertainty_score":0.3849061},"labels":[],"label_agreement":null},{"id":"W2102599529","doi":"10.1037/a0034177","title":"Why the resistance to statistical innovations? Bridging the communication gap.","year":2013,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Bridging (networking); Bridge (graph theory); Resistance (ecology); Unavailability; Publication; Computer science; Mandate; Statistical analysis; Statistical hypothesis testing; Statistical software; Publish or perish; Management science; Psychology; Data science; Statistics; Publishing; Engineering; Political science; Mathematics; Computer security","score_opus":0.46777193615161816,"score_gpt":0.5816223954573272,"score_spread":0.11385045930570903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102599529","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":[0.0022128623,0.00014426159,0.9115154,0.072776094,0.0004752893,0.0006820657,0.000014992326,0.000115928844,0.012063091],"genre_scores_gemma":[0.010069342,0.000036230136,0.9688797,0.01846568,0.00009978053,0.0005478934,0.0000069369294,0.000016782591,0.0018776482],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99506414,0.0036601906,0.0004750128,0.00028909047,0.0002208114,0.0002907717],"domain_scores_gemma":[0.9757126,0.022621488,0.00016517757,0.0011292874,0.00029091412,0.000080540456],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052448376,0.00015684005,0.00022141951,0.00005900337,0.00044199885,0.00016412955,0.0007980216,0.000084607185,0.0013608865],"category_scores_gemma":[0.0328031,0.00007894364,0.000044620756,0.0006826856,0.0003351222,0.000054785687,0.00014804692,0.00043000662,0.0001575098],"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":[0.000009217007,0.000056890323,0.000035553,0.0000058382498,0.00000939997,1.7276452e-7,0.00044362363,7.3063615e-7,0.00022287373,0.44768685,0.47281617,0.07871268],"study_design_scores_gemma":[0.0000940835,0.00002870231,0.014069783,0.000013777205,0.00001676018,0.0000059912836,0.0006893922,0.00007228321,0.00015123136,0.82866883,0.15606968,0.000119497134],"about_ca_topic_score_codex":0.000029080227,"about_ca_topic_score_gemma":0.000009518135,"teacher_disagreement_score":0.38098198,"about_ca_system_score_codex":0.000035292156,"about_ca_system_score_gemma":0.000013783419,"threshold_uncertainty_score":0.999552},"labels":[],"label_agreement":null},{"id":"W2105035924","doi":"10.1037/a0015566","title":"Integrative data analysis through coordination of measurement and analysis protocol across independent longitudinal studies.","year":2009,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":258,"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":"National Institute on Aging; National Institutes of Health","keywords":"Comparability; Replication (statistics); Sophistication; Meta-analysis; Computer science; Protocol (science); Longitudinal study; Data science; Sample (material); Statistics; Mathematics","score_opus":0.4613856083544618,"score_gpt":0.5923953237612258,"score_spread":0.13100971540676404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105035924","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":[0.0020096393,0.00020731783,0.9915514,0.0007588886,0.000055061457,0.004492419,0.00000789074,0.000043230626,0.0008741573],"genre_scores_gemma":[0.46420082,0.000026921589,0.5341372,0.0002651919,0.000017128768,0.0013321027,0.000003816716,0.0000015077107,0.000015302974],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967652,0.0007674154,0.00046832635,0.0010827148,0.0006246829,0.00029167984],"domain_scores_gemma":[0.99775445,0.0002745547,0.00030036422,0.00094229484,0.00065273634,0.00007561147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067648017,0.00018668626,0.0006165453,0.0002427234,0.00016254715,0.000107752654,0.0011583174,0.00007363235,0.000014442106],"category_scores_gemma":[0.0013716196,0.00012156706,0.0001670572,0.00502562,0.00022109448,0.0007984855,0.00058279425,0.00018594557,0.0000011568613],"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":[0.000046023433,0.0004981486,0.01199589,0.0000143010375,0.0019701861,0.000008758028,0.0027074097,0.000042440395,0.0019733906,0.0052950666,0.000090252746,0.9753581],"study_design_scores_gemma":[0.00096205523,0.0009767088,0.9156937,0.00004105502,0.0012850853,0.0000068703935,0.0012228141,0.025614936,0.0022015017,0.050635803,0.000915808,0.00044366912],"about_ca_topic_score_codex":0.000012376514,"about_ca_topic_score_gemma":0.000029902376,"teacher_disagreement_score":0.9749145,"about_ca_system_score_codex":0.00005372906,"about_ca_system_score_gemma":0.000014540288,"threshold_uncertainty_score":0.4957361},"labels":[],"label_agreement":null},{"id":"W2129748849","doi":"10.1037/a0014694","title":"Reporting practices in confirmatory factor analysis: An overview and some recommendations.","year":2009,"lang":"en","type":"review","venue":"Psychological Methods","topic":"Psychological Testing and Assessment","field":"Psychology","cited_by":2243,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Confirmatory factor analysis; Checklist; Psychology; Normality; Structural equation modeling; Test (biology); Statistics; Applied psychology; Clinical psychology; Social psychology; Mathematics","score_opus":0.8017652952165407,"score_gpt":0.719740427808512,"score_spread":0.08202486740802872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129748849","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023981371,0.9867798,0.0011408607,0.0003106509,0.0010286281,0.0008844488,0.00003848055,0.00030464897,0.0092726555],"genre_scores_gemma":[0.000048666214,0.8856504,0.11218429,0.0010720952,0.0002624838,0.0003560349,0.00014174297,0.000042592943,0.00024168355],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9812253,0.011221401,0.004160559,0.0023052664,0.0002737195,0.0008137398],"domain_scores_gemma":[0.9816696,0.0040213144,0.012372122,0.0014731179,0.000062325584,0.00040152448],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010235145,0.00085287984,0.0043440545,0.0008404549,0.00014637227,0.00018606892,0.00074715965,0.0012419007,0.0017520816],"category_scores_gemma":[0.0065516904,0.0006088299,0.00081271323,0.0020200643,0.00017055428,0.00027483577,0.0001259924,0.0021313655,0.000092353475],"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":[0.000013119509,0.0010526668,0.00036876323,0.00045077127,0.00052405644,0.00016507975,0.000098708544,1.9383255e-7,9.058977e-7,0.0025394286,0.00029488743,0.9944914],"study_design_scores_gemma":[0.00038095863,0.00055333675,0.02810687,0.0018131856,0.0018838574,0.00029473414,0.0001332586,0.000010197527,6.4227095e-8,0.005276184,0.9606275,0.0009198824],"about_ca_topic_score_codex":0.000032841035,"about_ca_topic_score_gemma":0.0000036463784,"teacher_disagreement_score":0.9935715,"about_ca_system_score_codex":0.00009947249,"about_ca_system_score_gemma":0.000039856768,"threshold_uncertainty_score":0.9996363},"labels":[],"label_agreement":null},{"id":"W2160348024","doi":"10.1037/a0034282","title":"Modeling continuous self-report measures of perceived emotion using generalized additive mixed models.","year":2013,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Categorical variable; Generalized additive model; Ambiguity; Inference; Generalized linear mixed model; Autocorrelation; Computer science; Facial expression; Mixed model; Feature (linguistics); Statistical inference; Econometrics; Artificial intelligence; Statistics; Mathematics; Machine learning","score_opus":0.39491482003814043,"score_gpt":0.5170832974120531,"score_spread":0.12216847737391262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160348024","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":[0.26376247,0.000063653264,0.73335874,0.000036288573,0.0002476143,0.00055698137,0.00001650055,0.00015750092,0.0018002521],"genre_scores_gemma":[0.2545744,0.00004041041,0.7450589,0.00007163673,0.00007563159,0.00007946288,0.000005676391,0.00003731159,0.000056586654],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953236,0.002053219,0.0010539556,0.00069372205,0.0003892035,0.00048633057],"domain_scores_gemma":[0.99673665,0.0015075409,0.0003511357,0.00054292625,0.00064186385,0.00021989686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023209231,0.00034588424,0.0009741673,0.000101688514,0.00011995045,0.00003197442,0.0002489743,0.00030625632,0.00026957152],"category_scores_gemma":[0.003631153,0.00026073144,0.00025452685,0.00021158662,0.00013551662,0.00023469797,0.00008647331,0.00034825542,0.000004564631],"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":[0.00028038048,0.0020467339,0.000028551178,0.0001733412,0.00048335944,0.000090498506,0.0020043396,0.034775466,0.20265934,0.2039095,0.00032440302,0.5532241],"study_design_scores_gemma":[0.00041571428,0.000087031854,0.00008669507,0.000029917297,0.00008255506,0.000054928463,0.00013210336,0.45372316,0.00052030536,0.5446567,0.000013565248,0.00019729626],"about_ca_topic_score_codex":0.000068628244,"about_ca_topic_score_gemma":8.602903e-7,"teacher_disagreement_score":0.5530268,"about_ca_system_score_codex":0.000062044484,"about_ca_system_score_gemma":0.000018490071,"threshold_uncertainty_score":0.9999845},"labels":[],"label_agreement":null},{"id":"W2164150544","doi":"10.1037/a0029487","title":"The ironic effect of significant results on the credibility of multiple-study articles.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":476,"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","keywords":"Credibility; Replication (statistics); Statistical power; Sample size determination; Publication; Psychology; Extrasensory perception; Replicate; Sample (material); Power (physics); Statistics; Econometrics; Statistical hypothesis testing; Social psychology; Mathematics; Medicine; Law; Political science","score_opus":0.292115897921022,"score_gpt":0.5647337317607719,"score_spread":0.2726178338397499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164150544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904841,0.0003767796,0.00060953025,0.00064088224,0.0013024344,0.001225669,0.000027408805,0.00003354074,0.0052996497],"genre_scores_gemma":[0.9980539,0.0000064517862,0.0013031665,0.000104201434,0.00008653387,0.0002608249,0.0000012301956,0.000010431086,0.00017323723],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.989743,0.008305455,0.00087994436,0.0003393271,0.00021579876,0.0005164774],"domain_scores_gemma":[0.9886681,0.009590249,0.00033922546,0.0011949962,0.00005866025,0.00014878353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014984764,0.00016976331,0.00035598144,0.00003745726,0.00017475396,0.000007383521,0.000481086,0.00014402623,0.00051071413],"category_scores_gemma":[0.003136799,0.0000720219,0.00027259497,0.0003129889,0.00045942003,0.000028431594,0.00006429901,0.0004937405,0.00007913377],"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":[0.008258574,0.01071384,0.23561199,0.00002193625,0.00010500332,0.0000023536752,0.0023685151,0.0000015897492,0.0045332224,0.005841669,0.003755689,0.72878563],"study_design_scores_gemma":[0.0015085692,0.007313294,0.9853268,0.000015576024,0.00005575317,0.0000021062426,0.0007415642,0.000014237928,0.0033144215,0.00037431787,0.0012473874,0.00008593976],"about_ca_topic_score_codex":0.0001270029,"about_ca_topic_score_gemma":0.0000073563947,"teacher_disagreement_score":0.74971485,"about_ca_system_score_codex":0.00002450021,"about_ca_system_score_gemma":0.0000046436676,"threshold_uncertainty_score":0.5591962},"labels":[],"label_agreement":null},{"id":"W2167269590","doi":"10.1037/a0034176","title":"Cognitive diagnostic assessment via Bayesian evaluation of informative diagnostic hypotheses.","year":2013,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Bayes factor; Bayes' theorem; Diagnostic test; Bayesian probability; Bayesian statistics; Cognition; Cognitive test; Psychology; Psychometrics; Machine learning; Artificial intelligence; Cognitive psychology; Computer science; Bayesian inference; Clinical psychology; Medicine; Psychiatry","score_opus":0.2813465974015578,"score_gpt":0.612014935139333,"score_spread":0.3306683377377752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167269590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3907267,0.0008330763,0.36797628,0.0008516672,0.0014865316,0.005617341,0.000038455026,0.00011084275,0.23235911],"genre_scores_gemma":[0.91574407,0.00006887514,0.07988498,0.00093411317,0.00011614907,0.0030298894,0.000025162528,0.000023829061,0.0001729259],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99004126,0.006861272,0.0008946531,0.00053548586,0.0009565827,0.0007107758],"domain_scores_gemma":[0.97127986,0.026745798,0.0003790387,0.0005323317,0.00068788073,0.00037508894],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070409253,0.00027829065,0.00050160807,0.00021380984,0.000120768345,0.000035380253,0.00039281842,0.00029522218,0.03146875],"category_scores_gemma":[0.01694317,0.00021577546,0.00012947017,0.00050537096,0.00039300605,0.00022681452,0.00012555244,0.0006673803,0.0010279136],"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":[0.000049854763,0.0010551729,0.012928871,0.000051809046,0.00009256044,0.0000071691475,0.0010293198,0.00000451705,0.00015475997,0.0019197733,0.0010961567,0.98161006],"study_design_scores_gemma":[0.0019377843,0.0014203417,0.9475886,0.00010066654,0.00009484877,0.000022462991,0.0012651157,0.0016272679,0.0003480084,0.045047447,0.00029203857,0.00025537913],"about_ca_topic_score_codex":0.00015569846,"about_ca_topic_score_gemma":0.0000039715896,"teacher_disagreement_score":0.98135465,"about_ca_system_score_codex":0.00018591726,"about_ca_system_score_gemma":0.000058642818,"threshold_uncertainty_score":0.9997499},"labels":[],"label_agreement":null},{"id":"W2193158494","doi":"10.1037/met0000059","title":"A flexible full-information approach to the modeling of response styles.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Institute of Education Sciences","keywords":"Item response theory; PsycINFO; Trait; Set (abstract data type); Computer science; Factor analysis; Statistics; Estimation; Structural equation modeling; Econometrics; Psychometrics; Psychology; Data mining; Machine learning; Mathematics","score_opus":0.8157017601333325,"score_gpt":0.6109273046144487,"score_spread":0.20477445551888385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2193158494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053339552,0.00017725024,0.87648314,0.0014945735,0.00059186644,0.00031328725,0.0000055263995,0.000082886414,0.067511946],"genre_scores_gemma":[0.26790404,0.000003539025,0.7310196,0.0008372551,0.00006373021,0.00003529468,7.3053235e-7,0.000004878409,0.00013089692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9900044,0.006632881,0.0011933143,0.00050122716,0.0012812456,0.00038688275],"domain_scores_gemma":[0.9728836,0.024554437,0.00039188497,0.0012298712,0.0006500877,0.00029012823],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08815691,0.0001737857,0.0004751481,0.0005652232,0.00012470646,0.00017313322,0.0017245549,0.00016226155,0.000058575126],"category_scores_gemma":[0.3209161,0.000085578096,0.00016232734,0.0042740325,0.0001075888,0.00029881854,0.00033239246,0.00030437886,0.000135265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002304121,0.0001720246,0.0003812743,0.0000037093198,0.000014586828,6.47763e-7,0.0016469153,0.041871265,0.0006618742,0.0044945343,0.009821615,0.9386274],"study_design_scores_gemma":[0.001963468,0.0023261267,0.020566395,0.000027369782,0.00003463091,0.00013900375,0.01881212,0.5326486,0.0005395664,0.30043623,0.12180885,0.0006976451],"about_ca_topic_score_codex":0.00001302408,"about_ca_topic_score_gemma":1.3962264e-7,"teacher_disagreement_score":0.9379298,"about_ca_system_score_codex":0.00003401548,"about_ca_system_score_gemma":0.000035390785,"threshold_uncertainty_score":0.9389343},"labels":[],"label_agreement":null},{"id":"W2320131044","doi":"10.1037/a0034524","title":"Longitudinal design considerations to optimize power to detect variances and covariances among rates of change: Simulation results based on actual longitudinal studies.","year":2013,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":98,"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":"National Institute on Aging; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Sample size determination; Statistics; Statistical power; Context (archaeology); Variance (accounting); Growth curve (statistics); Bivariate analysis; Monte Carlo method; Econometrics; Reliability (semiconductor); Mathematics; Covariance; Power (physics); Sample (material)","score_opus":0.5016745736120142,"score_gpt":0.5277738604236346,"score_spread":0.026099286811620437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320131044","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":[0.27765858,0.00059129705,0.7122042,0.0023333223,0.0008531071,0.0022906333,0.000043483582,0.0001108514,0.0039144745],"genre_scores_gemma":[0.6397707,0.0000071998384,0.35867968,0.00094207004,0.000092137416,0.00046274738,0.0000017164925,0.000012961004,0.00003079503],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961091,0.0016487351,0.0006414377,0.00094309874,0.00020879504,0.0004488079],"domain_scores_gemma":[0.9805576,0.018098352,0.00022337837,0.00040363354,0.0004908248,0.00022616178],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024242487,0.00031316877,0.00057262066,0.00020493462,0.00022118047,0.00008061686,0.00014281362,0.00016880056,0.0013974535],"category_scores_gemma":[0.0116954725,0.00024086046,0.00008395417,0.0004716585,0.00031367893,0.00017860238,0.00008036972,0.00024403824,0.00005309102],"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":[0.011624232,0.0026041525,0.0712617,0.00016439364,0.0011354162,0.00019300335,0.02095478,0.08461914,0.0030000485,0.0059027597,0.007846439,0.79069394],"study_design_scores_gemma":[0.0019198402,0.0051106936,0.97642887,0.00015934726,0.00007434023,0.000012795584,0.0011359612,0.0049243295,0.0005163038,0.009069941,0.00015792117,0.00048968],"about_ca_topic_score_codex":0.00009417966,"about_ca_topic_score_gemma":0.000009672552,"teacher_disagreement_score":0.90516716,"about_ca_system_score_codex":0.0000334563,"about_ca_system_score_gemma":0.000011437838,"threshold_uncertainty_score":0.9995154},"labels":[],"label_agreement":null},{"id":"W2329543180","doi":"10.1037/met0000015","title":"An affirmation of the phenomenological psychological descriptive method: A response to Rennie (2012).","year":2014,"lang":"en","type":"letter","venue":"Psychological Methods","topic":"Social Representations and Identity","field":"Psychology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Phenomenology (philosophy); Phenomenological method; Epistemology; Interpretation (philosophy); Psychology; Perspective (graphical); Object (grammar); Value (mathematics); Descriptive statistics; Core (optical fiber); Social psychology; Philosophy; Computer science; Mathematics; Statistics; Artificial intelligence","score_opus":0.19200363662915845,"score_gpt":0.5393592691486196,"score_spread":0.3473556325194612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2329543180","genre_codex":"methods","genre_gemma":"commentary","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":[0.05274949,0.00036412696,0.5494733,0.33611444,0.008828865,0.0030346108,0.00015734161,0.00047269036,0.048805147],"genre_scores_gemma":[0.027291918,0.000021508735,0.4801985,0.48131514,0.0038436155,0.0011792079,0.00007851367,0.00014152586,0.0059300745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95977443,0.034704,0.0014747722,0.002103862,0.00082426926,0.001118667],"domain_scores_gemma":[0.99024343,0.0048504374,0.0010126049,0.0031512019,0.00042464535,0.00031769622],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009013905,0.00079355296,0.0015084097,0.00044583852,0.0003729908,0.00013667469,0.0027366646,0.003311615,0.0066420017],"category_scores_gemma":[0.004457502,0.00051367894,0.00082277047,0.0015469507,0.00080582214,0.00017278161,0.00034819267,0.0036932293,0.000624404],"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":[0.0020955398,0.0012031269,0.00018710268,0.000022021248,0.00020680588,0.00007253583,0.0027021947,0.000011230085,0.0054443283,0.0030446455,0.9043121,0.08069841],"study_design_scores_gemma":[0.0015370016,0.0041639213,0.13291065,0.000064550695,0.00031606184,0.0002000447,0.0011600499,0.00002500227,0.00013603545,0.05330236,0.80499417,0.0011901438],"about_ca_topic_score_codex":0.00010145179,"about_ca_topic_score_gemma":0.0000037346892,"teacher_disagreement_score":0.14520068,"about_ca_system_score_codex":0.00019554987,"about_ca_system_score_gemma":0.000030049967,"threshold_uncertainty_score":0.9997315},"labels":[],"label_agreement":null},{"id":"W2395889112","doi":"10.1037/met0000075","title":"Testing measurement invariance in longitudinal data with ordered-categorical measures.","year":2016,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":344,"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 Health Network","funders":"National Institute of Mental Health","keywords":"Categorical variable; Measurement invariance; Item response theory; Latent variable; Metric (unit); Latent variable model; Psychology; Econometrics; Statistics; Structural equation modeling; Psychometrics; Computer science; Confirmatory factor analysis; Mathematics","score_opus":0.49908626373203135,"score_gpt":0.48438075925113383,"score_spread":0.014705504480897524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395889112","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":[0.00015841534,0.00014321238,0.9952041,0.0021095627,0.00012720875,0.00025173707,0.000003828915,0.0004850708,0.0015168474],"genre_scores_gemma":[0.30284098,0.000011512858,0.6968479,0.00020185894,0.000032660784,0.000048419588,4.6211687e-7,0.0000107060705,0.0000054529146],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99602973,0.00083972473,0.00047619914,0.001421909,0.00066546886,0.0005669456],"domain_scores_gemma":[0.995767,0.0016641407,0.00013684285,0.0019595681,0.00028918224,0.00018326227],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004687258,0.00025643152,0.00037050742,0.00009709947,0.000078853656,0.00007301821,0.002615007,0.00012777511,0.000015504347],"category_scores_gemma":[0.00927223,0.00014006096,0.000022931326,0.00088800635,0.00017971337,0.0005318405,0.00076221925,0.0003457632,0.000018014533],"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":[0.00005219878,0.00024541636,0.002184003,0.000005033516,0.000008341123,0.00009401552,0.000010979449,0.000018489332,0.005529435,0.06271091,0.0001480565,0.9289931],"study_design_scores_gemma":[0.0013342457,0.0009356335,0.07640392,0.00021698787,0.000014704144,0.00019912788,0.0000031228633,0.027812675,0.0010390142,0.8892727,0.0019828165,0.00078506436],"about_ca_topic_score_codex":0.000017638156,"about_ca_topic_score_gemma":0.00001194862,"teacher_disagreement_score":0.92820805,"about_ca_system_score_codex":0.00014021588,"about_ca_system_score_gemma":0.00005048131,"threshold_uncertainty_score":0.9990731},"labels":[],"label_agreement":null},{"id":"W2412046924","doi":"10.1037/met0000071","title":"Dynamical correlation: A new method for quantifying synchrony with multivariate intensive longitudinal data.","year":2016,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences North","funders":"","keywords":"Correlation; Nonparametric statistics; Bivariate analysis; Homogeneity (statistics); Multivariate statistics; Dynamical systems theory; Statistical hypothesis testing; Computer science; Population; Statistics; Econometrics; Mathematics; Data mining","score_opus":0.39901170294233734,"score_gpt":0.525208746155382,"score_spread":0.1261970432130447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2412046924","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":[0.0030239439,0.000052949697,0.9752338,0.019243838,0.001080025,0.0005919403,0.00006983061,0.00017479753,0.0005288994],"genre_scores_gemma":[0.11933958,0.000011698294,0.87599367,0.0037095165,0.00028739194,0.000087616885,0.000004752717,0.000031126183,0.00053462724],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959539,0.0012265465,0.00034946183,0.001700014,0.00029004802,0.00048000412],"domain_scores_gemma":[0.9480619,0.050502554,0.00019869971,0.00085451186,0.00020549266,0.00017685174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018544461,0.0002997276,0.0004683053,0.00009449796,0.00028113628,0.0000501984,0.0006070136,0.00016028948,0.00015830467],"category_scores_gemma":[0.07899409,0.0001622226,0.00010344412,0.00040150093,0.00031213753,0.000348155,0.00035586703,0.00026936425,0.00005882003],"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":[0.003357474,0.0003594843,0.0037554197,0.000029115185,0.00013756489,0.000057273093,0.00017173648,0.0001005808,0.3874811,0.03694811,0.010192973,0.55740917],"study_design_scores_gemma":[0.026315516,0.011394973,0.33764765,0.000895679,0.0008119422,0.0028744184,0.00062512734,0.2230766,0.070932224,0.19711207,0.123675555,0.004638255],"about_ca_topic_score_codex":0.000020135682,"about_ca_topic_score_gemma":0.000011625899,"teacher_disagreement_score":0.5527709,"about_ca_system_score_codex":0.00007801037,"about_ca_system_score_gemma":0.000036138634,"threshold_uncertainty_score":0.9287639},"labels":[],"label_agreement":null},{"id":"W2417673837","doi":"10.1037/met0000053","title":"Partial least squares correspondence analysis: A framework to simultaneously analyze behavioral and genetic data.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; National Institute on Drug Abuse; Agence Nationale de la Recherche; U.S. Department of Defense","keywords":"Partial least squares regression; Categorical variable; Computer science; Correspondence analysis; Multivariate statistics; Artificial intelligence; Multivariate analysis; Statistics; Machine learning; Data mining; Psychology; Mathematics","score_opus":0.2672039613477072,"score_gpt":0.4999134662670226,"score_spread":0.2327095049193154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417673837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6343272,0.00027057438,0.36398917,0.0007295505,0.00017700088,0.0001721049,0.00011990052,0.000077118515,0.00013740122],"genre_scores_gemma":[0.5218049,0.000014127979,0.47722057,0.00065216486,0.00018911423,0.000015092132,0.000032758533,0.0000014303613,0.00006983822],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946281,0.002591798,0.0005531699,0.001265392,0.00043180486,0.0005297927],"domain_scores_gemma":[0.9949412,0.0034215075,0.00013199433,0.00045369635,0.00015466606,0.0008969552],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021628574,0.00029931962,0.000714128,0.00006717387,0.00018078717,0.00020115254,0.00085982896,0.00026884885,0.0010113877],"category_scores_gemma":[0.0048194076,0.000121031066,0.00016343682,0.0022584528,0.00021350551,0.00009230112,0.00035519752,0.0003539523,0.00006378961],"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":[0.000514302,0.00050312805,0.019599155,0.0000025640916,0.00018271735,0.00018633067,0.00019225173,0.0007493677,0.010123212,0.0005763446,0.00046213565,0.9669085],"study_design_scores_gemma":[0.00044536722,0.0043775686,0.8783264,0.000032229527,0.0024955706,0.00012537866,0.0014802011,0.06304579,0.00027594,0.01876466,0.029160252,0.0014705963],"about_ca_topic_score_codex":0.00016606839,"about_ca_topic_score_gemma":0.00011673372,"teacher_disagreement_score":0.9654379,"about_ca_system_score_codex":0.000018643763,"about_ca_system_score_gemma":0.0000055612545,"threshold_uncertainty_score":0.99990183},"labels":[],"label_agreement":null},{"id":"W2460913564","doi":"10.1037/met0000055","title":"A correction factor for the impact of cluster randomized sampling and its applications.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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":"Université du Québec à Trois-Rivières; University of Ottawa","funders":"","keywords":"Statistics; Spurious relationship; Cluster sampling; Sample size determination; Statistical power; Sampling (signal processing); Covariate; Cluster analysis; Variance (accounting); Population; Cluster (spacecraft); Mathematics; Standard error; Confidence interval; Sample (material); Population variance; Statistical hypothesis testing; Type I and type II errors; Econometrics; Computer science; Demography; Filter (signal processing)","score_opus":0.19036396902259523,"score_gpt":0.5067937905813413,"score_spread":0.3164298215587461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460913564","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":[0.00089048344,0.0010913257,0.99534863,0.000375958,0.0004883778,0.0011679194,0.0000035108671,0.000047577658,0.00058622437],"genre_scores_gemma":[0.067677,0.0000534992,0.93160814,0.00017226765,0.000081081635,0.00033477115,3.5870178e-7,0.000005202047,0.00006767327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810743,0.0010675957,0.000268586,0.00030900168,0.00008761894,0.00015974701],"domain_scores_gemma":[0.9926527,0.006627457,0.00014771741,0.00032341608,0.00014383758,0.00010488671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046554334,0.00011731175,0.00036375748,0.00004352433,0.00007413225,0.00005025749,0.00036399328,0.00010119265,0.0000058162864],"category_scores_gemma":[0.0019554158,0.00005651916,0.00019704206,0.00020932834,0.00007247985,0.00009692477,0.00008122711,0.00012997437,0.0000010290523],"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":[0.001823138,0.00005381997,0.000008520891,0.0000047742997,0.00003701561,5.6186128e-8,0.00030396596,0.000045143974,0.0011448583,0.016008412,0.00021112098,0.9803592],"study_design_scores_gemma":[0.028932754,0.00041456756,0.0015875627,0.000013197124,0.000045873076,0.00004358957,0.000015942705,0.5523791,0.0011845538,0.41362995,0.0015175464,0.00023535428],"about_ca_topic_score_codex":0.0000062107733,"about_ca_topic_score_gemma":1.1558927e-7,"teacher_disagreement_score":0.9801238,"about_ca_system_score_codex":0.000015754486,"about_ca_system_score_gemma":0.000014988579,"threshold_uncertainty_score":0.23409566},"labels":[],"label_agreement":null},{"id":"W2470860284","doi":"10.1037/met0000036","title":"Planning sample sizes when effect sizes are uncertain: The power-calibrated effect size approach.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Sample size determination; Statistical power; Sample (material); Statistics; Replication (statistics); Computer science; Power (physics); Confidence interval; Econometrics; Mathematics","score_opus":0.6449695789679178,"score_gpt":0.6157682207415001,"score_spread":0.029201358226417784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470860284","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":[0.023378694,0.00035600952,0.94609797,0.001460722,0.0021277752,0.0042526913,0.00007790025,0.00094130076,0.02130696],"genre_scores_gemma":[0.020096174,0.0000046791115,0.97634995,0.0014940037,0.00058846385,0.0011992861,0.0000030480605,0.000106948566,0.00015743972],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96092165,0.03429405,0.0015082697,0.0013418744,0.0009009516,0.0010332108],"domain_scores_gemma":[0.5883963,0.4090869,0.00059579295,0.0012547178,0.0001465317,0.0005197146],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03699339,0.0008121863,0.0023127173,0.00007406262,0.00027891324,0.00023592275,0.0014571028,0.0008329925,0.0010221609],"category_scores_gemma":[0.62264806,0.00041885886,0.00057028054,0.00074094784,0.000851589,0.00011737971,0.0004246324,0.0015363006,0.000074093776],"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":[0.025730183,0.006119605,0.043043915,0.0018986379,0.002922186,0.00061781483,0.0049744095,0.00040777033,0.004628019,0.12923418,0.22464047,0.5557828],"study_design_scores_gemma":[0.0041719875,0.0032445826,0.0052533415,0.00016929177,0.00027163196,0.00004551326,0.00021963644,0.00068087305,0.0011659334,0.9807897,0.0032977865,0.0006897219],"about_ca_topic_score_codex":0.000018556677,"about_ca_topic_score_gemma":3.4278904e-7,"teacher_disagreement_score":0.8515555,"about_ca_system_score_codex":0.00009207883,"about_ca_system_score_gemma":0.00003153883,"threshold_uncertainty_score":0.99989104},"labels":[],"label_agreement":null},{"id":"W2474654233","doi":"10.1037/met0000048","title":"Modeling intensive longitudinal data with mixtures of nonparametric trajectories and time-varying effects.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"National Cancer Institute; National Institute on Drug Abuse","keywords":"Covariate; Semiparametric regression; Nonparametric statistics; Econometrics; Population; Regression analysis; Regression; Statistics; Mathematics; Latent variable; Linear regression; Semiparametric model; Demography","score_opus":0.2803564483775052,"score_gpt":0.498751203955735,"score_spread":0.21839475557822985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474654233","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":[0.041942928,0.00046991996,0.9555964,0.00006973541,0.00013762483,0.00023656868,0.000020357265,0.00004884701,0.0014776493],"genre_scores_gemma":[0.16166967,0.000013767753,0.8381526,0.0000745652,0.000049471804,0.000012090313,0.0000037312923,0.00001562169,0.000008489863],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753904,0.0009666995,0.00038154743,0.00057796884,0.0002601511,0.00027456335],"domain_scores_gemma":[0.99136597,0.007309073,0.00013010959,0.0006535844,0.00034051144,0.00020076387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023698974,0.0002264421,0.0006690074,0.00010975667,0.000047908492,0.000037753583,0.00038944065,0.00014527394,0.000030610758],"category_scores_gemma":[0.026715154,0.00013893939,0.00003442555,0.00047204885,0.00028108177,0.00010917705,0.00021371465,0.00030809257,0.0000028061354],"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":[0.0019114092,0.0008921549,0.004525251,0.00078427105,0.00042239056,0.00017640932,0.0013077687,0.000051537645,0.009889004,0.18471038,0.0010731253,0.79425627],"study_design_scores_gemma":[0.0009258639,0.001268308,0.0012794486,0.00015806855,0.00020401689,0.00012364585,0.00011535012,0.059608705,0.0021610497,0.93381524,0.000012801335,0.00032748104],"about_ca_topic_score_codex":0.000019248542,"about_ca_topic_score_gemma":4.3854047e-7,"teacher_disagreement_score":0.7939288,"about_ca_system_score_codex":0.000013078575,"about_ca_system_score_gemma":0.0000178721,"threshold_uncertainty_score":0.9814832},"labels":[],"label_agreement":null},{"id":"W2522861822","doi":"10.1037/met0000084","title":"The impact of total and partial inclusion or exclusion of active and inactive time invariant covariates in growth mixture models.","year":2016,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Covariate; Statistics; Mathematics; Bayesian information criterion; Akaike information criterion; Econometrics; Population; Sample size determination; Latent class model; Demography","score_opus":0.08867699414247705,"score_gpt":0.46423015804126466,"score_spread":0.3755531638987876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2522861822","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":[0.27634144,0.00005325941,0.72241825,0.00024208892,0.000033427743,0.00024837803,0.000043686778,0.000010117083,0.00060934824],"genre_scores_gemma":[0.4834335,0.00011785507,0.5163938,0.000009748903,0.000014260867,0.000012032189,2.5763433e-7,0.0000068311465,0.000011711855],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723744,0.0016348615,0.00043465645,0.00031280078,0.00015641439,0.00022384698],"domain_scores_gemma":[0.9858742,0.013485725,0.00024494028,0.00019984489,0.00010381227,0.00009150483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001973576,0.00017851035,0.0005086401,0.000059876627,0.00011084426,0.000011272941,0.00013823553,0.00019639077,0.00011982903],"category_scores_gemma":[0.007804299,0.000069102935,0.000061387036,0.00020907568,0.000412384,0.00010193551,0.00052326964,0.00018131868,3.4998533e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035994933,0.00045820506,0.00026560502,0.000043871718,0.000066458255,0.000011175142,0.0015909859,4.363037e-7,0.10594475,0.30310866,0.000042541044,0.58486784],"study_design_scores_gemma":[0.0008469956,0.0010519857,0.024017401,0.00012009051,0.000023010864,0.000023681223,0.000047470483,0.0025460115,0.008381666,0.96282226,0.0000011388335,0.000118260214],"about_ca_topic_score_codex":0.00006485008,"about_ca_topic_score_gemma":0.0000017390785,"teacher_disagreement_score":0.6597136,"about_ca_system_score_codex":0.000036058962,"about_ca_system_score_gemma":0.00002285585,"threshold_uncertainty_score":0.9343038},"labels":[],"label_agreement":null},{"id":"W2558952171","doi":"10.1037/met0000097","title":"Type I error rates and power of several versions of scaled chi-square difference tests in investigations of measurement invariance.","year":2016,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Type I and type II errors; Mathematics; Measurement invariance; Sample size determination; Goodness of fit; Monte Carlo method; Confirmatory factor analysis; Population; Statistical power; Chi-square test; Econometrics; Structural equation modeling; Demography","score_opus":0.679952449318081,"score_gpt":0.5593365285098917,"score_spread":0.12061592080818928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558952171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8983172,0.00034737182,0.09849953,0.00059256726,0.00036623416,0.00019727109,0.00001473866,0.000013531934,0.0016515179],"genre_scores_gemma":[0.64255726,0.000030750118,0.35731894,0.000045163913,0.000006512357,0.000005259279,1.6373674e-7,0.000003321392,0.00003260657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99507314,0.0023829371,0.0010678214,0.00050504674,0.00073818787,0.00023286855],"domain_scores_gemma":[0.97442764,0.02357387,0.0006461958,0.0006023569,0.0006179008,0.00013204069],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011008177,0.00015097586,0.00065339514,0.00044296327,0.00004136631,0.000011520079,0.00057971216,0.00015397197,0.00035450514],"category_scores_gemma":[0.1933334,0.00007945688,0.000088226436,0.0023978152,0.00056657026,0.00009144445,0.00017696386,0.00014643797,0.000003021747],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021301994,0.00038793834,0.673287,0.000021224381,0.00002480731,0.0000017972511,0.0004032346,0.00001606419,0.1871465,0.0027457864,0.0002603309,0.13549235],"study_design_scores_gemma":[0.0006512096,0.00046437577,0.9055998,0.00014862418,0.0000081499,0.0000033037022,0.00019192281,0.0000841603,0.004589336,0.08809432,0.00006667061,0.000098169876],"about_ca_topic_score_codex":0.000019448871,"about_ca_topic_score_gemma":0.000005278924,"teacher_disagreement_score":0.2588194,"about_ca_system_score_codex":0.000020022204,"about_ca_system_score_gemma":0.000037199286,"threshold_uncertainty_score":0.8134615},"labels":[],"label_agreement":null},{"id":"W2593944763","doi":"10.1037/met0000126","title":"Reporting effect sizes in original psychological research: A discussion and tutorial.","year":2017,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Categorical variable; PsycINFO; Psychology; Mediation; Variety (cybernetics); Interpretation (philosophy); Statistical hypothesis testing; Regression analysis; Statistics; MEDLINE; Computer science; Mathematics","score_opus":0.6435478184034068,"score_gpt":0.7307775730395879,"score_spread":0.0872297546361811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593944763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89924103,0.0004819215,0.0009010805,0.005393686,0.00388085,0.0013081459,0.0000042550787,0.00011611083,0.08867291],"genre_scores_gemma":[0.92080355,0.00012540538,0.07373878,0.00026244004,0.00111211,0.0005951574,0.000003647442,0.00003890713,0.0033200171],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9848577,0.0097859455,0.0015019823,0.0016166976,0.00071645546,0.0015212215],"domain_scores_gemma":[0.99337125,0.003187571,0.00085929676,0.0018989125,0.00009169607,0.00059130095],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04144841,0.00033632762,0.0008601474,0.00030377484,0.0009848108,0.0002748216,0.0010450928,0.000655888,0.001874794],"category_scores_gemma":[0.02704017,0.00018825615,0.00013610678,0.00034711324,0.0012322763,0.00018753446,0.0005828542,0.002482066,0.0002317771],"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":[0.001665097,0.00078113197,0.13054869,0.00007103139,0.000017527489,0.0009582051,0.00042455507,1.035581e-7,0.002381005,0.008926114,0.0022561033,0.85197043],"study_design_scores_gemma":[0.0025961555,0.003348892,0.9273007,0.00013097502,0.000007798495,0.00025944173,0.0001709342,0.000022594308,0.00018812614,0.032242514,0.033418093,0.00031381278],"about_ca_topic_score_codex":0.00021883215,"about_ca_topic_score_gemma":0.000018867097,"teacher_disagreement_score":0.8516566,"about_ca_system_score_codex":0.00013237594,"about_ca_system_score_gemma":0.00001732506,"threshold_uncertainty_score":0.9998192},"labels":[],"label_agreement":null},{"id":"W2624920789","doi":"10.1037/met0000151","title":"ExperienceSampler: An open-source scaffold for building smartphone apps for experience sampling.","year":2017,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":87,"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","keywords":"Experience sampling method; Computer science; The Internet; Android (operating system); Internet access; PsycINFO; Sampling (signal processing); World Wide Web; Multimedia; Usage data; Operating system; Psychology; Telecommunications","score_opus":0.6325151645478696,"score_gpt":0.6907879567918435,"score_spread":0.05827279224397386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624920789","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":[0.27938855,0.0003010762,0.70641214,0.00094852055,0.0029295662,0.003104027,0.000048891314,0.00013740239,0.006729852],"genre_scores_gemma":[0.18900439,0.000020926127,0.7997251,0.0014824249,0.0005770681,0.0069234287,0.000015819172,0.000060506874,0.0021903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950938,0.0008902894,0.0007061185,0.0016157081,0.0002966732,0.0013973597],"domain_scores_gemma":[0.99420196,0.0021565903,0.00043376483,0.0023520621,0.00015970544,0.00069594366],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056369645,0.00035742993,0.00064833014,0.00010350701,0.0020053873,0.0006266039,0.0040469407,0.00039713125,0.0015517006],"category_scores_gemma":[0.0031246934,0.00029709644,0.0001629505,0.00014227258,0.0006512307,0.0004838169,0.00065015093,0.00033937555,0.00003205657],"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":[0.0014960013,0.00088975456,0.0013619522,0.000048189064,0.000027264572,0.000004053263,0.0033142853,0.0000014342189,0.010097888,0.034488507,0.0018649775,0.9464057],"study_design_scores_gemma":[0.0068737897,0.006804494,0.05653662,0.00010082615,0.000028388004,0.0000709846,0.0054212455,0.00076636387,0.0063095773,0.06471913,0.8511777,0.0011908783],"about_ca_topic_score_codex":0.00021703262,"about_ca_topic_score_gemma":0.000013907412,"teacher_disagreement_score":0.9452148,"about_ca_system_score_codex":0.00008486778,"about_ca_system_score_gemma":0.000027325983,"threshold_uncertainty_score":0.99994814},"labels":[],"label_agreement":null},{"id":"W2778345604","doi":"10.1037/met0000112","title":"An alternative to post hoc model modification in confirmatory factor analysis: The Bayesian lasso.","year":2017,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Wake Forest Clinical and Translational Science Institute, Wake Forest School of Medicine; National Center for Advancing Translational Sciences; China Scholarship Council; National Natural Science Foundation of China","keywords":"Residual; Covariance; Computer science; Bayesian probability; Covariance matrix; Overfitting; Mathematics; Statistics; Robustness (evolution); Algorithm; Artificial intelligence","score_opus":0.42000440021908697,"score_gpt":0.6572029316560931,"score_spread":0.23719853143700614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778345604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6402778,0.00012408657,0.32958362,0.006791747,0.0005932088,0.0010277224,0.000079218735,0.000062631916,0.021459984],"genre_scores_gemma":[0.9241846,0.00002054607,0.07222177,0.0025405632,0.00011542997,0.00034722377,0.000010768324,0.000017349525,0.0005417278],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948252,0.0029595844,0.00048143175,0.0007859726,0.00033256365,0.00061528326],"domain_scores_gemma":[0.99662656,0.0004732383,0.0002467414,0.0021286993,0.000116314106,0.00040848044],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031528878,0.00021083231,0.00039836275,0.0002791885,0.0003782221,0.00014201255,0.0016635415,0.00023207357,0.0010489809],"category_scores_gemma":[0.0006052256,0.00014018216,0.00012853662,0.00032670636,0.00023580201,0.00016154161,0.00012365464,0.0006412405,0.00018342843],"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":[0.0018786229,0.0024394696,0.038882427,0.000027546655,0.000507454,0.000076256256,0.011834655,0.0012250694,0.006520149,0.061590027,0.0007696397,0.8742487],"study_design_scores_gemma":[0.0007561288,0.00067074056,0.9439463,0.000009046598,0.00004582721,0.000004190711,0.0006845181,0.04302287,0.00017834864,0.009246822,0.0011782397,0.00025693615],"about_ca_topic_score_codex":0.00037194943,"about_ca_topic_score_gemma":0.00015783477,"teacher_disagreement_score":0.9050639,"about_ca_system_score_codex":0.00010376946,"about_ca_system_score_gemma":0.000019799705,"threshold_uncertainty_score":0.9998642},"labels":[],"label_agreement":null},{"id":"W2803568088","doi":"10.1037/met0000181","title":"A comparison of several approaches for controlling measurement error in small samples.","year":2018,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structural equation modeling; Reliability (semiconductor); Statistics; Latent variable; Standard error; Mathematics; Inference; Observational error; Variable (mathematics); Econometrics; Computer science; Power (physics); Artificial intelligence","score_opus":0.9584692213383208,"score_gpt":0.6539327846799784,"score_spread":0.3045364366583424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803568088","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15148069,0.0005094015,0.84162205,0.00036099157,0.0008574954,0.00053449743,0.0000064955566,0.00003963605,0.004588724],"genre_scores_gemma":[0.4829129,0.0000015688464,0.51678604,0.0001171576,0.000106853746,0.000048015394,4.2179596e-7,0.000006152167,0.00002093141],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99282527,0.003305934,0.0016523595,0.00093397324,0.0007418444,0.0005406418],"domain_scores_gemma":[0.9553593,0.04235062,0.0007647714,0.0007668474,0.00061388133,0.00014458054],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051778648,0.00022423833,0.0011398235,0.0005044796,0.00011641431,0.000068806905,0.0010977829,0.00022585089,0.00016151131],"category_scores_gemma":[0.20021018,0.00014311963,0.00026944897,0.001919076,0.00034292025,0.00006531119,0.00012934428,0.00026586218,0.0000084505755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006339564,0.0005436441,0.07144773,0.000012102375,0.000028234519,6.3754254e-7,0.00053756224,0.00033089705,0.0026172632,0.0029152678,0.0005056921,0.920427],"study_design_scores_gemma":[0.0036947723,0.0024248536,0.51660687,0.000059953723,0.000037012764,0.0000083285595,0.0020567204,0.08559465,0.003244027,0.3763879,0.009382405,0.0005025009],"about_ca_topic_score_codex":0.000022750495,"about_ca_topic_score_gemma":0.000021041235,"teacher_disagreement_score":0.9199245,"about_ca_system_score_codex":0.000048380934,"about_ca_system_score_gemma":0.000020998245,"threshold_uncertainty_score":0.9763934},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2888454927","doi":"10.1037/met0000176","title":"A cautionary note on the finite sample behavior of maximal reliability.","year":2018,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Safety Canada","funders":"Aalto-Yliopisto; Academy of Finland","keywords":"Reliability (semiconductor); Sample (material); Statistics; Mathematics; Psychology; Econometrics; Applied mathematics; Physics; Thermodynamics","score_opus":0.056199717784466405,"score_gpt":0.38422726487056996,"score_spread":0.32802754708610354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888454927","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":[0.11069176,0.000026229542,0.87925774,0.00061764085,0.0006276983,0.0003069102,0.000023796454,0.00015383384,0.008294393],"genre_scores_gemma":[0.5393152,0.000036740756,0.46020517,0.00024553714,0.00007788471,0.000074590745,0.000004015517,0.000010562126,0.000030282476],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989177,0.0002901528,0.0002643389,0.00022339536,0.00011317142,0.0001912241],"domain_scores_gemma":[0.9974042,0.0019761517,0.000037513597,0.0004533598,0.00008510853,0.00004362775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011587985,0.000116842806,0.00016399432,0.000033812445,0.000064671876,0.0000092396,0.00019767952,0.00013981198,0.0006283738],"category_scores_gemma":[0.0026759303,0.00007128824,0.000088144014,0.0002451889,0.0003110936,0.00004114908,0.00002806667,0.00021560008,0.00003594234],"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":[0.0010316689,0.0023990285,0.00445531,0.0001673926,0.00008007233,0.000011046318,0.0017341719,0.11726264,0.049280662,0.06336186,0.008053745,0.7521624],"study_design_scores_gemma":[0.00156867,0.0045495797,0.25171208,0.00014718626,0.00017307537,0.000024432838,0.0001859502,0.37863648,0.042833928,0.2317376,0.08716099,0.001270014],"about_ca_topic_score_codex":0.000006985661,"about_ca_topic_score_gemma":6.3149656e-7,"teacher_disagreement_score":0.7508924,"about_ca_system_score_codex":0.000029978419,"about_ca_system_score_gemma":0.0000036136616,"threshold_uncertainty_score":0.68802524},"labels":[],"label_agreement":null},{"id":"W2914981656","doi":"10.1037/met0000337","title":"Power contours: Optimising sample size and precision in experimental psychology and human neuroscience.","year":2020,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":212,"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":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Medical Research Council; Centre for Chronic Diseases and Disorders; University of Cambridge; Wellcome Trust","keywords":"Sample size determination; Statistical power; Variance (accounting); Sample (material); Design of experiments; Power (physics); Meaning (existential); Statistical hypothesis testing; Experimental data","score_opus":0.27881685704017695,"score_gpt":0.5244552156108684,"score_spread":0.24563835857069144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914981656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97635627,0.00009257126,0.015534981,0.002376182,0.00024388816,0.00025235148,0.0000059481526,0.00007789545,0.005059942],"genre_scores_gemma":[0.9092317,0.00010653434,0.07633995,0.014255651,0.000030233512,0.000015107819,4.007011e-7,0.000009276164,0.000011140352],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9975408,0.0009895266,0.0002545964,0.00082628004,0.00013091779,0.0002579364],"domain_scores_gemma":[0.99848235,0.0011083677,0.000060010927,0.00013005639,0.000009269619,0.00020994458],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005455039,0.0001511325,0.00022341248,0.000054372456,0.00013307478,0.00008052215,0.0001503865,0.00013015929,0.0010030379],"category_scores_gemma":[0.00331664,0.00012465882,0.000034196135,0.00026494046,0.00035492665,0.00015358161,0.0000922686,0.00027314533,0.000008272133],"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":[0.00009052193,0.00013535321,0.0006346387,0.0000020805328,2.4033665e-7,0.000008570444,0.00045029208,0.0000017510741,0.9666196,0.00018167334,0.000067647656,0.031807628],"study_design_scores_gemma":[0.007912426,0.007923087,0.69594675,0.0000751995,0.000013669207,0.00042100652,0.0010674502,0.0024748005,0.2388111,0.025329301,0.018634379,0.0013908196],"about_ca_topic_score_codex":0.0000036930812,"about_ca_topic_score_gemma":3.4894515e-7,"teacher_disagreement_score":0.7278085,"about_ca_system_score_codex":0.000008484105,"about_ca_system_score_gemma":0.0000020926186,"threshold_uncertainty_score":0.9999102},"labels":[],"label_agreement":null},{"id":"W2963126549","doi":"10.1037/met0000163","title":"Parameter uncertainty in structural equation models: Confidence sets and fungible estimates.","year":2018,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Thriving; Structural equation modeling; PsycINFO; Context (archaeology); Proxy (statistics); Psychology; Statistics; Mathematics; Political science; MEDLINE; History; Law","score_opus":0.40841950830771173,"score_gpt":0.5997492743696715,"score_spread":0.19132976606195978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963126549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8157276,0.000916129,0.14646041,0.00088699243,0.0011618618,0.00081098755,0.00001174328,0.00010419578,0.033920106],"genre_scores_gemma":[0.7350297,0.000028562585,0.263663,0.00090893434,0.00008065625,0.000094846815,0.000005985317,0.000011631704,0.00017665594],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99666524,0.0013832202,0.0004252208,0.0006707307,0.00021650792,0.0006390684],"domain_scores_gemma":[0.99757916,0.0015903831,0.000090891335,0.00043612864,0.00007220767,0.00023124844],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002394711,0.00018647822,0.0003018336,0.00013513146,0.00010482957,0.0000422643,0.00026000856,0.00026204123,0.002518184],"category_scores_gemma":[0.00076711865,0.0001427443,0.000036100406,0.00032343608,0.0004621348,0.00013532756,0.000100402154,0.00045073213,0.000114601076],"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":[0.0007616043,0.00018701176,0.010039373,0.000052476855,0.00002579767,0.000042694275,0.0018658935,0.00007348996,0.00078791776,0.11495721,0.00054562866,0.8706609],"study_design_scores_gemma":[0.0013820013,0.0013391812,0.17311303,0.000043173324,0.0000093759745,0.000081882696,0.00026072565,0.16864416,0.00019977713,0.6538895,0.00072652305,0.0003107201],"about_ca_topic_score_codex":0.00035589153,"about_ca_topic_score_gemma":0.000027698781,"teacher_disagreement_score":0.8703502,"about_ca_system_score_codex":0.000071865776,"about_ca_system_score_gemma":0.000015215651,"threshold_uncertainty_score":0.99839365},"labels":[],"label_agreement":null},{"id":"W2963672622","doi":"10.1037/met0000175","title":"Alternating optimization for G × E modelling with weighted genetic and environmental scores: Examples from the MAVAN study.","year":2018,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Linear model; Statistics; Genetic algorithm; Computer science; Construct (python library); Mixed model; R package; Econometrics; Mathematics; Machine learning","score_opus":0.257036098063129,"score_gpt":0.5134929462929112,"score_spread":0.2564568482297822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963672622","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":[0.48598388,0.00026631987,0.5121844,0.000113169204,0.00017213813,0.00084001885,0.000018980265,0.000023574989,0.00039755576],"genre_scores_gemma":[0.3826576,0.00004311183,0.61627895,0.0003572498,0.0003254384,0.00022920802,0.000013784124,0.000020190058,0.00007450451],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714404,0.001277091,0.00031564705,0.0006449132,0.00021202024,0.000406262],"domain_scores_gemma":[0.9977739,0.0015000517,0.000117729316,0.0004465568,0.000023396737,0.00013836753],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012104084,0.00017509543,0.00020844614,0.00003919572,0.00033952866,0.00005133743,0.0003015532,0.000100409125,0.001201701],"category_scores_gemma":[0.00004201863,0.00010276879,0.000029335068,0.000101884194,0.00032909546,0.000042070267,0.000085715146,0.0002241938,0.000013795595],"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":[0.0021462848,0.0016614351,0.10354782,0.000021961301,0.0002480347,0.000025372105,0.008362892,0.0011657887,0.0005862496,0.0010310061,0.00029721085,0.8809059],"study_design_scores_gemma":[0.009806221,0.01560883,0.33648804,0.00010557589,0.00019357921,0.00007791262,0.011007232,0.6005635,0.00039547466,0.016609237,0.008177982,0.00096636906],"about_ca_topic_score_codex":0.00017360273,"about_ca_topic_score_gemma":0.0000143014195,"teacher_disagreement_score":0.87993956,"about_ca_system_score_codex":0.000032990436,"about_ca_system_score_gemma":0.0000045439106,"threshold_uncertainty_score":0.99971133},"labels":[],"label_agreement":null},{"id":"W3006757787","doi":"10.1037/met0000254","title":"Comparing Gaussian graphical models with the posterior predictive distribution and Bayesian model selection.","year":2020,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Institute of General Medical Sciences; National Academies of Sciences, Engineering, and Medicine; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Bayesian probability; Posterior probability; Statistics; Model selection; Selection (genetic algorithm); Graphical model; Bayesian linear regression; Posterior predictive distribution; Gaussian; Mathematics; Econometrics; Computer science; Artificial intelligence; Bayesian inference","score_opus":0.21833325465925038,"score_gpt":0.4943070645323446,"score_spread":0.27597380987309417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006757787","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":[0.105138466,0.00017668764,0.8708341,0.015061211,0.0000841766,0.0006433146,0.000026790745,0.00012804565,0.0079072155],"genre_scores_gemma":[0.91998667,0.000018420378,0.07690652,0.0026706676,0.00012242157,0.00018363055,0.000013664495,0.000018271818,0.00007974434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967274,0.0015331879,0.00028164886,0.0006659841,0.00026757154,0.00052418414],"domain_scores_gemma":[0.99881375,0.00032163927,0.00008918096,0.00025545538,0.000057448495,0.00046251138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00099917,0.00020686122,0.00031027934,0.000033629876,0.00030647547,0.000054159817,0.00027730028,0.00019961825,0.00016286627],"category_scores_gemma":[0.00008524247,0.000120475706,0.000055109183,0.00045784854,0.00038255632,0.00010305432,0.00010716304,0.00088834466,0.000010440194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021836536,0.0023794696,0.05216671,0.00034830897,0.0007300862,0.00015516789,0.016059224,0.0062713795,0.0032455488,0.42566994,0.01769509,0.45344254],"study_design_scores_gemma":[0.002073173,0.0036465235,0.13958542,0.000029958399,0.00006605776,0.00021607283,0.00081934716,0.8260667,0.000078102334,0.025704358,0.0013178474,0.00039646294],"about_ca_topic_score_codex":0.00002051278,"about_ca_topic_score_gemma":0.0000051573006,"teacher_disagreement_score":0.8197953,"about_ca_system_score_codex":0.00004455858,"about_ca_system_score_gemma":0.000014641827,"threshold_uncertainty_score":0.49128568},"labels":[],"label_agreement":null},{"id":"W3015042751","doi":"10.1037/met0000265","title":"Partitioning variation in multilevel models for count data.","year":2020,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":67,"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":"Economic and Social Research Council","keywords":"Overdispersion; Categorical variable; Intraclass correlation; Statistics; Count data; Multilevel model; Mathematics; Cluster analysis; Negative binomial distribution; Poisson distribution; Item response theory; Variance (accounting); Binary data; Econometrics; Correlation; Binary number; Psychometrics","score_opus":0.6438736940352537,"score_gpt":0.5849986390061367,"score_spread":0.05887505502911705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015042751","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":[0.00045909136,0.000023916728,0.99603677,0.0012270733,0.00015471966,0.000417162,0.00013417548,0.0000814828,0.0014655958],"genre_scores_gemma":[0.0266652,0.000008467075,0.97187924,0.0011635409,0.00012933399,0.00011787295,0.000015026214,0.000014756342,0.000006552526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99791527,0.0006738905,0.00045963528,0.0005558071,0.00013261632,0.0002627541],"domain_scores_gemma":[0.9936315,0.0056998394,0.00011289669,0.00037087259,0.00006230574,0.00012262647],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024187227,0.00013726915,0.00034059802,0.000028509448,0.0000539938,0.000039849816,0.00036258763,0.00013783807,0.00019486099],"category_scores_gemma":[0.013286733,0.00010866195,0.000042219428,0.00017765735,0.000047271762,0.00014447936,0.00009325515,0.00021129295,0.0000076117035],"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":[0.00009808165,0.00017242665,0.000043880427,0.000057979873,0.0000100618645,0.0000032756454,0.0003636442,0.000024995485,0.0012338485,0.7646125,0.0007525069,0.2326268],"study_design_scores_gemma":[0.0003876913,0.00009808477,0.0018651792,0.000015383994,0.000014319904,0.0000011570112,0.000015947393,0.3178901,0.000048314992,0.67915404,0.00040274358,0.00010706827],"about_ca_topic_score_codex":0.0000052047885,"about_ca_topic_score_gemma":9.4680763e-7,"teacher_disagreement_score":0.3178651,"about_ca_system_score_codex":0.000018885903,"about_ca_system_score_gemma":0.000010368838,"threshold_uncertainty_score":0.9950248},"labels":[],"label_agreement":null},{"id":"W3041079116","doi":"10.1037/met0000422","title":"Parsimony in model selection: Tools for assessing fit propensity.","year":2021,"lang":"en","type":"preprint","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Model selection; Occam's razor; Computer science; Range (aeronautics); Econometrics; Equating; Statistical model; Statistical inference; Selection (genetic algorithm); Counterfactual conditional; Inference; Statistics; Mathematics; Machine learning; Artificial intelligence; Counterfactual thinking; Psychology","score_opus":0.7544020784369739,"score_gpt":0.6733340687936658,"score_spread":0.08106800964330818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041079116","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":[0.30672026,0.0012902031,0.6435781,0.0022993253,0.0035710467,0.0037684191,0.00003680567,0.00020116384,0.03853469],"genre_scores_gemma":[0.12774116,0.00010889791,0.8638943,0.001906353,0.00049077027,0.0028766566,0.000082486855,0.00006952,0.002829854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99136245,0.0041225804,0.0010372507,0.0019200786,0.00038552727,0.0011721011],"domain_scores_gemma":[0.99596864,0.0020673014,0.0003268545,0.0010438242,0.00025888954,0.0003344985],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0062927045,0.0004798623,0.0011154175,0.00025470217,0.0001746396,0.00045677266,0.0007640644,0.0014944603,0.0016676905],"category_scores_gemma":[0.0022129542,0.00043046701,0.00032438754,0.0004933449,0.0001516287,0.00019360782,0.0007137735,0.0030120548,0.000033493776],"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":[0.00058903004,0.0021988668,0.0036035473,0.00073417235,0.00011247078,0.0001267077,0.0008367917,0.0018453932,0.0009066059,0.0034267127,0.0039192243,0.9817005],"study_design_scores_gemma":[0.010494081,0.0027054138,0.5071223,0.002244433,0.00028852708,0.00046476736,0.0029091442,0.19893372,0.0018856917,0.23132335,0.03650512,0.0051234667],"about_ca_topic_score_codex":0.000068474335,"about_ca_topic_score_gemma":0.00002962795,"teacher_disagreement_score":0.976577,"about_ca_system_score_codex":0.00038600367,"about_ca_system_score_gemma":0.00019395507,"threshold_uncertainty_score":0.9998147},"labels":[],"label_agreement":null},{"id":"W3042438175","doi":"10.1037/met0000336","title":"An approach to structural equation modeling with both factors and components: Integrated generalized structured component analysis.","year":2020,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Research Foundation of Korea","keywords":"Structural equation modeling; Component (thermodynamics); Path analysis (statistics); Component analysis; Factor analysis; Factor (programming language); Econometrics; Computer science; Data mining; Statistics; Mathematics","score_opus":0.19276253301681595,"score_gpt":0.43470238270303097,"score_spread":0.241939849686215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042438175","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":[0.2596438,0.00002338764,0.73930234,0.00020977863,0.00003431168,0.00028107842,0.000011992521,0.00045893743,0.000034403965],"genre_scores_gemma":[0.48937926,0.0000017204118,0.5099919,0.0005559347,0.000012241901,0.000014129624,0.00003655043,0.000008059611,2.4553205e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969165,0.00089576835,0.0004230157,0.001106874,0.00031829934,0.00033956562],"domain_scores_gemma":[0.99857366,0.00017586404,0.00011211957,0.0005286255,0.000116978794,0.0004927455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041467595,0.00033010254,0.000605328,0.0001553918,0.0001377969,0.00018012444,0.0007929744,0.00012390205,0.000008331884],"category_scores_gemma":[0.00020116381,0.00020670654,0.00006996709,0.0011489525,0.00007770267,0.0002940224,0.00015981037,0.0003333556,5.0014114e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005639686,0.00027306372,0.002936051,0.000026709557,0.00038133722,0.000010953843,0.0031400763,0.65744364,0.06334548,0.17644018,0.000012816722,0.09542575],"study_design_scores_gemma":[0.00030231345,0.00038001582,0.0058547766,0.0000034164523,0.00006025579,0.0000035570642,0.000038370294,0.9636652,0.00037931983,0.029002229,0.000008316561,0.00030224814],"about_ca_topic_score_codex":0.00004480329,"about_ca_topic_score_gemma":9.758248e-7,"teacher_disagreement_score":0.30622157,"about_ca_system_score_codex":0.000039965504,"about_ca_system_score_gemma":0.0000067743636,"threshold_uncertainty_score":0.8429248},"labels":[],"label_agreement":null},{"id":"W3132372564","doi":"10.1037/met0000269","title":"Determining the number of factors using parallel analysis and its recent variants: Comment on Lim and Jahng (2019).","year":2021,"lang":"en","type":"letter","venue":"Psychological Methods","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mathematics; Statistics; Ranking (information retrieval); Rank (graph theory); Context (archaeology); Dimension (graph theory); Eigenvalues and eigenvectors; Factor analysis; Population; Algorithm; Computer science; Combinatorics; Artificial intelligence","score_opus":0.21819536965108474,"score_gpt":0.489994029440274,"score_spread":0.27179865978918927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132372564","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":[0.0010565019,0.00016562894,0.9350286,0.06305401,0.00022442582,0.00020682436,0.000025109417,0.00007760985,0.00016127019],"genre_scores_gemma":[0.0012373916,0.00044606146,0.86574805,0.13243577,0.00007280676,0.000015565014,0.000014464648,0.00001646192,0.000013440778],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957737,0.001949358,0.00055879453,0.0009978258,0.00033835138,0.00038199808],"domain_scores_gemma":[0.9948121,0.003752298,0.00035693718,0.0008357209,0.00015491663,0.00008808239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001141449,0.00036978672,0.00082731183,0.00013198772,0.00014262415,0.00012420697,0.0007690162,0.00048070934,0.000049387723],"category_scores_gemma":[0.0010287381,0.00023144422,0.00013513234,0.00058557896,0.00014425347,0.00009139193,0.00058702927,0.0012165224,7.438831e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093109484,0.0009426045,0.0054733492,0.00027715432,0.0020654965,0.0005036619,0.0010734122,0.00046323068,0.0005758786,0.030140787,0.06090528,0.89748603],"study_design_scores_gemma":[0.0021218983,0.0016806631,0.075479254,0.00092610525,0.0031485124,0.00021532922,0.000074573574,0.3732042,0.0011005705,0.39134508,0.14626476,0.004439039],"about_ca_topic_score_codex":0.0000075052612,"about_ca_topic_score_gemma":1.7271591e-7,"teacher_disagreement_score":0.893047,"about_ca_system_score_codex":0.000043665168,"about_ca_system_score_gemma":0.0000101058895,"threshold_uncertainty_score":0.9438022},"labels":[],"label_agreement":null},{"id":"W3190043208","doi":"10.1037/met0000678","title":"Why multiple hypothesis test corrections provide poor control of false positives in the real world.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prioris.ai (Canada)","funders":"","keywords":"False positive paradox; Statistical hypothesis testing; False positives and false negatives; Statistics; Test (biology); Econometrics; Psychology; Multiple comparisons problem; Statistical analysis; Control (management); Mathematics; Artificial intelligence; Computer science","score_opus":0.7374936027261868,"score_gpt":0.6119179092144343,"score_spread":0.12557569351175246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190043208","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":[0.073717445,0.0035448512,0.82932067,0.015357558,0.0015163849,0.0029014202,0.00011080426,0.00005000308,0.07348089],"genre_scores_gemma":[0.8504677,0.000034832276,0.1447814,0.0020284017,0.000086715634,0.00021035553,8.212561e-7,0.000008817813,0.002380968],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9601363,0.032774985,0.0043803984,0.00092984986,0.001532741,0.00024571875],"domain_scores_gemma":[0.8672994,0.12950352,0.0010218757,0.0018020566,0.00028372774,0.00008942338],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.116676256,0.00023651864,0.0020460822,0.00049582135,0.00008712797,0.0004790074,0.0014244185,0.00009639463,0.0029327818],"category_scores_gemma":[0.1071601,0.00008530804,0.0013284145,0.0032583973,0.00017115742,0.00012227122,0.000045613706,0.00031025338,0.00037493676],"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":[0.00006612442,0.00090423494,0.08489706,0.00005729333,0.0002487803,0.000040345225,0.0014838503,0.000054719618,0.009905372,0.005719324,0.051719952,0.84490293],"study_design_scores_gemma":[0.0006729485,0.000502963,0.5773417,0.00016530891,0.00057845376,0.000042091066,0.0026589988,0.022764282,0.00039647456,0.07956842,0.3148707,0.0004376976],"about_ca_topic_score_codex":0.000060000897,"about_ca_topic_score_gemma":0.00013422621,"teacher_disagreement_score":0.84446526,"about_ca_system_score_codex":0.000019398041,"about_ca_system_score_gemma":0.00001415975,"threshold_uncertainty_score":0.9979787},"labels":[],"label_agreement":null},{"id":"W3206560547","doi":"10.1037/met0000414","title":"Using copulas to enable causal inference from nonexperimental data: Tutorial and simulation studies.","year":2021,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Employment and Social Development Canada","funders":"","keywords":"Skewness; Copula (linguistics); Confounding; Econometrics; Statistics; Sample size determination; Covariate; Psychology; Inference; Causal inference; Variables; Personality; Statistical inference; Computer science; Mathematics; Social psychology; Artificial intelligence","score_opus":0.8249197191980218,"score_gpt":0.748911382878569,"score_spread":0.07600833631945281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206560547","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8380904,0.0051132934,0.1416733,0.0006050914,0.008888354,0.0007415232,0.00016046381,0.00010128737,0.0046262895],"genre_scores_gemma":[0.41420224,0.00007540894,0.5824739,0.0013927704,0.0013148197,0.000050037772,0.00007896932,0.000022465529,0.0003893956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956699,0.0020210429,0.00044285262,0.0010543909,0.0002936738,0.00051811046],"domain_scores_gemma":[0.9964575,0.002060944,0.00008207661,0.00094121473,0.00011321165,0.00034502556],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014873078,0.00019920198,0.00041876247,0.00006065676,0.00018509115,0.00006376508,0.00032612277,0.00021394202,0.0019742707],"category_scores_gemma":[0.0021197496,0.0001738975,0.000030480958,0.0003363252,0.00014269483,0.00014519301,0.00077848946,0.0003807714,0.000096449294],"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":[0.002516985,0.0029142168,0.018219259,0.00012944703,0.0007104593,0.0011562314,0.009377457,0.0006875724,0.14456148,0.009532618,0.0073149204,0.80287933],"study_design_scores_gemma":[0.024819028,0.007356903,0.22786625,0.00069208484,0.0005446514,0.00046718336,0.024861518,0.06357319,0.034010347,0.10116321,0.5095127,0.0051329318],"about_ca_topic_score_codex":0.00028670917,"about_ca_topic_score_gemma":0.000014327233,"teacher_disagreement_score":0.7977464,"about_ca_system_score_codex":0.00013641255,"about_ca_system_score_gemma":0.000033782366,"threshold_uncertainty_score":0.9989381},"labels":[],"label_agreement":null},{"id":"W34647757","doi":"10.1037/met0000422","title":"Juan Ramón Barat - Selection of Poems Translated into English","year":2010,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Comparative Literary Analysis and Criticism","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Poetry; Selection (genetic algorithm); Art; Media studies; Library science; Sociology; Literature; Computer science; Artificial intelligence","score_opus":0.09039564540262292,"score_gpt":0.43068538723789135,"score_spread":0.34028974183526844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W34647757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8561884,0.00016520824,0.011134875,0.00028670183,0.0014814847,0.00013170153,0.0000068870777,0.00012106052,0.13048369],"genre_scores_gemma":[0.9710513,0.0000065755617,0.026917508,0.00027246625,0.0005936127,0.000017347607,0.000008572612,0.000008665123,0.0011239473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99859434,0.00045108737,0.00036528747,0.00029464473,0.000115575735,0.00017907847],"domain_scores_gemma":[0.9991956,0.00024464293,0.00007812958,0.00019622491,0.00020978577,0.000075636075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00067141285,0.00014768525,0.00033722282,0.000089782836,0.00016176136,0.000083364095,0.00018191872,0.00009892205,0.009792903],"category_scores_gemma":[0.00011980182,0.00010543512,0.00019109767,0.00012334126,0.00028352535,0.00016330046,0.000012768219,0.00041389273,0.000014983149],"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":[0.00016853082,0.0009244456,0.00065080356,0.000024416593,0.00013166571,0.000003166815,0.055792324,0.0000037865007,0.1311229,0.54960924,0.0017232967,0.2598454],"study_design_scores_gemma":[0.00064868934,0.00068956596,0.0056466423,0.000014453321,0.000113294525,0.0000050294734,0.0009434533,0.00084314006,0.011667756,0.075934045,0.90310085,0.00039307176],"about_ca_topic_score_codex":0.000031815845,"about_ca_topic_score_gemma":0.00008777979,"teacher_disagreement_score":0.90137756,"about_ca_system_score_codex":0.0000041220615,"about_ca_system_score_gemma":0.000003770053,"threshold_uncertainty_score":0.9911123},"labels":[],"label_agreement":null},{"id":"W4205105826","doi":"10.1037/met0000295","title":"Intermittent faking of personality profiles in high-stakes assessments: A grade of membership analysis.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"PsycINFO; Psychology; Item response theory; Test (biology); Scale (ratio); Psychometrics; Personality; Social psychology; Big Five personality traits; Ideal (ethics); Test validity; Control (management); Statistics; Applied psychology; Computer science; Artificial intelligence; Clinical psychology; Mathematics","score_opus":0.7410462818435025,"score_gpt":0.6411131628585449,"score_spread":0.0999331189849576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205105826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83273464,0.00036739217,0.1607822,0.0003069425,0.0005522253,0.00023175671,0.00003769686,0.000032497628,0.0049546603],"genre_scores_gemma":[0.60644686,0.0000062899076,0.3933063,0.00010640194,0.000016034717,0.000044407727,0.0000025540137,0.00000472409,0.00006642554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98254335,0.012647443,0.0018403956,0.00097151694,0.0015897155,0.0004075685],"domain_scores_gemma":[0.9606238,0.036859885,0.0013357446,0.00089797477,0.00018546784,0.00009711527],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04362603,0.00020703951,0.0012562467,0.0016068795,0.000109044406,0.000039389146,0.0016186568,0.00010523523,0.0034364269],"category_scores_gemma":[0.048772797,0.00014303808,0.0005191994,0.010717125,0.00025494338,0.00010566859,0.00052540266,0.00057691353,0.0000012102059],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017562995,0.0009637883,0.64135414,0.00001787459,0.00021292992,0.000016452586,0.00064354914,0.0008219282,0.0041667824,0.006093894,0.00015957968,0.34537345],"study_design_scores_gemma":[0.00050647947,0.00052288966,0.9081372,0.0000102809345,0.000089036024,0.000008099517,0.0045665368,0.0016935267,0.0006078211,0.083094,0.000586618,0.00017751468],"about_ca_topic_score_codex":0.00021426108,"about_ca_topic_score_gemma":0.000005484202,"teacher_disagreement_score":0.34519592,"about_ca_system_score_codex":0.00007407641,"about_ca_system_score_gemma":0.000021222553,"threshold_uncertainty_score":0.99747455},"labels":[],"label_agreement":null},{"id":"W4205329525","doi":"10.1037/met0000445","title":"New computations for RMSEA and CFI following FIML and TS estimation with missing data.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Structural equation modeling; Missing data; Statistics; Computation; Estimation; Econometrics; Mathematics; Algorithm; Economics","score_opus":0.1610506147015826,"score_gpt":0.5012766047666443,"score_spread":0.34022599006506166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205329525","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":[0.0034711736,0.00017885702,0.99156815,0.003841171,0.00009303252,0.00028957127,0.000004205948,0.00021833858,0.00033548856],"genre_scores_gemma":[0.04906738,0.0000033579083,0.94978,0.0010336959,0.000014917543,0.00004025797,0.0000153202,0.0000058742203,0.000039194383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871176,0.00041571129,0.00015346239,0.0004594548,0.00013239397,0.00012722553],"domain_scores_gemma":[0.99874794,0.00071806414,0.00007426348,0.00035796154,0.000017934597,0.00008385702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012744863,0.00008798869,0.00013777049,0.000068919275,0.00033425255,0.00018855341,0.00038940168,0.000034251618,0.0000072144558],"category_scores_gemma":[0.00018263928,0.00007199632,0.00001926315,0.0002591249,0.00002747999,0.0003426653,0.0003308447,0.00013922254,2.5445237e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012661474,0.00003424801,0.00010466257,0.0000044747794,0.000009753098,0.0000022398087,0.0005158444,0.00027737112,0.00030645035,0.012564559,0.0008520741,0.9853157],"study_design_scores_gemma":[0.0008207628,0.0006850167,0.0074712336,0.000013919613,0.000023762223,0.00008931055,0.00006695915,0.7969658,0.00022057693,0.18295589,0.010434583,0.0002522247],"about_ca_topic_score_codex":0.0000052043674,"about_ca_topic_score_gemma":4.8982724e-7,"teacher_disagreement_score":0.98506343,"about_ca_system_score_codex":0.000011229441,"about_ca_system_score_gemma":0.000019567695,"threshold_uncertainty_score":0.29359245},"labels":[],"label_agreement":null},{"id":"W4220760233","doi":"10.1037/met0000448","title":"How to think clearly about the central limit theorem.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"University of British Columbia","keywords":"Sample (material); Central limit theorem; PsycINFO; Sample size determination; Psychology; Mathematics education; Statistics; Mathematics; Political science; Law; MEDLINE","score_opus":0.43218665808245893,"score_gpt":0.5531479969564407,"score_spread":0.12096133887398175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220760233","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":[0.0216328,0.0003132234,0.92549556,0.031094324,0.0046043117,0.0007116574,0.000057064757,0.00030884155,0.015782213],"genre_scores_gemma":[0.02657578,0.000035331625,0.96087265,0.006539684,0.00023670356,0.00022953982,0.0000034988218,0.000026628884,0.005480208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935212,0.0049614892,0.00028445362,0.00043043256,0.00032137497,0.00048104854],"domain_scores_gemma":[0.98982024,0.009113207,0.00014213807,0.000701595,0.000060395392,0.0001624082],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005505236,0.00018637098,0.00029295628,0.000066254644,0.00046474682,0.00013592957,0.000815617,0.00007688817,0.0018575774],"category_scores_gemma":[0.01697085,0.000111532056,0.00014204076,0.00042170438,0.00014954977,0.000031483032,0.00029635834,0.0005926999,0.000027683649],"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":[0.000099079196,0.00024725584,0.000106882406,0.000008935069,0.0000284278,0.000005606318,0.0037961479,0.000004027201,0.0008912198,0.6799409,0.08707602,0.2277955],"study_design_scores_gemma":[0.00018356634,0.0003037048,0.01227421,0.000003328692,0.000029772285,0.000035719953,0.0046545514,0.000021114689,0.0002615426,0.71626896,0.26578122,0.00018229189],"about_ca_topic_score_codex":0.0000041965995,"about_ca_topic_score_gemma":7.6763826e-7,"teacher_disagreement_score":0.22761321,"about_ca_system_score_codex":0.00006210703,"about_ca_system_score_gemma":0.000019023377,"threshold_uncertainty_score":0.99905485},"labels":[],"label_agreement":null},{"id":"W4236539520","doi":"10.1037/1082-989x.10.3.285.supp","title":"Supplemental Material for Structural Equation Modeling of Paired-Comparison and Ranking Data","year":2005,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Impact of AI and Big Data on Business and Society","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Structural equation modeling; Ranking (information retrieval); Statistics; Econometrics; Mathematics; Psychology; Computer science; Artificial intelligence","score_opus":0.6691282874472614,"score_gpt":0.6089437633112126,"score_spread":0.0601845241360488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236539520","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":[0.43890536,0.000070280716,0.55957586,0.00056301674,0.0003090312,0.00012583526,0.0003791918,0.000010966551,0.000060465438],"genre_scores_gemma":[0.579574,0.000008584994,0.4199749,0.000110139204,0.00016279591,0.0000028473003,0.00015827529,0.0000027578667,0.000005713311],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803793,0.00029071706,0.00063960627,0.00044763804,0.00038363112,0.0002004594],"domain_scores_gemma":[0.9984091,0.00075535115,0.00019947514,0.0004753053,0.000102783146,0.000057976904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059155817,0.00010864795,0.00032944954,0.000047954305,0.00014418975,0.00016309078,0.0006213211,0.00009976356,0.00057062134],"category_scores_gemma":[0.0013986035,0.000065614215,0.0000619753,0.00015489841,0.000073485804,0.00048617323,0.00023012525,0.00007045653,0.0000015626038],"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":[0.00024552905,0.00007117629,0.0026745985,0.0000071583504,0.000013005967,1.4299759e-7,0.00039792832,0.00035001375,0.0082134055,0.0007797927,0.0023208142,0.98492646],"study_design_scores_gemma":[0.00094337127,0.0001670415,0.008603711,0.0000074540567,0.000021763506,0.000005047106,0.0006782761,0.9591072,0.0010236606,0.023406569,0.0058808075,0.00015508446],"about_ca_topic_score_codex":0.00001412417,"about_ca_topic_score_gemma":0.0000020788361,"teacher_disagreement_score":0.9847714,"about_ca_system_score_codex":0.000008394923,"about_ca_system_score_gemma":0.0000065752133,"threshold_uncertainty_score":0.6247903},"labels":[],"label_agreement":null},{"id":"W4280565590","doi":"10.1037/met0000441","title":"Measurement invariance testing using confirmatory factor analysis and alignment optimization: A tutorial for transparent analysis planning and reporting.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":170,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Measurement invariance; Computer science; PsycINFO; Confirmatory factor analysis; Key (lock); Field (mathematics); Data science; Data mining; Management science; Machine learning; Structural equation modeling; Mathematics","score_opus":0.728377638129674,"score_gpt":0.6079763110290402,"score_spread":0.12040132710063389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280565590","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":[0.1102995,0.001558822,0.8857477,0.00020573223,0.00070531474,0.0008618074,0.00005231032,0.000060554885,0.0005082676],"genre_scores_gemma":[0.535554,0.0000063027724,0.46353224,0.00029502227,0.00012652921,0.0004295773,0.000014022791,0.000014686555,0.00002758982],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945154,0.002169308,0.001274004,0.0009104472,0.0006040928,0.0005267133],"domain_scores_gemma":[0.99747443,0.0007992241,0.0009125581,0.00039294804,0.0001346162,0.00028619994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008108715,0.00022362682,0.0007703165,0.00041938125,0.00062554574,0.00006223884,0.00018433778,0.0001127118,0.0008407897],"category_scores_gemma":[0.0013698046,0.00020610096,0.00018332158,0.0016072907,0.000106022366,0.000049405757,0.00011875129,0.00035360106,2.458636e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024078581,0.0017649278,0.62444454,0.00039388431,0.013478842,0.00024889503,0.007894642,0.15408541,0.006510541,0.0015437271,0.00020564378,0.1870211],"study_design_scores_gemma":[0.0042868005,0.002197622,0.67168325,0.00004893338,0.0066855163,0.00013583833,0.0023903295,0.3057843,0.00022351732,0.0010085067,0.004476526,0.00107888],"about_ca_topic_score_codex":0.00011051068,"about_ca_topic_score_gemma":0.0000032928365,"teacher_disagreement_score":0.42525452,"about_ca_system_score_codex":0.00024256085,"about_ca_system_score_gemma":0.000033143395,"threshold_uncertainty_score":0.9206057},"labels":[],"label_agreement":null},{"id":"W4280596915","doi":"10.1037/met0000497","title":"Causal mediation effects in single case experimental designs.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse","keywords":"Mediation; Type I and type II errors; Statistics; Confidence interval; Econometrics; Estimator; Statistical power; Monte Carlo method; Causal model; Psychology; Standard error; Outcome (game theory); Statistical hypothesis testing; Mathematics","score_opus":0.551208401110505,"score_gpt":0.5270712642831462,"score_spread":0.02413713682735874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280596915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9560073,0.0028469544,0.008667922,0.00041712038,0.0042301593,0.0007163137,0.00001325732,0.00021489043,0.026886066],"genre_scores_gemma":[0.9600266,0.0000040213567,0.036183566,0.0015353884,0.00015886268,0.0015419628,0.000009543043,0.000024610606,0.00051543105],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935651,0.004173269,0.00050208654,0.0008788162,0.0002537756,0.0006269488],"domain_scores_gemma":[0.998229,0.0010612223,0.00013960284,0.0003910855,0.000018554914,0.00016049441],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001795688,0.00029606163,0.00045604238,0.00014942994,0.00033897377,0.000022927827,0.00032214558,0.00020073925,0.015225017],"category_scores_gemma":[0.00015946358,0.00023752342,0.0001488804,0.0007006449,0.00017607526,0.000053782853,0.00023091618,0.0007602661,0.00018524216],"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":[0.0017930609,0.019968614,0.026365966,0.00001524914,0.00010665315,0.026500152,0.007328074,0.000031852043,0.09158251,0.010472568,0.014937511,0.8008978],"study_design_scores_gemma":[0.015581168,0.028545605,0.7944581,0.000025251526,0.00015501787,0.017797213,0.015125317,0.00006879339,0.0067535085,0.034980856,0.083231285,0.0032779207],"about_ca_topic_score_codex":0.00009923743,"about_ca_topic_score_gemma":0.0000052879723,"teacher_disagreement_score":0.7976199,"about_ca_system_score_codex":0.00015845857,"about_ca_system_score_gemma":0.0000029509283,"threshold_uncertainty_score":0.9856752},"labels":[],"label_agreement":null},{"id":"W4281687743","doi":"10.1037/met0000493","title":"Spatial analysis for psychologists: How to use individual-level data for research at the geographically aggregated level.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"PsycINFO; Data science; Variation (astronomy); Computer science; Spatial analysis; Variety (cybernetics); Cluster analysis; Information retrieval; Data mining; Statistics; Artificial intelligence; MEDLINE; Mathematics","score_opus":0.7344584376473206,"score_gpt":0.5972475058072007,"score_spread":0.1372109318401199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281687743","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":[0.30938113,0.00022032138,0.64398307,0.034033276,0.0008497061,0.0032932106,0.0075971186,0.00014352439,0.0004986411],"genre_scores_gemma":[0.6923481,0.000028777744,0.29956916,0.0020834815,0.00031141104,0.0017388844,0.00094713445,0.000023500877,0.0029495333],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904068,0.0051776664,0.00050688756,0.0016629164,0.0011672932,0.0010784277],"domain_scores_gemma":[0.989572,0.0075327386,0.00020586912,0.0019469828,0.00041164676,0.0003307845],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035835244,0.00022932504,0.0005086448,0.0003703114,0.00360186,0.00040712144,0.004089036,0.00025259878,0.001472685],"category_scores_gemma":[0.009731805,0.00015670032,0.00043769338,0.0044604717,0.0011140896,0.00023459758,0.0008962885,0.00069949427,0.0000046423247],"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":[0.0032616945,0.002044804,0.47559804,0.000025360767,0.0014250446,0.000017693159,0.0033065528,0.00005474138,0.0010153498,0.0030513075,0.09767801,0.41252142],"study_design_scores_gemma":[0.0005693752,0.00043046052,0.6788889,0.0000023119455,0.00025735647,4.853953e-7,0.0006697433,0.000079069454,0.000023506058,0.009733658,0.30909303,0.000252101],"about_ca_topic_score_codex":0.0016767306,"about_ca_topic_score_gemma":0.0070786322,"teacher_disagreement_score":0.41226932,"about_ca_system_score_codex":0.00012468052,"about_ca_system_score_gemma":0.00006787795,"threshold_uncertainty_score":0.99944013},"labels":[],"label_agreement":null},{"id":"W4283816293","doi":"10.1037/met0000512","title":"Regression with reduced rank predictor matrices: A model of trade-offs.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","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":"Learning Partnership","funders":"","keywords":"Statistics; Mathematics; Linear regression; Regression analysis; Constant (computer programming); Regression; Rank (graph theory); Regression diagnostic; Variable (mathematics); Variables; Econometrics; Combinatorics; Polynomial regression; Computer science","score_opus":0.41604150202304757,"score_gpt":0.556736739686867,"score_spread":0.14069523766381942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283816293","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":[0.38530475,0.00036901116,0.60733306,0.0010404397,0.0007754547,0.00047426394,0.000070886585,0.00011508786,0.004517061],"genre_scores_gemma":[0.4808407,0.000010467889,0.51821935,0.0003640707,0.000044784072,0.00008230798,0.0000018251856,0.000017888407,0.00041855214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9897844,0.0042819995,0.0014067437,0.0012853285,0.0028032123,0.00043831492],"domain_scores_gemma":[0.99249864,0.0047711725,0.00083033415,0.0015146916,0.00015061705,0.00023457315],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013602016,0.00029509477,0.00083906634,0.0005270482,0.00032712577,0.00010884569,0.0021446138,0.00015380686,0.003476727],"category_scores_gemma":[0.00518801,0.00016370848,0.00026821776,0.0021474413,0.00023392953,0.00020012619,0.0005831604,0.00060955645,0.000012843819],"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":[0.0042385138,0.0012897018,0.0012403738,0.00001502692,0.000047775946,0.00006801846,0.0018999192,0.012655233,0.18100196,0.0021693367,0.015853336,0.7795208],"study_design_scores_gemma":[0.0063257287,0.003141724,0.018237105,0.00012670888,0.00010833394,0.00034846208,0.0023002895,0.69086754,0.005499235,0.24803618,0.023842564,0.001166158],"about_ca_topic_score_codex":0.0000024559786,"about_ca_topic_score_gemma":2.3612883e-7,"teacher_disagreement_score":0.77835464,"about_ca_system_score_codex":0.000053526892,"about_ca_system_score_gemma":0.000043743377,"threshold_uncertainty_score":0.99743426},"labels":[],"label_agreement":null},{"id":"W4284894098","doi":"10.1037/met0000487","title":"Tutorial: Artificial neural networks to analyze single-case experimental designs.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":8,"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; Institut universitaire en santé mentale de Montréal; Institut Universitaire en Santé Mentale de Québec","funders":"Fonds de Recherche du Québec - Santé","keywords":"Artificial neural network; Computer science; Artificial intelligence; Replication (statistics); PsycINFO; Machine learning; Monte Carlo method; Statistics; MEDLINE; Mathematics","score_opus":0.301411646461321,"score_gpt":0.49046597917977713,"score_spread":0.18905433271845612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284894098","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":[0.004788107,0.000104274266,0.9907788,0.00055289554,0.002127802,0.00035534587,0.000005170738,0.00083909545,0.0004484965],"genre_scores_gemma":[0.39374986,3.2892055e-7,0.60455126,0.0013179632,0.00017162318,0.00018351116,0.0000012477117,0.000012267716,0.0000119556435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959287,0.0017707001,0.00047313637,0.00095767237,0.00032561945,0.00054416206],"domain_scores_gemma":[0.9979095,0.0008856722,0.000099888384,0.0007651716,0.00004911805,0.0002906388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016111636,0.00023716288,0.00032599646,0.00012331684,0.00042354167,0.00013611541,0.0011103863,0.00008528079,0.00025637497],"category_scores_gemma":[0.000528855,0.00021683186,0.00011768968,0.00087134284,0.000080408645,0.00015178621,0.0009948883,0.0005225047,0.000008828948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022190313,0.0012804767,0.00000773265,0.0000016452204,0.00001528903,0.0019218168,0.00028960136,0.03775935,0.04398609,0.11809476,0.002512059,0.7939093],"study_design_scores_gemma":[0.00023073266,0.0028339378,0.000025280191,0.000002558898,0.000010065104,0.0011265203,0.00005962606,0.8317527,0.0064919638,0.15346035,0.0034290398,0.00057720643],"about_ca_topic_score_codex":0.000006904361,"about_ca_topic_score_gemma":3.372711e-7,"teacher_disagreement_score":0.79399335,"about_ca_system_score_codex":0.00014449483,"about_ca_system_score_gemma":0.000006175194,"threshold_uncertainty_score":0.8842147},"labels":[],"label_agreement":null},{"id":"W4285730034","doi":"10.1037/met0000508","title":"Correcting bias in extreme groups design using a missing data approach.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Missing data; PsycINFO; Statistics; Data collection; Statistical power; Econometrics; Computer science; Psychology; Data mining; Mathematics; MEDLINE; Political science","score_opus":0.8796631252223159,"score_gpt":0.5764435918938456,"score_spread":0.3032195333284703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285730034","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":[0.004558966,0.0001459449,0.9913904,0.00008557162,0.0005312979,0.00041554103,0.000024503846,0.00012066621,0.0027270783],"genre_scores_gemma":[0.017304566,0.0000026065818,0.9822024,0.00027458344,0.00009304666,0.00006098017,0.000007335069,0.000035505032,0.00001897666],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98815286,0.009242875,0.0007195395,0.0009694979,0.0003618553,0.00055339775],"domain_scores_gemma":[0.986488,0.01204958,0.0002674237,0.0010259134,0.000030030005,0.00013908552],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0151308635,0.00026031132,0.00059409876,0.00016489936,0.00033308263,0.0000780283,0.0010152946,0.00011797234,0.00078579126],"category_scores_gemma":[0.016856799,0.00021783817,0.00007031726,0.00090587384,0.00012006841,0.00011062869,0.0008005165,0.0009238395,0.0000023135733],"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":[0.00015176446,0.00085096055,0.0006098587,0.000046288358,0.00001939231,0.00008092943,0.00043767694,0.000059787453,0.0026804414,0.0388943,0.0003295797,0.95583904],"study_design_scores_gemma":[0.00048579514,0.00016569963,0.00075695524,0.000030780946,0.000038068003,0.00036913564,0.0005669136,0.18559025,0.00008708744,0.8113976,0.00017433481,0.00033737696],"about_ca_topic_score_codex":0.00002382851,"about_ca_topic_score_gemma":4.2582428e-7,"teacher_disagreement_score":0.9555016,"about_ca_system_score_codex":0.000111138885,"about_ca_system_score_gemma":0.000029291597,"threshold_uncertainty_score":0.9914246},"labels":[],"label_agreement":null},{"id":"W4303188607","doi":"10.1037/met0000514","title":"Aberrant distortion of variance components in multilevel models under conflation of level-specific effects.","year":2022,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Conflation; Variance (accounting); Random effects model; Inference; Multilevel model; Statistics; Econometrics; Distortion (music); Cluster (spacecraft); Mathematics; Psychology; Computer science; Artificial intelligence; Meta-analysis; Epistemology; Economics","score_opus":0.5737664376662643,"score_gpt":0.5591809436304295,"score_spread":0.014585494035834867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303188607","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":[0.4370593,0.00063928904,0.55450225,0.00018123884,0.001150274,0.00078740297,0.00004957003,0.00002147024,0.005609214],"genre_scores_gemma":[0.91643465,0.00003065329,0.08274052,0.00015268952,0.000025437079,0.0002606822,0.00002429921,0.0000151794875,0.0003159168],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939389,0.004023369,0.0007619703,0.00048004798,0.0004272394,0.00036845746],"domain_scores_gemma":[0.9979305,0.0011405804,0.00030914726,0.00046855456,0.000052998068,0.00009821475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030850917,0.00014566515,0.00044594237,0.00019990513,0.00007755561,0.0000032868431,0.00034352712,0.00013515452,0.0014793222],"category_scores_gemma":[0.00009291929,0.00013532645,0.00008768504,0.0003985922,0.00016472247,0.00005567128,0.00012761955,0.0005546377,0.00001017776],"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":[0.0032646225,0.0061841854,0.0065480894,0.00033283627,0.0000800352,0.00004476127,0.003628711,0.0037235955,0.080043234,0.1269468,0.0006393465,0.7685638],"study_design_scores_gemma":[0.0030161892,0.00090614305,0.93638194,0.0000384012,0.00000765571,0.000014052882,0.00022232892,0.0047856276,0.0014121684,0.05184459,0.001180383,0.00019050905],"about_ca_topic_score_codex":0.00018614915,"about_ca_topic_score_gemma":0.0000026204461,"teacher_disagreement_score":0.9298339,"about_ca_system_score_codex":0.00018298675,"about_ca_system_score_gemma":0.000011495464,"threshold_uncertainty_score":0.99943346},"labels":[],"label_agreement":null},{"id":"W4313857752","doi":"10.1037/met0000537","title":"We need to change how we compute RMSEA for nested model comparisons in structural equation modeling.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Structural equation modeling; Nested set model; Mathematics; Statistics; Applied mathematics; Computer science; Data mining","score_opus":0.5169415510137839,"score_gpt":0.49881246533518586,"score_spread":0.018129085678598056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313857752","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":[0.015503778,0.0001234987,0.93836766,0.044128254,0.0006034478,0.00065474736,0.000009073425,0.00054074096,0.00006878538],"genre_scores_gemma":[0.41175833,0.000030367637,0.5869977,0.00088017684,0.000074973985,0.00020156219,0.000007727899,0.000010755833,0.000038443206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974054,0.00045153196,0.00038577165,0.00086091773,0.0002564794,0.0006399125],"domain_scores_gemma":[0.9984959,0.00048148434,0.000088015455,0.0005776227,0.0001211291,0.0002358741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015160374,0.00026593354,0.0004365641,0.00033755033,0.0001351492,0.00020712985,0.0010616592,0.0002232803,0.0000027412457],"category_scores_gemma":[0.00023373638,0.00022180969,0.00011903144,0.0014804612,0.000032060492,0.00030962093,0.00027888478,0.0003183973,0.000024165145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007103146,0.00009316289,0.000094873394,0.00003261627,0.000012504457,0.000005604946,0.0031107466,0.43946946,0.0015767962,0.047763817,0.0019466615,0.5058227],"study_design_scores_gemma":[0.00040189308,0.00017427243,0.0004490666,0.00003727299,0.0000045845686,0.0000031410277,0.00006355096,0.88747317,0.000046157118,0.110930674,0.00014727587,0.00026892705],"about_ca_topic_score_codex":0.000015971631,"about_ca_topic_score_gemma":0.000007110444,"teacher_disagreement_score":0.50555384,"about_ca_system_score_codex":0.000052670744,"about_ca_system_score_gemma":0.000019614383,"threshold_uncertainty_score":0.90451366},"labels":[],"label_agreement":null},{"id":"W4321004017","doi":"10.1037/met0000540","title":"Let the algorithm speak: How to use neural networks for automatic item generation in psychological scale development.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Economic and Social Research Council; Cambridge Trust","keywords":"Computer science; Scale (ratio); Generator (circuit theory); Process (computing); Code (set theory); Artificial neural network; Generative grammar; Artificial intelligence; Machine learning; Algorithm; Natural language processing; Programming language","score_opus":0.23907500105885265,"score_gpt":0.46337447013331007,"score_spread":0.2242994690744574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321004017","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":[0.07411549,0.00008549393,0.91106474,0.0119102765,0.0011803115,0.0011106624,0.0000018248157,0.00043506423,0.00009612246],"genre_scores_gemma":[0.053017616,0.000048092174,0.93781954,0.007820833,0.00023754772,0.0007199142,0.000013623088,0.0000191978,0.00030360883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959932,0.0012194695,0.0005803063,0.0010266319,0.00032158612,0.00085881364],"domain_scores_gemma":[0.99664396,0.0020683785,0.0001233855,0.0008489978,0.00011777626,0.00019749497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004531591,0.00028026057,0.00036463115,0.00019536473,0.00030283383,0.00044193523,0.001537306,0.00020989255,0.000033890185],"category_scores_gemma":[0.0017317653,0.00018557292,0.00012476393,0.0023741482,0.00009809187,0.00043936033,0.00034120187,0.0003707081,0.00008744636],"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":[0.000009278595,0.00014124229,0.00018635918,0.000008106033,0.000006891726,0.00002309204,0.00041569883,0.0020780782,0.00090935966,0.0010481013,0.00908913,0.98608464],"study_design_scores_gemma":[0.00015118907,0.00027650245,0.024087226,0.000027194947,0.0000044848966,0.000024291905,0.00006333544,0.9632928,0.0010798048,0.0025249291,0.008160195,0.0003080499],"about_ca_topic_score_codex":0.0000064422866,"about_ca_topic_score_gemma":0.00002030858,"teacher_disagreement_score":0.9857766,"about_ca_system_score_codex":0.00006952805,"about_ca_system_score_gemma":0.0000107075875,"threshold_uncertainty_score":0.7567444},"labels":[],"label_agreement":null},{"id":"W4385715273","doi":"10.1037/met0000551","title":"Mixture multilevel vector-autoregressive modeling.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Max-Planck-Gesellschaft; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Autoregressive model; STAR model; Multilevel model; Statistics; Econometrics; Mathematics; Nonlinear autoregressive exogenous model; Applied mathematics; Autoregressive integrated moving average; Time series","score_opus":0.2471882376413364,"score_gpt":0.5709472765805209,"score_spread":0.3237590389391845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385715273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38308424,0.0022625434,0.29819265,0.1146901,0.015058356,0.0017404965,0.00007070871,0.0039107273,0.18099017],"genre_scores_gemma":[0.7981211,0.0008814741,0.1809984,0.010918378,0.0013901661,0.00014410014,0.000010328251,0.00003213409,0.0075039286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707144,0.0012693218,0.0002599352,0.00038117776,0.00029891604,0.0007192272],"domain_scores_gemma":[0.99814737,0.0011612442,0.000059372254,0.00023460132,0.0000760951,0.00032130544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028000646,0.00013311124,0.00026373786,0.00007346788,0.0005396174,0.000058083613,0.0003718087,0.00031631818,0.00071446714],"category_scores_gemma":[0.0032099027,0.00009893929,0.00013016212,0.00039977874,0.00016733332,0.00007747987,0.000060780498,0.00031900808,0.0002913601],"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":[0.000087042536,0.0002439273,0.006753366,0.00008346557,0.000042712873,0.00009470456,0.017803945,0.00033651944,0.00017354048,0.15167168,0.045871783,0.7768373],"study_design_scores_gemma":[0.0010509338,0.00015368586,0.2896585,0.00011494036,0.000031180003,0.0000045658835,0.0062683965,0.025341533,0.000065083885,0.13338113,0.5430253,0.0009047563],"about_ca_topic_score_codex":0.0007157397,"about_ca_topic_score_gemma":0.00007155719,"teacher_disagreement_score":0.77593255,"about_ca_system_score_codex":0.00006275442,"about_ca_system_score_gemma":0.00004195162,"threshold_uncertainty_score":0.7822914},"labels":[],"label_agreement":null},{"id":"W4388023864","doi":"10.1037/met0000596.supp","title":"Supplemental Material for Equivalence Testing for Linear Regression","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Equivalence (formal languages); Statistics; Regression analysis; Linear regression; Mathematics; Econometrics; Statistical hypothesis testing; Psychology; Regression; Discrete mathematics","score_opus":0.15170678181754713,"score_gpt":0.4677150525645851,"score_spread":0.31600827074703797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388023864","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":[0.16644117,0.000048044138,0.82141364,0.00023193694,0.006862608,0.0013108297,0.00029925775,0.0020313088,0.0013612309],"genre_scores_gemma":[0.36499295,0.0000058563473,0.63249886,0.00008442254,0.0009294331,0.0010684729,0.00005901705,0.000041113268,0.00031987194],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905235,0.00008940491,0.0002518704,0.00022831022,0.000070618386,0.00030744704],"domain_scores_gemma":[0.99907917,0.000660126,0.000031516352,0.00013898031,0.00002824422,0.00006198016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009839416,0.00012274702,0.0001911941,0.000053608383,0.00009008926,0.000026532369,0.00012921456,0.00011136366,0.0001303111],"category_scores_gemma":[0.0004902445,0.00009222101,0.00009014332,0.00020677963,0.000017825534,0.00003646545,0.000019366706,0.000068900095,0.00002468133],"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":[0.00012708393,0.000018986253,0.000049909446,0.000115915886,0.000017028326,0.0000016351174,0.000036481513,0.00045591683,0.73620296,0.00014817248,0.008082805,0.2547431],"study_design_scores_gemma":[0.0032505223,0.0013748612,0.0025414533,0.00010684716,0.000034348304,0.000030606523,0.0002053432,0.72787803,0.074197404,0.005954054,0.18383722,0.00058932503],"about_ca_topic_score_codex":0.0000013031336,"about_ca_topic_score_gemma":2.4746134e-7,"teacher_disagreement_score":0.7274221,"about_ca_system_score_codex":0.000019331843,"about_ca_system_score_gemma":0.0000014519694,"threshold_uncertainty_score":0.37606636},"labels":[],"label_agreement":null},{"id":"W4388628386","doi":"10.1037/met0000596","title":"Equivalence testing for linear regression.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Equivalence (formal languages); Linear regression; Statistics; PsycINFO; Mathematics; Regression analysis; Linear model; Regression; Multilevel model; Econometrics; Discrete mathematics; MEDLINE","score_opus":0.725563039131135,"score_gpt":0.6745870036714725,"score_spread":0.05097603545966245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388628386","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":[0.003255708,0.000042503216,0.99073505,0.00034977432,0.0004551603,0.00041162787,0.000027646547,0.00057730445,0.004145204],"genre_scores_gemma":[0.0015416846,0.000014143098,0.9964954,0.0002693571,0.000219261,0.00022791134,0.0000031471136,0.00003507932,0.0011939667],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99777853,0.00058142043,0.00041234534,0.0005491323,0.00016842945,0.0005101309],"domain_scores_gemma":[0.9766343,0.022547131,0.00012969936,0.00039727695,0.00013010735,0.0001614788],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003625583,0.0001939821,0.000394736,0.00006703454,0.00017305161,0.000015351923,0.00027668072,0.00016089852,0.00008051534],"category_scores_gemma":[0.049767245,0.00012773422,0.00011753432,0.0005624529,0.000113604816,0.000052485266,0.00011076427,0.00024037807,0.000035416513],"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":[0.000060473067,0.000099164354,0.000032350406,0.00009294173,0.000010035391,0.00001319023,0.000055393306,0.000019481446,0.01455439,0.19103965,0.0026081926,0.79141474],"study_design_scores_gemma":[0.00031811924,0.00032364196,0.00039615625,0.000064315886,0.000019271345,0.00000872407,0.000030019606,0.013971484,0.0009012159,0.9802749,0.0034989389,0.00019318497],"about_ca_topic_score_codex":3.8987676e-7,"about_ca_topic_score_gemma":4.8628316e-8,"teacher_disagreement_score":0.79122156,"about_ca_system_score_codex":0.000014477402,"about_ca_system_score_gemma":0.000006489605,"threshold_uncertainty_score":0.958237},"labels":[],"label_agreement":null},{"id":"W4388730146","doi":"10.1037/met0000616","title":"Tutorial: Assessing the impact of nonignorable missingness on regression analysis using Index of Local Sensitivity to Nonignorability.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Missing data; Credibility; Sensitivity (control systems); Statistics; Computer science; Econometrics; Robustness (evolution); Data mining; Regression; Syntax; Regression analysis; Spurious relationship; Mathematics; Artificial intelligence","score_opus":0.16370209868771823,"score_gpt":0.5713806165324973,"score_spread":0.40767851784477904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388730146","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":[0.21590331,0.000007100147,0.7832548,0.00013180336,0.00017328263,0.00017714263,0.0000068333834,0.0001987239,0.00014701854],"genre_scores_gemma":[0.51632345,0.0000010691937,0.4836093,0.000031306434,0.000019846026,0.00000502062,7.442861e-7,0.0000064695982,0.0000027993278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952351,0.0025794287,0.0005970891,0.00072073966,0.0004623409,0.00040530754],"domain_scores_gemma":[0.99375314,0.004263857,0.0003062721,0.0012237721,0.00029603078,0.00015690758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058742836,0.0002397519,0.0007274161,0.00037202885,0.0001621186,0.00007650112,0.000700217,0.00018343375,0.0000097537895],"category_scores_gemma":[0.0022892803,0.00013723697,0.00033806296,0.004511514,0.00027830375,0.00018611026,0.00037227673,0.00034757995,0.0000018814263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001370979,0.000498212,0.0025591617,0.000024533092,0.00014451674,0.000034866014,0.00033601985,0.44376978,0.07368715,0.005078679,0.00008157947,0.4736484],"study_design_scores_gemma":[0.00011944042,0.0003733816,0.04307964,0.00007193877,0.000046668374,0.00000482775,0.000035407393,0.8772476,0.010912067,0.06791533,0.0000062991335,0.00018743821],"about_ca_topic_score_codex":0.00016496945,"about_ca_topic_score_gemma":0.0000013220971,"teacher_disagreement_score":0.47346097,"about_ca_system_score_codex":0.00012469232,"about_ca_system_score_gemma":0.00004991119,"threshold_uncertainty_score":0.5596361},"labels":[],"label_agreement":null},{"id":"W4389724851","doi":"10.1037/met0000629","title":"The case for the curve: Parametric regression with second- and third-order polynomial functions of predictors should be routine.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Data Analysis with R","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Polynomial regression; Spurious relationship; Polynomial; Regression analysis; Nonparametric regression; Regression; Computer science; Local regression; Smoothing; Nonparametric statistics; Econometrics; Mathematics; Statistics","score_opus":0.13247304336046892,"score_gpt":0.4390515366897398,"score_spread":0.3065784933292709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389724851","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":[0.064313024,0.00044508209,0.92690855,0.0066179694,0.00063656515,0.00044321528,0.00004377824,0.00016101319,0.0004307882],"genre_scores_gemma":[0.54410154,0.00017279993,0.45257232,0.00092941924,0.00017639498,0.0002967887,0.000012677171,0.000021814947,0.0017162447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786234,0.00074339967,0.00032874558,0.0005299703,0.00021694294,0.00031860315],"domain_scores_gemma":[0.99133855,0.007238616,0.00019780266,0.0010176972,0.00011091546,0.00009638929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040487032,0.00016588364,0.00025301983,0.00014313404,0.00051935733,0.00015180054,0.000838032,0.00011419957,0.000024051296],"category_scores_gemma":[0.001809187,0.00006567659,0.000097226046,0.002525987,0.00030607657,0.00015913749,0.00031231763,0.00028331077,0.0000025805687],"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":[0.00043724055,0.00029916794,0.009570173,0.00003557662,0.00048352603,0.00011970143,0.0006383012,0.00045255604,0.00053903915,0.0046419124,0.2015498,0.781233],"study_design_scores_gemma":[0.0041503753,0.0036258362,0.2583015,0.00006498399,0.00064520474,0.0015994365,0.002018078,0.46697918,0.0010065008,0.0055493163,0.25498614,0.0010734758],"about_ca_topic_score_codex":0.000026170626,"about_ca_topic_score_gemma":0.000032707074,"teacher_disagreement_score":0.78015953,"about_ca_system_score_codex":0.0000104242445,"about_ca_system_score_gemma":0.000017958952,"threshold_uncertainty_score":0.39945292},"labels":[],"label_agreement":null},{"id":"W4393039792","doi":"10.1037/met0000507","title":"The Bayes factor, HDI-ROPE, and frequentist equivalence tests can all be reverse engineered—Almost exactly—From one another: Reply to Linde et al. (2021).","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Bayes factor; Rope; Bayesian probability; Bayes' theorem; Statistical hypothesis testing; Statistics; Equivalence (formal languages); Null hypothesis; Econometrics; Frequentist probability; Bayes' rule; Type I and type II errors; Mathematics; Bayesian inference; Computer science; Algorithm; Discrete mathematics","score_opus":0.6313980920682659,"score_gpt":0.6237437826978459,"score_spread":0.007654309370419998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393039792","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":[0.010545998,0.0020896194,0.90877885,0.068539254,0.0036262989,0.0014426231,0.0010016764,0.00054596266,0.0034297106],"genre_scores_gemma":[0.0044266805,0.0013262413,0.96444416,0.028362151,0.0003590778,0.00016056545,0.0000058095957,0.00010292862,0.0008123835],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99028474,0.005292278,0.0013956234,0.001583614,0.000642711,0.0008010072],"domain_scores_gemma":[0.8774553,0.12038993,0.0002013628,0.0013537684,0.00013399696,0.00046565794],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0113413865,0.00053773023,0.0010336355,0.00009486435,0.00017568997,0.00042897236,0.00086766464,0.00036100275,0.0015235175],"category_scores_gemma":[0.16123556,0.0003489009,0.00023807284,0.0005987626,0.0004661259,0.00009803714,0.00040476085,0.0012528831,0.00007448737],"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":[0.00039773996,0.00072123157,0.00023215299,0.0001715834,0.00071666134,0.00031938488,0.0007775679,0.0000020988357,0.038541995,0.08809594,0.09960217,0.77042145],"study_design_scores_gemma":[0.0005359441,0.0006602589,0.0059552407,0.00036607383,0.00019950085,0.00002790042,0.000053484822,0.00013543418,0.0018802744,0.71393865,0.27562913,0.0006181348],"about_ca_topic_score_codex":0.00011725074,"about_ca_topic_score_gemma":0.000026290634,"teacher_disagreement_score":0.76980335,"about_ca_system_score_codex":0.00008853965,"about_ca_system_score_gemma":0.000046868823,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W4396673092","doi":"10.1037/met0000645","title":"A deep learning method for comparing Bayesian hierarchical models.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"Deutsche Forschungsgemeinschaft; Google","keywords":"Computer science; Benchmark (surveying); Machine learning; Artificial intelligence; Inference; Bayesian inference; Model selection; Bayesian probability; Set (abstract data type); Hierarchical database model; Probabilistic logic; Code (set theory); Approximate Bayesian computation; Data mining","score_opus":0.08995888785594917,"score_gpt":0.442734058898519,"score_spread":0.35277517104256984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396673092","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":[0.000049560796,0.0011455895,0.97935355,0.0020923982,0.0006835188,0.0002409468,6.587106e-7,0.00082413334,0.015609642],"genre_scores_gemma":[0.14214897,0.000038059305,0.8568806,0.00045330185,0.00014530428,0.00012498676,0.0000021266337,0.00001901711,0.000187648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694693,0.00072399963,0.00040898102,0.0011063906,0.00021485017,0.0005988649],"domain_scores_gemma":[0.99757653,0.0016065257,0.00006170766,0.00045318366,0.000063234205,0.00023879293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023771194,0.00026326158,0.0004170022,0.00017330643,0.00021976713,0.00062511524,0.0011743951,0.00020412874,0.00004895133],"category_scores_gemma":[0.0003233664,0.00019535558,0.00023484256,0.00077862706,0.000073627125,0.00044086494,0.0002685986,0.00073696725,0.000024662539],"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":[0.000011023317,0.000040647115,0.00001281338,0.00005186434,0.00001559843,0.00001346707,0.00025083334,0.0007594669,0.00029219035,0.41903564,0.00008014984,0.5794363],"study_design_scores_gemma":[0.000114245704,0.00016400899,0.0001325649,0.000030994597,0.000008525096,0.000059445076,0.00000926978,0.58092827,0.00008881919,0.41285366,0.0054391944,0.00017101761],"about_ca_topic_score_codex":0.000003569832,"about_ca_topic_score_gemma":7.308252e-7,"teacher_disagreement_score":0.5801688,"about_ca_system_score_codex":0.000031826716,"about_ca_system_score_gemma":0.000022439659,"threshold_uncertainty_score":0.7966369},"labels":[],"label_agreement":null},{"id":"W4402642427","doi":"10.1037/met0000689","title":"Solving variables with Monte Carlo simulation experiments: A stochastic root-solving approach.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Database Systems and Queries","field":"Computer Science","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":"Monte Carlo method; Monte Carlo method in statistical physics; Statistical physics; Applied mathematics; Computer science; Statistics; Econometrics; Mathematics; Hybrid Monte Carlo; Markov chain Monte Carlo; Physics","score_opus":0.07748759442895121,"score_gpt":0.4205089106345848,"score_spread":0.3430213162056336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402642427","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":[0.0019376393,0.002280958,0.9919318,0.00006563381,0.0006886405,0.00029449002,0.0000053682415,0.0006056359,0.0021898306],"genre_scores_gemma":[0.32489547,0.0000028538464,0.6747161,0.00007000594,0.000111990346,0.00008971152,0.0000015548809,0.000014348681,0.00009795362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976971,0.00043060535,0.00032492136,0.0008972969,0.00026040964,0.00038963757],"domain_scores_gemma":[0.9983127,0.0007734173,0.00007962655,0.0006522877,0.000058149646,0.00012377986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001052969,0.00024972347,0.00030481504,0.000109435794,0.000173612,0.00022659948,0.00038878445,0.0001021559,0.000023333356],"category_scores_gemma":[0.00024510286,0.00016438165,0.000071652794,0.0005721678,0.000079519676,0.0008574916,0.00020748629,0.00027391897,0.000012114175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009075416,0.0003276738,0.00005820283,0.00017232729,0.00014713046,0.00011712944,0.0035535486,0.44494686,0.006300425,0.25506967,0.00020626854,0.28901002],"study_design_scores_gemma":[0.00023150042,0.00022161938,0.00022087728,0.00017056848,0.000014159918,0.000065245964,0.00015260458,0.9905352,0.00013876108,0.0020065578,0.005904054,0.00033887156],"about_ca_topic_score_codex":0.000018067753,"about_ca_topic_score_gemma":8.9836175e-7,"teacher_disagreement_score":0.5455883,"about_ca_system_score_codex":0.000051758983,"about_ca_system_score_gemma":0.000018189832,"threshold_uncertainty_score":0.6703289},"labels":[],"label_agreement":null},{"id":"W4402730880","doi":"10.1037/met0000631","title":"An overview of alternative formats to the Likert format: A comment on Wilson et al. (2022).","year":2024,"lang":"en","type":"review","venue":"Psychological Methods","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Likert scale; Psychology; Statistics; Computer science; Mathematics","score_opus":0.5365356742093091,"score_gpt":0.6770973150293158,"score_spread":0.14056164082000666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402730880","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000255746,0.87207156,0.073124625,0.019391838,0.0030304897,0.002328732,0.00010305847,0.00018565105,0.029761504],"genre_scores_gemma":[0.0000020417847,0.7593553,0.19570418,0.04408613,0.0002301975,0.00042626972,0.000017623483,0.00004707774,0.00013115523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9681708,0.028152274,0.0012144077,0.0008744311,0.0009039881,0.00068410416],"domain_scores_gemma":[0.9939956,0.0037873902,0.00069829944,0.0011187383,0.00016445656,0.00023551234],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.03992881,0.00062910386,0.0019846745,0.0003616032,0.00038537217,0.00017691149,0.0022181703,0.00042582597,0.00024972585],"category_scores_gemma":[0.002589111,0.0003311219,0.0007180644,0.002029301,0.00033874725,0.00018853525,0.00035162305,0.002163946,0.00018656655],"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":[0.000015214051,0.0002072372,2.2025394e-7,0.0006056084,0.0000991454,0.0000033924753,0.0035405587,5.390078e-7,0.0000010457285,0.1556919,0.041407518,0.7984276],"study_design_scores_gemma":[0.00008083676,0.0006972466,0.0000055241426,0.0041714283,0.00020846268,0.000006708624,0.0003296796,0.000010715808,0.0000029181874,0.0141209485,0.9799872,0.00037829785],"about_ca_topic_score_codex":0.00017865335,"about_ca_topic_score_gemma":0.0000168314,"teacher_disagreement_score":0.93857974,"about_ca_system_score_codex":0.0003487568,"about_ca_system_score_gemma":0.00011234819,"threshold_uncertainty_score":0.9999141},"labels":[],"label_agreement":null},{"id":"W4403303551","doi":"10.1037/met0000691","title":"Lagged multidimensional recurrence quantification analysis for determining leader–follower relationships within multidimensional time series.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Series (stratigraphy); Recurrence quantification analysis; Multidimensional analysis; Statistics; Statistical analysis; Econometrics; Time series; Psychology; Mathematics; Geology; Nonlinear system; Physics","score_opus":0.14224758821313951,"score_gpt":0.427926050321445,"score_spread":0.2856784621083055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403303551","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":[0.05597541,0.000492075,0.9395164,0.0009766147,0.0019240847,0.00044294845,0.000013356366,0.0005540391,0.000105018145],"genre_scores_gemma":[0.27150643,0.000008597269,0.7277511,0.000105256244,0.00007480167,0.00013880964,0.00002762323,0.000010592308,0.00037681716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962437,0.0011104868,0.00074210955,0.0011868633,0.0003559979,0.0003608071],"domain_scores_gemma":[0.9955324,0.0031336325,0.00016935467,0.0007966151,0.00021888016,0.00014911906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063079926,0.0002588634,0.00043483078,0.00030927666,0.00041822798,0.00012913541,0.00046414376,0.0002940867,0.00006395598],"category_scores_gemma":[0.0017653966,0.00018711577,0.0003801294,0.0017978419,0.00014425695,0.0006063717,0.00011513588,0.0004632882,0.00019771818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008073416,0.0020849116,0.06333008,0.00071375846,0.002532736,0.00010378595,0.013301749,0.017526338,0.104500726,0.119476564,0.0061987108,0.6694233],"study_design_scores_gemma":[0.0005007281,0.00037257015,0.0863735,0.00016330389,0.00023358675,0.000069565824,0.00007558047,0.8948824,0.0036986289,0.0067956084,0.0061621536,0.00067240396],"about_ca_topic_score_codex":0.0000033044087,"about_ca_topic_score_gemma":0.0000015494531,"teacher_disagreement_score":0.87735605,"about_ca_system_score_codex":0.00006240285,"about_ca_system_score_gemma":0.000056283574,"threshold_uncertainty_score":0.763036},"labels":[],"label_agreement":null},{"id":"W4405320068","doi":"10.1037/met0000707","title":"Testing bipolarity.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; University of Nevada, Las Vegas","keywords":"Psychology; Pessimism; Econometrics; Dimension (graph theory); Test (biology); Social psychology; Extraversion and introversion; Statistics; PsycINFO; Optimism; Type I and type II errors; Mathematics; Big Five personality traits; Personality; Epistemology","score_opus":0.5204120153975895,"score_gpt":0.6753057951375634,"score_spread":0.15489377973997387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405320068","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05497502,0.012560224,0.11792476,0.003311392,0.008274388,0.0006675848,0.00001624691,0.0013024353,0.80096793],"genre_scores_gemma":[0.15587488,0.000030865707,0.8298733,0.0021337492,0.001011793,0.0002286354,0.0000052811247,0.000051470204,0.0107900025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99634296,0.0016846105,0.00035714978,0.0007017794,0.00022635759,0.00068713963],"domain_scores_gemma":[0.99653697,0.002602832,0.00002985408,0.0004948973,0.000039219773,0.0002962118],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003594545,0.00016822977,0.00022132753,0.00016167553,0.00011495044,0.00008926765,0.00035905157,0.00025157706,0.009405023],"category_scores_gemma":[0.0010971098,0.00012564109,0.00009172334,0.0009021524,0.00015708942,0.00006425608,0.00010369283,0.0009116094,0.0031012418],"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":[0.000026824839,0.00016134286,0.0013351749,0.000056072353,0.000022125652,0.00019214692,0.00017517392,1.0096816e-7,0.0024352763,0.04871871,0.006252759,0.9406243],"study_design_scores_gemma":[0.00039645418,0.0010936798,0.20302118,0.00009848099,0.00002026616,0.0004240786,0.00014802942,0.00045813448,0.000259198,0.07816693,0.7155343,0.00037922568],"about_ca_topic_score_codex":0.000057474634,"about_ca_topic_score_gemma":7.423754e-7,"teacher_disagreement_score":0.9402451,"about_ca_system_score_codex":0.000062708794,"about_ca_system_score_gemma":0.000016285458,"threshold_uncertainty_score":0.99767494},"labels":[],"label_agreement":null},{"id":"W4407299576","doi":"10.1037/met0000735","title":"Reassessing the fitting propensity of factor models.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institute of Education Sciences; University of Missouri; U.S. Department of Education; National Science Foundation","keywords":"Statistics; Econometrics; Factor (programming language); Propensity score matching; Psychology; Mathematics; Computer science","score_opus":0.2529208410047625,"score_gpt":0.48388635618993864,"score_spread":0.23096551518517616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407299576","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":[0.0197118,0.00023283002,0.95958245,0.001556208,0.00031174909,0.00009817489,4.790382e-7,0.00010306127,0.018403245],"genre_scores_gemma":[0.5093929,0.00000932749,0.49001428,0.0004946602,0.0000097626225,0.0000050501885,6.927886e-8,0.0000014335176,0.00007253496],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830174,0.0007373811,0.00027227573,0.00036502286,0.00012613552,0.000197441],"domain_scores_gemma":[0.99857074,0.0005677507,0.00009898845,0.0006180894,0.00010532244,0.000039118077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015174589,0.00010424752,0.00020957598,0.00004194691,0.00013530892,0.00009176738,0.001004766,0.00009313957,0.000007820516],"category_scores_gemma":[0.00036504833,0.0000576837,0.00007629758,0.00047119422,0.000102934144,0.00016274191,0.00027446795,0.00028032868,0.000002220744],"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":[0.0000061357696,0.00006510985,0.00017623049,0.000009131558,0.000009124469,0.0000011614209,0.00014785293,0.00016034418,0.004777577,0.18370329,0.0000850093,0.810859],"study_design_scores_gemma":[0.00017228027,0.00007995086,0.01745839,0.00009760741,0.0000098613555,0.000008140573,0.000023370068,0.35315254,0.0059576333,0.62257946,0.00029390003,0.00016684443],"about_ca_topic_score_codex":0.000010985717,"about_ca_topic_score_gemma":2.4779314e-7,"teacher_disagreement_score":0.8106922,"about_ca_system_score_codex":0.0000108406975,"about_ca_system_score_gemma":0.000024949728,"threshold_uncertainty_score":0.2352273},"labels":[],"label_agreement":null},{"id":"W4407299679","doi":"10.1037/met0000739","title":"Reliability in unidimensional ordinal data: A comparison of continuous and ordinal estimators.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Research Foundation of Korea; Kwangwoon University","keywords":"Ordinal data; Estimator; Statistics; Ordinal optimization; Reliability (semiconductor); Ordinal regression; Mathematics; Econometrics; Ordered logit; Psychology","score_opus":0.3421491523690011,"score_gpt":0.6311549700243662,"score_spread":0.28900581765536504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407299679","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":[0.118752174,0.0002608329,0.8780459,0.00021854402,0.00018511536,0.00026027422,0.000034908455,0.000036843954,0.0022054112],"genre_scores_gemma":[0.23672354,0.000010312622,0.7630921,0.00007899489,0.000011026035,0.000015209198,0.000004099399,0.0000067515934,0.00005796229],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99677444,0.0013088812,0.00079421187,0.00068003585,0.0001637511,0.0002786709],"domain_scores_gemma":[0.990888,0.008034347,0.0001672138,0.0007166968,0.000098076714,0.00009564191],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003884328,0.00019185724,0.0008742727,0.000095435775,0.000053252777,0.000011944996,0.00032837296,0.00017626169,0.000053893345],"category_scores_gemma":[0.013574511,0.00014189497,0.00004533522,0.0003553171,0.00038715242,0.000080900965,0.00035813736,0.00042362537,7.1032e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005308465,0.0014090701,0.011382051,0.00020637683,0.000030161107,0.00001332489,0.00008970616,0.000028760265,0.0031255558,0.57142264,0.0009556772,0.41080585],"study_design_scores_gemma":[0.0007755776,0.0002557023,0.023737984,0.00010018058,0.000048192596,0.000008113944,0.00008759421,0.012537597,0.00028619394,0.96090174,0.0011052017,0.00015595485],"about_ca_topic_score_codex":0.000014419458,"about_ca_topic_score_gemma":0.0000032315372,"teacher_disagreement_score":0.4106499,"about_ca_system_score_codex":0.000024071778,"about_ca_system_score_gemma":0.000020784546,"threshold_uncertainty_score":0.9947346},"labels":[],"label_agreement":null},{"id":"W4407505237","doi":"10.1037/met0000718","title":"Fit indices are insensitive to multiple minor violations of perfect simple structure in confirmatory factor analysis.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Confirmatory factor analysis; Minor (academic); Statistics; Simple (philosophy); Statistical analysis; Factor (programming language); Psychology; Econometrics; Mathematics; Structural equation modeling; Computer science; Humanities","score_opus":0.3580454211727005,"score_gpt":0.6116049977086426,"score_spread":0.25355957653594213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407505237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8173769,0.000112380156,0.18051861,0.00036843552,0.00037145233,0.0003761388,0.00022756317,0.000030629577,0.00061787735],"genre_scores_gemma":[0.83581215,0.0000022390295,0.16277508,0.0012806847,0.000023003107,0.000016573096,0.0000045278853,0.0000063634548,0.0000793502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9932579,0.0031892252,0.0013928587,0.0010393213,0.0007711208,0.0003496189],"domain_scores_gemma":[0.98312986,0.014775661,0.00051594333,0.0009743023,0.00044024028,0.00016397263],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038194123,0.00026130344,0.0010815018,0.002174018,0.00011830246,0.00013349703,0.0009459047,0.00029565245,0.002006351],"category_scores_gemma":[0.029733172,0.00018042079,0.00033203416,0.0058333194,0.00018525435,0.000150324,0.0003038494,0.00037449677,0.000030552903],"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":[0.00030304384,0.00025037848,0.7088133,0.000008039497,0.00015599288,0.000020334926,0.0015782859,0.0017433937,0.03621863,0.00024821842,0.0011502723,0.24951008],"study_design_scores_gemma":[0.0005130049,0.000062038926,0.9769973,0.000023556879,0.000046992598,0.0000015338348,0.0010785469,0.0060269437,0.0021269475,0.00764033,0.005296967,0.00018584932],"about_ca_topic_score_codex":0.000047807553,"about_ca_topic_score_gemma":0.00024284892,"teacher_disagreement_score":0.26818395,"about_ca_system_score_codex":0.000052370877,"about_ca_system_score_gemma":0.000025337698,"threshold_uncertainty_score":0.99890596},"labels":[],"label_agreement":null},{"id":"W4407762147","doi":"10.1037/met0000730","title":"Evaluating statistical fit of confirmatory bifactor models: Updated recommendations and a review of current practice.","year":2025,"lang":"en","type":"review","venue":"Psychological Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Current (fluid); Confirmatory factor analysis; Psychology; Econometrics; Statistics; Statistical analysis; Psychometrics; Statistical hypothesis testing; Clinical psychology; Structural equation modeling; Mathematics; Engineering","score_opus":0.8475355186061376,"score_gpt":0.7654928065091957,"score_spread":0.08204271209694192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407762147","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4049135e-7,0.6438505,0.3500727,0.00010220033,0.00058785063,0.0011586659,0.00033126227,0.000021643444,0.0038750097],"genre_scores_gemma":[1.632096e-7,0.51327443,0.4863393,0.00015671486,0.000014998669,0.0001225212,0.00003467985,0.00001247067,0.000044710327],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95958906,0.032943662,0.004419345,0.0013515985,0.0013445287,0.00035181383],"domain_scores_gemma":[0.93544346,0.059070207,0.0030529625,0.001258019,0.0009421862,0.00023318034],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040541023,0.000563541,0.004408319,0.0005282657,0.00008358014,0.00006962153,0.0012402743,0.00040324792,0.0026957938],"category_scores_gemma":[0.09656748,0.00036141693,0.00059168995,0.001963258,0.0004932892,0.00028330635,0.0005671101,0.00092901837,0.000023902307],"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":[0.000027832974,0.00034786947,2.3143984e-7,0.014479227,0.000078378616,0.0000015630008,0.000027505706,6.567786e-7,0.0000097780385,0.0062022135,0.0042720605,0.9745527],"study_design_scores_gemma":[0.00026399372,0.00040192893,0.0000027396102,0.062017858,0.0010787769,0.000038983977,0.00006364709,0.0007026532,0.000008993041,0.017860383,0.91716003,0.00040000927],"about_ca_topic_score_codex":0.0000033482108,"about_ca_topic_score_gemma":4.7570303e-8,"teacher_disagreement_score":0.9741527,"about_ca_system_score_codex":0.0000773626,"about_ca_system_score_gemma":0.00031378414,"threshold_uncertainty_score":0.9998838},"labels":[],"label_agreement":null},{"id":"W4408293278","doi":"10.1037/met0000746","title":"Unsupervised [randomly responding] survey bot detection: In search of high classification accuracy.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Artificial intelligence; Pattern recognition (psychology); Statistical analysis; Computer science; Psychology; Mathematics","score_opus":0.16687389522439644,"score_gpt":0.4706631522301324,"score_spread":0.30378925700573595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408293278","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":[0.28423926,0.00007902093,0.7126823,0.00063223636,0.00083475903,0.00017388813,0.0000013018426,0.00008223021,0.001274967],"genre_scores_gemma":[0.87513524,0.000032335178,0.12446298,0.0001660415,0.000025816964,0.000033154713,0.0000016805334,0.0000039586953,0.00013878557],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947683,0.0037964091,0.00044065327,0.00055722106,0.00020418476,0.00023319598],"domain_scores_gemma":[0.9956017,0.0034700076,0.00009288227,0.00064901204,0.000133839,0.000052572643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007505352,0.00012414025,0.00028460973,0.0005346213,0.000086130036,0.000077414436,0.00077417423,0.00020929871,0.000030887324],"category_scores_gemma":[0.002873637,0.00010438,0.00007263453,0.003265882,0.00007551221,0.00020468829,0.000117650095,0.0003731363,0.000009267442],"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":[0.0008235098,0.00028129818,0.009599475,0.000021994869,0.000017702749,0.0000035233459,0.00021094098,0.000057176036,0.10880472,0.014884817,0.00010827134,0.8651866],"study_design_scores_gemma":[0.0010994839,0.0002104051,0.94079095,0.000023607849,0.0000036239765,0.000004111884,0.000014351581,0.010308107,0.030702623,0.016226472,0.00049977074,0.00011649895],"about_ca_topic_score_codex":0.000229029,"about_ca_topic_score_gemma":0.00003461259,"teacher_disagreement_score":0.93119144,"about_ca_system_score_codex":0.000058006954,"about_ca_system_score_gemma":0.000024518578,"threshold_uncertainty_score":0.4256493},"labels":[],"label_agreement":null},{"id":"W4414082743","doi":"10.1037/met0000797","title":"On the uncanny relationship between nonnormality and moderated multiple regression.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Multivariate statistics; Generalization; Regression; Regression analysis; Linear regression; Multivariate analysis; Asymmetry; Association (psychology)","score_opus":0.4858594828500195,"score_gpt":0.6028049536091047,"score_spread":0.11694547075908518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414082743","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":[0.07308119,0.00006278611,0.91333,0.0023477995,0.00012726018,0.00032431458,0.00002243042,0.00009318375,0.010611011],"genre_scores_gemma":[0.41654965,0.0000039798397,0.58234376,0.0005851484,0.000020603626,0.000044412933,0.0000016230069,0.0000068945806,0.00044393702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963008,0.002477466,0.0003889827,0.0004314174,0.00014486299,0.00025643557],"domain_scores_gemma":[0.95332474,0.045951664,0.00010070045,0.00046322698,0.00006440928,0.00009528229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033012636,0.00019199631,0.0003500011,0.000052410665,0.00033858023,0.000034398894,0.00019324724,0.00020080608,0.00007303667],"category_scores_gemma":[0.03465442,0.00009924086,0.00006346494,0.00030768078,0.00023529594,0.000043857333,0.00009007108,0.0005747052,0.000004117516],"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":[0.00010844353,0.000089342975,0.003612552,0.000020077063,0.000017179176,0.0000014304367,0.000053467003,0.0000072130233,0.0001289517,0.90904534,0.0009560624,0.08595996],"study_design_scores_gemma":[0.000311503,0.00007151201,0.06878187,0.000050431805,0.00003045316,0.0000011388823,0.000025130994,0.0019068129,0.0002418848,0.92805153,0.0004133111,0.00011440423],"about_ca_topic_score_codex":0.000002437145,"about_ca_topic_score_gemma":6.42552e-7,"teacher_disagreement_score":0.3434685,"about_ca_system_score_codex":0.00002325435,"about_ca_system_score_gemma":0.000008397061,"threshold_uncertainty_score":0.9734771},"labels":[],"label_agreement":null},{"id":"W4414341611","doi":"10.1037/met0000770","title":"Crowdsourcing multiverse analyses to explore the impact of different data-processing and analysis decisions: A tutorial.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Crowdsourcing; Generalizability theory; Objectivity (philosophy); Focus (optics); Outcome (game theory); Heuristics; Conflation","score_opus":0.757406363254655,"score_gpt":0.6943019283092987,"score_spread":0.06310443494535634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414341611","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":[0.301085,0.00016180314,0.6971952,0.0004276984,0.000050508977,0.0001722134,0.000023696444,0.000036973575,0.000846942],"genre_scores_gemma":[0.6115011,0.000022198901,0.3882995,0.000081355436,0.000022435896,0.000026612499,0.0000036213657,0.0000027542485,0.000040392446],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99705064,0.0009090841,0.00069378124,0.00075885234,0.00039458933,0.00019306103],"domain_scores_gemma":[0.9898159,0.007911038,0.0002749846,0.0016230011,0.00025734567,0.000117741394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005737328,0.00016088644,0.00056197675,0.0005193589,0.00026091412,0.0002028183,0.0015399399,0.0000937621,0.000097952754],"category_scores_gemma":[0.016205933,0.00006977274,0.0002648338,0.004422063,0.00019992999,0.00010319069,0.0008078699,0.00018496873,0.000003389852],"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":[0.00007359549,0.00016279066,0.006274627,0.0000010153576,0.00014708751,7.2545856e-7,0.00038257695,0.00042115923,0.0062715923,0.00031042242,0.0023947696,0.9835596],"study_design_scores_gemma":[0.00045556165,0.0003925321,0.6883534,0.000087554785,0.0008392374,0.0000045272914,0.0025752187,0.13270548,0.001648798,0.16720352,0.005395067,0.000339056],"about_ca_topic_score_codex":0.00007288376,"about_ca_topic_score_gemma":0.0000043793625,"teacher_disagreement_score":0.9832206,"about_ca_system_score_codex":0.000030279842,"about_ca_system_score_gemma":0.000017814664,"threshold_uncertainty_score":0.992081},"labels":[],"label_agreement":null},{"id":"W4414753970","doi":"10.1037/met0000781.supp","title":"Supplemental Material for Causal Mediation Analysis With Two Mediators: A Comprehensive Guide to Estimating Total and Natural Effects Across Various Multiple Mediators Setups","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Information and Cyber Security","field":"Computer Science","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":"Mediation; Natural (archaeology); Causal model; Causal analysis; Causal inference; Causality (physics)","score_opus":0.014206761890993121,"score_gpt":0.4123835212198742,"score_spread":0.3981767593288811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414753970","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":[0.3760794,0.00001697105,0.62143487,0.00037357933,0.0013707966,0.00051386276,0.00006219062,0.00011059662,0.000037731857],"genre_scores_gemma":[0.45685047,5.7544077e-7,0.54188037,0.00095714297,0.00008263416,0.00013921864,0.000077917466,0.0000041308735,0.0000075231487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977857,0.00040109458,0.00048901263,0.00057282473,0.00028554848,0.00046583076],"domain_scores_gemma":[0.99769294,0.0014405246,0.0001701164,0.0003444258,0.00016498052,0.00018698919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009792967,0.0002579109,0.00046114504,0.00020740254,0.0002812547,0.00026702124,0.00041240302,0.00011352338,0.000021414538],"category_scores_gemma":[0.0005918153,0.00019119235,0.0001043345,0.0009779527,0.00008580281,0.00035784402,0.00031863502,0.00018120835,0.0000034245206],"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":[0.0028598222,0.0012984519,0.04863374,0.0008605671,0.003550969,0.000115378694,0.047963936,0.00494109,0.03247188,0.05417799,0.0077888514,0.7953373],"study_design_scores_gemma":[0.0120200915,0.0014920825,0.27155286,0.000050195147,0.0004095848,0.000074210824,0.00085907866,0.689926,0.015239264,0.00371697,0.0033385507,0.0013210857],"about_ca_topic_score_codex":0.000055916404,"about_ca_topic_score_gemma":0.00005592113,"teacher_disagreement_score":0.79401624,"about_ca_system_score_codex":0.000069741,"about_ca_system_score_gemma":0.000023721326,"threshold_uncertainty_score":0.77965975},"labels":[],"label_agreement":null},{"id":"W4415247091","doi":"10.1037/met0000781","title":"Causal mediation analysis with two mediators: A comprehensive guide to estimating total and natural effects across various multiple mediators setups.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec","keywords":"Mediation; Causal inference; Causal model; Imputation (statistics); Causal analysis; Natural (archaeology); Structural equation modeling; Causality (physics)","score_opus":0.0642801776188526,"score_gpt":0.5832066838773483,"score_spread":0.5189265062584957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415247091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5945416,0.00033881117,0.40222722,0.0010502705,0.00035148126,0.00053338433,0.000011286349,0.00008865141,0.00085729506],"genre_scores_gemma":[0.68050915,0.000010017892,0.31837234,0.0005748169,0.00014794021,0.00013994469,0.000015965104,0.000008533496,0.00022126827],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9900768,0.0068975287,0.0005265879,0.00090924,0.0008465442,0.00074331614],"domain_scores_gemma":[0.98421043,0.014227343,0.00019571619,0.00033549982,0.0006137153,0.00041727084],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0045504165,0.00030047132,0.00085713423,0.00047058638,0.00076019333,0.00020926094,0.00041238274,0.00016571986,0.00010357271],"category_scores_gemma":[0.014273283,0.00022035665,0.00017379293,0.004642418,0.0008415863,0.00020802864,0.00023126016,0.0005166628,0.000024571062],"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":[0.0017126456,0.0012065456,0.44409743,0.00023824126,0.008119867,0.00019036683,0.1724794,0.0074308887,0.0248493,0.018296177,0.0048365192,0.31654263],"study_design_scores_gemma":[0.0039855917,0.0007562162,0.9112665,0.00007106085,0.00083083595,0.0000038907206,0.016422214,0.052897763,0.0013162561,0.0069728717,0.004398562,0.001078223],"about_ca_topic_score_codex":0.0010750769,"about_ca_topic_score_gemma":0.001972229,"teacher_disagreement_score":0.46716908,"about_ca_system_score_codex":0.00020395583,"about_ca_system_score_gemma":0.00007822439,"threshold_uncertainty_score":0.99402994},"labels":[],"label_agreement":null}]}