{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":95,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":95,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"b6f3f6bdb720","filters":{"venue":"Psychological Methods"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.35917610160414,"gpt":0.5393551820295689,"spread":0.1801790804254289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01985353,0.0004308987,0.001415986,0.0002661441,0.0002947318,0.0002113082,0.0006962457,0.0004921583,0.001759439],"category_scores_gemma":[0.009291993,0.0002864,0.0002461573,0.0008991836,0.0006933506,0.0003313724,0.0002004708,0.0005656711,0.00003739318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001212677,"about_ca_system_score_gemma":0.0000365577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002334369,"about_ca_topic_score_gemma":0.000006330643,"domain_scores_codex":[0.9880808,0.007052256,0.001833522,0.0009840264,0.001299522,0.0007498622],"domain_scores_gemma":[0.9887494,0.008602803,0.0007382056,0.0008331003,0.0005398568,0.0005366234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008796751,0.008410262,0.2674582,0.000064655,0.0004405153,0.0000159655,0.004969495,0.004061446,0.03602914,0.1547667,0.02701853,0.4958854],"study_design_scores_gemma":[0.003436225,0.0029655,0.2208232,0.00004391505,0.0005982096,0.0002133696,0.005875295,0.02839177,0.01431786,0.7070454,0.01488032,0.001408929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2184741,0.0006506965,0.7715866,0.002958117,0.0006295535,0.0006335424,0.00001984766,0.00009562784,0.004951901],"genre_scores_gemma":[0.5634009,0.00001465114,0.4358103,0.0003829806,0.00006637195,0.00005947203,0.00001744137,0.00001211629,0.0002357817],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5522787,"threshold_uncertainty_score":0.9999588,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8017652952165407,"gpt":0.719740427808512,"spread":0.08202486740802872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01023514,0.0008528798,0.004344054,0.0008404549,0.0001463723,0.0001860689,0.0007471596,0.001241901,0.001752082],"category_scores_gemma":[0.00655169,0.0006088299,0.0008127132,0.002020064,0.0001705543,0.0002748358,0.0001259924,0.002131365,0.00009235348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009947249,"about_ca_system_score_gemma":0.00003985677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003284104,"about_ca_topic_score_gemma":0.000003646378,"domain_scores_codex":[0.9812253,0.0112214,0.004160559,0.002305266,0.0002737195,0.0008137398],"domain_scores_gemma":[0.9816696,0.004021314,0.01237212,0.001473118,0.00006232558,0.0004015245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001311951,0.001052667,0.0003687632,0.0004507713,0.0005240564,0.0001650797,0.00009870854,1.938325e-7,9.058977e-7,0.002539429,0.0002948874,0.9944914],"study_design_scores_gemma":[0.0003809586,0.0005533368,0.02810687,0.001813186,0.001883857,0.0002947341,0.0001332586,0.00001019753,6.422709e-8,0.005276184,0.9606275,0.0009198824],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002398137,0.9867798,0.001140861,0.0003106509,0.001028628,0.0008844488,0.00003848055,0.000304649,0.009272655],"genre_scores_gemma":[0.00004866621,0.8856504,0.1121843,0.001072095,0.0002624838,0.0003560349,0.000141743,0.00004259294,0.0002416835],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9935715,"threshold_uncertainty_score":0.9996363,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6121447167284271,"gpt":0.5685405495960681,"spread":0.04360416713235893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00687352,0.0004909632,0.001469882,0.0002478905,0.0003669052,0.0006971173,0.001044266,0.0005612285,0.002714772],"category_scores_gemma":[0.01081226,0.0002725413,0.0007494809,0.001081407,0.000238151,0.0002489506,0.0003581546,0.001160097,0.001187633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005862257,"about_ca_system_score_gemma":0.00004029686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003252051,"about_ca_topic_score_gemma":0.000004473362,"domain_scores_codex":[0.996025,0.0007543796,0.001044642,0.0007925784,0.00069443,0.0006890006],"domain_scores_gemma":[0.9945312,0.003122258,0.001083972,0.0009079917,0.0003101102,0.00004453688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002280502,0.00009063909,0.000003123723,0.0008563579,0.00008005278,0.000005546101,0.000003904137,3.906762e-7,0.000001386962,0.005978693,0.06520374,0.9277533],"study_design_scores_gemma":[0.0003853623,0.00004695071,0.00005450023,0.0005185643,0.0003890636,0.000003191055,0.00002157433,0.00006266874,1.324568e-7,0.002654998,0.9955162,0.0003467358],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001174669,0.9056085,0.005133884,0.003100544,0.003498897,0.001906376,0.000004603112,0.0002126582,0.08052275],"genre_scores_gemma":[0.000005676408,0.9772628,0.009726796,0.006091759,0.003817198,0.0009066295,0.00005927085,0.00007690225,0.00205299],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9303125,"threshold_uncertainty_score":0.9999727,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.915936087266207,"gpt":0.7443180110581955,"spread":0.1716180762080115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020981,0.0002963858,0.0009653323,0.0001466595,0.0001132431,0.00005713073,0.0006240472,0.000228412,0.001776686],"category_scores_gemma":[0.2010913,0.0002316169,0.00024217,0.0006947675,0.00027161,0.0000603097,0.0002224239,0.0006152294,0.0001710537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008430584,"about_ca_system_score_gemma":0.00001257553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009550187,"about_ca_topic_score_gemma":0.000001708654,"domain_scores_codex":[0.9934767,0.003096048,0.001614716,0.0007637758,0.0004125689,0.000636223],"domain_scores_gemma":[0.9027226,0.09551849,0.0003194914,0.0007088883,0.0002298955,0.000500637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006887632,0.0008721092,0.001881923,0.00008779249,0.0001027283,0.0001020892,0.0006326517,0.00002360665,0.01061919,0.6164291,0.004276105,0.3642839],"study_design_scores_gemma":[0.0005004468,0.0002307715,0.01009108,0.0001076506,0.00007127367,0.00004729715,0.0001480489,0.0004133864,0.002427461,0.9839951,0.00162304,0.0003444463],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0253276,0.00004020152,0.9607531,0.0005206976,0.002222108,0.0006684487,0.00001751149,0.0002341467,0.01021612],"genre_scores_gemma":[0.1170871,0.000003497593,0.8805161,0.001873572,0.0003502162,0.00002039245,4.965482e-7,0.00003088066,0.00011783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.367566,"threshold_uncertainty_score":0.9991359,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6806927522206976,"gpt":0.6148759361173601,"spread":0.06581681610333745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01038201,0.0003579142,0.001273923,0.0001956431,0.00009962252,0.00002615945,0.0009711917,0.0002923213,0.0006030247],"category_scores_gemma":[0.02866011,0.0002562336,0.0003359905,0.001076055,0.0002811133,0.0001484144,0.0001938457,0.0004776025,0.000002581949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003249956,"about_ca_system_score_gemma":0.00002347462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007209667,"about_ca_topic_score_gemma":0.000004145797,"domain_scores_codex":[0.9895346,0.00713883,0.00102532,0.001167947,0.0004345266,0.0006987536],"domain_scores_gemma":[0.9892493,0.00764826,0.000377939,0.002224093,0.0001802524,0.0003201598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000803362,0.0007753448,0.000267791,0.00005370139,0.0007495502,0.00001190067,0.0001906181,0.0007983838,0.005542077,0.3997288,0.0002295135,0.591572],"study_design_scores_gemma":[0.0003691258,0.0001209797,0.0009236678,0.00001237578,0.001078769,0.00001278308,0.00007672164,0.02111457,0.001750612,0.9726127,0.001593274,0.0003343577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003499997,0.0006780704,0.9859085,0.00006603677,0.0002961627,0.0002885507,0.0001118584,0.0001065259,0.01219428],"genre_scores_gemma":[0.009860176,0.0001079296,0.9895853,0.0001351319,0.00004380848,0.00002674326,0.00001332537,0.000034747,0.0001928823],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5912376,"threshold_uncertainty_score":0.999989,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.292115897921022,"gpt":0.5647337317607719,"spread":0.2726178338397499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01498476,0.0001697633,0.0003559814,0.00003745726,0.000174754,0.000007383521,0.000481086,0.0001440262,0.0005107141],"category_scores_gemma":[0.003136799,0.0000720219,0.000272595,0.0003129889,0.00045942,0.00002843159,0.00006429901,0.0004937405,0.00007913377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002450021,"about_ca_system_score_gemma":0.000004643668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001270029,"about_ca_topic_score_gemma":0.000007356395,"domain_scores_codex":[0.989743,0.008305455,0.0008799444,0.0003393271,0.0002157988,0.0005164774],"domain_scores_gemma":[0.9886681,0.009590249,0.0003392255,0.001194996,0.00005866025,0.0001487835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.008258574,0.01071384,0.235612,0.00002193625,0.0001050033,0.000002353675,0.002368515,0.000001589749,0.004533222,0.005841669,0.003755689,0.7287856],"study_design_scores_gemma":[0.001508569,0.007313294,0.9853268,0.00001557602,0.00005575317,0.000002106243,0.0007415642,0.00001423793,0.003314422,0.0003743179,0.001247387,0.00008593976],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904841,0.0003767796,0.0006095303,0.0006408822,0.001302434,0.001225669,0.00002740881,0.00003354074,0.00529965],"genre_scores_gemma":[0.9980539,0.000006451786,0.001303167,0.0001042014,0.00008653387,0.0002608249,0.000001230196,0.00001043109,0.0001732372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7497149,"threshold_uncertainty_score":0.5591962,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4990862637320314,"gpt":0.4843807592511338,"spread":0.01470550448089752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004687258,0.0002564315,0.0003705074,0.00009709947,0.00007885366,0.00007301821,0.002615007,0.0001277751,0.00001550435],"category_scores_gemma":[0.00927223,0.000140061,0.00002293133,0.0008880064,0.0001797134,0.0005318405,0.0007622192,0.0003457632,0.00001801453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001402159,"about_ca_system_score_gemma":0.00005048131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001763816,"about_ca_topic_score_gemma":0.00001194862,"domain_scores_codex":[0.9960297,0.0008397247,0.0004761991,0.001421909,0.0006654689,0.0005669456],"domain_scores_gemma":[0.995767,0.001664141,0.0001368428,0.001959568,0.0002891822,0.0001832623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005219878,0.0002454164,0.002184003,0.000005033516,0.000008341123,0.00009401552,0.00001097945,0.00001848933,0.005529435,0.06271091,0.0001480565,0.9289931],"study_design_scores_gemma":[0.001334246,0.0009356335,0.07640392,0.0002169879,0.00001470414,0.0001991279,0.000003122863,0.02781267,0.001039014,0.8892727,0.001982816,0.0007850644],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001584153,0.0001432124,0.9952041,0.002109563,0.0001272088,0.0002517371,0.000003828915,0.0004850708,0.001516847],"genre_scores_gemma":[0.302841,0.00001151286,0.6968479,0.0002018589,0.00003266078,0.00004841959,4.621169e-7,0.00001070607,0.000005452915],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9282081,"threshold_uncertainty_score":0.9990731,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6435478184034068,"gpt":0.7307775730395879,"spread":0.0872297546361811,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04144841,0.0003363276,0.0008601474,0.0003037748,0.0009848108,0.0002748216,0.001045093,0.000655888,0.001874794],"category_scores_gemma":[0.02704017,0.0001882561,0.0001361068,0.0003471132,0.001232276,0.0001875345,0.0005828542,0.002482066,0.0002317771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001323759,"about_ca_system_score_gemma":0.00001732506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002188322,"about_ca_topic_score_gemma":0.0000188671,"domain_scores_codex":[0.9848577,0.009785946,0.001501982,0.001616698,0.0007164555,0.001521221],"domain_scores_gemma":[0.9933712,0.003187571,0.0008592968,0.001898912,0.00009169607,0.000591301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001665097,0.000781132,0.1305487,0.00007103139,0.00001752749,0.0009582051,0.0004245551,1.035581e-7,0.002381005,0.008926114,0.002256103,0.8519704],"study_design_scores_gemma":[0.002596156,0.003348892,0.9273007,0.000130975,0.000007798495,0.0002594417,0.0001709342,0.00002259431,0.0001881261,0.03224251,0.03341809,0.0003138128],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.899241,0.0004819215,0.0009010805,0.005393686,0.00388085,0.001308146,0.000004255079,0.0001161108,0.08867291],"genre_scores_gemma":[0.9208035,0.0001254054,0.07373878,0.00026244,0.00111211,0.0005951574,0.000003647442,0.00003890713,0.003320017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8516566,"threshold_uncertainty_score":0.9998192,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4903035578928938,"gpt":0.6284214039490661,"spread":0.1381178460561723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02677309,0.0004522564,0.001305008,0.00009353076,0.0001161482,0.0002005614,0.0008736,0.0002704611,0.0003862732],"category_scores_gemma":[0.1349491,0.000258065,0.0001769397,0.0003736835,0.0004533623,0.0001029205,0.0002317018,0.001118268,0.00001260881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008788912,"about_ca_system_score_gemma":0.000009799477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004307423,"about_ca_topic_score_gemma":0.00006777177,"domain_scores_codex":[0.9742556,0.02219982,0.00120455,0.001125451,0.0006137919,0.0006007593],"domain_scores_gemma":[0.8201193,0.1783938,0.0002463637,0.0008293131,0.00009161534,0.0003195554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003248772,0.001482778,0.001753689,0.00007883898,0.0001493705,0.00141331,0.004737314,0.00004563609,0.00253815,0.08425903,0.0001765652,0.9001166],"study_design_scores_gemma":[0.004365852,0.003428238,0.011923,0.0001324631,0.0001408336,0.0007971115,0.0004047396,0.002135997,0.001445774,0.9746147,0.00007682775,0.0005344829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4430777,0.00002370074,0.5545641,0.000553954,0.0002914468,0.00101049,0.00003270695,0.000056651,0.0003892524],"genre_scores_gemma":[0.448929,0.00000814065,0.5493469,0.001304301,0.0001785936,0.00020375,2.688928e-7,0.0000181095,0.00001093341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8995821,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7505569186862165,"gpt":0.6029601374272204,"spread":0.1475967812589961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007139158,0.0001965381,0.000523607,0.0002834317,0.00008469209,0.00003592427,0.0002104869,0.0001473,0.00005619461],"category_scores_gemma":[0.001111004,0.0001556689,0.00006999222,0.0008631899,0.0001068295,0.0001824442,0.00005779812,0.0004400316,5.900721e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005201834,"about_ca_system_score_gemma":0.000006142534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002223558,"about_ca_topic_score_gemma":0.0001857472,"domain_scores_codex":[0.9973857,0.001048001,0.0005275923,0.0005202928,0.0002229732,0.0002954505],"domain_scores_gemma":[0.9964577,0.002817034,0.0001670512,0.0003777114,0.00006845604,0.0001120795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001882983,0.002071025,0.9289572,0.00002096488,0.00006376801,0.00005678197,0.0007329514,0.00004486023,0.01123498,0.01735886,0.000003577892,0.03926678],"study_design_scores_gemma":[0.000340238,0.0004438781,0.7458445,0.00001181483,0.00006288737,0.000001915475,0.0002085602,0.000229073,0.0003040319,0.2523876,0.000002279458,0.0001632515],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5322487,0.000008115736,0.4671167,0.00001849173,0.0000205856,0.0002803985,0.000001146544,0.0001404305,0.0001654056],"genre_scores_gemma":[0.519919,5.851282e-7,0.4798669,0.0001665996,0.000009833866,0.00002366213,0.000004598262,0.000006699965,0.00000208264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2350287,"threshold_uncertainty_score":0.6347992,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4613856083544618,"gpt":0.5923953237612258,"spread":0.131009715406764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006764802,0.0001866863,0.0006165453,0.0002427234,0.0001625471,0.0001077527,0.001158317,0.00007363235,0.00001444211],"category_scores_gemma":[0.00137162,0.0001215671,0.0001670572,0.00502562,0.0002210945,0.0007984855,0.0005827943,0.0001859456,0.000001156861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005372906,"about_ca_system_score_gemma":0.00001454029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001237651,"about_ca_topic_score_gemma":0.00002990238,"domain_scores_codex":[0.9967652,0.0007674154,0.0004683264,0.001082715,0.0006246829,0.0002916798],"domain_scores_gemma":[0.9977545,0.0002745547,0.0003003642,0.0009422948,0.0006527363,0.00007561147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004602343,0.0004981486,0.01199589,0.00001430104,0.001970186,0.000008758028,0.00270741,0.0000424404,0.001973391,0.005295067,0.00009025275,0.9753581],"study_design_scores_gemma":[0.0009620552,0.0009767088,0.9156937,0.00004105502,0.001285085,0.000006870393,0.001222814,0.02561494,0.002201502,0.0506358,0.000915808,0.0004436691],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002009639,0.0002073178,0.9915514,0.0007588886,0.00005506146,0.004492419,0.00000789074,0.00004323063,0.0008741573],"genre_scores_gemma":[0.4642008,0.00002692159,0.5341372,0.0002651919,0.00001712877,0.001332103,0.000003816716,0.000001507711,0.00001530297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9749145,"threshold_uncertainty_score":0.4957361,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.870865608223874,"gpt":0.6743232721351252,"spread":0.1965423360887488,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.01217676,0.001179553,0.00452716,0.001595213,0.0002415369,0.0001441972,0.001792003,0.003078654,0.0008800317],"category_scores_gemma":[0.0004220748,0.0008752628,0.0005589266,0.004121989,0.001121229,0.00004928699,0.0004764472,0.005304172,0.0007659614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002725062,"about_ca_system_score_gemma":0.00005513729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002409397,"about_ca_topic_score_gemma":0.00002010249,"domain_scores_codex":[0.975926,0.01560702,0.002170956,0.003533478,0.0005498569,0.0022127],"domain_scores_gemma":[0.9917994,0.005021506,0.0003705551,0.002005221,0.00007824502,0.0007250493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002595849,0.002226231,0.0004689268,0.0004703638,0.0001712435,0.0002051388,0.003627782,9.883996e-7,4.159071e-7,0.00256335,0.002336661,0.9876693],"study_design_scores_gemma":[0.0008413807,0.001543914,0.001931413,0.0007778058,0.0001485784,0.0004271433,0.001503208,0.00001543145,1.739806e-9,0.02214635,0.9697053,0.0009594575],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0007592469,0.9416381,0.01035668,0.0007123545,0.001492793,0.002606413,0.00002346594,0.0002236586,0.04218733],"genre_scores_gemma":[0.0002306399,0.9086633,0.0864697,0.001509086,0.0005302611,0.001861501,0.00003388155,0.0001413931,0.0005602106],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9867098,"threshold_uncertainty_score":0.9993698,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2788168570401769,"gpt":0.5244552156108684,"spread":0.2456383585706914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005455039,0.0001511325,0.0002234125,0.00005437246,0.0001330748,0.00008052215,0.0001503865,0.0001301593,0.001003038],"category_scores_gemma":[0.00331664,0.0001246588,0.00003419613,0.0002649405,0.0003549267,0.0001535816,0.0000922686,0.0002731453,0.000008272133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008484105,"about_ca_system_score_gemma":0.000002092619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003693081,"about_ca_topic_score_gemma":3.489452e-7,"domain_scores_codex":[0.9975408,0.0009895266,0.0002545964,0.00082628,0.0001309178,0.0002579364],"domain_scores_gemma":[0.9984823,0.001108368,0.00006001093,0.0001300564,0.000009269619,0.0002099446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00009052193,0.0001353532,0.0006346387,0.000002080533,2.403366e-7,0.000008570444,0.0004502921,0.000001751074,0.9666196,0.0001816733,0.00006764766,0.03180763],"study_design_scores_gemma":[0.007912426,0.007923087,0.6959468,0.0000751995,0.00001366921,0.0004210065,0.00106745,0.0024748,0.2388111,0.0253293,0.01863438,0.00139082],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9763563,0.00009257126,0.01553498,0.002376182,0.0002438882,0.0002523515,0.000005948153,0.00007789545,0.005059942],"genre_scores_gemma":[0.9092317,0.0001065343,0.07633995,0.01425565,0.00003023351,0.00001510782,4.007011e-7,0.000009276164,0.00001114035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7278085,"threshold_uncertainty_score":0.9999102,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7749174545978643,"gpt":0.7295370932943747,"spread":0.04538036130348966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01624228,0.0001965074,0.0003256012,0.0001493781,0.000563105,0.0002356473,0.0007023133,0.0001538336,0.01366844],"category_scores_gemma":[0.002280052,0.0001340117,0.0001331493,0.0001709706,0.001810564,0.0003290134,0.000225924,0.0009241936,0.001319169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004600981,"about_ca_system_score_gemma":0.00002148369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007519836,"about_ca_topic_score_gemma":0.00001122779,"domain_scores_codex":[0.9833502,0.01469089,0.0004000427,0.0003354269,0.00047662,0.0007468342],"domain_scores_gemma":[0.9931015,0.005465877,0.00009884203,0.0008044643,0.0002562367,0.000273039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003379153,0.0003912885,0.00001542861,0.000006498286,0.00002944941,0.000001858606,0.1859842,1.0345e-7,0.0003928709,0.7757152,0.003129312,0.03429993],"study_design_scores_gemma":[0.0002514466,0.0002308796,0.0005030514,0.00001244838,0.00002007548,0.00001160328,0.2189571,0.000003994517,0.0004612461,0.4165776,0.3627209,0.0002496403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04799064,0.001553284,0.003985036,0.003056429,0.0008206945,0.0002705078,0.00001040103,0.0002018663,0.9421111],"genre_scores_gemma":[0.7349944,0.0000778373,0.2543014,0.001198819,0.0008974524,0.0001534123,0.00000921057,0.00002749505,0.008339923],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9337712,"threshold_uncertainty_score":0.9994584,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9375029604873701,"gpt":0.8324841901757505,"spread":0.1050187703116197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1253068,0.0001189281,0.0003481349,0.0003604667,0.0002803812,0.0001670491,0.001376161,0.0001720436,0.007345484],"category_scores_gemma":[0.01519728,0.00005497122,0.0001408868,0.002592566,0.0006824816,0.0001605042,0.0001359368,0.0009031989,0.0005211517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003620322,"about_ca_system_score_gemma":0.000008418303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004991409,"about_ca_topic_score_gemma":0.000005368148,"domain_scores_codex":[0.9704429,0.02457314,0.00135745,0.0005819649,0.002533609,0.0005109739],"domain_scores_gemma":[0.9730021,0.0252032,0.0002902099,0.0007487409,0.0006247978,0.0001309902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000738244,0.0004253943,0.003294932,5.34131e-7,0.000005033755,0.000002172525,0.003499191,0.00001271307,0.00132133,0.02033557,0.002358517,0.9686708],"study_design_scores_gemma":[0.0004234338,0.0005919901,0.09659927,0.00001283433,0.000001608849,0.000010714,0.01230831,0.002639046,0.0002737186,0.8330836,0.0539583,0.00009722701],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.50292,0.007284496,0.01766171,0.02131618,0.0008823148,0.0006068209,0.000005238865,0.00003384536,0.4492894],"genre_scores_gemma":[0.9168964,0.0007487345,0.08095983,0.0003371218,0.00007302813,0.00005673225,1.936408e-7,0.000004920134,0.0009230337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9685736,"threshold_uncertainty_score":0.9935619,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.1831145640464929,"gpt":0.4891395659614176,"spread":0.3060250019149247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001277565,0.0001351836,0.0001865047,0.00003241902,0.0001032315,0.00003263217,0.00009233538,0.0001001176,0.0002855248],"category_scores_gemma":[0.001451663,0.00008217872,0.00002336439,0.0001331952,0.0002144666,0.0001331132,0.00005743485,0.0002620024,0.000002691597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004719174,"about_ca_system_score_gemma":0.000006512183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004135855,"about_ca_topic_score_gemma":6.785435e-7,"domain_scores_codex":[0.9985687,0.0006585645,0.0002242935,0.0002675039,0.0001455198,0.0001354376],"domain_scores_gemma":[0.9972932,0.002299259,0.00007015236,0.0002056889,0.00006006381,0.000071653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002605145,0.000433503,0.011405,0.000116149,0.0002702776,0.00003188686,0.000624444,0.0002054398,0.1137411,0.007875967,0.004154506,0.8608812],"study_design_scores_gemma":[0.0159244,0.0008711083,0.520891,0.0021249,0.0007588572,0.001494368,0.002153724,0.1268022,0.1241766,0.1732716,0.028677,0.002854308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665803,0.001821882,0.02175904,0.0003314409,0.0004434157,0.0003080413,0.0001450529,0.0001012869,0.008509502],"genre_scores_gemma":[0.913358,0.00002760739,0.08568873,0.0008263775,0.00002976664,0.000007380861,0.000044302,0.00001185732,0.000005994079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8580269,"threshold_uncertainty_score":0.3351151,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.728377638129674,"gpt":0.6079763110290402,"spread":0.1204013271006339,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008108715,0.0002236268,0.0007703165,0.0004193812,0.0006255457,0.00006223884,0.0001843378,0.0001127118,0.0008407897],"category_scores_gemma":[0.001369805,0.000206101,0.0001833216,0.001607291,0.0001060224,0.00004940576,0.0001187513,0.0003536011,2.458636e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002425609,"about_ca_system_score_gemma":0.00003314339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001105107,"about_ca_topic_score_gemma":0.000003292836,"domain_scores_codex":[0.9945154,0.002169308,0.001274004,0.0009104472,0.0006040928,0.0005267133],"domain_scores_gemma":[0.9974744,0.0007992241,0.0009125581,0.000392948,0.0001346162,0.0002861999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002407858,0.001764928,0.6244445,0.0003938843,0.01347884,0.000248895,0.007894642,0.1540854,0.006510541,0.001543727,0.0002056438,0.1870211],"study_design_scores_gemma":[0.004286801,0.002197622,0.6716833,0.00004893338,0.006685516,0.0001358383,0.002390329,0.3057843,0.0002235173,0.001008507,0.004476526,0.00107888],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1102995,0.001558822,0.8857477,0.0002057322,0.0007053147,0.0008618074,0.00005231032,0.00006055488,0.0005082676],"genre_scores_gemma":[0.535554,0.000006302772,0.4635322,0.0002950223,0.0001265292,0.0004295773,0.00001402279,0.00001468656,0.00002758982],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4252545,"threshold_uncertainty_score":0.9206057,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8579973400321181,"gpt":0.6038590198508541,"spread":0.254138320181264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02167672,0.0002795271,0.0006644564,0.000824534,0.0001601539,0.0002630412,0.001177523,0.0002628037,0.0003658529],"category_scores_gemma":[0.207381,0.0001954142,0.0001661292,0.005280873,0.0001260797,0.0003351094,0.0002078372,0.0005720123,0.00007996628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006682277,"about_ca_system_score_gemma":0.00001226665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008028478,"about_ca_topic_score_gemma":0.000001899238,"domain_scores_codex":[0.9915307,0.004141248,0.001425597,0.001205868,0.0009830421,0.0007135739],"domain_scores_gemma":[0.9401643,0.05807202,0.0004330042,0.0008972773,0.0002341771,0.0001992724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009025264,0.00007425129,0.1134821,0.000002500421,0.000008132305,0.00002409647,0.000120997,0.01430302,0.001891585,0.0003249657,0.0001356508,0.8695424],"study_design_scores_gemma":[0.0004569567,0.0001744599,0.2419558,0.00002120511,0.000007206931,0.00006641295,0.0002817064,0.3705886,0.00004957422,0.3858747,0.0002359724,0.0002874693],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5084123,0.0001218003,0.4843797,0.001119429,0.0006797996,0.0001524527,9.662311e-7,0.00009172027,0.005041865],"genre_scores_gemma":[0.4395142,0.000007896851,0.5590312,0.001305013,0.00006788973,0.00001693962,8.668279e-7,0.000009510721,0.00004641654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8692549,"threshold_uncertainty_score":0.7992955,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08867699414247705,"gpt":0.4642301580412647,"spread":0.3755531638987876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001973576,0.0001785104,0.0005086401,0.00005987663,0.0001108443,0.00001127294,0.0001382355,0.0001963908,0.000119829],"category_scores_gemma":[0.007804299,0.00006910293,0.00006138704,0.0002090757,0.000412384,0.0001019355,0.0005232696,0.0001813187,3.499853e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003605896,"about_ca_system_score_gemma":0.00002285585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006485008,"about_ca_topic_score_gemma":0.000001739078,"domain_scores_codex":[0.9972374,0.001634861,0.0004346565,0.0003128008,0.0001564144,0.000223847],"domain_scores_gemma":[0.9858742,0.01348573,0.0002449403,0.0001998449,0.0001038123,0.00009150483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003599493,0.0004582051,0.000265605,0.00004387172,0.00006645825,0.00001117514,0.001590986,4.363037e-7,0.1059448,0.3031087,0.00004254104,0.5848678],"study_design_scores_gemma":[0.0008469956,0.001051986,0.0240174,0.0001200905,0.00002301086,0.00002368122,0.00004747048,0.002546011,0.008381666,0.9628223,0.000001138833,0.0001182602],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2763414,0.00005325941,0.7224182,0.0002420889,0.00003342774,0.000248378,0.00004368678,0.00001011708,0.0006093482],"genre_scores_gemma":[0.4834335,0.0001178551,0.5163938,0.000009748903,0.00001426087,0.00001203219,2.576343e-7,0.000006831146,0.00001171186],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6597136,"threshold_uncertainty_score":0.9343038,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5411151333206106,"gpt":0.547425561088569,"spread":0.006310427767958426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00435891,0.000289812,0.0007127605,0.00004483339,0.0002835979,0.00003344046,0.0002147478,0.0001809838,0.000009214931],"category_scores_gemma":[0.05515043,0.0002024029,0.0001499499,0.00012436,0.0002501611,0.00007609108,0.00007439769,0.0002138703,3.732478e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001798937,"about_ca_system_score_gemma":0.000008821974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001396994,"about_ca_topic_score_gemma":9.977197e-8,"domain_scores_codex":[0.9972206,0.0009268325,0.0005150828,0.0007240421,0.0001252477,0.0004882155],"domain_scores_gemma":[0.9556491,0.04356828,0.0002021671,0.0002756577,0.0001471389,0.00015769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005138004,0.00034975,0.0002015274,0.0008451164,0.00008132189,0.00001078858,0.0003370026,0.000249116,0.02937724,0.107963,0.0008304167,0.8592409],"study_design_scores_gemma":[0.00133607,0.001509072,0.0004073687,0.00007297299,0.0000876121,0.0001602726,0.00002863443,0.06755658,0.002825184,0.9252364,0.0003755374,0.0004043111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00776591,0.0002113427,0.9884416,0.00008291318,0.0001160268,0.001505517,0.00003834583,0.0001492461,0.00168905],"genre_scores_gemma":[0.008586347,0.00001595987,0.9896419,0.0004528855,0.000175724,0.0008983618,0.000002882408,0.00004550772,0.0001804297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8588367,"threshold_uncertainty_score":0.9528084,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6611313861810452,"gpt":0.4362018312628033,"spread":0.2249295549182419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001702811,0.00008420298,0.0002732151,0.00005354157,0.00004821011,0.00001693153,0.0001729606,0.00008504523,0.000351535],"category_scores_gemma":[0.0001517914,0.00008416799,0.00003215078,0.00005011305,0.00004633862,0.0002530654,0.00008448076,0.00009648121,0.00003940603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002950697,"about_ca_system_score_gemma":8.822103e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001907939,"about_ca_topic_score_gemma":0.000001236691,"domain_scores_codex":[0.9988627,0.00006533317,0.0005563676,0.000372572,0.00002017892,0.0001228574],"domain_scores_gemma":[0.9993376,0.00009543962,0.0002280656,0.000298583,0.000004022787,0.00003634385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004485383,0.0001238307,0.402366,0.00001923858,0.00004500469,1.702576e-7,0.0007534541,0.03620291,0.0004033502,0.05672359,0.00006427623,0.5032534],"study_design_scores_gemma":[0.000296438,0.00003777033,0.1006091,0.000003242936,0.00000485521,0.000001427582,0.00004551791,0.8565396,0.00003693696,0.04197979,0.0003469187,0.00009837323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6217903,0.001201975,0.3731237,0.0001745838,0.0001053631,0.00006837844,0.00001337562,0.00001198324,0.003510302],"genre_scores_gemma":[0.7235739,0.00007729197,0.276156,0.00008881899,0.0000593685,0.000003378569,0.00001980347,0.000005265963,0.00001615608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8203367,"threshold_uncertainty_score":0.3849061,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8157017601333325,"gpt":0.6109273046144487,"spread":0.2047744555188838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08815691,0.0001737857,0.0004751481,0.0005652232,0.0001247065,0.0001731332,0.001724555,0.0001622616,0.00005857513],"category_scores_gemma":[0.3209161,0.0000855781,0.0001623273,0.004274033,0.0001075888,0.0002988185,0.0003323925,0.0003043789,0.000135265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003401548,"about_ca_system_score_gemma":0.00003539079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001302408,"about_ca_topic_score_gemma":1.396226e-7,"domain_scores_codex":[0.9900044,0.006632881,0.001193314,0.0005012272,0.001281246,0.0003868827],"domain_scores_gemma":[0.9728836,0.02455444,0.000391885,0.001229871,0.0006500877,0.0002901282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002304121,0.0001720246,0.0003812743,0.00000370932,0.00001458683,6.47763e-7,0.001646915,0.04187126,0.0006618742,0.004494534,0.009821615,0.9386274],"study_design_scores_gemma":[0.001963468,0.002326127,0.02056639,0.00002736978,0.00003463091,0.0001390038,0.01881212,0.5326486,0.0005395664,0.3004362,0.1218088,0.0006976451],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05333955,0.0001772502,0.8764831,0.001494574,0.0005918664,0.0003132873,0.000005526399,0.00008288641,0.06751195],"genre_scores_gemma":[0.267904,0.000003539025,0.7310196,0.0008372551,0.00006373021,0.00003529468,7.305323e-7,0.000004878409,0.0001308969],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9379298,"threshold_uncertainty_score":0.9389343,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4677719361516182,"gpt":0.5816223954573272,"spread":0.113850459305709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005244838,0.00015684,0.0002214195,0.00005900337,0.0004419989,0.0001641296,0.0007980216,0.00008460719,0.001360886],"category_scores_gemma":[0.0328031,0.00007894364,0.00004462076,0.0006826856,0.0003351222,0.00005478569,0.0001480469,0.0004300066,0.0001575098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003529216,"about_ca_system_score_gemma":0.00001378342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002908023,"about_ca_topic_score_gemma":0.000009518135,"domain_scores_codex":[0.9950641,0.003660191,0.0004750128,0.0002890905,0.0002208114,0.0002907717],"domain_scores_gemma":[0.9757126,0.02262149,0.0001651776,0.001129287,0.0002909141,0.00008054046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009217007,0.00005689032,0.000035553,0.00000583825,0.00000939997,1.727645e-7,0.0004436236,7.306361e-7,0.0002228737,0.4476869,0.4728162,0.07871268],"study_design_scores_gemma":[0.0000940835,0.00002870231,0.01406978,0.0000137772,0.00001676018,0.000005991284,0.0006893922,0.00007228321,0.0001512314,0.8286688,0.1560697,0.0001194971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002212862,0.0001442616,0.9115154,0.07277609,0.0004752893,0.0006820657,0.00001499233,0.0001159288,0.01206309],"genre_scores_gemma":[0.01006934,0.00003623014,0.9688797,0.01846568,0.00009978053,0.0005478934,0.000006936929,0.00001678259,0.001877648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.380982,"threshold_uncertainty_score":0.999552,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.793516695385926,"gpt":0.6567447400249953,"spread":0.1367719553609307,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002488183,0.000336573,0.0005060565,0.00004307852,0.0002114667,0.00003807781,0.0004030967,0.0001593589,0.0001472021],"category_scores_gemma":[0.001579336,0.0002255701,0.00005791933,0.0001542016,0.0001601939,0.0003410526,0.0001456359,0.0001911119,0.000001442302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004910014,"about_ca_system_score_gemma":0.0000124641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000346355,"about_ca_topic_score_gemma":0.000003858791,"domain_scores_codex":[0.9968522,0.001114158,0.0005100788,0.0009330831,0.0002168006,0.0003736824],"domain_scores_gemma":[0.9957712,0.00277861,0.0003425269,0.0008889504,0.0001156313,0.0001030773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002179784,0.002014185,0.001088138,0.0001060367,0.0004360345,0.00001695605,0.007040004,0.000002186079,0.5194012,0.1545401,0.0001454371,0.31303],"study_design_scores_gemma":[0.004305995,0.002457433,0.001056961,0.00008293605,0.0003035872,0.0001115845,0.001181138,0.02815381,0.1842142,0.7773541,0.0001290827,0.0006492066],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05555241,0.0001006197,0.9397705,0.00004134096,0.00005931352,0.001389844,0.00004010181,0.0003070584,0.002738848],"genre_scores_gemma":[0.04467795,0.00001384471,0.9545158,0.000104222,0.00005298375,0.0004797073,0.00004653431,0.0000446073,0.00006430633],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6228139,"threshold_uncertainty_score":0.9198482,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9584692213383208,"gpt":0.6539327846799784,"spread":0.3045364366583424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05177865,0.0002242383,0.001139823,0.0005044796,0.0001164143,0.0000688069,0.001097783,0.0002258509,0.0001615113],"category_scores_gemma":[0.2002102,0.0001431196,0.000269449,0.001919076,0.0003429202,0.00006531119,0.0001293443,0.0002658622,0.000008450575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004838093,"about_ca_system_score_gemma":0.00002099824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000227505,"about_ca_topic_score_gemma":0.00002104123,"domain_scores_codex":[0.9928253,0.003305934,0.001652359,0.0009339732,0.0007418444,0.0005406418],"domain_scores_gemma":[0.9553593,0.04235062,0.0007647714,0.0007668474,0.0006138813,0.0001445805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006339564,0.0005436441,0.07144773,0.00001210237,0.00002823452,6.375425e-7,0.0005375622,0.000330897,0.002617263,0.002915268,0.0005056921,0.920427],"study_design_scores_gemma":[0.003694772,0.002424854,0.5166069,0.00005995372,0.00003701276,0.000008328559,0.00205672,0.08559465,0.003244027,0.3763879,0.009382405,0.0005025009],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1514807,0.0005094015,0.8416221,0.0003609916,0.0008574954,0.0005344974,0.000006495557,0.00003963605,0.004588724],"genre_scores_gemma":[0.4829129,0.000001568846,0.516786,0.0001171576,0.0001068537,0.00004801539,4.21796e-7,0.000006152167,0.00002093141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9199245,"threshold_uncertainty_score":0.9763934,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6554148748889531,"gpt":0.6096974645123965,"spread":0.04571741037655663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007636446,0.000259685,0.0005411622,0.0005264911,0.0001958861,0.0001450692,0.0007918479,0.0002702688,0.001687863],"category_scores_gemma":[0.03416156,0.000184585,0.0001657412,0.001371797,0.0003209048,0.0004007941,0.0001196413,0.0003791244,0.0001796255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009166955,"about_ca_system_score_gemma":0.00004121833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001828203,"about_ca_topic_score_gemma":0.000007140306,"domain_scores_codex":[0.9938405,0.002123824,0.001439922,0.0009766935,0.001189714,0.0004293992],"domain_scores_gemma":[0.9915071,0.006990234,0.0003046257,0.0007338606,0.0002885667,0.0001756342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008760173,0.0001030672,0.001802985,0.000001747907,0.00001075194,0.00007536702,0.0008473041,0.05169168,0.00356106,0.005189164,0.0001233351,0.9357175],"study_design_scores_gemma":[0.002118427,0.000139315,0.01121063,0.000008775013,0.000004149525,0.00006923822,0.0002012194,0.8742181,0.00007922377,0.1116773,0.00006010222,0.0002134704],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4397911,0.00003175726,0.554992,0.0002683518,0.001023967,0.0001868211,0.000004575991,0.00006459491,0.003636825],"genre_scores_gemma":[0.5335121,0.00000226017,0.4662676,0.0001246036,0.00003872325,0.0000128026,0.000003833339,0.000006610691,0.00003140785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.935504,"threshold_uncertainty_score":0.9992247,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.5016745736120142,"gpt":0.5277738604236346,"spread":0.02609928681162044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002424249,0.0003131688,0.0005726207,0.0002049346,0.0002211805,0.00008061686,0.0001428136,0.0001688006,0.001397453],"category_scores_gemma":[0.01169547,0.0002408605,0.00008395417,0.0004716585,0.0003136789,0.0001786024,0.00008036972,0.0002440382,0.00005309102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000334563,"about_ca_system_score_gemma":0.00001143784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009417966,"about_ca_topic_score_gemma":0.000009672552,"domain_scores_codex":[0.9961091,0.001648735,0.0006414377,0.0009430987,0.000208795,0.0004488079],"domain_scores_gemma":[0.9805576,0.01809835,0.0002233784,0.0004036335,0.0004908248,0.0002261618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01162423,0.002604153,0.0712617,0.0001643936,0.001135416,0.0001930033,0.02095478,0.08461914,0.003000048,0.00590276,0.007846439,0.7906939],"study_design_scores_gemma":[0.00191984,0.005110694,0.9764289,0.0001593473,0.00007434023,0.00001279558,0.001135961,0.004924329,0.0005163038,0.009069941,0.0001579212,0.00048968],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2776586,0.0005912971,0.7122042,0.002333322,0.0008531071,0.002290633,0.00004348358,0.0001108514,0.003914475],"genre_scores_gemma":[0.6397707,0.000007199838,0.3586797,0.00094207,0.00009213742,0.0004627474,0.000001716493,0.000012961,0.00003079503],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9051672,"threshold_uncertainty_score":0.9995154,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2598997714356185,"gpt":0.5457960284064142,"spread":0.2858962569707957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005391021,0.0006537495,0.000998188,0.000974282,0.0001972922,0.0001411997,0.0005715602,0.001711277,0.001386682],"category_scores_gemma":[0.0005655438,0.0005438282,0.000192835,0.0006713007,0.0009335675,0.0001190411,0.0003775021,0.005369042,0.0004464553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002191856,"about_ca_system_score_gemma":0.00001363695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009293159,"about_ca_topic_score_gemma":0.0000414178,"domain_scores_codex":[0.9867843,0.008017768,0.001250153,0.001861858,0.0006045148,0.001481455],"domain_scores_gemma":[0.9891134,0.00924009,0.0002568186,0.001028525,0.00007246816,0.0002887139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002400654,0.00100053,0.0005185928,0.0001962459,0.00005352706,0.0008611915,0.00009393557,1.345101e-7,0.00000800016,0.001573822,0.8528889,0.142565],"study_design_scores_gemma":[0.001501323,0.002776459,0.0492763,0.0004840732,0.00003208525,0.0001126697,0.00004167428,0.000005411436,0.000004264969,0.04030073,0.9049223,0.0005427261],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.006970636,0.00474675,0.001432623,0.874505,0.00424537,0.00188224,0.0004653291,0.0001978405,0.1055543],"genre_scores_gemma":[0.009451824,0.0001173964,0.01581422,0.9541165,0.001657823,0.001315741,0.0002756271,0.0001838523,0.01706701],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.1420223,"threshold_uncertainty_score":0.9997013,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6325151645478696,"gpt":0.6907879567918435,"spread":0.05827279224397386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005636964,0.0003574299,0.0006483301,0.000103507,0.002005387,0.0006266039,0.004046941,0.0003971313,0.001551701],"category_scores_gemma":[0.003124693,0.0002970964,0.0001629505,0.0001422726,0.0006512307,0.0004838169,0.0006501509,0.0003393755,0.00003205657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008486778,"about_ca_system_score_gemma":0.00002732598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002170326,"about_ca_topic_score_gemma":0.00001390741,"domain_scores_codex":[0.9950938,0.0008902894,0.0007061185,0.001615708,0.0002966732,0.00139736],"domain_scores_gemma":[0.994202,0.00215659,0.0004337648,0.002352062,0.0001597054,0.0006959437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001496001,0.0008897546,0.001361952,0.00004818906,0.00002726457,0.000004053263,0.003314285,0.000001434219,0.01009789,0.03448851,0.001864978,0.9464057],"study_design_scores_gemma":[0.00687379,0.006804494,0.05653662,0.0001008262,0.000028388,0.0000709846,0.005421245,0.0007663639,0.006309577,0.06471913,0.8511777,0.001190878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2793885,0.0003010762,0.7064121,0.0009485206,0.002929566,0.003104027,0.00004889131,0.0001374024,0.006729852],"genre_scores_gemma":[0.1890044,0.00002092613,0.7997251,0.001482425,0.0005770681,0.006923429,0.00001581917,0.00006050687,0.0021903],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9452148,"threshold_uncertainty_score":0.9999481,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2183332546592504,"gpt":0.4943070645323446,"spread":0.2759738098730942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00099917,0.0002068612,0.0003102793,0.00003362988,0.0003064755,0.00005415982,0.0002773003,0.0001996183,0.0001628663],"category_scores_gemma":[0.00008524247,0.0001204757,0.00005510918,0.0004578485,0.0003825563,0.0001030543,0.000107163,0.0008883447,0.00001044019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004455858,"about_ca_system_score_gemma":0.00001464183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002051278,"about_ca_topic_score_gemma":0.000005157301,"domain_scores_codex":[0.9967274,0.001533188,0.0002816489,0.0006659841,0.0002675715,0.0005241841],"domain_scores_gemma":[0.9988137,0.0003216393,0.00008918096,0.0002554554,0.00005744849,0.0004625114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02183654,0.00237947,0.05216671,0.000348309,0.0007300862,0.0001551679,0.01605922,0.00627138,0.003245549,0.4256699,0.01769509,0.4534425],"study_design_scores_gemma":[0.002073173,0.003646523,0.1395854,0.0000299584,0.00006605776,0.0002160728,0.0008193472,0.8260667,0.00007810233,0.02570436,0.001317847,0.0003964629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1051385,0.0001766876,0.8708341,0.01506121,0.0000841766,0.0006433146,0.00002679075,0.0001280456,0.007907216],"genre_scores_gemma":[0.9199867,0.00001842038,0.07690652,0.002670668,0.0001224216,0.0001836305,0.00001366449,0.00001827182,0.00007974434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8197953,"threshold_uncertainty_score":0.4912857,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3949998641647077,"gpt":0.6121051813343663,"spread":0.2171053171696586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02329171,0.0003757823,0.0009214871,0.0002629205,0.0001811867,0.0002739564,0.0007994767,0.0002686549,0.00205451],"category_scores_gemma":[0.01718145,0.000254636,0.0002936258,0.001765109,0.0003551664,0.0005637128,0.00009106511,0.0005056309,0.000081247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001470001,"about_ca_system_score_gemma":0.00001538378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005079465,"about_ca_topic_score_gemma":9.944565e-7,"domain_scores_codex":[0.9902726,0.004620101,0.001688804,0.001600527,0.001193172,0.0006247857],"domain_scores_gemma":[0.9881411,0.01004401,0.0003419381,0.001049158,0.0001967008,0.0002270927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002660546,0.000391252,0.002555382,0.000008725655,0.00001683563,0.00003614882,0.003024217,0.01702082,0.008320876,0.0001021174,0.000377097,0.9678805],"study_design_scores_gemma":[0.001283782,0.0008190936,0.01488405,0.00005653888,0.00002499016,0.00002506416,0.001867353,0.7896479,0.003035121,0.1776195,0.01006006,0.0006765568],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4723047,0.001514813,0.5145627,0.002997641,0.0009272154,0.0007061131,0.000007553786,0.0001226361,0.006856704],"genre_scores_gemma":[0.2960408,0.00002457077,0.7019984,0.001038842,0.0000708488,0.00005159187,7.504109e-7,0.00001720276,0.0007570368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9672039,"threshold_uncertainty_score":0.9999906,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6072341590302414,"gpt":0.5821967672574048,"spread":0.02503739177283659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008079202,0.0002358988,0.0004487175,0.0004149023,0.0001374791,0.0005350451,0.001718948,0.0002366732,0.0009342424],"category_scores_gemma":[0.01313266,0.0001460421,0.00004072134,0.001230327,0.0002413713,0.002037171,0.0008309187,0.0006975914,0.0001254901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001324067,"about_ca_system_score_gemma":0.00001966832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003416773,"about_ca_topic_score_gemma":0.0001352569,"domain_scores_codex":[0.9956679,0.001136386,0.001044314,0.0007589823,0.0009765965,0.0004157916],"domain_scores_gemma":[0.9921781,0.005349973,0.0003426155,0.001673448,0.0002422626,0.0002136429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002129038,0.0001293413,0.01840369,0.00000367781,0.00001100384,0.00002848826,0.0006472917,0.00003368076,0.008162059,0.0009224271,0.0005392443,0.9689901],"study_design_scores_gemma":[0.00468612,0.0004191543,0.919892,0.00001489894,0.000009596782,0.00008750171,0.0005767593,0.02791485,0.0001845609,0.004304689,0.04149216,0.0004176648],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8486754,0.0000156588,0.1455626,0.0004140571,0.001274045,0.0002535127,0.00002972241,0.00007061865,0.003704413],"genre_scores_gemma":[0.4890673,0.000002105885,0.5105693,0.0002512909,0.00006093126,0.00001339611,0.0000148797,0.000005525536,0.00001526817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9685724,"threshold_uncertainty_score":0.999979,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.192762533016816,"gpt":0.434702382703031,"spread":0.241939849686215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004146759,0.0003301025,0.000605328,0.0001553918,0.0001377969,0.0001801244,0.0007929744,0.000123902,0.000008331884],"category_scores_gemma":[0.0002011638,0.0002067065,0.00006996709,0.001148953,0.00007770267,0.0002940224,0.0001598104,0.0003333556,5.001411e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000399655,"about_ca_system_score_gemma":0.000006774364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004480329,"about_ca_topic_score_gemma":9.758248e-7,"domain_scores_codex":[0.9969165,0.0008957683,0.0004230157,0.001106874,0.0003182993,0.0003395656],"domain_scores_gemma":[0.9985737,0.000175864,0.0001121196,0.0005286255,0.0001169788,0.0004927455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005639686,0.0002730637,0.002936051,0.00002670956,0.0003813372,0.00001095384,0.003140076,0.6574436,0.06334548,0.1764402,0.00001281672,0.09542575],"study_design_scores_gemma":[0.0003023134,0.0003800158,0.005854777,0.000003416452,0.00006025579,0.000003557064,0.00003837029,0.9636652,0.0003793198,0.02900223,0.000008316561,0.0003022481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2596438,0.00002338764,0.7393023,0.0002097786,0.00003431168,0.0002810784,0.00001199252,0.0004589374,0.00003440397],"genre_scores_gemma":[0.4893793,0.000001720412,0.5099919,0.0005559347,0.0000122419,0.00001412962,0.00003655043,0.000008059611,2.45532e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3062216,"threshold_uncertainty_score":0.8429248,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5169415510137839,"gpt":0.4988124653351859,"spread":0.01812908567859806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001516037,0.0002659335,0.0004365641,0.0003375503,0.0001351492,0.0002071299,0.001061659,0.0002232803,0.000002741246],"category_scores_gemma":[0.0002337364,0.0002218097,0.0001190314,0.001480461,0.00003206049,0.0003096209,0.0002788848,0.0003183973,0.00002416515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005267074,"about_ca_system_score_gemma":0.00001961438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001597163,"about_ca_topic_score_gemma":0.000007110444,"domain_scores_codex":[0.9974054,0.000451532,0.0003857717,0.0008609177,0.0002564794,0.0006399125],"domain_scores_gemma":[0.9984959,0.0004814843,0.00008801545,0.0005776227,0.0001211291,0.0002358741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007103146,0.00009316289,0.00009487339,0.00003261627,0.00001250446,0.000005604946,0.003110747,0.4394695,0.001576796,0.04776382,0.001946662,0.5058227],"study_design_scores_gemma":[0.0004018931,0.0001742724,0.0004490666,0.00003727299,0.000004584569,0.000003141028,0.00006355096,0.8874732,0.00004615712,0.1109307,0.0001472759,0.000268927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01550378,0.0001234987,0.9383677,0.04412825,0.0006034478,0.0006547474,0.000009073425,0.000540741,0.00006878538],"genre_scores_gemma":[0.4117583,0.00003036764,0.5869977,0.0008801768,0.00007497398,0.0002015622,0.000007727899,0.00001075583,0.00003844321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5055538,"threshold_uncertainty_score":0.9045137,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.420004400219087,"gpt":0.6572029316560931,"spread":0.2371985314370061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003152888,0.0002108323,0.0003983628,0.0002791885,0.0003782221,0.0001420125,0.001663542,0.0002320736,0.001048981],"category_scores_gemma":[0.0006052256,0.0001401822,0.0001285366,0.0003267064,0.000235802,0.0001615416,0.0001236546,0.0006412405,0.0001834284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037695,"about_ca_system_score_gemma":0.00001979971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003719494,"about_ca_topic_score_gemma":0.0001578348,"domain_scores_codex":[0.9948252,0.002959584,0.0004814318,0.0007859726,0.0003325636,0.0006152833],"domain_scores_gemma":[0.9966266,0.0004732383,0.0002467414,0.002128699,0.0001163141,0.0004084804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001878623,0.00243947,0.03888243,0.00002754666,0.000507454,0.00007625626,0.01183465,0.001225069,0.006520149,0.06159003,0.0007696397,0.8742487],"study_design_scores_gemma":[0.0007561288,0.0006707406,0.9439463,0.000009046598,0.00004582721,0.000004190711,0.0006845181,0.04302287,0.0001783486,0.009246822,0.00117824,0.0002569362],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6402778,0.0001240866,0.3295836,0.006791747,0.0005932088,0.001027722,0.00007921873,0.00006263192,0.02145998],"genre_scores_gemma":[0.9241846,0.00002054607,0.07222177,0.002540563,0.00011543,0.0003472238,0.00001076832,0.00001734952,0.0005417278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9050639,"threshold_uncertainty_score":0.9998642,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2830794992700697,"gpt":0.5610199716537944,"spread":0.2779404723837247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02763968,0.0001685913,0.001138731,0.000376155,0.00005866047,0.00001660254,0.0001158213,0.0001874217,0.000268394],"category_scores_gemma":[0.03870296,0.00012023,0.0003038017,0.00075517,0.000256503,0.00008071489,0.00004143719,0.0002157427,0.000004522795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003082035,"about_ca_system_score_gemma":0.000007417488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001398473,"about_ca_topic_score_gemma":4.90843e-7,"domain_scores_codex":[0.9886039,0.009971418,0.0006515309,0.0002523098,0.0002378621,0.0002830023],"domain_scores_gemma":[0.9624132,0.03660262,0.0002808561,0.00037958,0.0001979962,0.0001257626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.07299909,0.001805387,0.0004419874,0.00003709911,0.002799557,0.000007961973,0.00389297,0.0002943806,0.004385406,0.8743543,0.001058118,0.03792374],"study_design_scores_gemma":[0.009072223,0.0001949745,0.009526278,0.00005918928,0.002366689,0.0000181036,0.0001879915,0.03295132,0.002191025,0.9429097,0.0001161744,0.0004063649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05282803,0.00008622889,0.9440926,0.0001264345,0.0001164802,0.0002723632,0.00004331428,0.000232701,0.002201839],"genre_scores_gemma":[0.4364423,0.000008866628,0.5633656,0.00008824457,0.00001078227,0.00004378366,0.000006551431,0.000008405446,0.00002539527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3836143,"threshold_uncertainty_score":0.9693944,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6618471505924736,"gpt":0.6779126136633634,"spread":0.01606546307088985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01347759,0.0003337658,0.0006768568,0.0003048874,0.0005584678,0.001101835,0.002857445,0.0001405114,0.001646424],"category_scores_gemma":[0.007767005,0.0001780506,0.0002059296,0.001683919,0.0002843018,0.0005679337,0.0005261953,0.0004990406,0.002565601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001008768,"about_ca_system_score_gemma":0.00002451637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005423207,"about_ca_topic_score_gemma":0.00001708672,"domain_scores_codex":[0.9911693,0.003725579,0.0011497,0.001488697,0.001911376,0.0005553886],"domain_scores_gemma":[0.9926926,0.004546779,0.0004273755,0.001442057,0.0004664177,0.0004247324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007568128,0.001352817,0.001688309,0.000003121572,0.00007077675,0.0001073266,0.03135582,0.004122863,0.09762065,0.01940194,0.003975362,0.8395442],"study_design_scores_gemma":[0.001755972,0.0009429731,0.04518883,0.00007206838,0.00002312989,0.00009646344,0.007068276,0.002019748,0.01939772,0.896439,0.02635214,0.0006437136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4605648,0.00004148184,0.5281514,0.001170984,0.001457508,0.0004495744,0.000005974908,0.0000650953,0.008093214],"genre_scores_gemma":[0.4728939,0.000002597412,0.5228761,0.003627525,0.0001824179,0.00006387738,8.737822e-7,0.0000111494,0.0003414901],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.877037,"threshold_uncertainty_score":0.9999351,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6438736940352537,"gpt":0.5849986390061367,"spread":0.05887505502911705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002418723,0.0001372691,0.000340598,0.00002850945,0.0000539938,0.00003984982,0.0003625876,0.0001378381,0.000194861],"category_scores_gemma":[0.01328673,0.000108662,0.00004221943,0.0001776573,0.00004727176,0.0001444794,0.00009325515,0.000211293,0.000007611703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000188859,"about_ca_system_score_gemma":0.00001036884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005204789,"about_ca_topic_score_gemma":9.468076e-7,"domain_scores_codex":[0.9979153,0.0006738905,0.0004596353,0.0005558071,0.0001326163,0.0002627541],"domain_scores_gemma":[0.9936315,0.005699839,0.0001128967,0.0003708726,0.00006230574,0.0001226265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009808165,0.0001724266,0.00004388043,0.00005797987,0.00001006186,0.000003275645,0.0003636442,0.00002499548,0.001233849,0.7646125,0.0007525069,0.2326268],"study_design_scores_gemma":[0.0003876913,0.00009808477,0.001865179,0.00001538399,0.0000143199,0.000001157011,0.00001594739,0.3178901,0.00004831499,0.679154,0.0004027436,0.0001070683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004590914,0.00002391673,0.9960368,0.001227073,0.0001547197,0.000417162,0.0001341755,0.0000814828,0.001465596],"genre_scores_gemma":[0.0266652,0.000008467075,0.9718792,0.001163541,0.000129334,0.000117873,0.00001502621,0.00001475634,0.000006552526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3178651,"threshold_uncertainty_score":0.9950248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2135921817672836,"gpt":0.4363520711109367,"spread":0.2227598893436532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001735457,0.0002141175,0.0002983869,0.0001437707,0.0001239426,0.00009365268,0.0001738602,0.0002582275,0.006912554],"category_scores_gemma":[0.00149487,0.0001910519,0.00004807122,0.0002016578,0.0005214209,0.0001922347,0.00006119823,0.000481488,0.00005303279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007170106,"about_ca_system_score_gemma":0.000006351414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002069682,"about_ca_topic_score_gemma":0.0000352251,"domain_scores_codex":[0.9970094,0.001064941,0.0006539257,0.0007252779,0.0001568846,0.0003895473],"domain_scores_gemma":[0.9981745,0.00110635,0.0001845052,0.0002901637,0.0001415845,0.0001028502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000601223,0.0001609316,0.01129504,0.0000201643,0.00002189249,0.00001218735,0.004872852,0.00002701668,0.003070737,0.0188811,0.00004970355,0.9615282],"study_design_scores_gemma":[0.003275774,0.0004885889,0.4675622,0.0002820648,0.00009613414,0.0006371076,0.009932999,0.2477318,0.0002061924,0.2684472,0.0002606507,0.00107933],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6879764,0.0006155782,0.2793002,0.0002556262,0.000487034,0.0003704616,0.00003082097,0.00009291408,0.03087088],"genre_scores_gemma":[0.9271901,0.00003674714,0.07218887,0.0002178118,0.00005724237,0.00008074833,0.0000215979,0.0000116092,0.0001952262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9604489,"threshold_uncertainty_score":0.9939952,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2735179449844107,"gpt":0.540779147405514,"spread":0.2672612024211033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00122542,0.0001978838,0.0002330822,0.00007159091,0.0002721649,0.0000546947,0.0003762095,0.000281406,0.0006433034],"category_scores_gemma":[0.0001795535,0.0001135652,0.0001595994,0.0001868275,0.0001479536,0.0001028095,0.00005394399,0.0003804267,0.0000468529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005084535,"about_ca_system_score_gemma":0.000003992267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008866518,"about_ca_topic_score_gemma":0.000007625552,"domain_scores_codex":[0.9979442,0.0007313739,0.0003607319,0.0004301291,0.0001275545,0.0004060591],"domain_scores_gemma":[0.9978332,0.001511619,0.000136051,0.00039331,0.00005664569,0.00006917842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002139302,0.0001285527,0.00326709,0.000007671706,0.00008622374,8.531485e-7,0.005152371,0.0009327582,0.0003594912,0.3699443,0.0005770717,0.6193296],"study_design_scores_gemma":[0.0009088027,0.000321115,0.03720208,0.00001542084,0.00007669351,0.00001981562,0.0008074827,0.301591,0.00002587259,0.6562594,0.00247163,0.0003006787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1213689,0.0003752662,0.8555405,0.004438416,0.001094104,0.0006296801,0.000009184184,0.0001209437,0.01642303],"genre_scores_gemma":[0.6946618,0.00001267759,0.2987975,0.001160009,0.0004416799,0.0002926302,0.00002154625,0.00001822514,0.004593918],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.619029,"threshold_uncertainty_score":0.7043721,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2390750010588527,"gpt":0.4633744701333101,"spread":0.2242994690744574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004531591,0.0002802606,0.0003646312,0.0001953647,0.0003028338,0.0004419352,0.001537306,0.0002098925,0.00003389018],"category_scores_gemma":[0.001731765,0.0001855729,0.0001247639,0.002374148,0.00009809187,0.0004393603,0.0003412019,0.0003707081,0.00008744636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006952805,"about_ca_system_score_gemma":0.00001070759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006442287,"about_ca_topic_score_gemma":0.00002030858,"domain_scores_codex":[0.9959932,0.001219469,0.0005803063,0.001026632,0.0003215861,0.0008588136],"domain_scores_gemma":[0.996644,0.002068378,0.0001233855,0.0008489978,0.0001177763,0.000197495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009278595,0.0001412423,0.0001863592,0.000008106033,0.000006891726,0.00002309204,0.0004156988,0.002078078,0.0009093597,0.001048101,0.00908913,0.9860846],"study_design_scores_gemma":[0.0001511891,0.0002765025,0.02408723,0.00002719495,0.000004484897,0.0000242919,0.00006333544,0.9632928,0.001079805,0.002524929,0.008160195,0.0003080499],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07411549,0.00008549393,0.9110647,0.01191028,0.001180312,0.001110662,0.000001824816,0.0004350642,0.00009612246],"genre_scores_gemma":[0.05301762,0.00004809217,0.9378195,0.007820833,0.0002375477,0.0007199142,0.00001362309,0.0000191978,0.0003036088],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9857766,"threshold_uncertainty_score":0.7567444,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3949148200381404,"gpt":0.5170832974120531,"spread":0.1221684773739126,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002320923,0.0003458842,0.0009741673,0.0001016885,0.0001199504,0.00003197442,0.0002489743,0.0003062563,0.0002695715],"category_scores_gemma":[0.003631153,0.0002607314,0.0002545269,0.0002115866,0.0001355166,0.000234698,0.00008647331,0.0003482554,0.000004564631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006204448,"about_ca_system_score_gemma":0.00001849007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006862824,"about_ca_topic_score_gemma":8.602903e-7,"domain_scores_codex":[0.9953236,0.002053219,0.001053956,0.000693722,0.0003892035,0.0004863306],"domain_scores_gemma":[0.9967366,0.001507541,0.0003511357,0.0005429263,0.0006418639,0.0002198969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002803805,0.002046734,0.00002855118,0.0001733412,0.0004833594,0.00009049851,0.00200434,0.03477547,0.2026593,0.2039095,0.000324403,0.5532241],"study_design_scores_gemma":[0.0004157143,0.00008703185,0.00008669507,0.0000299173,0.00008255506,0.00005492846,0.0001321034,0.4537232,0.0005203054,0.5446567,0.00001356525,0.0001972963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2637625,0.00006365326,0.7333587,0.00003628857,0.0002476143,0.0005569814,0.00001650055,0.0001575009,0.001800252],"genre_scores_gemma":[0.2545744,0.00004041041,0.7450589,0.00007163673,0.00007563159,0.00007946288,0.000005676391,0.00003731159,0.00005658665],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5530268,"threshold_uncertainty_score":0.9999845,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2803564483775052,"gpt":0.498751203955735,"spread":0.2183947555782298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002369897,0.0002264421,0.0006690074,0.0001097567,0.00004790849,0.00003775358,0.0003894407,0.0001452739,0.00003061076],"category_scores_gemma":[0.02671515,0.0001389394,0.00003442555,0.0004720489,0.0002810818,0.000109177,0.0002137147,0.0003080926,0.000002806135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001307857,"about_ca_system_score_gemma":0.0000178721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001924854,"about_ca_topic_score_gemma":4.385405e-7,"domain_scores_codex":[0.997539,0.0009666995,0.0003815474,0.0005779688,0.0002601511,0.0002745634],"domain_scores_gemma":[0.991366,0.007309073,0.0001301096,0.0006535844,0.0003405114,0.0002007639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001911409,0.0008921549,0.004525251,0.000784271,0.0004223906,0.0001764093,0.001307769,0.00005153765,0.009889004,0.1847104,0.001073125,0.7942563],"study_design_scores_gemma":[0.0009258639,0.001268308,0.001279449,0.0001580685,0.0002040169,0.0001236458,0.0001153501,0.05960871,0.00216105,0.9338152,0.00001280134,0.000327481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04194293,0.00046992,0.9555964,0.00006973541,0.0001376248,0.0002365687,0.00002035727,0.00004884701,0.001477649],"genre_scores_gemma":[0.1616697,0.00001376775,0.8381526,0.0000745652,0.0000494718,0.00001209031,0.000003731292,0.00001562169,0.000008489863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7939288,"threshold_uncertainty_score":0.9814832,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2726942149715341,"gpt":0.5589278597371689,"spread":0.2862336447656347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033133,0.0001234938,0.0004140093,0.0002381234,0.0001127347,0.00001976542,0.0003947786,0.0001318675,0.001027377],"category_scores_gemma":[0.0003152296,0.00008328904,0.0000728941,0.0009181703,0.0001874279,0.00006278337,0.00007068909,0.0002499645,0.000005554477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003963585,"about_ca_system_score_gemma":0.00001794035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000712807,"about_ca_topic_score_gemma":0.0002267267,"domain_scores_codex":[0.9973749,0.001051726,0.0005592515,0.0005068023,0.0001572657,0.0003500639],"domain_scores_gemma":[0.9971133,0.001873792,0.0001093076,0.0007223659,0.00007841051,0.0001028248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002461946,0.002362958,0.009131422,0.00005886374,0.001282639,0.00001221955,0.00227688,0.002091493,0.0007621133,0.002883282,0.01317706,0.9634991],"study_design_scores_gemma":[0.001131193,0.0001892507,0.2800717,0.000006520425,0.000261571,0.000007186725,0.00009878391,0.7159494,0.000008088348,0.0008322265,0.001346742,0.00009725459],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1974439,0.002588252,0.7836632,0.01165908,0.0001183522,0.002023968,0.001084598,0.00004544493,0.001373247],"genre_scores_gemma":[0.336125,0.0004491977,0.6591595,0.0008776171,0.0000560748,0.0004939532,0.0003789333,0.00001790967,0.002441761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9634019,"threshold_uncertainty_score":0.9998858,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6449695789679178,"gpt":0.6157682207415001,"spread":0.02920135822641778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03699339,0.0008121863,0.002312717,0.00007406262,0.0002789132,0.0002359228,0.001457103,0.0008329925,0.001022161],"category_scores_gemma":[0.6226481,0.0004188589,0.0005702805,0.0007409478,0.000851589,0.0001173797,0.0004246324,0.001536301,0.00007409378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009207883,"about_ca_system_score_gemma":0.00003153883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001855668,"about_ca_topic_score_gemma":3.42789e-7,"domain_scores_codex":[0.9609216,0.03429405,0.00150827,0.001341874,0.0009009516,0.001033211],"domain_scores_gemma":[0.5883963,0.4090869,0.000595793,0.001254718,0.0001465317,0.0005197146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.02573018,0.006119605,0.04304392,0.001898638,0.002922186,0.0006178148,0.004974409,0.0004077703,0.004628019,0.1292342,0.2246405,0.5557828],"study_design_scores_gemma":[0.004171988,0.003244583,0.005253342,0.0001692918,0.000271632,0.00004551326,0.0002196364,0.0006808731,0.001165933,0.9807897,0.003297786,0.0006897219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02337869,0.0003560095,0.946098,0.001460722,0.002127775,0.004252691,0.00007790025,0.0009413008,0.02130696],"genre_scores_gemma":[0.02009617,0.000004679111,0.9763499,0.001494004,0.0005884639,0.001199286,0.000003048061,0.0001069486,0.0001574397],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8515555,"threshold_uncertainty_score":0.999891,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4321866580824589,"gpt":0.5531479969564407,"spread":0.1209613388739817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005505236,0.000186371,0.0002929563,0.00006625464,0.0004647468,0.0001359296,0.000815617,0.00007688817,0.001857577],"category_scores_gemma":[0.01697085,0.0001115321,0.0001420408,0.0004217044,0.0001495498,0.00003148303,0.0002963583,0.0005926999,0.00002768365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006210703,"about_ca_system_score_gemma":0.00001902338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000041966,"about_ca_topic_score_gemma":7.676383e-7,"domain_scores_codex":[0.9935212,0.004961489,0.0002844536,0.0004304326,0.000321375,0.0004810485],"domain_scores_gemma":[0.9898202,0.009113207,0.0001421381,0.000701595,0.00006039539,0.0001624082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000990792,0.0002472558,0.0001068824,0.000008935069,0.0000284278,0.000005606318,0.003796148,0.000004027201,0.0008912198,0.6799409,0.08707602,0.2277955],"study_design_scores_gemma":[0.0001835663,0.0003037048,0.01227421,0.000003328692,0.00002977229,0.00003571995,0.004654551,0.00002111469,0.0002615426,0.716269,0.2657812,0.0001822919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0216328,0.0003132234,0.9254956,0.03109432,0.004604312,0.0007116574,0.00005706476,0.0003088416,0.01578221],"genre_scores_gemma":[0.02657578,0.00003533162,0.9608727,0.006539684,0.0002367036,0.0002295398,0.000003498822,0.00002662888,0.005480208],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2276132,"threshold_uncertainty_score":0.9990548,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3990117029423373,"gpt":0.525208746155382,"spread":0.1261970432130447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001854446,0.0002997276,0.0004683053,0.00009449796,0.0002811363,0.0000501984,0.0006070136,0.0001602895,0.0001583047],"category_scores_gemma":[0.07899409,0.0001622226,0.0001034441,0.0004015009,0.0003121375,0.000348155,0.000355867,0.0002693642,0.00005882003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007801037,"about_ca_system_score_gemma":0.00003613863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002013568,"about_ca_topic_score_gemma":0.0000116259,"domain_scores_codex":[0.9959539,0.001226546,0.0003494618,0.001700014,0.000290048,0.0004800041],"domain_scores_gemma":[0.9480619,0.05050255,0.0001986997,0.0008545119,0.0002054927,0.0001768517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003357474,0.0003594843,0.00375542,0.00002911518,0.0001375649,0.00005727309,0.0001717365,0.0001005808,0.3874811,0.03694811,0.01019297,0.5574092],"study_design_scores_gemma":[0.02631552,0.01139497,0.3376476,0.000895679,0.0008119422,0.002874418,0.0006251273,0.2230766,0.07093222,0.1971121,0.1236756,0.004638255],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003023944,0.0000529497,0.9752338,0.01924384,0.001080025,0.0005919403,0.00006983061,0.0001747975,0.0005288994],"genre_scores_gemma":[0.1193396,0.00001169829,0.8759937,0.003709516,0.0002873919,0.00008761689,0.000004752717,0.00003112618,0.0005346272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5527709,"threshold_uncertainty_score":0.9287639,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9565826883810709,"gpt":0.7111345330937316,"spread":0.2454481552873392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03781359,0.0003193908,0.001172152,0.0009375089,0.0005751526,0.0001846911,0.003426444,0.0003788302,0.0008598824],"category_scores_gemma":[0.6951944,0.0001968979,0.0004851947,0.01005608,0.0004395001,0.0002186878,0.0003542438,0.0005752073,0.00004839182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002496551,"about_ca_system_score_gemma":0.00004560177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007286564,"about_ca_topic_score_gemma":6.142022e-7,"domain_scores_codex":[0.9914123,0.003347993,0.001419141,0.002070588,0.001034681,0.0007153212],"domain_scores_gemma":[0.6658209,0.328798,0.0009137862,0.003605639,0.0005429289,0.0003187463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001820923,0.000807958,0.1924505,0.000009683715,0.0002281868,0.00003510245,0.000131495,0.0003097192,0.001542757,0.002469177,0.006091946,0.7957414],"study_design_scores_gemma":[0.001817757,0.001400934,0.3585839,0.00002535263,0.0005112675,0.00006721015,0.0005433851,0.06759359,0.001766987,0.5195189,0.04707084,0.001099904],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03866244,0.0003705765,0.9553593,0.001329856,0.001049882,0.0005131687,0.00006577071,0.0002361931,0.00241282],"genre_scores_gemma":[0.1863574,0.00001096867,0.811788,0.001327331,0.0002629391,0.00003952916,0.00001914619,0.00001593691,0.0001788495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7946415,"threshold_uncertainty_score":0.9907734,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Multiple comparisons problem; Control (management); Computer science; Mathematics; Statistics; False discovery rate; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.8514252015725781,"gpt":0.7047830235817717,"spread":0.1466421779908064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0210058,0.0003968887,0.001820618,0.0001147749,0.00007767128,0.00001824151,0.0008055696,0.0005889914,0.001898522],"category_scores_gemma":[0.2862344,0.0002906529,0.0004995556,0.0005697979,0.0004063963,0.00005746963,0.0001152754,0.0005260089,0.00002060985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002752056,"about_ca_system_score_gemma":0.00005555374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001304829,"about_ca_topic_score_gemma":4.7419e-7,"domain_scores_codex":[0.9903572,0.005887685,0.00195783,0.0008972952,0.0002533371,0.0006466775],"domain_scores_gemma":[0.866086,0.1314219,0.0007961415,0.0009489642,0.0003605051,0.0003865251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001754357,0.000748754,0.0001484758,0.0001336728,0.0001728059,0.000004056924,0.0001975378,6.466444e-7,0.02790714,0.3135695,0.001739751,0.6536233],"study_design_scores_gemma":[0.002012898,0.001576284,0.001783235,0.00005641779,0.0002707963,0.000006008866,0.00003957027,0.0002692094,0.01787246,0.9731148,0.002650437,0.0003478541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001117778,0.0002858948,0.9837286,0.0001479546,0.002228479,0.001423768,0.00002407483,0.0001912051,0.0108522],"genre_scores_gemma":[0.002115902,0.00004637672,0.9961085,0.0004277228,0.000412033,0.0001439211,8.442401e-7,0.00006932189,0.0006753781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6595454,"threshold_uncertainty_score":0.9999546,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2672039613477072,"gpt":0.4999134662670226,"spread":0.2327095049193154,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002162857,0.0002993196,0.000714128,0.00006717387,0.0001807872,0.0002011525,0.000859829,0.0002688488,0.001011388],"category_scores_gemma":[0.004819408,0.0001210311,0.0001634368,0.002258453,0.0002135055,0.00009230112,0.0003551975,0.0003539523,0.00006378961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001864376,"about_ca_system_score_gemma":0.000005561255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001660684,"about_ca_topic_score_gemma":0.0001167337,"domain_scores_codex":[0.9946281,0.002591798,0.0005531699,0.001265392,0.0004318049,0.0005297927],"domain_scores_gemma":[0.9949412,0.003421508,0.0001319943,0.0004536964,0.0001546661,0.0008969552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000514302,0.000503128,0.01959915,0.000002564092,0.0001827174,0.0001863307,0.0001922517,0.0007493677,0.01012321,0.0005763446,0.0004621356,0.9669085],"study_design_scores_gemma":[0.0004453672,0.004377569,0.8783264,0.00003222953,0.002495571,0.0001253787,0.001480201,0.06304579,0.00027594,0.01876466,0.02916025,0.001470596],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6343272,0.0002705744,0.3639892,0.0007295505,0.0001770009,0.0001721049,0.0001199005,0.00007711852,0.0001374012],"genre_scores_gemma":[0.5218049,0.00001412798,0.4772206,0.0006521649,0.0001891142,0.00001509213,0.00003275853,0.000001430361,0.00006983822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9654379,"threshold_uncertainty_score":0.9999018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}