{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":759,"total_is_capped":false,"direct_labels_cover":20,"predictions_cover":759,"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":"203cf04dfb66","filters":{"topic":"Psychometric Methodologies and Testing"}},"results":[{"id":"W2125001590","doi":"10.1016/j.jml.2007.12.005","title":"Mixed-effects modeling with crossed random effects for subjects and items","year":2008,"lang":"en","type":"article","venue":"Journal of Memory and Language","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8560,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Developmental psychology; Cognitive psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2151326486886005,"gpt":0.3957748843215883,"spread":0.1806422356329878,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004823345,0.0001274894,0.0005011257,0.0003192356,0.0002363773,0.0001094686,0.000194475,0.00006378157,0.000005449601],"category_scores_gemma":[0.02685284,0.0000704281,0.00008893481,0.000386758,0.00008892371,0.000242453,0.00003528451,0.0001763423,5.405618e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007771281,"about_ca_system_score_gemma":0.00003539428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001021078,"about_ca_topic_score_gemma":0.000003244837,"domain_scores_codex":[0.9983518,0.0003109946,0.0004327072,0.0002041264,0.0004957893,0.0002045513],"domain_scores_gemma":[0.9748839,0.02424234,0.0003857983,0.000157284,0.000183739,0.0001469852],"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":[0.009282594,0.0003773091,0.04519222,0.0009080021,0.0004763108,0.004579578,0.03625385,0.006151386,0.06749357,0.0003121403,0.004719051,0.824254],"study_design_scores_gemma":[0.1777523,0.01966514,0.2876321,0.003447182,0.001053036,0.03746253,0.05615441,0.2378985,0.1453539,0.02753163,0.002470763,0.003578544],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8803278,0.006127556,0.1126932,0.00005260359,0.0003595455,0.0001910107,0.000001250266,0.000009345242,0.000237654],"genre_scores_gemma":[0.9763307,0.0001040316,0.02299981,0.0001344834,0.0002342814,0.00000354391,1.951423e-7,0.000009140691,0.0001838288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8206754,"threshold_uncertainty_score":0.9813444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144487201","doi":"10.1080/10705510903008220","title":"Exploratory Structural Equation Modeling, Integrating CFA and EFA: Application to Students' Evaluations of University Teaching","year":2009,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1080,"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":"Economic and Social Research Council","keywords":"Structural equation modeling; Confirmatory factor analysis; Goodness of fit; Latent variable; Psychology; Statistics; Measurement invariance; Environmental scanning electron microscope; Exploratory factor analysis; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3055562692897275,"gpt":0.4805804396433995,"spread":0.175024170353672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01030822,0.0003011278,0.0004831565,0.001179103,0.001612588,0.0003632999,0.0009051192,0.0001396121,0.00002100346],"category_scores_gemma":[0.01685427,0.0002418132,0.0001602003,0.001194232,0.00005465569,0.001418235,0.0002921305,0.0007023928,0.000004364087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002491533,"about_ca_system_score_gemma":0.0001467615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006261094,"about_ca_topic_score_gemma":0.00001568596,"domain_scores_codex":[0.9940871,0.001333053,0.001463927,0.0006875217,0.002047091,0.0003812823],"domain_scores_gemma":[0.994534,0.00240349,0.0009797879,0.0004714546,0.001323069,0.0002881696],"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":[0.0001388738,0.00001565223,0.01112052,0.000004327908,0.00001852908,0.000001660892,0.006822102,0.856172,0.00450882,0.001285432,0.000007472349,0.1199046],"study_design_scores_gemma":[0.0006469531,0.0002380353,0.009929092,0.00006863029,0.00003769656,0.00003611497,0.01313946,0.874589,0.00002828444,0.101053,0.000001282042,0.0002324252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5077713,0.00008687597,0.4912621,0.0003401241,0.0002137006,0.0002327026,0.000006683262,0.00003170827,0.00005486755],"genre_scores_gemma":[0.8408621,0.00001482726,0.1588542,0.00002798587,0.0001875997,0.000002404758,0.00001397701,0.00001223396,0.00002470459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3330908,"threshold_uncertainty_score":0.9996872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2612259620","doi":"10.22237/jmasm/1177992180","title":"Ordinal Versions of Coefficients Alpha and Theta for Likert Rating Scales","year":2007,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1013,"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":"Ordinal data; Mathematics; Statistics; Likert scale; Ordinal Scale; Skewness; Ordinal regression; Reliability (semiconductor); Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.3690266326624584,"gpt":0.5562911121253126,"spread":0.1872644794628542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03453816,0.0001509658,0.0007193896,0.0004916315,0.0001755042,0.00007603189,0.0004870922,0.0001007224,0.00004569739],"category_scores_gemma":[0.08774735,0.00009916865,0.000123706,0.0006970453,0.0002539866,0.00007772589,0.0001369516,0.0002781581,9.200718e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000273365,"about_ca_system_score_gemma":0.00006143885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002112499,"about_ca_topic_score_gemma":8.176644e-7,"domain_scores_codex":[0.9962251,0.0005320592,0.001565585,0.0003032612,0.001029037,0.0003450203],"domain_scores_gemma":[0.8615126,0.1362977,0.001096584,0.0002409862,0.0005852264,0.0002668871],"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":[0.0004621102,0.00008526143,0.001130308,0.00001648472,0.0000362434,0.00000551959,0.0001909164,0.0001283326,0.01668558,0.01975238,0.0005158798,0.960991],"study_design_scores_gemma":[0.002054481,0.0007097095,0.03326255,0.00005430801,0.0001177999,0.0001091234,0.001623973,0.04818296,0.004983963,0.9060911,0.002561224,0.0002488197],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02387316,0.0003478346,0.9726278,0.00009126041,0.0003837757,0.0001640745,0.00003425503,0.000006940891,0.002470953],"genre_scores_gemma":[0.3995767,0.000007761013,0.6002842,0.00003822401,0.00006185078,0.000001003589,3.941799e-7,0.000007371673,0.00002259807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9607422,"threshold_uncertainty_score":0.9941461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2769536523","doi":"10.1002/pfi.21727","title":"Evidence-Based Survey Design: The Use of a Midpoint on the Likert Scale","year":2017,"lang":"en","type":"article","venue":"Performance Improvement Journal","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":823,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Government of Alberta","funders":"","keywords":"Likert scale; Midpoint; Scale (ratio); Computer science; Survey research; Psychology; Management science; Applied psychology; Mathematics; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.9048798418730529,"gpt":0.4941430133169829,"spread":0.41073682855607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04372335,0.000162095,0.000275631,0.0002043914,0.001873476,0.001546578,0.002709655,0.00004615373,0.0002437695],"category_scores_gemma":[0.1346142,0.0000636112,0.0001586111,0.000462382,0.0003151665,0.0008813184,0.0002372366,0.0004743438,0.00003243164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005337825,"about_ca_system_score_gemma":0.0001908759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001080425,"about_ca_topic_score_gemma":0.00001931433,"domain_scores_codex":[0.9955772,0.00108681,0.0008699034,0.0002692717,0.001789457,0.0004073679],"domain_scores_gemma":[0.9526426,0.04335911,0.001684633,0.001552988,0.0006580562,0.0001026204],"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":[0.0003114308,0.00006021393,0.3922879,0.000004501308,0.00002182554,0.000001525861,0.0001087276,0.002198944,0.001473365,0.00001069256,0.009090503,0.5944304],"study_design_scores_gemma":[0.0003521212,0.0008742376,0.9387509,0.0002331473,0.00001123419,0.000009616132,0.0001106763,0.04788385,0.009561236,0.0006065386,0.001494384,0.0001120621],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9642161,0.0001370248,0.02873525,0.005249165,0.001130445,0.0003196174,0.000004073352,0.000007711878,0.0002005663],"genre_scores_gemma":[0.9906796,0.0003795507,0.007353527,0.001061398,0.0001596495,0.00001318093,1.254251e-7,0.000008274697,0.0003446586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5943183,"threshold_uncertainty_score":0.9994899,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1980472079","doi":"10.1136/bmj.c117","title":"Is a subgroup effect believable? Updating criteria to evaluate the credibility of subgroup analyses","year":2010,"lang":"en","type":"article","venue":"BMJ","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":812,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Subgroup analysis; Credibility; Psychology; Computer science; Information retrieval; Mathematics; Statistics; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.5243444902286908,"gpt":0.5884504748589897,"spread":0.06410598463029893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05210993,0.0001989426,0.0005820959,0.0003848359,0.0002585465,0.0002472036,0.001533039,0.0001034805,0.001950391],"category_scores_gemma":[0.3680751,0.0001033338,0.0002576032,0.003468795,0.0001644727,0.000178368,0.0004634486,0.0003171815,0.0001281999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001466392,"about_ca_system_score_gemma":0.00005704839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003766624,"about_ca_topic_score_gemma":0.00007445804,"domain_scores_codex":[0.9941485,0.001821451,0.001201906,0.0007075477,0.001716189,0.0004043984],"domain_scores_gemma":[0.9256036,0.07074651,0.0005233983,0.002279896,0.0006732249,0.0001733789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000197372,0.00007285809,0.6027064,0.00002913739,0.00006816762,0.000005413349,0.001032575,0.0000525382,0.1972111,0.0002506351,0.06077076,0.137603],"study_design_scores_gemma":[0.0004405424,0.0003618735,0.950068,0.00002947949,0.00006166435,0.00001965875,0.0006044412,0.006016744,0.02582115,0.01304283,0.003298929,0.0002346762],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9839177,0.00007732087,0.003968733,0.002394823,0.001428874,0.0005750382,0.00002126142,0.00004360427,0.007572626],"genre_scores_gemma":[0.9683033,0.000001679801,0.03063382,0.0005131312,0.0003049655,0.00003712335,0.000001282904,0.00001086592,0.0001938963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3473616,"threshold_uncertainty_score":0.998962,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126395473","doi":"","title":"Testing for multigroup equivalence of a measuring instrument: a walk through the process.","year":2008,"lang":"en","type":"article","venue":"PubMed","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":737,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Equivalence (formal languages); Psychology; Covariance; Social psychology; Computer science; Cognitive psychology; Mathematics; Statistics; Pure mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.7434047361636618,"gpt":0.4296999713785657,"spread":0.313704764785096,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006450676,0.0001286171,0.0003047208,0.0001544969,0.0003692346,0.00005759008,0.001098186,0.00004938403,0.000007608812],"category_scores_gemma":[0.2554175,0.00007262335,0.0001122499,0.002425599,0.0002175296,0.000306575,0.0001520316,0.0001200126,0.000002424147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002365915,"about_ca_system_score_gemma":0.00004558378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000583911,"about_ca_topic_score_gemma":0.000002151371,"domain_scores_codex":[0.9971178,0.0001860061,0.0007090909,0.0004290649,0.001063242,0.0004947805],"domain_scores_gemma":[0.9677932,0.03052096,0.0005874432,0.0005225024,0.000505537,0.00007031243],"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":[0.00003404106,0.00004557439,0.1413755,0.0000310717,0.0000160604,0.000002033202,0.001252248,0.0001704682,0.0001321142,0.000203046,0.0002460282,0.8564918],"study_design_scores_gemma":[0.0006892073,0.00006326734,0.9532328,0.00002904959,0.00001349856,0.0000539643,0.001203029,0.001570605,0.002326253,0.03890895,0.001736098,0.0001733003],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.963113,0.0005849348,0.02261377,0.0004381088,0.0004472017,0.001226486,0.000008758398,0.00007505967,0.01149274],"genre_scores_gemma":[0.960082,0.000008873384,0.03863442,0.00009816324,0.000095014,0.0008996253,2.102574e-7,0.00000962799,0.0001720832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8563185,"threshold_uncertainty_score":0.7508544,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061477359","doi":"10.1371/journal.pone.0058067","title":"The Center for Epidemiologic Studies Depression Scale: A Review with a Theoretical and Empirical Examination of Item Content and Factor Structure","year":2013,"lang":"en","type":"review","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":552,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Regina Qu'Appelle Health Region; University of Regina","funders":"","keywords":"Differential item functioning; Anhedonia; Center for Epidemiologic Studies Depression Scale; Clinical psychology; Item response theory; Psychology; PsycINFO; Psychometrics; Confirmatory factor analysis; Scale (ratio); Depressive symptoms; Medicine; Psychiatry; MEDLINE; Structural equation modeling; Anxiety; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.8519675177471471,"gpt":0.5481175019615244,"spread":0.3038500157856227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005837948,0.0002808633,0.002503122,0.0001346457,0.0001575998,0.00006558825,0.0003941433,0.0001737557,0.00002590884],"category_scores_gemma":[0.2027068,0.00009667219,0.0001324104,0.0004767759,0.0006143294,0.00006640569,0.0002685025,0.0002518354,8.481028e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002050938,"about_ca_system_score_gemma":0.00002439607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.427619e-7,"about_ca_topic_score_gemma":9.710417e-7,"domain_scores_codex":[0.9951573,0.00221517,0.001141182,0.0005924808,0.000659908,0.0002339549],"domain_scores_gemma":[0.8756728,0.1222172,0.001044975,0.0004228334,0.0005617713,0.00008043242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000009025925,0.00004490474,0.003667929,0.009664284,0.0001837,2.849137e-7,0.00003184245,3.878146e-9,0.000001704731,0.0001248339,0.0002792567,0.9859923],"study_design_scores_gemma":[0.002982332,0.004109846,0.07951432,0.5431873,0.009755117,0.0002639009,0.00168183,0.0006609618,0.00005206207,0.0545796,0.3008014,0.002411365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005802384,0.9913794,0.0003038965,0.0003119143,0.00004637334,0.00201381,0.00009648666,0.00001214528,0.00003356226],"genre_scores_gemma":[0.0006846456,0.9880064,0.01090553,0.0001081498,0.00004409229,0.0001833303,0.000006186056,0.00001216787,0.00004957234],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9835809,"threshold_uncertainty_score":0.8040092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3095583164","doi":"10.1177/2515245920951747","title":"Your Coefficient Alpha Is Probably Wrong, but Which Coefficient Omega Is Right? A Tutorial on Using R to Obtain Better Reliability Estimates","year":2020,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":542,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Omega; Confusion; Reliability (semiconductor); Construct (python library); Alpha (finance); Variety (cybernetics); Quality (philosophy); Confirmatory factor analysis; Cronbach's alpha; Computer science; Correlation coefficient; Statistics; Mathematics; Psychology; Epistemology; Physics; Psychometrics; Structural equation modeling; Philosophy; Programming language; Thermodynamics","retraction":null,"screen_n_in":null,"score":{"opus":0.3780115946846152,"gpt":0.6190029165631815,"spread":0.2409913218785663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04428627,0.0004327078,0.0008644495,0.0007120636,0.000520473,0.0007844348,0.002381212,0.0002222602,0.0002658087],"category_scores_gemma":[0.3259605,0.0002786504,0.00009341305,0.01341003,0.0009888133,0.001564458,0.0007774964,0.0009493185,0.00003228144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001615915,"about_ca_system_score_gemma":0.0001036569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006929998,"about_ca_topic_score_gemma":0.000009375878,"domain_scores_codex":[0.9892201,0.002703129,0.001540781,0.003175521,0.002264244,0.00109618],"domain_scores_gemma":[0.9518736,0.04430597,0.001419586,0.001198952,0.0005517133,0.0006502033],"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":[0.001386248,0.001098042,0.1408803,0.00004498196,0.000008154156,0.00007985701,0.00446268,0.02501967,0.009165606,0.001976746,0.000563462,0.8153143],"study_design_scores_gemma":[0.00357061,0.006478912,0.1841644,0.0003400315,0.00005467365,0.0001248886,0.004947643,0.3421361,0.00717781,0.2160769,0.2325131,0.002414868],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7593341,0.0009788109,0.2191463,0.01139368,0.002469201,0.0008374414,0.00001591005,0.00006396168,0.005760574],"genre_scores_gemma":[0.3859877,0.0001793424,0.6075401,0.006074179,0.0001642542,0.00003064337,2.842006e-7,0.000009185737,0.00001431559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8128994,"threshold_uncertainty_score":0.9999666,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4214760420","doi":"10.1186/s12913-022-07577-3","title":"Development of a theory-informed questionnaire to assess the acceptability of healthcare interventions","year":2022,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":538,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Psychological intervention; Medicine; Intervention (counseling); Content validity; Health care; Nursing research; Discriminant validity; Focus group; Health administration; Health informatics; Public health; Nursing; Patient satisfaction; Psychometrics; Clinical psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.7507588387515985,"gpt":0.6539609633253661,"spread":0.09679787542623242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1029906,0.0001047269,0.0004379078,0.00104083,0.001423488,0.00007242225,0.002669679,0.00003911975,0.001360007],"category_scores_gemma":[0.02777835,0.00006694782,0.0001554257,0.007309871,0.000130272,0.0001299698,0.00204349,0.0005093808,0.00001512888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003680975,"about_ca_system_score_gemma":0.002805872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001231009,"about_ca_topic_score_gemma":0.003553097,"domain_scores_codex":[0.9824864,0.01017191,0.002171702,0.0005178063,0.003981265,0.0006709208],"domain_scores_gemma":[0.9298296,0.0642565,0.001166466,0.00193201,0.002364684,0.0004507655],"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":[0.0002432325,0.0002433959,0.2640243,0.00237708,0.00001572569,3.293314e-7,0.02937244,0.000230023,0.00001549343,0.007253322,0.0001498032,0.6960748],"study_design_scores_gemma":[0.0001572841,0.0003095213,0.8821769,0.000121506,0.000001030025,0.000002032939,0.09941006,0.0003028214,0.00007186025,0.01001793,0.007370119,0.00005897826],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726901,0.001639684,0.01898392,0.003185545,0.0004977373,0.001711539,0.00006606642,0.00003675419,0.001188636],"genre_scores_gemma":[0.9566974,0.00001470154,0.04252697,0.000317786,0.00002454462,0.0002735168,0.000004535793,0.000007879776,0.0001326626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6960158,"threshold_uncertainty_score":0.9998765,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102743086","doi":"10.1016/j.jpsychores.2010.01.006","title":"Introduction to health measurement scales","year":2010,"lang":"en","type":"review","venue":"Journal of Psychosomatic Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":499,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Baycrest Hospital; University Health Network; University of Toronto","funders":"","keywords":"Scale (ratio); Psychometrics; Psychology; Applied psychology; Psychometric testing; Clinical psychology; Internal consistency; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.8911488147396245,"gpt":0.6819205607602203,"spread":0.2092282539794041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1908447,0.0003356182,0.003087913,0.006783549,0.000360333,0.0007336563,0.003626809,0.0003076447,0.0004872826],"category_scores_gemma":[0.3667979,0.000188743,0.0008403392,0.01017654,0.0001504409,0.0002294915,0.0002748655,0.003194554,0.0006148827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005678665,"about_ca_system_score_gemma":0.001505901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001044433,"about_ca_topic_score_gemma":0.00001235603,"domain_scores_codex":[0.970606,0.008701554,0.005278083,0.0007970082,0.0137051,0.0009122016],"domain_scores_gemma":[0.9483413,0.03946687,0.004123198,0.002067543,0.005009593,0.0009915147],"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":[0.000008793988,0.00007718319,0.0000148113,0.0009426065,0.00004268085,0.000005338562,0.00007470898,8.143766e-7,0.000002100672,0.00006018038,0.2357062,0.7630646],"study_design_scores_gemma":[0.0001286453,0.0005790759,0.000203953,0.006274565,0.00002308062,0.0003682495,0.0002109837,0.000002880548,4.451162e-7,0.008333193,0.9837253,0.0001496323],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002715651,0.9759157,0.006309311,0.009985338,0.005937485,0.0008742753,0.000004191028,0.00001154027,0.0009350312],"genre_scores_gemma":[0.000006517597,0.952333,0.04099889,0.00005805639,0.006140169,0.00002415457,4.348321e-7,0.00003641094,0.0004023836],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.762915,"threshold_uncertainty_score":0.9991051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087062758","doi":"10.1207/s15327752jpa8501_02","title":"Factor Analytic Models: Viewing the Structure of an Assessment Instrument From Three Perspectives","year":2005,"lang":"en","type":"review","venue":"Journal of Personality Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":492,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Confirmatory factor analysis; Psychology; Structural equation modeling; CLARITY; Exploratory factor analysis; Psychometrics; Notional amount; Social psychology; Clinical psychology; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.6885502201466005,"gpt":0.588745809497927,"spread":0.09980441064867351,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01123183,0.0007019624,0.00405889,0.0009657491,0.0002965063,0.0005999114,0.003491587,0.0003570839,0.001469424],"category_scores_gemma":[0.004873816,0.0003519246,0.002015635,0.00194488,0.0002486196,0.0009347469,0.000415276,0.002024424,0.000001836963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001291086,"about_ca_system_score_gemma":0.002104384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001651126,"about_ca_topic_score_gemma":0.00008889097,"domain_scores_codex":[0.9855521,0.003724477,0.004058477,0.0008840506,0.005299346,0.0004815456],"domain_scores_gemma":[0.9720228,0.01702124,0.00802957,0.00139748,0.001220747,0.0003082186],"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":[0.00001100368,0.0002336107,0.0007423722,0.0002661278,0.0008924569,0.00001388113,0.001119755,0.0003841919,0.000004799924,0.0006687305,0.00009738671,0.9955657],"study_design_scores_gemma":[0.002758245,0.002425103,0.1006533,0.01485954,0.00737279,0.0006498969,0.04783364,0.028327,0.000004405173,0.1281445,0.6642616,0.002709881],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01424363,0.9568688,0.02575476,0.0004168912,0.001070357,0.0005734318,0.0005555193,0.00001333846,0.0005033024],"genre_scores_gemma":[0.04454431,0.8336045,0.1204278,0.00005902359,0.001272649,0.000004905435,0.00001366175,0.0000436963,0.00002942225],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9928558,"threshold_uncertainty_score":0.9998932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972479177","doi":"10.1186/1756-0500-3-267","title":"Structural equation modeling in medical research: a primer","year":2010,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":481,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Structural equation modeling; Latent variable; Computer science; Medical research; Set (abstract data type); Data science; Linear regression; Measure (data warehouse); Management science; Data mining; Machine learning; Medicine; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.9628487103961001,"gpt":0.6876974379363604,"spread":0.2751512724597397,"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":[0.1489981,0.0001111971,0.0002788312,0.002910665,0.0005429237,0.00047815,0.002058518,0.000263084,0.00163754],"category_scores_gemma":[0.8455004,0.00007455266,0.00007255365,0.007375434,0.0005004038,0.0003604155,0.0008769687,0.00272547,0.0002893477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007162593,"about_ca_system_score_gemma":0.0006739402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002155564,"about_ca_topic_score_gemma":0.002034754,"domain_scores_codex":[0.9812111,0.005320048,0.0008425668,0.0008366094,0.01065436,0.001135375],"domain_scores_gemma":[0.6549978,0.3397864,0.000123054,0.001605301,0.00287669,0.0006107018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001483224,0.00007211295,0.4995404,0.00001714925,0.000005489487,0.00003978914,0.00141488,0.001522655,0.005549739,0.007831268,0.0008583579,0.4829999],"study_design_scores_gemma":[0.0003036992,0.00005968836,0.04431538,0.00002505618,3.470668e-7,0.000008331727,0.0007549883,0.7354504,0.0003169608,0.2183618,0.0003133787,0.00008993588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794917,0.00016094,0.01444532,0.002381529,0.0004743832,0.0003064261,0.000001758576,0.00003334653,0.002704584],"genre_scores_gemma":[0.9644549,0.00001720262,0.03488374,0.00002264253,0.0004016403,0.00003205807,0.000001706347,0.00001235078,0.0001737305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7339278,"threshold_uncertainty_score":0.9995753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134792407","doi":"10.1186/1471-2288-12-159","title":"Should researchers use single indicators, best indicators, or multiple indicators in structural equation models?","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":422,"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":"Structural equation modeling; Latent variable; Path analysis (statistics); Econometrics; Computer science; Statistical model; Performance indicator; Confounding; Statistics; Risk analysis (engineering); Mathematics; Machine learning; Medicine; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.9615285550475937,"gpt":0.6606017935692375,"spread":0.3009267614783562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","research_integrity"],"category_scores_codex":[0.2797406,0.0004901982,0.001607435,0.0191726,0.0005554737,0.0003809817,0.004226325,0.001549289,0.003893149],"category_scores_gemma":[0.9326814,0.0003258387,0.0002936981,0.02976135,0.002644595,0.001624047,0.002337086,0.004276934,0.000191823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006479849,"about_ca_system_score_gemma":0.002590837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001530983,"about_ca_topic_score_gemma":0.001156232,"domain_scores_codex":[0.900068,0.07724222,0.002924924,0.001847331,0.01405228,0.003865181],"domain_scores_gemma":[0.1953667,0.7965987,0.001039673,0.002414043,0.0007218213,0.0038591],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006298674,0.0002954572,0.6568246,0.00003779817,0.00003448917,0.00004976792,0.001497525,0.00007872343,0.0001791988,0.005745786,0.00139521,0.3332315],"study_design_scores_gemma":[0.007153624,0.002405596,0.751096,0.0004744467,0.00005748705,0.0002498536,0.02222594,0.06022914,0.002670245,0.1026196,0.04893985,0.001878299],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8312503,0.001724994,0.1612789,0.001047739,0.001303451,0.0009707824,0.00002700877,0.0001106884,0.002286045],"genre_scores_gemma":[0.7845387,0.0003049903,0.2131133,0.0002796279,0.0006282906,0.0001609766,0.00002340782,0.00006083049,0.0008898939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7193565,"threshold_uncertainty_score":0.9999194,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016005933","doi":"10.1037/0021-9010.87.3.517","title":"Measurement equivalence: A comparison of methods based on confirmatory factor analysis and item response theory.","year":2002,"lang":"en","type":"article","venue":"Journal of Applied Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":412,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Equivalence (formal languages); Item response theory; Differential item functioning; Confirmatory factor analysis; Psychology; Raw score; Psychometrics; Factor analysis; Social psychology; Econometrics; Classical test theory; Test (biology); Statistics; Raw data; Mathematics; Structural equation modeling; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.6434044207719166,"gpt":0.5717001743794533,"spread":0.07170424639246331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0385383,0.0001922116,0.001183498,0.002615152,0.00008744744,0.00005117751,0.0007833327,0.0001700102,0.001150554],"category_scores_gemma":[0.03244312,0.0001281509,0.0003137228,0.002844883,0.0002551111,0.00005717363,0.00004832941,0.0004371156,0.000009820699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004177116,"about_ca_system_score_gemma":0.00003398682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.547217e-7,"about_ca_topic_score_gemma":4.106423e-7,"domain_scores_codex":[0.9922427,0.00370199,0.00189931,0.0004136928,0.001459216,0.0002830701],"domain_scores_gemma":[0.957559,0.0387877,0.002269196,0.0006443436,0.0005597621,0.0001799265],"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":[0.01008186,0.0008877653,0.08668891,0.00002006452,0.0009100575,0.00001794438,0.002006848,0.001127247,0.05557378,0.001198253,0.005162079,0.8363252],"study_design_scores_gemma":[0.003942546,0.002532304,0.9404571,0.00006187383,0.0005650013,0.00004753279,0.00223014,0.01195533,0.006946917,0.01742044,0.01342602,0.0004147695],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5372857,0.001386397,0.4512395,0.0006372011,0.0005815176,0.0001423063,0.000006348503,0.00001298427,0.008707982],"genre_scores_gemma":[0.9218976,0.00003334954,0.07744216,0.0005515445,0.00004208385,0.000002598451,6.764886e-8,0.000008281786,0.00002234548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8537682,"threshold_uncertainty_score":0.9997625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2905628759","doi":"10.20982/tqmp.14.4.p242","title":"A review of effect sizes and their confidence intervals, Part I: The Cohen's d family","year":2018,"lang":"en","type":"review","venue":"The Quantitative Methods for Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":365,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Confidence interval; Statistics; Mathematics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.7976858719762024,"gpt":0.6853861465175152,"spread":0.1122997254586873,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1283878,0.0007022314,0.004924865,0.0004428519,0.0003443943,0.00009856492,0.003729489,0.0003109695,0.0001047589],"category_scores_gemma":[0.3351032,0.000252137,0.001336108,0.002811679,0.002688482,0.00008775896,0.0005182004,0.000677322,0.00004373954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001937555,"about_ca_system_score_gemma":0.0001104746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001259718,"about_ca_topic_score_gemma":0.000001528033,"domain_scores_codex":[0.9504936,0.04448614,0.002726452,0.001326154,0.0004058858,0.0005617692],"domain_scores_gemma":[0.5077233,0.485562,0.003514192,0.002315155,0.0007986527,0.00008678369],"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":[0.00005015083,0.00001744439,0.000002254517,0.008573228,0.0002906557,3.468224e-7,0.000258167,1.500205e-8,0.000005287855,0.005044318,0.02435795,0.9614002],"study_design_scores_gemma":[0.0001925736,0.001356764,0.0000199727,0.024028,0.0004905324,0.00006980604,0.0002977462,0.00001724875,0.000005021177,0.07495292,0.898321,0.000248453],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003359402,0.6899285,0.304232,0.0005290008,0.001963492,0.002199319,0.00008983632,0.00002316703,0.001031252],"genre_scores_gemma":[4.265844e-7,0.8375292,0.1600011,0.001638342,0.0001433497,0.0004974744,0.00000562866,0.00004003984,0.0001444259],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9611517,"threshold_uncertainty_score":0.9999931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029517174","doi":"10.1007/s11336-005-1295-9","title":"Limited Information Goodness-of-fit Testing in Multidimensional Contingency Tables","year":2006,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":327,"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":"Goodness of fit; Statistics; Contingency table; Mathematics; Statistical hypothesis testing; Estimator; Null hypothesis; Econometrics; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4253619074110371,"gpt":0.4361651235139779,"spread":0.01080321610294077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00781257,0.0002112035,0.0005417665,0.004460074,0.0001166946,0.0001351061,0.0006696324,0.0001455356,0.0002736798],"category_scores_gemma":[0.2022282,0.0001675721,0.0001167139,0.01974521,0.00009248346,0.0008476142,0.0001324587,0.0002371728,0.0001016242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004490419,"about_ca_system_score_gemma":0.00005763673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007460023,"about_ca_topic_score_gemma":0.00003029518,"domain_scores_codex":[0.995376,0.0003017911,0.001941244,0.0004325419,0.001473932,0.0004744723],"domain_scores_gemma":[0.9520485,0.04518643,0.001144576,0.0006288972,0.0009003746,0.00009116396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003135585,0.0001315613,0.7983192,0.00001075904,0.000005341207,0.000001760337,0.00007195706,0.00064252,0.001094438,0.0008706569,0.002127281,0.1966931],"study_design_scores_gemma":[0.001113677,0.00008941839,0.9705344,0.0000619472,0.000005535932,0.000008643244,0.0004027146,0.004740093,0.000547709,0.01072206,0.01154721,0.000226541],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9589913,0.0008784543,0.01151606,0.0001518333,0.00111252,0.0002752692,0.00003032965,0.00008026232,0.02696391],"genre_scores_gemma":[0.8926264,0.00001377235,0.106965,0.00007614618,0.00009641025,0.00001293925,0.00001151637,0.000009823052,0.0001879736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1964666,"threshold_uncertainty_score":0.948692,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2037416776","doi":"10.3758/brm.42.3.847","title":"A general framework and an R package for the detection of dichotomous differential item functioning","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":288,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Differential item functioning; R package; Set (abstract data type); Differential (mechanical device); Psychometrics; Item response theory; Computer science; Psychology; Cognitive psychology; Artificial intelligence; Developmental psychology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.7240286491433732,"gpt":0.6707538589519908,"spread":0.05327479019138237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04173879,0.0001276265,0.0003022995,0.0006411377,0.0008020937,0.0004097341,0.0008099093,0.0002088637,0.0002063638],"category_scores_gemma":[0.2013333,0.00007432065,0.0001255226,0.001874959,0.0004516749,0.0001883227,0.0002765824,0.00103471,0.0000017504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001536208,"about_ca_system_score_gemma":0.00004569809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001859585,"about_ca_topic_score_gemma":0.00005244689,"domain_scores_codex":[0.9936786,0.003488145,0.0005347093,0.00056839,0.001264056,0.0004660657],"domain_scores_gemma":[0.8626857,0.134658,0.0002576457,0.001217753,0.0009541544,0.0002267364],"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":[0.00005341176,0.00004020192,0.01735636,0.00000309087,0.000004898132,6.91855e-7,0.0001571218,5.581072e-7,0.3598624,0.0004127407,0.00001766914,0.6220908],"study_design_scores_gemma":[0.0004706751,0.000804253,0.8548586,0.00001221796,0.00004442828,0.0000293316,0.001573878,0.007421458,0.08832646,0.04297403,0.003298538,0.0001861319],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5136876,0.0001000204,0.4848782,0.00004357234,0.0008415768,0.0003779292,0.00000662176,0.00001883984,0.00004565116],"genre_scores_gemma":[0.6185635,0.00001293465,0.3806398,0.000006831375,0.0003366646,0.0002148166,7.247385e-7,0.00001318176,0.0002115974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8375022,"threshold_uncertainty_score":0.9867316,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089944619","doi":"10.1080/00224540009600503","title":"Confirmatory Factor Analyses of the Full and Short Versions of the Marlowe-Crowne Social Desirability Scale","year":2000,"lang":"en","type":"article","venue":"The Journal of Social Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":277,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Lethbridge","funders":"","keywords":"Scale (ratio); Confirmatory factor analysis; Short Forms; Psychology; Social desirability; Full scale; Social psychology; Statistics; Econometrics; Structural equation modeling; Computer science; Mathematics; Clinical psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.5809835667547556,"gpt":0.540996276488838,"spread":0.03998729026591763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00769594,0.0001136084,0.0005528273,0.0001240533,0.0005472947,0.00001924123,0.001444631,0.0001446146,0.000783182],"category_scores_gemma":[0.007268728,0.00004748572,0.0004083397,0.001196245,0.001645054,0.0000843515,0.0001372194,0.0004352132,0.000002602683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002231883,"about_ca_system_score_gemma":0.0000848408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003368257,"about_ca_topic_score_gemma":0.00001445748,"domain_scores_codex":[0.9950114,0.002496781,0.001332518,0.0001520469,0.0008132125,0.0001940127],"domain_scores_gemma":[0.991145,0.006478026,0.001593304,0.0003773145,0.0003607083,0.00004570525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001760513,0.0005849162,0.4845383,0.00002546713,0.000452133,0.000002882428,0.02158355,0.00004644587,0.1251193,0.0002200339,0.03079876,0.3348678],"study_design_scores_gemma":[0.0003516807,0.00009619832,0.9843233,0.000007513537,0.00007528318,0.00003706436,0.001889086,0.000005870098,0.0008063347,0.01112346,0.001232439,0.0000518238],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913719,0.0002703803,0.0002579487,0.004200159,0.0006609429,0.0001024814,0.00001553233,0.000003216787,0.003117393],"genre_scores_gemma":[0.9990054,0.00005783134,0.0003623503,0.0002958884,0.0001688707,3.589336e-7,4.98393e-8,0.000005113171,0.0001040807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.499785,"threshold_uncertainty_score":0.8701872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089004370","doi":"10.1080/00273171.2014.911075","title":"Assessing Approximate Fit in Categorical Data Analysis","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":276,"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":"Mathematics; Statistics; Categorical variable; Goodness of fit; Bivariate analysis; Statistic; Ordinal data; Mean squared error; Multivariate statistics; Item response theory; Cutoff; Econometrics; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.959382260741685,"gpt":0.7182746444274037,"spread":0.2411076163142812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06789506,0.00019378,0.0006847961,0.003695402,0.0003645494,0.001568493,0.003915066,0.0001948321,0.0004574907],"category_scores_gemma":[0.1353053,0.0001387953,0.0001248472,0.01809684,0.0002166894,0.001025268,0.00237268,0.0009957455,0.0001513954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381085,"about_ca_system_score_gemma":0.0001155104,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00768937,"about_ca_topic_score_gemma":0.0002825699,"domain_scores_codex":[0.9877265,0.005116583,0.001031515,0.001591223,0.003483151,0.001051025],"domain_scores_gemma":[0.9401888,0.05426135,0.000291132,0.004070431,0.0008200483,0.0003682886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003253505,0.0003797802,0.5946727,0.000003554449,0.00002128683,0.00005240723,0.0002381581,0.0003247374,0.001274263,0.0006026227,0.0003631779,0.4020348],"study_design_scores_gemma":[0.0004344537,0.00006212924,0.6948122,0.00000672899,0.00003637165,0.000003376153,0.0008846339,0.2945472,0.00005222311,0.008106944,0.0008746418,0.0001790714],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8743252,0.00005339425,0.120998,0.0003043569,0.0002561329,0.000262758,0.00001853803,0.000063156,0.003718504],"genre_scores_gemma":[0.9463621,0.000004795175,0.05303899,0.00001360396,0.00009085159,0.00002121219,0.00003299737,0.00001622875,0.0004191595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4018557,"threshold_uncertainty_score":0.999468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128090963","doi":"10.1080/00223980009598225","title":"Common Method Variance and Specification Errors: A Practical Approach to Detection","year":2000,"lang":"en","type":"article","venue":"The Journal of Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":274,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"LISREL; Variance (accounting); Bivariate analysis; Psychology; Social desirability; Econometrics; Construct (python library); Common-method variance; Structural equation modeling; Specification; Point (geometry); Statistics; Correlation; Variable (mathematics); Social psychology; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5461551079132649,"gpt":0.5639502931705979,"spread":0.01779518525733292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02039809,0.00008812518,0.0002950447,0.0003172632,0.0001324899,0.00006194514,0.0005419509,0.00008443445,0.0002261398],"category_scores_gemma":[0.01407491,0.00004844493,0.0000548958,0.001326518,0.00008536795,0.0001748472,0.00003337755,0.0003999706,0.00005053737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001577018,"about_ca_system_score_gemma":0.00001540385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001107811,"about_ca_topic_score_gemma":0.000002630824,"domain_scores_codex":[0.9957063,0.002659142,0.0007438071,0.0002162017,0.0004959443,0.0001785835],"domain_scores_gemma":[0.9858345,0.01288974,0.0005371762,0.0004494114,0.0001797963,0.0001094104],"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":[0.0006054457,0.0001111965,0.0006805756,0.000001074434,0.00001988539,0.000003773536,0.0007762831,0.0002630278,0.003579527,0.0004330271,0.00540166,0.9881245],"study_design_scores_gemma":[0.001436365,0.001666671,0.5798497,0.00002022402,0.00009772756,0.0134384,0.002235561,0.004114334,0.0005920613,0.1750382,0.2212329,0.0002779276],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1837659,0.0001997926,0.7880756,0.007297485,0.0004443371,0.000102269,6.010583e-7,0.000008329318,0.0201057],"genre_scores_gemma":[0.6077578,0.0001395011,0.390294,0.0012416,0.0002846646,0.000001895524,6.515943e-8,0.00000678162,0.0002736722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9878466,"threshold_uncertainty_score":0.99423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089262464","doi":"10.1007/s11205-010-9682-8","title":"Assessing the Unidimensionality of Psychological Scales: Using Multiple Criteria from Factor Analysis","year":2010,"lang":"en","type":"article","venue":"Social Indicators Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":252,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Item response theory; Factor analysis; Sample (material); Sample size determination; Scale (ratio); Psychology; Mathematics; Curse of dimensionality; Econometrics; Quality of Life Research; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.8500569143669792,"gpt":0.7003382737954648,"spread":0.1497186405715144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02352032,0.0001375101,0.000534253,0.001536642,0.00129226,0.0005285779,0.00178412,0.0003158156,0.001722584],"category_scores_gemma":[0.1490379,0.0000785664,0.0003450426,0.01374864,0.001634682,0.000237782,0.0005728418,0.001272524,0.00001932556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000446804,"about_ca_system_score_gemma":0.0001148821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000790672,"about_ca_topic_score_gemma":0.0001508379,"domain_scores_codex":[0.9901653,0.004496384,0.0008385339,0.0006978926,0.003268215,0.0005337092],"domain_scores_gemma":[0.9222589,0.07560123,0.000457689,0.0008251147,0.0006954729,0.0001616697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004110009,0.0001423911,0.9253888,0.000001724244,0.0001174212,0.000003263153,0.0008616053,0.00000330196,0.02803477,0.0003279939,0.0005023212,0.04457531],"study_design_scores_gemma":[0.0001446059,0.00003768274,0.9765896,0.000002906943,0.00002478876,5.496807e-7,0.002929464,0.001799189,0.0008683396,0.01707608,0.0004330938,0.00009375766],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954081,0.00005402369,0.002293985,0.0004609256,0.0004793115,0.0001572643,0.00008031389,0.00002389505,0.0010422],"genre_scores_gemma":[0.9885451,0.00000281829,0.01105449,0.00004415399,0.0003097643,0.000005410774,0.000005838072,0.000008925828,0.00002347615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1255176,"threshold_uncertainty_score":0.99919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005967696","doi":"10.1080/00273171.2014.933697","title":"Adjusting Incremental Fit Indices for Nonnormality","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":223,"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 Ottawa","funders":"","keywords":"Statistics; Mathematics; Index (typography); Structural equation modeling; Population; Goodness of fit; Econometrics; Value (mathematics); Sample (material); Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.9278926090737645,"gpt":0.6852634534042872,"spread":0.2426291556694773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05641448,0.0001873673,0.0004105004,0.0009965936,0.00093226,0.000591249,0.001634173,0.0001723155,0.0004546859],"category_scores_gemma":[0.180586,0.0001377169,0.0001582609,0.002561103,0.0002389319,0.0004064249,0.0008081178,0.000584781,0.0001521226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001159992,"about_ca_system_score_gemma":0.00008661178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001932621,"about_ca_topic_score_gemma":0.0000725313,"domain_scores_codex":[0.9920772,0.002280232,0.0008729646,0.0008892365,0.00283668,0.001043633],"domain_scores_gemma":[0.9223975,0.07431196,0.0003666044,0.001053583,0.001512047,0.0003582792],"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":[0.000257606,0.000321476,0.294523,0.00001676729,0.000009366798,0.000005221196,0.0005909563,0.00003461782,0.01142213,0.0009836545,0.003255972,0.6885792],"study_design_scores_gemma":[0.002122472,0.0009794842,0.9219866,0.00004903533,0.00001957337,0.000006870419,0.002832764,0.02035731,0.004262455,0.0135643,0.0333947,0.0004243928],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755841,0.00003838995,0.01869609,0.0004438318,0.0005689469,0.0006837728,0.00004660296,0.00008300533,0.003855187],"genre_scores_gemma":[0.9538386,0.000002004198,0.04469671,0.00005914607,0.000302807,0.0001170745,0.000009207622,0.00002050412,0.0009538931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6881548,"threshold_uncertainty_score":0.9716198,"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":"medium"}],"label_agreement":"agree"},{"id":"W1991374387","doi":"10.1080/00273171.2012.715252","title":"An Investigation of the Sample Performance of Two Nonnormality Corrections for RMSEA","year":2012,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":221,"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; Statistics; Mathematics; Goodness of fit; Sample (material); Sample size determination; Population; Econometrics; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.873633224993975,"gpt":0.6517804000643616,"spread":0.2218528249296134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0241766,0.00008742293,0.0002328704,0.0004126316,0.0004074126,0.00005099568,0.0009480464,0.00007402121,0.00009574462],"category_scores_gemma":[0.03919747,0.00005280105,0.000102536,0.002830484,0.0003860438,0.0005126517,0.0002295821,0.0002797187,0.000004323742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005367625,"about_ca_system_score_gemma":0.0001284078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003479877,"about_ca_topic_score_gemma":0.00006014653,"domain_scores_codex":[0.9956516,0.001528303,0.0006303616,0.0002588848,0.001470815,0.0004600253],"domain_scores_gemma":[0.9750326,0.0221137,0.000333796,0.0008512459,0.001511491,0.0001571478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006543299,0.0001456425,0.931098,0.000007782463,0.000002271338,1.733228e-8,0.0008270971,0.0000577459,0.0303112,0.000361832,0.00006175139,0.03706123],"study_design_scores_gemma":[0.0003405302,0.0002564165,0.9584437,0.00001484701,0.000007937462,6.276337e-7,0.0007429856,0.006556606,0.03131136,0.002125281,0.0001384415,0.00006124989],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992302,0.00002016519,0.006285017,0.00006183633,0.0006472869,0.0004929941,0.00008572871,0.00001314088,0.00009180956],"genre_scores_gemma":[0.9666016,0.000001959836,0.03313487,0.000005552337,0.00008496102,0.00005261032,0.000005165366,0.000008039115,0.0001052542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03699997,"threshold_uncertainty_score":0.9688958,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159759566","doi":"10.1177/1094428114529165","title":"Reflections on Partial Least Squares Path Modeling","year":2014,"lang":"en","type":"article","venue":"Organizational Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Safety Canada","funders":"","keywords":"Structural equation modeling; Partial least squares regression; Econometrics; Path analysis (statistics); Path (computing); Null hypothesis; Sample (material); Computer science; Key (lock); Management science; Data mining; Mathematics; Machine learning; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.8883201917735504,"gpt":0.7223769447242043,"spread":0.165943247049346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06253579,0.0001467375,0.0002883489,0.001282149,0.00106095,0.0004673812,0.001035656,0.0001277641,0.002042453],"category_scores_gemma":[0.6258862,0.0001081489,0.00007870325,0.008319179,0.0001600108,0.0001984145,0.0003344943,0.0006041473,0.0004933419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009993977,"about_ca_system_score_gemma":0.0002029834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003713503,"about_ca_topic_score_gemma":0.000003486795,"domain_scores_codex":[0.9847786,0.009993893,0.0006348278,0.0007764727,0.003240185,0.0005759626],"domain_scores_gemma":[0.8996348,0.0960344,0.0001473845,0.0009307622,0.002939647,0.0003129803],"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":[0.0001006035,0.0002257445,0.005737127,0.000008848325,0.00003064167,0.000003838862,0.0005542514,0.04064928,0.01221176,0.4774978,0.009631028,0.4533491],"study_design_scores_gemma":[0.0003097136,0.0003249111,0.0042274,0.00002379658,0.000004644241,0.00001128883,0.0007926367,0.3703606,0.002296014,0.5735325,0.04788698,0.0002295091],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007150548,0.00004684508,0.9206955,0.001904125,0.0005489531,0.000135377,0.000005469632,0.00008752642,0.06942562],"genre_scores_gemma":[0.5071223,0.00001539478,0.4907097,0.000205224,0.0005935716,0.00001463822,0.000006506049,0.00002599218,0.001306646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5633504,"threshold_uncertainty_score":0.9988698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2760364374","doi":"10.3102/0034654317726529","title":"Developing, Analyzing, and Using Distractors for Multiple-Choice Tests in Education: A Comprehensive Review","year":2017,"lang":"en","type":"review","venue":"Review of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":217,"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":"Task (project management); Quality (philosophy); Process (computing); Psychology; Cognitive psychology; Multiple choice; Computer science; Applied psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.9466681700442642,"gpt":0.7483343693634743,"spread":0.1983338006807899,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02083228,0.0003952302,0.003366808,0.001666955,0.0003738725,0.000191434,0.002159496,0.0001890464,0.0003463821],"category_scores_gemma":[0.7840396,0.0002798506,0.0005490006,0.00397793,0.0003703116,0.0002539061,0.0004563629,0.0006873726,0.00002744036],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004369001,"about_ca_system_score_gemma":0.01025622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001951966,"about_ca_topic_score_gemma":0.00002684071,"domain_scores_codex":[0.9911433,0.00263995,0.002829629,0.001111194,0.001743468,0.000532414],"domain_scores_gemma":[0.5552396,0.4339007,0.003404998,0.00199499,0.005166262,0.0002933787],"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":[8.310841e-7,0.00006277508,0.002820321,0.244022,0.00002502783,1.784985e-7,0.000004707653,2.929615e-8,5.34082e-8,0.0005074039,0.009549277,0.7430074],"study_design_scores_gemma":[0.00004294793,0.00001620459,0.00431738,0.3530236,0.00008329793,0.0000227355,0.00001248145,0.000002338651,2.464538e-8,0.001217646,0.6410951,0.0001663086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002014519,0.9935573,0.0000281169,0.001664191,0.0005952428,0.003529699,0.00007355806,0.000002952251,0.0005288105],"genre_scores_gemma":[0.000002039081,0.9802318,0.01797561,0.0001514336,0.0003283142,0.0006243188,0.0001061613,0.00002995994,0.0005504253],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7632073,"threshold_uncertainty_score":0.9999654,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2142004159","doi":"10.3899/jrheum.130813","title":"Item Response Theory, Computerized Adaptive Testing, and PROMIS: Assessment of Physical Function","year":2013,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":208,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Computerized adaptive testing; Patient-Reported Outcomes Measurement Information System; Item response theory; Item bank; CLARITY; Medicine; Reliability (semiconductor); Standardization; Perspective (graphical); Short Forms; Construct (python library); Applied psychology; Function (biology); Psychometrics; Computer science; Psychology; Clinical psychology; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2335860100349148,"gpt":0.4218876205134344,"spread":0.1883016104785196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0154809,0.0001031569,0.0005673713,0.000310514,0.0001074517,0.0000434645,0.0005097551,0.00004959184,0.00005912826],"category_scores_gemma":[0.05904254,0.00004979067,0.00007697244,0.0006533259,0.0002940212,0.0001681188,0.000153304,0.0002538413,0.000005612734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001464191,"about_ca_system_score_gemma":0.00009269891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003963614,"about_ca_topic_score_gemma":5.606864e-7,"domain_scores_codex":[0.993971,0.004418541,0.0008096184,0.000132092,0.0005059398,0.0001628118],"domain_scores_gemma":[0.8501359,0.147348,0.001524179,0.0002502488,0.00067645,0.00006528357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004867864,0.0002960891,0.5812816,0.00002271852,0.0003053717,0.000005927265,0.002366733,0.0003802337,0.02271704,0.01072782,0.003307013,0.3737216],"study_design_scores_gemma":[0.001060213,0.002442164,0.7784851,0.00008228234,0.00004281864,0.001593102,0.001927994,0.0320612,0.00008814554,0.1820283,0.0001006917,0.00008792774],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9041982,0.0001219068,0.0945632,0.0003993905,0.000283187,0.0001252263,7.284783e-7,0.000007852213,0.0003003129],"genre_scores_gemma":[0.9639931,0.0000150743,0.03589916,0.00003888801,0.0000116704,0.000001986652,2.905115e-8,0.000005012017,0.00003509649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3736337,"threshold_uncertainty_score":0.9488835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073056556","doi":"10.1016/j.jclinepi.2005.09.005","title":"“Precision” and “Accuracy”: Two Terms That Are Neither","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Baycrest Hospital; McMaster University; University of Toronto","funders":"","keywords":"Reliability (semiconductor); Conceptualization; Inter-rater reliability; Scale (ratio); Test (biology); Computer science; Synonym (taxonomy); Validity; Criterion validity; Psychology; Process (computing); Cognitive psychology; Psychometrics; Artificial intelligence; Statistics; Mathematics; Rating scale; Construct validity; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.9346514191644626,"gpt":0.7216304917470712,"spread":0.2130209274173914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2454556,0.0005666703,0.01731947,0.001125968,0.0001216012,0.0001068938,0.002515462,0.00126043,0.00029993],"category_scores_gemma":[0.9239976,0.0002734778,0.003453757,0.001174284,0.000592939,0.0002423109,0.0005891158,0.003184811,0.0001010976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003854253,"about_ca_system_score_gemma":0.0002926205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001788585,"about_ca_topic_score_gemma":0.000006142411,"domain_scores_codex":[0.9344106,0.04206487,0.02042772,0.001182595,0.001182417,0.0007318214],"domain_scores_gemma":[0.1495854,0.8122269,0.036054,0.001120459,0.0004868119,0.0005264995],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002584851,0.00005045498,0.06419694,0.0001452878,0.0001051304,0.00006961007,0.000002108507,0.000006875588,4.056935e-9,0.0001823184,0.04666371,0.8885517],"study_design_scores_gemma":[0.0004751779,0.0002590205,0.03342006,0.002617276,0.0002631297,0.0008479923,0.00001574924,0.00003177483,7.143739e-9,0.08696296,0.8748732,0.0002336323],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002084478,0.9806215,0.009252972,0.001239733,0.0060287,0.0002293562,0.00001965283,0.00001455929,0.002385144],"genre_scores_gemma":[0.00003590116,0.9553931,0.03956634,0.001164817,0.002940106,0.000003601595,0.000001644241,0.00003358386,0.0008609406],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8883181,"threshold_uncertainty_score":0.9999717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2431662475","doi":"10.1371/journal.pone.0157795","title":"Examining the Effect of Reverse Worded Items on the Factor Structure of the Need for Cognition Scale","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"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":"Psychology; Confirmatory factor analysis; Scale (ratio); Covariance; Factor analysis; Scale factor (cosmology); Factor (programming language); Cognition; Statistics; Psychometrics; Structural equation modeling; Developmental psychology; Mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.5134880551927866,"gpt":0.3872550404907291,"spread":0.1262330147020576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00295489,0.00008888976,0.0002620775,0.0000882649,0.0001387507,0.00002563201,0.0006718894,0.0000544146,0.0001669982],"category_scores_gemma":[0.1144728,0.0000249226,0.00008978553,0.0008098178,0.0001549338,0.00005136473,0.00008516367,0.00009465856,0.000004128884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008881929,"about_ca_system_score_gemma":0.00001130083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006126315,"about_ca_topic_score_gemma":0.000003425306,"domain_scores_codex":[0.9977569,0.0007931471,0.0003365054,0.0001916037,0.000782854,0.0001389868],"domain_scores_gemma":[0.9039336,0.09490129,0.0004288244,0.0005450204,0.0001724135,0.00001883532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002535573,0.00006345341,0.09818943,0.00003121179,0.00009977532,8.098268e-8,0.0003990811,0.000003806483,0.8369696,0.00009386188,0.001040566,0.06285558],"study_design_scores_gemma":[0.000994087,0.0006974579,0.1699155,0.0004691716,0.00009447522,6.353125e-7,0.0006098493,0.0001819316,0.8172666,0.009574395,0.00010227,0.0000936535],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970346,0.00003024631,0.0005943436,0.0009898776,0.0001761792,0.0006082615,0.00008655232,0.00001022229,0.0004697094],"genre_scores_gemma":[0.9985786,0.000004089968,0.000949436,0.00009311851,0.00006808597,0.00001391361,3.506485e-7,0.000006273149,0.000286126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1115179,"threshold_uncertainty_score":0.8929864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2364328457","doi":"10.1007/978-3-319-07794-9","title":"Validity and Validation in Social, Behavioral, and Health Sciences","year":2014,"lang":"en","type":"book","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Behavioural sciences; Psychology; Data science; Computer science; Psychotherapist","retraction":null,"screen_n_in":null,"score":{"opus":0.8242681565438117,"gpt":0.6357213862676169,"spread":0.1885467702761948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.05942034,0.0002661798,0.0008978146,0.0036218,0.003339972,0.001096003,0.0009567006,0.0005170724,0.0001120589],"category_scores_gemma":[0.01517,0.0002207094,0.00008727657,0.003649401,0.004319981,0.0004543143,0.000834883,0.001204162,0.00001639614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000309782,"about_ca_system_score_gemma":0.00145419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003206372,"about_ca_topic_score_gemma":0.0002034871,"domain_scores_codex":[0.9899892,0.003710517,0.000922724,0.001076957,0.003456519,0.0008440482],"domain_scores_gemma":[0.9882886,0.0101836,0.0007434877,0.0002629685,0.0002974275,0.0002239412],"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":[0.00005494879,0.0001182803,0.151098,0.0002245842,0.000018608,0.00001386099,0.01064356,2.879084e-7,0.00001163871,0.06138661,0.4271952,0.3492344],"study_design_scores_gemma":[0.0003483068,0.0008745419,0.1610985,0.0001046116,0.00000870614,0.000007071831,0.005416601,0.000004920154,0.00002337714,0.5843072,0.247341,0.0004651004],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6481026,0.00424305,0.0002158483,0.02564727,0.001249488,0.0024825,0.0002674751,0.0002281287,0.3175637],"genre_scores_gemma":[0.6803824,0.005469308,0.005948042,0.0005610156,0.004195553,0.0002417545,0.0001245869,0.0001643676,0.302913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5229206,"threshold_uncertainty_score":0.9999409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170853093","doi":"10.1111/j.1745-3992.2003.tb00136.x","title":"Using Multidimensional Item Response Theory to Evaluate Educational and Psychological Tests","year":2003,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":192,"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":"Item response theory; Test (biology); Measure (data warehouse); Ninth; Computer science; Process (computing); Meaning (existential); Multidimensional analysis; Psychology; Mathematics education; Psychometrics; Management science; Econometrics; Mathematics; Data mining; Developmental psychology; Psychotherapist","retraction":null,"screen_n_in":null,"score":{"opus":0.8128600435609681,"gpt":0.6116511900217015,"spread":0.2012088535392665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05058032,0.0001947472,0.0002388297,0.0003752727,0.0004601169,0.0002583107,0.000209834,0.0000757461,0.001204988],"category_scores_gemma":[0.6463413,0.0001460503,0.0000420616,0.0009438032,0.0001126364,0.0004408504,0.00007613112,0.000183248,0.00009124365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009356135,"about_ca_system_score_gemma":0.0003446095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002454763,"about_ca_topic_score_gemma":0.000001745588,"domain_scores_codex":[0.9904012,0.00588029,0.0005715716,0.0007551193,0.002108174,0.000283652],"domain_scores_gemma":[0.8754453,0.1217538,0.0003417781,0.0004156052,0.00171895,0.0003245768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0105423,0.005656771,0.2253975,0.00004733429,0.0003970318,0.00001585365,0.008179787,0.0007752535,0.07944028,0.4385619,0.08696332,0.1440227],"study_design_scores_gemma":[0.0005090386,0.0002813728,0.6620944,0.00005153928,0.00005219252,0.0004490313,0.002137011,0.00009915711,0.0001408088,0.1328589,0.2010121,0.0003144805],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.913103,0.007822783,0.003829669,0.06630247,0.001771152,0.0004524864,0.000007636509,0.00002046664,0.006690371],"genre_scores_gemma":[0.6327977,0.00006669179,0.3634975,0.002033121,0.000256745,0.00003090728,0.000001416599,0.00001156304,0.001304368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.595761,"threshold_uncertainty_score":0.9997081,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2768881033","doi":"10.1037/ipp0000042","title":"Adaptation of Assessment Scales in Cross-National Research: Issues, Guidelines, and Caveats","year":2015,"lang":"en","type":"article","venue":"International Perspectives in Psychology","topic":"Psychometric Methodologies and Testing","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 Ottawa","funders":"","keywords":"Equivalence (formal languages); Criticism; Scale (ratio); Set (abstract data type); Adaptation (eye); Psychology; Computer science; Management science; Data science; Political science; Mathematics; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.9019762010793025,"gpt":0.722889276717478,"spread":0.1790869243618245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01904705,0.00009566304,0.0002426453,0.002144376,0.00003200044,0.00007930789,0.0006726439,0.0001046716,0.00008596473],"category_scores_gemma":[0.1247672,0.00008162468,0.00003465733,0.001510921,0.0004535771,0.0002854281,0.000184506,0.000302314,0.00001138011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003007961,"about_ca_system_score_gemma":0.000154799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005339621,"about_ca_topic_score_gemma":0.0004113934,"domain_scores_codex":[0.9951218,0.0008838924,0.0008989655,0.0006038076,0.00228421,0.00020735],"domain_scores_gemma":[0.9884564,0.00640429,0.0002330663,0.0002396867,0.004602537,0.00006402277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001734873,0.0002835913,0.8416911,0.000001644205,0.00001783198,0.00001792493,0.002700463,0.002713425,0.0001595088,0.08269278,0.007728415,0.0618198],"study_design_scores_gemma":[0.0008039342,0.00008198371,0.6282693,0.00001427182,3.322325e-7,0.00001843681,0.006607903,0.007487283,0.000004744174,0.3519403,0.004715356,0.00005618902],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8647325,0.004300357,0.0113185,0.01474069,0.001573292,0.0002412769,0.00003024328,0.00001869187,0.1030445],"genre_scores_gemma":[0.9411087,0.0005013461,0.05785568,0.0001091684,0.0001628281,0.00001777159,0.000003159583,0.000006172701,0.0002351879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2692476,"threshold_uncertainty_score":0.8826053,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2166319027","doi":"10.1177/070674370605100507","title":"Building a Better Model: An Introduction to Structural Equation Modelling","year":2006,"lang":"en","type":"article","venue":"The Canadian Journal of Psychiatry","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":183,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Structural equation modeling; Latent variable; Confirmatory factor analysis; Path analysis (statistics); Exploratory factor analysis; Path coefficient; A priori and a posteriori; Econometrics; Latent variable model; Variable (mathematics); Scale (ratio); Statistics; Psychology; Factor analysis; Variables; Construct (python library); Path (computing); Psychometrics; Mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2531690852912864,"gpt":0.3971817068862711,"spread":0.1440126215949847,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005708815,0.0001098729,0.0001974894,0.0008902065,0.0004931244,0.0004141477,0.0008283066,0.00006050027,0.00006746744],"category_scores_gemma":[0.00244294,0.00006824152,0.0001012214,0.001216563,0.00004986589,0.0004133783,0.00001480231,0.0002982177,0.000005859803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001116507,"about_ca_system_score_gemma":0.0006389408,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006514597,"about_ca_topic_score_gemma":0.04470326,"domain_scores_codex":[0.99778,0.0002788992,0.0007471875,0.0002229164,0.0006621503,0.0003088168],"domain_scores_gemma":[0.9977983,0.0006204514,0.0004883633,0.0003740219,0.0004132142,0.0003056451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001389327,0.000002751406,0.01772375,8.259983e-7,0.000006137853,0.000001300179,0.0001530468,0.923503,0.00006768,0.03873902,0.008825503,0.01096311],"study_design_scores_gemma":[0.00009719376,0.000057217,0.005429298,0.000006754011,0.00001147139,0.0000677787,0.0001565953,0.319027,0.00001862028,0.6742483,0.0007981583,0.00008157828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5284681,0.0001268514,0.4371188,0.0317776,0.002312512,0.00004995254,0.000002709303,0.000004961975,0.000138499],"genre_scores_gemma":[0.6180162,2.234688e-7,0.3788455,0.0004089343,0.002678073,4.545993e-7,3.611378e-7,0.000007473672,0.00004272455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6355093,"threshold_uncertainty_score":0.9848165,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2240102487","doi":"10.1007/s12144-015-9404-0","title":"Using the Gamma Generalized Linear Model for Modeling Continuous, Skewed and Heteroscedastic Outcomes in Psychology","year":2016,"lang":"en","type":"article","venue":"Current Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":178,"is_retracted":false,"has_abstract":false,"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":"Homoscedasticity; Heteroscedasticity; Psychology; Normality; Econometrics; Outcome (game theory); Linear regression; Linear model; Generalized linear model; Variance (accounting); Statistics; General linear model; Range (aeronautics); Mathematics; Social psychology; Mathematical economics; Engineering; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.7652380167565765,"gpt":0.5944211459043176,"spread":0.1708168708522589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00503241,0.0002878399,0.0007622971,0.0006362856,0.0001782613,0.00006579859,0.000947353,0.0001920782,0.00003251516],"category_scores_gemma":[0.02040351,0.000143954,0.000178897,0.0006904498,0.0002771993,0.0001572009,0.0001799329,0.0002409606,0.00001127469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000247985,"about_ca_system_score_gemma":0.00003331308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006291617,"about_ca_topic_score_gemma":0.00001156537,"domain_scores_codex":[0.9959236,0.0007338884,0.001196179,0.001084163,0.0003702295,0.0006918928],"domain_scores_gemma":[0.9890738,0.009243663,0.0003937285,0.000949559,0.0002196297,0.0001196612],"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":[0.0005836022,0.0003719238,0.2450345,0.00001918381,0.00006139676,0.000005060865,0.000538003,0.009254752,0.01194266,0.002958482,0.002489709,0.7267407],"study_design_scores_gemma":[0.00368453,0.0001068844,0.008147021,0.00003802588,0.00001952997,0.00003220009,0.00003926379,0.8601441,0.000009515151,0.1254977,0.002013007,0.0002681761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4154688,0.0009342447,0.57964,0.001777326,0.001756326,0.0003143248,0.00001956436,0.00002897867,0.00006046959],"genre_scores_gemma":[0.9209019,0.0004433142,0.07697678,0.001219237,0.000199361,0.00009220515,0.000001831572,0.00003335583,0.0001319878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8508893,"threshold_uncertainty_score":0.987848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077199939","doi":"10.1007/s11336-009-9123-2","title":"When Cognitive Diagnosis Meets Computerized Adaptive Testing: CD-CAT","year":2009,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":176,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Heuristics; Computerized adaptive testing; Entropy (arrow of time); Information theory; Item response theory; Computer science; Selection (genetic algorithm); Context (archaeology); Latent class model; Kullback–Leibler divergence; Artificial intelligence; Mathematics; Machine learning; Algorithm; Statistics; Mathematical optimization; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.5850420918789638,"gpt":0.4702225324092145,"spread":0.1148195594697494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00696086,0.0004704912,0.001001172,0.003126923,0.0003822092,0.0005779339,0.001792068,0.0002177229,0.0008932228],"category_scores_gemma":[0.2243391,0.0003622927,0.000319547,0.01483492,0.0001867425,0.0004871719,0.0002063296,0.0003519822,0.0006538735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008092784,"about_ca_system_score_gemma":0.00007105448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004681036,"about_ca_topic_score_gemma":0.00000350607,"domain_scores_codex":[0.9930904,0.000940679,0.001340946,0.001521268,0.002212974,0.000893748],"domain_scores_gemma":[0.8747033,0.1215869,0.0009008803,0.001066275,0.001255957,0.0004865816],"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":[0.0001540821,0.000317986,0.07325771,0.000002151887,0.00004723563,0.00002446188,0.0003301675,0.000008981793,0.000230494,0.0004212752,0.02154805,0.9036574],"study_design_scores_gemma":[0.002983809,0.001799309,0.8595602,0.0001613731,0.00006098154,0.00005728836,0.0008752619,0.00207942,0.0004654514,0.1046447,0.02645914,0.0008530609],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6911383,0.003700541,0.1876476,0.006505352,0.004731831,0.001514839,0.0001218348,0.000922212,0.1037174],"genre_scores_gemma":[0.7708109,0.00008731737,0.226355,0.001782506,0.0003877762,0.00004414613,0.000004978303,0.00002344086,0.0005038718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9028043,"threshold_uncertainty_score":0.9998829,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135663628","doi":"10.1177/0265532208097336","title":"Cognitive diagnostic assessment of L2 reading comprehension ability: Validity arguments for Fusion Model application to <i>LanguEdge</i> assessment","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":175,"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":"","keywords":"Reading comprehension; Psychology; Cognition; Test (biology); Profiling (computer programming); Dependability; Comprehension; Reading (process); Cognitive psychology; Computer science; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.4824119830634888,"gpt":0.5159648486704076,"spread":0.03355286560691884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005607481,0.000233323,0.000566214,0.0003597184,0.0004046212,0.00006082846,0.000509802,0.00009164836,0.00002018725],"category_scores_gemma":[0.1339034,0.0001909338,0.0001271029,0.001691146,0.00007605331,0.0001761379,0.0003434014,0.0001987398,0.000007722714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000126566,"about_ca_system_score_gemma":0.0001264369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00012942,"about_ca_topic_score_gemma":0.000006228173,"domain_scores_codex":[0.9961553,0.0004159203,0.001004955,0.0008236492,0.001181548,0.0004186427],"domain_scores_gemma":[0.9124872,0.0851215,0.000710158,0.0006375588,0.0008672672,0.0001762872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003764888,0.0003782486,0.6663653,0.00008788145,0.00002349876,0.0000170198,0.002140289,0.01127237,0.1008787,0.00018096,0.0006185359,0.2179995],"study_design_scores_gemma":[0.0009548515,0.0003929524,0.4863092,0.000242554,0.00005246457,0.00002515564,0.002254783,0.501873,0.003340098,0.00416316,0.00004141528,0.0003504124],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5328215,0.00002596287,0.4643598,0.00004385342,0.0001190898,0.0007316874,0.00004269867,0.00007494368,0.001780404],"genre_scores_gemma":[0.6565592,0.000003071366,0.342977,0.0001693233,0.0000724407,0.0001264413,0.0000228743,0.00001553337,0.00005407738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4906006,"threshold_uncertainty_score":0.873392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036831393","doi":"10.1177/0013164411409929","title":"Difference Scores From the Point of View of Reliability and Repeated-Measures ANOVA","year":2011,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":167,"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; Carleton University","funders":"","keywords":"Reliability (semiconductor); Repeated measures design; Significant difference; Statistics; Psychology; Analysis of variance; Point (geometry); Mean difference; Mathematics; Econometrics; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.7554307011056853,"gpt":0.4653795213841227,"spread":0.2900511797215626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007073482,0.0001113388,0.0002886284,0.000064427,0.00008802751,0.00002287375,0.0004211254,0.00005722675,0.000528036],"category_scores_gemma":[0.0388429,0.00005250085,0.00005942115,0.0004552616,0.0004226591,0.00004238106,0.00008314939,0.0001177334,0.000002807144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009741277,"about_ca_system_score_gemma":0.00003205881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002503211,"about_ca_topic_score_gemma":0.00001019118,"domain_scores_codex":[0.9971045,0.0006320529,0.0006785488,0.0004558421,0.001002931,0.0001261573],"domain_scores_gemma":[0.991173,0.007289697,0.0003483038,0.0004926272,0.0006169453,0.00007945801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001130944,0.0004731831,0.8170224,0.000008307061,0.00002119778,1.818328e-7,0.0007817693,5.04177e-7,0.00194558,0.002846088,0.001250037,0.1755377],"study_design_scores_gemma":[0.0001220334,0.0001576417,0.7876037,0.00003741558,0.000008047821,0.000002672828,0.0002196643,0.000002928116,0.0002745066,0.2112522,0.0002680671,0.00005118028],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886076,0.003997426,0.001219768,0.002071434,0.0004015245,0.000173817,0.0000154684,0.000007271472,0.003505657],"genre_scores_gemma":[0.9906312,0.0002093273,0.008859892,0.0002046245,0.00005185754,0.00001313172,8.029346e-7,0.000002249935,0.00002695076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2084061,"threshold_uncertainty_score":0.9692534,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039891070","doi":"10.3758/bf03192810","title":"SPSS and SAS programs for generalizability theory analyses","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":166,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Generalizability theory; Computer science; Psychology; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.9596454361401149,"gpt":0.7860996307771648,"spread":0.1735458053629501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14208,0.0001825408,0.0005040048,0.000957665,0.0005476671,0.0006173577,0.0009660035,0.0001501222,0.0001978226],"category_scores_gemma":[0.1550131,0.0001205858,0.0002161064,0.003689773,0.0007379934,0.0001900689,0.0004272142,0.0003488061,0.000007480075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005762881,"about_ca_system_score_gemma":0.00009150364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004167868,"about_ca_topic_score_gemma":0.00002452196,"domain_scores_codex":[0.9817787,0.01375893,0.0008415174,0.00104338,0.001731927,0.0008454998],"domain_scores_gemma":[0.895584,0.1014721,0.0001991768,0.001203579,0.001302272,0.0002388296],"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":[0.00005243669,0.0001650463,0.1143191,0.000008931846,0.000006531453,0.000004680217,0.00004862635,0.000003270379,0.01009315,0.003407137,0.001779799,0.8701112],"study_design_scores_gemma":[0.0004488422,0.0002892646,0.3840755,0.000007947978,0.00003018824,0.00001534323,0.0008686789,0.0005296164,0.007087787,0.5702252,0.03620155,0.0002200477],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5309699,0.001839213,0.4619292,0.000164093,0.0002697104,0.00120033,0.00001737733,0.00008295241,0.003527263],"genre_scores_gemma":[0.08487267,0.0000175854,0.9091967,0.00001970989,0.0002005632,0.0005560144,0.000006884723,0.00002165477,0.005108181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8698912,"threshold_uncertainty_score":0.8834092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2285879792","doi":"10.1080/00224499.2015.1137538","title":"A Methodological Review of Exploratory Factor Analysis in Sexuality Research: Used Practices, Best Practices, and Data Analysis Resources","year":2016,"lang":"en","type":"review","venue":"The Journal of Sex Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":161,"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":"","keywords":"Human sexuality; Exploratory factor analysis; Sample (material); Psychology; Exploratory research; Set (abstract data type); Best practice; Social psychology; Sociology; Psychometrics; Computer science; Clinical psychology; Social science; Political science; Gender studies","retraction":null,"screen_n_in":null,"score":{"opus":0.9901045164332588,"gpt":0.7777037022173531,"spread":0.2124008142159057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","open_science","research_integrity"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.687565,0.0004667397,0.007260805,0.0138648,0.0004407231,0.0005323901,0.01204148,0.0004958027,0.0008139887],"category_scores_gemma":[0.8970699,0.0001995391,0.0009221964,0.05776187,0.001598169,0.001298655,0.005191063,0.005545404,0.00002924954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002499024,"about_ca_system_score_gemma":0.001585588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007105875,"about_ca_topic_score_gemma":0.0002478301,"domain_scores_codex":[0.7270305,0.2506841,0.006471206,0.001603679,0.01305782,0.001152735],"domain_scores_gemma":[0.2216205,0.7460719,0.02094963,0.0059092,0.00495362,0.0004951837],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001440573,0.0002634556,0.004212082,0.007511061,0.004566512,0.00009191564,0.0007359001,0.000001513311,0.000006625043,0.0000103558,0.002482173,0.9799743],"study_design_scores_gemma":[0.0002346747,0.0004943092,0.001201932,0.01759904,0.005948533,0.0001039578,0.006315917,0.00004459356,0.000001303246,0.0009917235,0.9667926,0.0002714277],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001202248,0.9946719,0.0009134263,0.001605338,0.00009558643,0.0008245584,0.000220461,0.000006074389,0.0004603932],"genre_scores_gemma":[0.0001300063,0.9923494,0.006643302,0.00002671355,0.0003082259,0.00001544264,0.0000106191,0.00002599235,0.0004902744],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9797029,"threshold_uncertainty_score":0.9973122,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2811232920","doi":"10.1177/0272989x18776637","title":"Estimation of a Preference-Based Summary Score for the Patient-Reported Outcomes Measurement Information System: The PROMIS <sup>®</sup> -Preference (PROPr) Scoring System","year":2018,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"National Institutes of Health; National Cancer Institute; Social Sciences and Humanities Research Council of Canada; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Riksbankens Jubileumsfond","keywords":"Patient-Reported Outcomes Measurement Information System; Preference; Quality of life (healthcare); Medicine; Applied psychology; Physical therapy; Psychology; Statistics; Psychometrics; Clinical psychology; Computerized adaptive testing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4962130764892222,"gpt":0.4115047991206986,"spread":0.0847082773685236,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02767204,0.000288884,0.0006466564,0.0005532342,0.0008138057,0.0004066258,0.001873127,0.0002071509,0.0000797924],"category_scores_gemma":[0.2625647,0.0001285888,0.0002431735,0.002052554,0.00028657,0.0004683924,0.0003900581,0.0003096971,0.00003085026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002371209,"about_ca_system_score_gemma":0.000438075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004828454,"about_ca_topic_score_gemma":0.000009583979,"domain_scores_codex":[0.9879758,0.0007443507,0.002751016,0.0005412316,0.007527289,0.0004602872],"domain_scores_gemma":[0.9512224,0.04203887,0.002274705,0.001675063,0.002603748,0.0001852064],"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":[0.000246273,0.00002632223,0.01025982,0.0001502849,0.00004613601,0.000002053033,0.0007493252,0.004692215,0.00000628707,0.0007295905,0.0009729597,0.9821187],"study_design_scores_gemma":[0.001010985,0.0003162758,0.03371159,0.003461462,0.00007808475,0.00002208858,0.004441971,0.9540532,0.0001545309,0.001953017,0.0006077415,0.0001891124],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2422714,0.0001231287,0.7539767,0.0002486494,0.001106295,0.001438473,0.00001171803,0.0001106096,0.0007129926],"genre_scores_gemma":[0.9644021,0.000002656498,0.0351085,0.0001720172,0.0001150094,0.0001760967,0.000003108422,0.00001326921,0.000007186404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9819296,"threshold_uncertainty_score":0.9590631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157620189","doi":"10.3899/jrheum.110402","title":"The PROMIS of Better Outcome Assessment: Responsiveness, Floor and Ceiling Effects, and Internet Administration","year":2011,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institutes of Health; Stony Brook University; University of Pittsburgh; University of Washington; Northwestern University","keywords":"Ceiling effect; Medicine; Ceiling (cloud); Computerized adaptive testing; Item response theory; Sample size determination; Physical therapy; Rheumatoid arthritis; Physical medicine and rehabilitation; Psychometrics; Internal medicine; Statistics; Alternative medicine; Pathology; Clinical psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2544543516444623,"gpt":0.4364932432144383,"spread":0.1820388915699759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01262511,0.00007908969,0.0003630234,0.0001696905,0.000116589,0.00004359068,0.0004657938,0.00005372208,0.00002073539],"category_scores_gemma":[0.02786369,0.00003388341,0.00004567598,0.0002433053,0.0002932542,0.0001142056,0.0001208001,0.0002147963,0.000001096664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006419386,"about_ca_system_score_gemma":0.00005331601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003817406,"about_ca_topic_score_gemma":0.00001265895,"domain_scores_codex":[0.9970454,0.001552827,0.0008691351,0.0001012792,0.0003011302,0.0001302225],"domain_scores_gemma":[0.9679457,0.03047918,0.001102985,0.0002140276,0.0002152605,0.00004286928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003567806,0.00001522744,0.9499028,0.00001946961,0.00004229432,0.000004772551,0.0008012524,4.938349e-7,0.0002935106,0.001053297,0.0001455066,0.04736457],"study_design_scores_gemma":[0.0005793807,0.0006747261,0.9616826,0.00006993226,0.00004085593,0.002527024,0.001381658,0.0003204794,0.0008975437,0.03144492,0.0003176105,0.00006322919],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892507,0.0009447613,0.008166923,0.0009072305,0.0004345973,0.00008050245,5.300368e-7,0.000002878009,0.0002118868],"genre_scores_gemma":[0.9908513,0.0002926945,0.008760765,0.00004709504,0.000005684718,9.660139e-7,3.933418e-8,0.000003732929,0.00003774144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04730134,"threshold_uncertainty_score":0.980325,"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":"W2005249146","doi":"10.1007/s11205-011-9843-4","title":"Validity and the Consequences of Test Interpretation and Use","year":2011,"lang":"en","type":"article","venue":"Social Indicators Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":149,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Cognitive reframing; Interpretation (philosophy); Construct validity; Psychology; Test (biology); Construct (python library); Social psychology; Quality of Life Research; Value (mathematics); Meaning (existential); Test validity; External validity; Psychometrics; Applied psychology; Public health; Developmental psychology; Computer science; Medicine; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8223478813702115,"gpt":0.579589150324663,"spread":0.2427587310455486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.02358762,0.00005195052,0.0001941087,0.0005398933,0.0004242745,0.0001496248,0.0004176605,0.00007010411,0.00008325537],"category_scores_gemma":[0.2629593,0.00002818832,0.00003489508,0.001972822,0.004191282,0.0001638813,0.0002617913,0.0002551125,0.000004253149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001033644,"about_ca_system_score_gemma":0.00006938144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005887196,"about_ca_topic_score_gemma":0.00001610614,"domain_scores_codex":[0.9960663,0.002228891,0.0003230128,0.0002320554,0.0009594532,0.0001902437],"domain_scores_gemma":[0.8806477,0.1184856,0.0002403792,0.0002122202,0.0003389388,0.00007514451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000934841,0.00002302038,0.912714,0.000005265763,0.000007570685,0.000001434965,0.01259594,1.475987e-8,0.0001739378,0.01074553,0.0006615145,0.0629783],"study_design_scores_gemma":[0.0002623622,0.00008879333,0.7973757,0.000006781656,0.000004183314,0.000002548093,0.006516981,0.00005466031,0.0007907079,0.1945829,0.0002713221,0.00004303687],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926519,0.0001334411,0.0003134373,0.0005012775,0.00006778943,0.000157592,0.000008085014,0.000008128675,0.006158394],"genre_scores_gemma":[0.9986672,0.00008845067,0.001070924,0.00002525987,0.00002931362,0.000008635323,1.878714e-7,0.000002871754,0.0001071326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2393717,"threshold_uncertainty_score":0.9985188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407088834","doi":"10.3390/encyclopedia5010018","title":"Likert-Type Scale","year":2025,"lang":"en","type":"article","venue":"Encyclopedia","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Likert scale; Scale (ratio); Psychology; Statistics; Mathematics; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.2298581624155352,"gpt":0.4757040976475932,"spread":0.2458459352320581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003124348,0.00009810734,0.0002224708,0.0004601909,0.0001354939,0.0001167524,0.0007836204,0.00007335152,0.0008778063],"category_scores_gemma":[0.07643574,0.00006839506,0.00007101928,0.004082306,0.00005665383,0.0001223352,0.0002035751,0.0001455201,0.0006485948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001707063,"about_ca_system_score_gemma":0.00008026583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002416324,"about_ca_topic_score_gemma":0.000009997626,"domain_scores_codex":[0.9981531,0.0002229702,0.0004328841,0.0004074997,0.0005337367,0.0002498382],"domain_scores_gemma":[0.985777,0.01320734,0.0001029087,0.0006378898,0.000203048,0.00007180456],"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":[0.00001067682,0.0000221993,0.3467158,0.000001989601,0.000005495933,0.000003687684,0.0001021428,0.000009652884,0.00007470659,0.001083057,0.1928187,0.4591519],"study_design_scores_gemma":[0.0001249365,0.00002261812,0.3266636,0.000008742785,0.000004787753,0.000001632485,0.0002168345,0.0001232324,0.00007285547,0.05882539,0.6138514,0.00008393513],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2377836,0.0007696565,0.009078111,0.0009058364,0.003915146,0.00008379536,0.000001531534,0.00009144749,0.7473708],"genre_scores_gemma":[0.6588865,0.0005381154,0.07910638,0.002154452,0.0005590427,0.00001534565,0.000002677216,0.00001666374,0.2587208],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.48865,"threshold_uncertainty_score":0.9611364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3006236708","doi":"10.1080/00273171.2020.1717922","title":"Improving Fit Indices in Structural Equation Modeling with Categorical Data","year":2020,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":148,"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":"Categorical variable; Structural equation modeling; Estimator; Statistics; Computation; Mathematics; Binary data; Binary number; Econometrics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.9579372916956201,"gpt":0.654397403620915,"spread":0.3035398880747051,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01183124,0.000172233,0.0003583213,0.0007617478,0.0002995264,0.0006149238,0.002501517,0.0001344696,0.000169875],"category_scores_gemma":[0.06964718,0.000112919,0.00003262863,0.0048884,0.0001129082,0.0009687757,0.001553082,0.001022554,0.00005203852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001062536,"about_ca_system_score_gemma":0.0002274418,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008546857,"about_ca_topic_score_gemma":0.0001963814,"domain_scores_codex":[0.9930544,0.001305931,0.0007283404,0.001206503,0.002975363,0.0007294465],"domain_scores_gemma":[0.9865687,0.01117929,0.000206743,0.001114664,0.0006051898,0.0003253849],"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":[0.0006747642,0.0001446869,0.4316975,0.00001962077,0.000009979184,0.0002152805,0.004100123,0.01517987,0.004700505,0.0004509811,0.0001643316,0.5426424],"study_design_scores_gemma":[0.0006825828,0.0002487984,0.04742139,0.00001025864,0.000005071416,0.000003612354,0.002391896,0.9474733,0.00006214495,0.001500065,0.00004479162,0.0001560913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9135447,0.00007091426,0.08459555,0.001080552,0.000106923,0.0003708276,0.0000244297,0.00004904265,0.0001570278],"genre_scores_gemma":[0.9709654,0.000002796093,0.02877712,0.00003957761,0.0001260712,0.00001651028,0.00002553215,0.00001832647,0.00002863734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9322934,"threshold_uncertainty_score":0.9980553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2180735259","doi":"10.1177/2158244014545964","title":"The Conscientious Responders Scale","year":2014,"lang":"en","type":"article","venue":"SAGE Open","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; Thompson Rivers University","funders":"","keywords":"Scale (ratio); Reliability (semiconductor); Item response theory; Psychology; Odds; Clinical psychology; Psychometrics; Statistics; Social psychology; Medicine; Applied psychology; Logistic regression; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4342120929580178,"gpt":0.5144347334499795,"spread":0.08022264049196165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02775431,0.0000653051,0.0001532013,0.0001205719,0.0007172967,0.001620887,0.002979649,0.00003227888,0.0003904257],"category_scores_gemma":[0.1148579,0.00003295572,0.00005404166,0.001568205,0.0002019659,0.0001893956,0.0007566548,0.00009799492,0.0004600135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001070067,"about_ca_system_score_gemma":0.0000364902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005448008,"about_ca_topic_score_gemma":0.000111235,"domain_scores_codex":[0.9973832,0.0009937388,0.0003293469,0.0003521646,0.0006872627,0.0002543129],"domain_scores_gemma":[0.957566,0.04106586,0.0001907001,0.0009760542,0.0001131167,0.00008831194],"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":[0.00002508634,0.000008031149,0.01391801,2.903319e-7,0.000003309184,0.000001116869,0.0001281836,0.000007379249,0.0001914499,0.002539659,0.04048963,0.9426879],"study_design_scores_gemma":[0.0003293954,0.00005119657,0.06369662,0.000007043639,0.000002472876,0.000005992911,0.00111158,0.0005678743,0.0001654781,0.1773831,0.7565902,0.00008905419],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1603586,0.0003198089,0.04758068,0.005508558,0.002205593,0.0004474046,0.00000388455,0.00005161484,0.7835238],"genre_scores_gemma":[0.9132119,0.00001801347,0.01901592,0.001043252,0.00008946461,0.000009843649,3.98411e-7,0.00000816056,0.06660309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9425988,"threshold_uncertainty_score":0.9994155,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150705942","doi":"10.1016/j.ijpsycho.2003.12.009","title":"Analysis of covariance (ANCOVA) with difference scores","year":2004,"lang":"en","type":"article","venue":"International Journal of Psychophysiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"","keywords":"Analysis of covariance; Covariate; Statistics; Significant difference; Mathematics; Analysis of variance; Covariance; Variable (mathematics); Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2276957627367072,"gpt":0.4703214309101297,"spread":0.2426256681734224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001441498,0.0001106868,0.0005917295,0.001658409,0.00002885953,0.00004320769,0.001567269,0.00005887303,0.0001296389],"category_scores_gemma":[0.00923151,0.00006570546,0.0002702376,0.00237305,0.0001967533,0.0001480403,0.00006526628,0.0001845759,0.00000668234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004037534,"about_ca_system_score_gemma":0.00009619164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004421202,"about_ca_topic_score_gemma":0.0000119929,"domain_scores_codex":[0.997238,0.0001859787,0.0009857576,0.0002490885,0.001196197,0.0001449941],"domain_scores_gemma":[0.9914934,0.004756662,0.00168229,0.0002568477,0.001741343,0.00006945229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003926929,0.0008507996,0.4382804,0.000006538122,0.007373581,0.0001810658,0.0008923961,0.1645701,0.1838035,0.0138188,0.0005564532,0.1857394],"study_design_scores_gemma":[0.001177373,0.0005367768,0.8962338,0.00004196336,0.0001166549,0.00007315034,0.0001391,0.0003147955,0.001027041,0.1000373,0.0002106982,0.00009138474],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8183894,0.0001253795,0.179188,0.0006705691,0.001205067,0.00002738641,0.00001329641,0.000004411411,0.0003765246],"genre_scores_gemma":[0.9629747,0.00007047207,0.03645148,0.0002652264,0.0001896934,9.403578e-7,0.000001270069,0.00000430654,0.00004195764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4579534,"threshold_uncertainty_score":0.9991142,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148623326","doi":"10.1111/j.1365-2923.2012.04289.x","title":"Using automatic item generation to create multiple‐choice test items","year":2012,"lang":"en","type":"article","venue":"Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":142,"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":"Computer science; Multiple choice; Licensure; Item bank; Context (archaeology); Test (biology); Certification; Item response theory; Process (computing); Artificial intelligence; Machine learning; Information retrieval; Psychometrics; Psychology; Medical education; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6054844956655376,"gpt":0.5574866617688159,"spread":0.04799783389672174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00754963,0.0001246295,0.0002251578,0.0004737624,0.0002038713,0.0001623564,0.0004606701,0.0001244467,0.001159293],"category_scores_gemma":[0.7219349,0.00009067009,0.00005444048,0.002072776,0.00004246828,0.0003726033,0.00008944729,0.0001521877,0.0002914871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110577,"about_ca_system_score_gemma":0.0003857977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002472663,"about_ca_topic_score_gemma":0.00002085687,"domain_scores_codex":[0.9965877,0.0004326976,0.0006803739,0.0003338678,0.001597364,0.0003680128],"domain_scores_gemma":[0.9350457,0.06236453,0.0004350242,0.0008124126,0.0004866867,0.0008556939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[9.746194e-7,0.0002211427,0.5474888,0.00000503039,0.000002998182,1.962555e-7,0.0005292401,0.00002301638,0.001626257,0.00004544527,0.02773917,0.4223177],"study_design_scores_gemma":[0.000226101,0.00005248256,0.6983389,0.000073954,0.00001679217,0.00003385551,0.0006942624,0.2327972,0.0004955762,0.0003688578,0.06666813,0.0002338725],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9412984,0.0003112696,0.04952989,0.002484786,0.004477044,0.0002246369,0.000001650563,0.00007547002,0.0015969],"genre_scores_gemma":[0.9324903,0.00000447327,0.06168871,0.002929274,0.002228603,0.0000310311,0.000007089678,0.00001155873,0.0006089523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7143853,"threshold_uncertainty_score":0.9997538,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041006315","doi":"10.1002/jhbs.1098","title":"Measurement in psychology: A critical history of a methodological concept","year":2002,"lang":"en","type":"article","venue":"Journal of the History of the Behavioral Sciences","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"History of psychology; Citation; Psychology; Library science; Sociology; Psychoanalysis; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.9088941765489551,"gpt":0.5587217495193746,"spread":0.3501724270295805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03054114,0.0001418019,0.000667245,0.0004900176,0.00009872331,0.00001300197,0.00382755,0.0001120798,0.0006879866],"category_scores_gemma":[0.06613621,0.00006412822,0.0005318703,0.001301932,0.004132153,0.0002363372,0.000272557,0.0004901275,0.000002351841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101749,"about_ca_system_score_gemma":0.0003793984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008015394,"about_ca_topic_score_gemma":0.0000174081,"domain_scores_codex":[0.9910107,0.003630697,0.001582539,0.0003053737,0.00317902,0.0002916384],"domain_scores_gemma":[0.991197,0.005394671,0.002063334,0.0006249332,0.0006206676,0.00009934958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002558425,0.002620158,0.2481384,0.00002583218,0.00003239936,0.00003699618,0.01130371,0.0005087244,0.07362016,0.001290992,0.4716953,0.1904715],"study_design_scores_gemma":[0.002321262,0.0035683,0.7230331,0.0007018304,0.0002794579,0.0006062029,0.003121234,0.0007757766,0.001224161,0.05475906,0.2089614,0.0006483181],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8621019,0.06722978,0.002424485,0.01102656,0.04392702,0.0003736051,0.000005192367,0.00001484569,0.01289661],"genre_scores_gemma":[0.9792728,0.00003585459,0.01909043,0.0003397247,0.00006628421,0.00000172875,3.877906e-9,0.000004270514,0.001188845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4748946,"threshold_uncertainty_score":0.998578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024532747","doi":"10.1080/10401330701542685","title":"How to Use Structural Equation Modeling in Medical Education Research: A Brief Guide","year":2007,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Structural equation modeling; Latent variable; Test (biology); Statistical model; Computer science; Psychology; Measure (data warehouse); Statistical hypothesis testing; Medical education; Management science; Medicine; Artificial intelligence; Mathematics; Data mining; Statistics; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.6828362269846211,"gpt":0.5820779485981239,"spread":0.1007582783864972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.129585,0.000108259,0.0003030398,0.002265441,0.0003349402,0.0001728034,0.0003636898,0.0001148159,0.00004051235],"category_scores_gemma":[0.7725051,0.00007569834,0.00001719621,0.002024768,0.00009395646,0.0002757546,0.0001343511,0.002254471,0.000002233308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000104849,"about_ca_system_score_gemma":0.0001368179,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007195752,"about_ca_topic_score_gemma":0.000480917,"domain_scores_codex":[0.9926686,0.003421508,0.0007575172,0.0005299112,0.002160164,0.0004622771],"domain_scores_gemma":[0.9482799,0.05069045,0.0001523593,0.0003104848,0.0002547192,0.0003120936],"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":[0.00002990741,0.00001199339,0.1822016,0.000004522674,0.000001225724,0.00001165025,0.008490449,0.002225726,0.0001022721,0.0007376428,0.0005547838,0.8056282],"study_design_scores_gemma":[0.0008232192,0.0002743845,0.2661175,0.0006980201,0.000002791071,0.00004298294,0.04306841,0.6628935,0.000002293522,0.01013496,0.01576613,0.0001757726],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8455474,0.0002599626,0.141088,0.01067095,0.0002997752,0.0001212119,6.197065e-8,0.00003414199,0.001978522],"genre_scores_gemma":[0.9618266,0.00001540379,0.03572422,0.0006045931,0.0003016454,0.000003732525,0.000002458356,0.000008711704,0.001512605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8054525,"threshold_uncertainty_score":0.9994154,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1921155735","doi":"10.1023/a:1023488915557","title":"Use of differential item functioning analysis to assess the equivalence of translations of a questionnaire","year":2003,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Differential item functioning; Contingency table; Psychology; Scale (ratio); Item response theory; Statistics; Logistic regression; Test (biology); Cross-cultural studies; Linguistics; Psychometrics; Mathematics; Social psychology; Developmental psychology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.9498982239111976,"gpt":0.6535681604742923,"spread":0.2963300634369053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03855322,0.00007613962,0.00060366,0.001395905,0.0001518967,0.00004788758,0.0006973522,0.0000665749,0.0002646965],"category_scores_gemma":[0.4101694,0.00004904326,0.0002869098,0.01046231,0.0004429402,0.0001530579,0.0001012984,0.0002049109,0.000001530796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001518118,"about_ca_system_score_gemma":0.0002026245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001323589,"about_ca_topic_score_gemma":0.0001230587,"domain_scores_codex":[0.986983,0.007630789,0.001597717,0.000319531,0.00322541,0.0002435679],"domain_scores_gemma":[0.8295501,0.1643232,0.0009791662,0.001348755,0.003632702,0.0001660486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001052511,0.0001696868,0.9607228,0.00008012241,0.0002134488,1.067813e-7,0.001201135,0.002591913,0.01068049,0.01137837,0.0001276792,0.01272897],"study_design_scores_gemma":[0.0001380047,0.0001274627,0.9875903,0.00005314461,0.00004135784,1.754168e-7,0.00219965,0.001639468,0.003153965,0.00493238,0.0000704033,0.00005366341],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7574732,0.0001382564,0.2414763,0.0003328517,0.0000621958,0.0001413645,0.0000262397,0.000004368908,0.0003452372],"genre_scores_gemma":[0.9896286,0.00001940806,0.01018426,0.000006752534,0.00001409503,0.000006255281,8.605641e-7,0.000003491588,0.0001362456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3716162,"threshold_uncertainty_score":0.9900118,"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":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"}]}