{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":304,"total_is_capped":false,"direct_labels_cover":3,"predictions_cover":304,"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":"49b792a6fb40","filters":{"venue":"Behavior Research Methods"}},"results":[{"id":"W2023736093","doi":"10.3758/s13428-012-0314-x","title":"Norms of valence, arousal, and dominance for 13,915 English lemmas","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1978,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Psychology; Valence (chemistry); Stimulus (psychology); Taboo; Cognitive psychology; Arousal; Linguistics; Social psychology; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.2235629719078966,"gpt":0.5275938138999604,"spread":0.3040308419920638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004983515,0.0001192071,0.0002919669,0.0003323755,0.0001896486,0.0002325206,0.0008058702,0.00007358289,0.00007024999],"category_scores_gemma":[0.0006259746,0.0000982401,0.0001102414,0.0007199151,0.0002045946,0.0005537781,0.000425189,0.0002055244,0.000009594309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002307694,"about_ca_system_score_gemma":0.00006227638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001767926,"about_ca_topic_score_gemma":0.000004605906,"domain_scores_codex":[0.9976557,0.0005294,0.0003477538,0.0004727762,0.0005222512,0.0004720453],"domain_scores_gemma":[0.9973009,0.001040111,0.0001054592,0.0005987932,0.0008045727,0.0001502027],"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":[0.0000155234,0.0002780772,0.03933546,0.0000944455,0.00003581458,0.000004713691,0.002668955,0.000006107258,0.07092092,0.008320834,0.005625014,0.8726941],"study_design_scores_gemma":[0.004558884,0.002360138,0.4411436,0.0003949822,0.0001444108,0.00002339056,0.003962027,0.09494217,0.371912,0.0162034,0.06269742,0.001657535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.513875,0.0007097914,0.4832147,0.0002170878,0.0003043253,0.0009971914,0.00000525136,0.00005063127,0.0006260438],"genre_scores_gemma":[0.1650989,0.0001416142,0.8326613,0.00001718896,0.00009993105,0.000503104,0.000003470295,0.00001393696,0.001460513],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8710366,"threshold_uncertainty_score":0.4006115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974991592","doi":"10.3758/s13428-013-0403-5","title":"Concreteness ratings for 40 thousand generally known English word lemmas","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":1876,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Concreteness; Word (group theory); Crowdsourcing; Psychology; Set (abstract data type); Cognitive psychology; Computer science; Word lists by frequency; Natural language processing; Linguistics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.2074451318612571,"gpt":0.5283622746603649,"spread":0.3209171427991078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007616743,0.000261475,0.0004208743,0.0003314559,0.0004147461,0.0002871913,0.0005523858,0.0003227493,0.006503504],"category_scores_gemma":[0.001626821,0.0002225026,0.0002267028,0.0005293091,0.0003052031,0.0002567377,0.0001515513,0.0006870313,0.0002844815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007053392,"about_ca_system_score_gemma":0.0001237518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00101056,"about_ca_topic_score_gemma":0.00002894389,"domain_scores_codex":[0.993359,0.003728801,0.000475631,0.0007455293,0.000562189,0.001128848],"domain_scores_gemma":[0.995378,0.001803824,0.0001087146,0.0007386946,0.001647816,0.0003229516],"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":[0.0002514504,0.0002524689,0.001425075,0.00005315222,0.0000768622,0.00005611209,0.007394535,2.449917e-7,0.1142517,0.004184676,0.02150461,0.8505491],"study_design_scores_gemma":[0.014182,0.003277736,0.1567021,0.0002236476,0.0006810927,0.0001911811,0.04388869,0.0002739367,0.2455367,0.02014469,0.5117981,0.003100124],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9416031,0.001294585,0.02880891,0.0002170107,0.001673625,0.003630536,0.00005763825,0.0002375227,0.02247714],"genre_scores_gemma":[0.3966759,0.0000758351,0.4978444,0.0005335434,0.003771676,0.02570343,0.0002644492,0.0003073359,0.07482344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.847449,"threshold_uncertainty_score":0.9944047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127637041","doi":"10.3758/s13428-020-01516-y","title":"NeuroKit2: A Python toolbox for neurophysiological signal processing","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":1285,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Courtois Foundation","keywords":"Python (programming language); Toolbox; Computer science; Neurophysiology; Suite; Signal processing; Human–computer interaction; Data processing; Digital signal processing; Software engineering; Artificial intelligence; Computer architecture; Programming language; Computer hardware; Database; Psychology; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.4769790090589294,"gpt":0.582458395201068,"spread":0.1054793861421386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002205178,0.0002060024,0.0003077619,0.0001665501,0.0005559985,0.0004391674,0.0006817187,0.0001192108,0.0001709868],"category_scores_gemma":[0.003035233,0.0001694769,0.0001790832,0.000865505,0.0003568158,0.0002365605,0.0004237952,0.0008029036,0.00002625623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004087083,"about_ca_system_score_gemma":0.0002387146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003505164,"about_ca_topic_score_gemma":8.906263e-7,"domain_scores_codex":[0.9929611,0.004060825,0.0003370499,0.001081487,0.0006653016,0.0008942491],"domain_scores_gemma":[0.9955111,0.003367271,0.00006391991,0.0004268473,0.0004025648,0.0002283387],"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":[0.00005342702,0.0002244352,0.00003895244,0.00003451827,8.337387e-7,0.0002157431,0.00009813417,0.000007837461,0.7067545,0.0002267537,0.0003347269,0.2920101],"study_design_scores_gemma":[0.0003349792,0.0005595033,0.001955057,0.00003225256,0.000009118565,0.0001314019,0.00009301151,0.00342709,0.9632139,0.0009135982,0.02912682,0.0002033149],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9159907,0.0001889211,0.07999997,0.0009514504,0.0004129253,0.0009894122,0.00004280138,0.0002476021,0.00117626],"genre_scores_gemma":[0.7908048,0.00002484723,0.2039566,0.000828866,0.0004422977,0.0006664432,0.000006749637,0.0000774374,0.003192014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2918068,"threshold_uncertainty_score":0.6911066,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979532929","doi":"10.3758/s13428-012-0210-4","title":"Age-of-acquisition ratings for 30,000 English words","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":1250,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Economic and Social Research Council","keywords":"Age of Acquisition; Vocabulary; Lexicon; Noun; Crowdsourcing; Computer science; Psychology; Natural language processing; Word (group theory); Variance (accounting); Similarity (geometry); Correlation; Artificial intelligence; Linguistics; Statistics; Mathematics; Cognition; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.2541210475944673,"gpt":0.5307494941877987,"spread":0.2766284465933314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01413342,0.0001304181,0.0002696727,0.0003093526,0.0001987475,0.0001604579,0.0008893985,0.0001304831,0.00008156376],"category_scores_gemma":[0.00155909,0.000119,0.000125085,0.0007390201,0.0001327148,0.0005955466,0.0003122021,0.0002563403,0.00002303786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008382766,"about_ca_system_score_gemma":0.0001025281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000128688,"about_ca_topic_score_gemma":0.000001803433,"domain_scores_codex":[0.9960986,0.001650398,0.0003627154,0.0003404345,0.0006869287,0.0008608827],"domain_scores_gemma":[0.9969537,0.001264205,0.00009307179,0.0007416297,0.0006323582,0.000315037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007104505,0.0006994439,0.01490031,0.000179611,0.00002363235,0.00001859772,0.01314358,0.000001628364,0.2760974,0.03901856,0.004838569,0.6510077],"study_design_scores_gemma":[0.002772435,0.00165054,0.1050053,0.0002031424,0.00005272554,0.00003938533,0.002244906,0.001153086,0.7300912,0.007887963,0.1478092,0.001090185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0827001,0.0005184028,0.9104671,0.00005324344,0.001757562,0.001261077,0.00001771963,0.0001538124,0.003070952],"genre_scores_gemma":[0.3029345,0.000005438841,0.6951634,0.00002074134,0.0007005343,0.0007215098,0.00001540203,0.00001928332,0.0004191982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6499175,"threshold_uncertainty_score":0.4898389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013137720","doi":"10.3758/brm.42.3.671","title":"Controlling low-level image properties: The SHINE toolbox","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":1232,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; Université de Montréal","funders":"Université de Montréal","keywords":"Toolbox; Computer science; Image (mathematics); Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.362298902592299,"gpt":0.5548363531033043,"spread":0.1925374505110053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01135838,0.0001372167,0.0001696172,0.0002040241,0.000739239,0.0007106662,0.001536366,0.0001008501,0.0001368167],"category_scores_gemma":[0.001308637,0.00008324102,0.0001235375,0.0008375256,0.0003157027,0.0005878976,0.0003593196,0.001229838,0.0001532107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003947883,"about_ca_system_score_gemma":0.0001299777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001631722,"about_ca_topic_score_gemma":0.00004689445,"domain_scores_codex":[0.9961067,0.001692144,0.0003028392,0.0004599373,0.0008657763,0.0005725587],"domain_scores_gemma":[0.997839,0.000414727,0.00005588795,0.0009685814,0.0005543192,0.0001674214],"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":[0.00001052214,0.0001101923,0.00009152148,0.000006898788,0.000003631821,0.000008907658,0.0003896786,9.061304e-7,0.7066262,0.002631,0.0001337266,0.2899868],"study_design_scores_gemma":[0.001844034,0.0006112485,0.04446325,0.00006396486,0.00002736952,0.0001568927,0.000865492,0.08585244,0.8295188,0.004432347,0.03142482,0.0007393275],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2888849,0.00006303125,0.7062573,0.001812062,0.001020246,0.0007606089,0.000002614024,0.000186079,0.001013134],"genre_scores_gemma":[0.7019202,0.00001026849,0.2950708,0.0001218236,0.0001946643,0.0004564598,0.000001014753,0.00002013702,0.002204676],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4130353,"threshold_uncertainty_score":0.6852971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078894097","doi":"10.3758/bf03192726","title":"Semantic feature production norms for a large set of living and nonliving things","year":2005,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":1102,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"The Scarborough Hospital; University of Toronto; Western University","funders":"National Institute on Deafness and Other Communication Disorders; National Institute of Mental Health; U.S. Public Health Service; National Institutes of Health","keywords":"Categorization; Set (abstract data type); Feature (linguistics); Computer science; Cognitive psychology; Semantic memory; Semantic feature; Psychology; Neuropsychology; Semantics (computer science); Cognitive science; Natural language processing; Artificial intelligence; Cognition; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1772768251816343,"gpt":0.5544826933288824,"spread":0.3772058681472482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009185661,0.0001267725,0.0002400351,0.0002592338,0.0002878638,0.00004349523,0.0001683397,0.000131315,0.0002400182],"category_scores_gemma":[0.00241308,0.0001081459,0.00006897642,0.0002984312,0.00008121396,0.0001438724,0.0001676764,0.000584782,0.00001282786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005210193,"about_ca_system_score_gemma":0.00005140504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004539764,"about_ca_topic_score_gemma":0.00001949985,"domain_scores_codex":[0.9976864,0.0007668789,0.0002231107,0.0004791413,0.0003064797,0.000537931],"domain_scores_gemma":[0.9982286,0.001093609,0.00007896875,0.0002827077,0.0002176125,0.00009851973],"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":[0.0001870374,0.0007663339,0.1234401,0.0003392273,0.00009071378,0.00001238346,0.04961049,0.000001685264,0.1242121,0.003164323,0.008245429,0.6899303],"study_design_scores_gemma":[0.0003803948,0.0003885382,0.9059332,0.0004963891,0.00004802941,0.00007758937,0.004196454,0.0001383349,0.005504987,0.00007249905,0.08247784,0.0002857377],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990914,0.0008281891,0.003913799,0.002054484,0.0002905368,0.001082179,0.00001432431,0.00006755981,0.0008349566],"genre_scores_gemma":[0.7778471,0.00002985025,0.2108943,0.00004176791,0.0004376925,0.0001547706,0.000006585109,0.00003972803,0.01054826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7824931,"threshold_uncertainty_score":0.4410062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151069696","doi":"10.3758/s13428-010-0049-5","title":"A tutorial on a practical Bayesian alternative to null-hypothesis significance testing","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":773,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Null hypothesis; Null (SQL); Statistical hypothesis testing; Bayesian probability; Bayes factor; Alternative hypothesis; Computer science; p-value; Worksheet; Bayesian inference; Significance testing; Multiple comparisons problem; Bayesian statistics; Econometrics; Artificial intelligence; Statistics; Data mining; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.7699708216302553,"gpt":0.5899453915272571,"spread":0.1800254301029982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006357479,0.000233833,0.0002987778,0.0004510242,0.0006274379,0.0001105416,0.0005125277,0.00009061792,0.0002792393],"category_scores_gemma":[0.3054707,0.0002112012,0.00008853028,0.001488573,0.0004268976,0.0002387275,0.0004157401,0.0009212614,0.0003361072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003207047,"about_ca_system_score_gemma":0.0002712688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004928355,"about_ca_topic_score_gemma":0.00001942445,"domain_scores_codex":[0.9910462,0.005253338,0.0002869629,0.001157956,0.001405095,0.0008503984],"domain_scores_gemma":[0.9271729,0.07132912,0.0000832514,0.0006165245,0.0004306823,0.0003675144],"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":[0.0009635285,0.001226985,0.001589381,0.00001568824,0.00001573025,0.0005696266,0.002313235,0.000005893584,0.8426781,0.008820749,0.003798889,0.1380022],"study_design_scores_gemma":[0.0004435821,0.002204234,0.01884708,0.00005368068,0.00002074394,0.00005138152,0.0004249323,0.0001963523,0.9618233,0.006337054,0.009199695,0.000397949],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7409453,0.00002634542,0.09828166,0.01316626,0.006257567,0.008760469,0.0001502386,0.0009579511,0.1314543],"genre_scores_gemma":[0.5004508,0.000003218989,0.4948706,0.0008454514,0.0007499912,0.00184372,1.932028e-7,0.00006830219,0.001167704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.396589,"threshold_uncertainty_score":0.8612536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2047902775","doi":"10.3758/s13428-012-0186-0","title":"MorePower 6.0 for ANOVA with relational confidence intervals and Bayesian analysis","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":645,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Statistics; Analysis of variance; Confidence interval; Bayesian probability; Statistical power; Computer science; Mixed-design analysis of variance; One-way analysis of variance; Calculator; Interpretation (philosophy); Sample size determination; Repeated measures design; Factorial; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5923435475429615,"gpt":0.5003782614832487,"spread":0.09196528605971277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007058677,0.0000970536,0.0002799753,0.0003922204,0.0001552582,0.00005127522,0.0001065223,0.00007761156,0.001050009],"category_scores_gemma":[0.0002173727,0.00009804245,0.00008592045,0.0003137477,0.0001835355,0.0003839789,0.00006714332,0.0001554215,0.00005166617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001332759,"about_ca_system_score_gemma":0.00001208451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000122021,"about_ca_topic_score_gemma":0.00001126157,"domain_scores_codex":[0.9987342,0.0001359106,0.0003708248,0.0003330918,0.00006478443,0.000361203],"domain_scores_gemma":[0.999046,0.0003734682,0.0001348216,0.0002618301,0.00003559515,0.0001482805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001849436,0.00008043282,0.9192701,0.000007571068,0.00009760082,3.581985e-7,0.0004151597,0.00001814055,0.0001331264,0.07629962,0.00007352663,0.003585845],"study_design_scores_gemma":[0.0003170554,0.0001010202,0.9888505,0.00000449428,0.00006095291,0.000004624929,0.0002425209,0.001574822,0.000373514,0.004664526,0.003654015,0.0001519766],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5562547,0.0007796054,0.4397695,0.0001682202,0.00006634447,0.0004445122,0.00005945637,0.00001038677,0.00244718],"genre_scores_gemma":[0.8398661,0.00004053183,0.1586023,0.0000303616,0.00004721888,0.0002888998,0.00003333528,0.00001639168,0.001074883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2836114,"threshold_uncertainty_score":0.9998631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138172448","doi":"10.3758/brm.40.2.531","title":"The Montreal Affective Voices: A validated set of nonverbal affect bursts for research on auditory affective processing","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":476,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal","funders":"Economic and Social Research Council; Medical Research Council","keywords":"Sadness; Psychology; Disgust; Anger; Surprise; Affect (linguistics); Happiness; Valence (chemistry); Audiology; Nonverbal communication; Arousal; Facial expression; Developmental psychology; Clinical psychology; Social psychology; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.5345840841783612,"gpt":0.6108165772882865,"spread":0.0762324931099253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0178037,0.0002725564,0.0003765534,0.0007086433,0.00329718,0.0001772427,0.00115735,0.0001918509,0.0000169088],"category_scores_gemma":[0.0106373,0.0001926603,0.0002047053,0.002580875,0.003271598,0.0004621951,0.0003575584,0.001381092,0.00003224548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004175694,"about_ca_system_score_gemma":0.0007139309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004855795,"about_ca_topic_score_gemma":0.00010507,"domain_scores_codex":[0.9829286,0.01144408,0.0003576235,0.001246378,0.002527962,0.001495322],"domain_scores_gemma":[0.9832132,0.01461563,0.0001566992,0.0007986851,0.0009330713,0.0002826653],"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":[0.00060507,0.0003511193,0.0001106461,0.0000480727,0.000002941643,0.00005862567,0.002880077,0.000009045314,0.8908677,0.00008520496,0.001992748,0.1029888],"study_design_scores_gemma":[0.001091149,0.003390998,0.06494212,0.0001296958,0.00001873293,0.00006868877,0.001403313,0.0009690069,0.9246188,0.0005769409,0.002518498,0.0002720274],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916743,0.00003329117,0.002251551,0.0001750115,0.0006229156,0.003831692,0.00007038907,0.00009215497,0.001248691],"genre_scores_gemma":[0.994338,0.0001304434,0.001481208,0.0000372517,0.0004233233,0.002256948,0.000004124967,0.00005670049,0.001271997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1027167,"threshold_uncertainty_score":0.9994409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594456685","doi":"10.3758/s13428-017-0867-9","title":"The language and social background questionnaire: Assessing degree of bilingualism in a diverse population","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":415,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Aging; National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada","keywords":"Neuroscience of multilingualism; Psychology; Cognition; Population; Language proficiency; Developmental psychology; Cognitive psychology; Medicine; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.5036851353495614,"gpt":0.6149425197020493,"spread":0.1112573843524879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00577977,0.0001006147,0.0001784181,0.0001522027,0.001507543,0.0003016815,0.000517513,0.0001116117,0.000009105659],"category_scores_gemma":[0.004608203,0.00007218356,0.0000483718,0.0001410702,0.001045757,0.0002818226,0.0004035745,0.0004816197,0.000001902945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004187419,"about_ca_system_score_gemma":0.00005833973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001952694,"about_ca_topic_score_gemma":0.0005047308,"domain_scores_codex":[0.9957691,0.002922572,0.000253755,0.0003589477,0.0003331016,0.000362535],"domain_scores_gemma":[0.9980206,0.001244607,0.0001634113,0.0004480811,0.00007778858,0.00004551359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002840059,0.00006416985,0.02249578,0.00001796263,0.000001167718,0.0003570671,0.002927343,6.891989e-8,0.6714193,0.0005494577,0.000006232724,0.3021331],"study_design_scores_gemma":[0.0007141312,0.00009671551,0.8000749,0.00006758052,0.00001620666,0.0001214982,0.005844965,0.00004556762,0.1912778,0.001394023,0.0001557338,0.0001909261],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99878,0.000152175,0.00004327668,0.0003390584,0.000186673,0.0002937047,0.000005981274,0.00001862287,0.0001805278],"genre_scores_gemma":[0.9970003,0.00003345367,0.002611945,0.00002683103,0.00009331104,0.000027601,0.000001664427,0.00001285115,0.000191993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7775791,"threshold_uncertainty_score":0.9997923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889916852","doi":"10.3758/s13428-019-01293-3","title":"Survey-software implicit association tests: A methodological and empirical analysis","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":313,"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":"Psychology; Implicit-association test; Software; Applied psychology; Association (psychology); Empirical research; Data science; Computer science; Social psychology; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.679021047517433,"gpt":0.7112710266822435,"spread":0.03224997916481054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05700442,0.0001328777,0.0005464213,0.0004447644,0.0005454669,0.0001739931,0.0004420379,0.0005123777,0.001826391],"category_scores_gemma":[0.0276861,0.0001159895,0.0002053919,0.003033641,0.0003864934,0.0001554204,0.0002211036,0.0007765053,0.0001151038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004816263,"about_ca_system_score_gemma":0.0001581199,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008543738,"about_ca_topic_score_gemma":0.003286673,"domain_scores_codex":[0.9653525,0.03190354,0.000328435,0.0006067872,0.0009665944,0.0008421981],"domain_scores_gemma":[0.9810041,0.01759763,0.0001161199,0.0003169914,0.0006659335,0.0002992178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002694307,0.0001112729,0.93854,0.000002422409,0.00009515036,0.000003597471,0.002166705,1.307458e-7,0.001200306,0.0003772231,0.001332891,0.05614333],"study_design_scores_gemma":[0.0001793568,0.0001570194,0.9784142,0.000002691302,0.00008505083,5.506853e-7,0.001708975,0.000007355874,0.00003988471,0.001458868,0.01780613,0.0001398806],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867393,0.0002058901,0.005844028,0.00122499,0.0003525062,0.000618163,0.00002628528,0.000104115,0.004884681],"genre_scores_gemma":[0.8297814,0.0002881059,0.1520339,0.0004653932,0.0003979812,0.0003678617,0.00004390391,0.00003790715,0.01658367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.156958,"threshold_uncertainty_score":0.9990861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084990311","doi":"10.3758/bf03192800","title":"Behavioral phenotyping in zebrafish: Comparison of three behavioral quantification methods","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":299,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"College of Family Physicians of Canada; University of Toronto","funders":"","keywords":"Zebrafish; Novelty; Aggression; Animal behavior; Brain function; Neuroscience; Behavioral pattern; Psychology; Biology; Computer science; Developmental psychology; Genetics; Zoology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.3236072011575465,"gpt":0.6104451046833086,"spread":0.2868379035257621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009440921,0.0002728326,0.0005036035,0.0007374178,0.0002193797,0.00007962889,0.001024962,0.0004595247,0.0001261771],"category_scores_gemma":[0.000764214,0.0002819554,0.000195372,0.001619822,0.0009831104,0.00002197089,0.0005586006,0.0008804362,0.00001782034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001450056,"about_ca_system_score_gemma":0.0003545494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003600298,"about_ca_topic_score_gemma":0.001969698,"domain_scores_codex":[0.9932419,0.002730594,0.001045231,0.0009158097,0.001039947,0.001026513],"domain_scores_gemma":[0.9972018,0.0003726312,0.0002105776,0.001251849,0.0006805477,0.0002825989],"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":[0.00007480612,0.001838793,0.03432739,0.00002221896,0.000006250805,0.000003425277,0.00004840542,0.000007045261,0.7584465,0.0007589685,0.0004825437,0.2039837],"study_design_scores_gemma":[0.0007586907,0.0005693321,0.1507436,0.00003344777,0.00003371886,0.00000560017,0.0003370438,0.0005451348,0.8339726,0.00122517,0.01144749,0.0003281844],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7865521,0.0007044072,0.2105574,0.0001639642,0.00009874214,0.001291653,0.00004714819,0.00003151231,0.0005531095],"genre_scores_gemma":[0.7118279,0.0000244724,0.2865407,0.000005889837,0.0001220189,0.0009259204,0.0003459478,0.00005442251,0.0001527612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2036555,"threshold_uncertainty_score":0.9999633,"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":"W2027900864","doi":"10.3758/s13428-012-0289-7","title":"SPSS and SAS programs for comparing Pearson correlations and OLS regression coefficients","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Applications","field":"Mathematics","cited_by":287,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"NOSM University; Lakehead University","funders":"","keywords":"Rounding; Raw data; Computer science; Statistics; Pearson product-moment correlation coefficient; Regression analysis; Regression; Software; Data mining; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.6740604188140626,"gpt":0.6686980108350041,"spread":0.005362407979058514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003549122,0.0001287432,0.0002680264,0.0001245233,0.0004954975,0.0001986297,0.0001399209,0.00009780937,0.00005262835],"category_scores_gemma":[0.002975474,0.0001013405,0.00003708845,0.000284211,0.0003219618,0.00008562274,0.0001818317,0.0003240993,0.000007752385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003264012,"about_ca_system_score_gemma":0.00002541254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009313875,"about_ca_topic_score_gemma":0.000006008887,"domain_scores_codex":[0.9977922,0.0008134401,0.0002875727,0.0003647703,0.0003220447,0.0004199276],"domain_scores_gemma":[0.9938067,0.005212453,0.00006657445,0.0003124853,0.0003439662,0.0002578449],"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":[0.00001248809,0.0003234175,0.009413209,0.0001066999,0.000007793775,8.925254e-7,0.0004075949,1.21561e-7,0.007381381,0.06220664,0.001238595,0.9189011],"study_design_scores_gemma":[0.002624261,0.0007580825,0.2498613,0.0005783324,0.0002305143,0.00005116215,0.003344968,0.03937764,0.004807611,0.6831986,0.01437778,0.0007896851],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.286741,0.0001224609,0.7095298,0.0001958829,0.00004428856,0.002883732,0.00001505902,0.00005637859,0.000411398],"genre_scores_gemma":[0.09402148,0.00001624898,0.9024734,0.000004979472,0.00003557146,0.002634512,0.00001158137,0.000029296,0.000772919],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9181115,"threshold_uncertainty_score":0.4132546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021096528","doi":"10.3758/s13428-015-0576-1","title":"Is the cognitive reflection test a measure of both reflection and intuition?","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Learning Styles and Cognitive Differences","field":"Psychology","cited_by":254,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Intuition; Cognition; Cognitive psychology; Psychology; Measure (data warehouse); Cognitive style; Computer science; Cognitive science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.5571369298902951,"gpt":0.6457370586835582,"spread":0.08860012879326318,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006927297,0.000117654,0.0001819577,0.0002268024,0.0002772918,0.0000628854,0.0001461349,0.0001383154,0.0003484532],"category_scores_gemma":[0.002588741,0.00008184575,0.00005732356,0.0006843635,0.0005175968,0.00008168406,0.00008742057,0.000704834,0.00003693537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005492643,"about_ca_system_score_gemma":0.0001017311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001002559,"about_ca_topic_score_gemma":0.00006252261,"domain_scores_codex":[0.9943638,0.004191897,0.0002175852,0.0003620235,0.0005426099,0.000322093],"domain_scores_gemma":[0.9965314,0.001885315,0.00009763047,0.0002148562,0.001147939,0.0001228903],"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":[0.0004951365,0.0006529103,0.1455431,0.00002048943,0.00008446428,0.00001313362,0.02065807,4.448972e-8,0.01852267,0.001759992,0.002473538,0.8097765],"study_design_scores_gemma":[0.001800884,0.003423934,0.9223767,0.0001618755,0.0001760626,0.00009963363,0.04337212,0.00002220635,0.01516886,0.007961626,0.005160213,0.0002759158],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9456202,0.0009845685,0.01023783,0.0007275888,0.0003465371,0.0009764674,0.00003914317,0.00006108811,0.04100659],"genre_scores_gemma":[0.9943953,0.00003427553,0.001910569,0.00006613873,0.0001106307,0.0004264169,0.000006938918,0.00002011587,0.003029637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8095006,"threshold_uncertainty_score":0.3815318,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4308017781","doi":"10.3758/s13428-022-01999-x","title":"Evaluating CloudResearch’s Approved Group as a solution for problematic data quality on MTurk","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Vetting; Data quality; Psychology; Quality (philosophy); Sample (material); Applied psychology; Computer science; Computer security; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.8107478869005017,"gpt":0.6970883390979823,"spread":0.1136595478025194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.1043095,0.0002286181,0.0003895946,0.0004739044,0.00261186,0.0006045522,0.003978262,0.00008561958,0.00006778041],"category_scores_gemma":[0.008200325,0.0002234739,0.0001384751,0.001415976,0.0001948712,0.0004157061,0.005341304,0.001433607,0.00002370676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004965728,"about_ca_system_score_gemma":0.0005813192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006246304,"about_ca_topic_score_gemma":0.00001685032,"domain_scores_codex":[0.9773176,0.01601531,0.0006908594,0.001602242,0.003049981,0.001323994],"domain_scores_gemma":[0.9894028,0.005648254,0.0002078066,0.003932821,0.000506647,0.0003016139],"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":[0.0001582901,0.0007319215,0.00006027553,0.0001888793,0.00002173641,0.00001795226,0.001450766,0.0003025257,0.1853862,0.01780391,0.001745165,0.7921324],"study_design_scores_gemma":[0.001837761,0.003254912,0.001396221,0.000110421,0.00003307175,0.00007080341,0.001201634,0.9497103,0.008023578,0.021653,0.01209036,0.0006179208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0862129,0.0001487712,0.9060751,0.001973444,0.0004548134,0.004231249,0.00005615246,0.0002899121,0.000557709],"genre_scores_gemma":[0.1469935,0.000003175631,0.8476409,0.0001003188,0.0001329357,0.003915411,0.0001028121,0.00005018856,0.001060804],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9494078,"threshold_uncertainty_score":0.9986866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058821124","doi":"10.3758/brm.40.2.428","title":"Comparing online and lab methods in a problem-solving experiment","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":216,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Psychology; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.4997630286426059,"gpt":0.6502886072233989,"spread":0.150525578580793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01938509,0.0001389739,0.0003410794,0.0004576694,0.0009581465,0.00009627462,0.0003498807,0.0001410852,0.0001603713],"category_scores_gemma":[0.0015332,0.0001333617,0.00005564353,0.001042793,0.0006367282,0.0002575383,0.0003488853,0.001033688,0.000005261613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002341441,"about_ca_system_score_gemma":0.0005587364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005012541,"about_ca_topic_score_gemma":0.001482034,"domain_scores_codex":[0.9876562,0.009925307,0.0003656284,0.0004568877,0.0007230553,0.0008729575],"domain_scores_gemma":[0.9978076,0.001414259,0.00006170811,0.0002452013,0.0001979978,0.0002732745],"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":[0.00003189087,0.0006802698,0.1455212,0.00002672267,0.00001008942,0.0001433061,0.03344533,0.000009838343,0.05152101,0.001734267,0.0001378747,0.7667382],"study_design_scores_gemma":[0.002755153,0.0006125722,0.3357007,0.0003921344,0.00004264766,0.00007443967,0.1422314,0.001888453,0.02632296,0.002081225,0.486652,0.001246289],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9835528,0.001754782,0.005228939,0.0007579337,0.00009796155,0.0007521693,0.000001637165,0.00009346843,0.00776027],"genre_scores_gemma":[0.1122124,0.0005771697,0.885247,0.00001309145,0.0001563042,0.0001276404,0.000003664533,0.00002284534,0.001639929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8800181,"threshold_uncertainty_score":0.7577496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2290759784","doi":"10.3758/s13428-015-0700-2","title":"Norms of valence and arousal for 14,031 Spanish words","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":202,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Valence (chemistry); Psychology; Arousal; Verb; Emotional valence; Linguistics; Stimulus (psychology); Neuroscience of multilingualism; Cognitive psychology; Age of Acquisition; Social psychology; Cognition","retraction":null,"screen_n_in":null,"score":{"opus":0.4258874139141428,"gpt":0.6267026890361848,"spread":0.200815275122042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004835677,0.00009479003,0.0001879465,0.0002232007,0.00009635897,0.00001677397,0.0001739245,0.0001496912,0.001050352],"category_scores_gemma":[0.0007079476,0.00006485917,0.00007147763,0.0002017467,0.0003494352,0.0000843802,0.00007886607,0.0001839052,0.00004482861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002850757,"about_ca_system_score_gemma":0.0000421994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000560168,"about_ca_topic_score_gemma":0.00001428265,"domain_scores_codex":[0.9976489,0.00106337,0.0002467496,0.0003437678,0.0002770994,0.0004201427],"domain_scores_gemma":[0.9978992,0.00122104,0.00006175722,0.0003124077,0.0003560419,0.0001495574],"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":[0.0001146163,0.0002350446,0.008025073,0.00003217818,0.00001354263,0.000005616427,0.0004558766,4.63181e-9,0.1239851,0.002341881,0.001708422,0.8630827],"study_design_scores_gemma":[0.00752039,0.003506569,0.6283613,0.0003932402,0.0001430417,0.0001496976,0.002848986,0.000009175431,0.281437,0.02119273,0.05379518,0.0006426527],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8491518,0.000289703,0.1403876,0.000627252,0.0008399328,0.001377694,0.0001458988,0.0000649147,0.007115173],"genre_scores_gemma":[0.7897479,0.0002073296,0.1803697,0.00004917305,0.0002576764,0.001162954,0.00001371683,0.0000590132,0.02813257],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.86244,"threshold_uncertainty_score":0.9998628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200635405","doi":"10.3758/s13428-021-01624-3","title":"Best research practices for using the Implicit Association Test","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":182,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University; McGill University","funders":"Economic and Social Research Council","keywords":"Implicit-association test; Psychology; Association (psychology); Test (biology); Implicit attitude; Social psychology; Selection (genetic algorithm); Cognitive psychology; Applied psychology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.8389178653384918,"gpt":0.783184058779802,"spread":0.05573380655868976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06244358,0.00009482015,0.0002011475,0.0001807924,0.003889919,0.0005418629,0.0007231757,0.000332784,0.0004642814],"category_scores_gemma":[0.09847862,0.00007810378,0.0001417845,0.001952459,0.0006848066,0.0002967322,0.0002567115,0.001200603,0.00005429887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009576843,"about_ca_system_score_gemma":0.001115099,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120719,"about_ca_topic_score_gemma":0.004009413,"domain_scores_codex":[0.9809241,0.01548976,0.0002883873,0.0004764223,0.001588645,0.001232688],"domain_scores_gemma":[0.9664055,0.02885742,0.0002180457,0.0004228028,0.003912671,0.0001835196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009959848,0.002060213,0.09131938,0.00004100888,0.0001036979,0.00005428095,0.03337426,5.001431e-7,0.4313364,0.06537629,0.03656014,0.3396742],"study_design_scores_gemma":[0.0003869294,0.0003046288,0.01319569,0.00003402907,0.00005567228,0.000007240361,0.1045388,0.00003968798,0.009424293,0.01264497,0.859166,0.0002020022],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7871206,0.002091339,0.006918482,0.06223431,0.003326718,0.004788457,0.00009047467,0.000148686,0.133281],"genre_scores_gemma":[0.4577542,0.001768374,0.2864234,0.0008738479,0.0114842,0.005597395,0.00004467762,0.0002129848,0.2358409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8226059,"threshold_uncertainty_score":0.9974069,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968422660","doi":"10.3758/s13428-013-0426-y","title":"ANGST: Affective norms for German sentiment terms, derived from the affective norms for English words","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":172,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"German; Valence (chemistry); Psychology; Arousal; Linguistics; Cognitive psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1183788676704029,"gpt":0.5231030567677374,"spread":0.4047241890973345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00938779,0.0003524845,0.0005114708,0.0002359263,0.0006799704,0.0001936665,0.0006649167,0.0003199793,0.0006399651],"category_scores_gemma":[0.002084315,0.0002364219,0.0004281479,0.0004248565,0.0003675717,0.0001879327,0.0001998202,0.0007107732,0.00007171126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001992888,"about_ca_system_score_gemma":0.00006247592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009279546,"about_ca_topic_score_gemma":0.0003182839,"domain_scores_codex":[0.9924732,0.004483449,0.0003746129,0.0009594646,0.0005932837,0.001116008],"domain_scores_gemma":[0.9895778,0.008285307,0.0001590143,0.0009762919,0.0007580303,0.0002435215],"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":[0.001300896,0.001119362,0.004635456,0.00005455876,0.0004218902,0.00001775207,0.04439863,4.466184e-7,0.06851888,0.002403913,0.006610444,0.8705178],"study_design_scores_gemma":[0.01376496,0.004545403,0.5516186,0.0001878683,0.001277073,0.00002305795,0.03360972,0.0003230081,0.2882357,0.03539122,0.06931114,0.00171218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7985059,0.0003356008,0.1879186,0.0002029646,0.001786356,0.006691558,0.000490469,0.000154769,0.00391382],"genre_scores_gemma":[0.9167628,0.00001876975,0.05626746,0.0003139326,0.002486645,0.02001125,0.0005314787,0.0001729394,0.003434689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8688056,"threshold_uncertainty_score":0.9641007,"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":"W2055350558","doi":"10.3758/s13428-014-0550-3","title":"A comparison of scanpath comparison methods","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":164,"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; University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Measure (data warehouse); Encoding (memory); Eye movement; Natural language processing; Machine learning; Pattern recognition (psychology); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.4656973264764639,"gpt":0.6720252201736696,"spread":0.2063278936972057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01973926,0.0002188243,0.0008060152,0.0007701637,0.000287107,0.000118515,0.002548508,0.0002355744,0.00003487046],"category_scores_gemma":[0.002208522,0.0001969383,0.0001563843,0.001696339,0.0006277682,0.0001769781,0.00100449,0.001156064,0.00003413675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008931543,"about_ca_system_score_gemma":0.0001234686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001471959,"about_ca_topic_score_gemma":0.00001049563,"domain_scores_codex":[0.9886192,0.008233543,0.0007221451,0.0007466417,0.0008381904,0.0008402775],"domain_scores_gemma":[0.994393,0.002915587,0.000241641,0.001621746,0.0006045227,0.0002235148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006948761,0.0004805375,0.04514718,0.00002227176,0.000009789221,0.000002387563,0.0004398563,0.000007774563,0.08356711,0.03851349,0.0004664306,0.8313362],"study_design_scores_gemma":[0.0006301427,0.001258865,0.1816878,0.00007380459,0.00003186066,0.0000167321,0.0004337027,0.0684175,0.7066609,0.009318478,0.03102533,0.0004447891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0633009,0.0002978686,0.9327527,0.0003428309,0.0002906374,0.0003184813,0.00000177493,0.0003055715,0.002389183],"genre_scores_gemma":[0.4505228,0.000002683331,0.5492349,0.000007739843,0.00002267689,0.00008177718,0.000001155238,0.00001284963,0.000113486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8308914,"threshold_uncertainty_score":0.8030912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4225749806","doi":"10.3758/s13428-021-01762-8","title":"RETRACTED ARTICLE: Eye tracking: empirical foundations for a minimal reporting guideline","year":2022,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":163,"is_retracted":true,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; SR Research (Canada)","funders":"National Eye Institute; National Cancer Institute; National Institute for Health and Care Research","keywords":"Guideline; Eye tracking; Foundation (evidence); Empirical research; Computer science; Empirical evidence; Quality (philosophy); Gaze; Tracking (education); Eye movement; Artificial intelligence; Psychology; Medicine; Statistics; Political science; Mathematics","retraction":{"nature":"Retraction","openalex_flagged":true},"screen_n_in":null,"score":{"opus":0.7737194927129117,"gpt":0.7106257387479584,"spread":0.06309375396495331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03808073,0.0004710818,0.001775076,0.001313883,0.001127143,0.0005156105,0.002879961,0.000715978,0.0002305087],"category_scores_gemma":[0.03521427,0.0004239097,0.0008913431,0.003730249,0.0003238867,0.0002770353,0.001488353,0.003939699,0.00002400337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006152037,"about_ca_system_score_gemma":0.001712318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002656083,"about_ca_topic_score_gemma":0.000004294611,"domain_scores_codex":[0.9874944,0.004611755,0.003588042,0.001692833,0.001259929,0.001353048],"domain_scores_gemma":[0.9890599,0.005576212,0.001990936,0.002129938,0.000955259,0.0002878018],"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":[0.000003169226,0.0003061091,0.00005932039,0.0005429137,0.00003827566,0.0001615397,0.00007337592,1.888087e-7,0.0000563192,0.0009192509,0.002674792,0.9951648],"study_design_scores_gemma":[0.0001611763,0.000280354,0.0002901858,0.0004113384,0.0001922518,0.0002015666,0.00005110646,0.0005668189,0.00004833302,0.0005989611,0.9967848,0.0004130916],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000600553,0.4959878,0.4988582,0.0007186715,0.0006407332,0.002643411,0.00004160825,0.0007505485,0.0002989962],"genre_scores_gemma":[0.0000109869,0.2341288,0.7603918,0.00002356207,0.000227447,0.004306531,0.0001396842,0.00008970567,0.0006815742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9947516,"threshold_uncertainty_score":0.9998212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2747940070","doi":"10.3758/s13428-017-0963-x","title":"The cognitive reflection test is robust to multiple exposures","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Computer science; Cognition; Reflection (computer programming); Psychology; Cognitive psychology; Artificial intelligence; Statistics; Mathematics; Geology; Programming language; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.7821180915133141,"gpt":0.736822124123797,"spread":0.04529596738951713,"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":[0.03896362,0.0001426981,0.0001825726,0.0003001801,0.01193834,0.001874274,0.002291562,0.0002174209,0.0002477342],"category_scores_gemma":[0.07929762,0.0001126192,0.0001073136,0.00066219,0.002255302,0.0003597655,0.0008875641,0.001069147,0.0002110179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003653772,"about_ca_system_score_gemma":0.0005069834,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01434024,"about_ca_topic_score_gemma":0.008990362,"domain_scores_codex":[0.991716,0.003976754,0.0002850147,0.0005540193,0.002200087,0.001268076],"domain_scores_gemma":[0.9864343,0.009926327,0.0001046476,0.00116418,0.001880696,0.0004898285],"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":[0.0001134802,0.000244665,0.1228525,0.000006941428,0.00001300542,0.00004942892,0.006269635,2.824372e-7,0.0181916,0.001043918,0.02313568,0.8280789],"study_design_scores_gemma":[0.0006315969,0.0006912937,0.3756223,0.0001420731,0.00002639289,0.000006634591,0.02690391,0.00006895861,0.1150427,0.003872205,0.4764803,0.0005116041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5714381,0.0006645868,0.03476397,0.08071434,0.002368182,0.01751791,0.0001731018,0.00108721,0.2912726],"genre_scores_gemma":[0.891676,0.0003528389,0.07499979,0.00008365303,0.0005656469,0.003277599,0.000002077639,0.00005754788,0.02898485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8275672,"threshold_uncertainty_score":0.9991619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002429320","doi":"10.3758/s13428-013-0327-0","title":"Pupil diameter measurement errors as a function of gaze direction in corneal reflection eyetrackers","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pupillometry; Gaze; Pupillary response; Pupil; Eye tracking; Psychology; Nonverbal communication; Cognitive psychology; Computer vision; Reflection (computer programming); Task (project management); Artificial intelligence; Computer science; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.3221110839369203,"gpt":0.5182101067454136,"spread":0.1960990228084933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00830446,0.0001468995,0.0002465801,0.001044592,0.0001119966,0.0000876354,0.0005197946,0.0001896951,0.00005081606],"category_scores_gemma":[0.00101291,0.0001365588,0.00008650911,0.00182828,0.0002137367,0.0004297563,0.0001823876,0.0007402318,0.00005617847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004220768,"about_ca_system_score_gemma":0.000132255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001866922,"about_ca_topic_score_gemma":0.0001561983,"domain_scores_codex":[0.9953907,0.002151753,0.0003954276,0.0005570893,0.0009691347,0.0005358558],"domain_scores_gemma":[0.9981115,0.0002733346,0.0001124045,0.0006064167,0.0007878356,0.0001084961],"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":[0.00002126379,0.0003037167,0.01297177,0.00001409943,0.000009449155,0.000006070385,0.0001497714,0.000004602784,0.3120908,0.0008412725,0.000255379,0.6733319],"study_design_scores_gemma":[0.0004344095,0.0008576998,0.9106695,0.00006344055,0.00001120664,0.00001415266,0.0002046864,0.001002227,0.08098774,0.004509496,0.001065529,0.0001798891],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.660297,0.0001199223,0.3363523,0.0004898519,0.0005671523,0.0007767769,5.348767e-7,0.0003574973,0.001039017],"genre_scores_gemma":[0.861295,0.00001677989,0.1379202,0.00001340283,0.00002213249,0.0005513167,8.615917e-7,0.00001879785,0.0001615198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8976977,"threshold_uncertainty_score":0.5568705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124006395","doi":"10.3758/brm.42.2.393","title":"Exploring lexical co-occurrence space using HiDEx","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":154,"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":"Computer science; Representation (politics); Co-occurrence; Set (abstract data type); Space (punctuation); A priori and a posteriori; Semantic space; Lexical decision task; Natural language processing; Artificial intelligence; Basis (linear algebra); Semantic data model; Hyperspace; Mathematics; Cognition","retraction":null,"screen_n_in":null,"score":{"opus":0.8360044474353515,"gpt":0.6474662355025267,"spread":0.1885382119328248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008494222,0.0001667457,0.0002239549,0.0003922172,0.0004140926,0.00038647,0.001821425,0.0001116897,0.00007310764],"category_scores_gemma":[0.001071243,0.0001611009,0.00008964767,0.0008114876,0.0002235734,0.001038944,0.0009058259,0.001721608,0.00005133874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008689293,"about_ca_system_score_gemma":0.0002970342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002210237,"about_ca_topic_score_gemma":0.000008650139,"domain_scores_codex":[0.995764,0.001234082,0.0003019015,0.0007577005,0.001037146,0.0009051346],"domain_scores_gemma":[0.9970671,0.0007812361,0.00005130302,0.001431552,0.0002797777,0.0003890232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003983363,0.0001173607,0.004166203,0.00001627028,0.000003783574,0.00009664246,0.0007699186,0.00004003489,0.3933397,0.02626682,0.00008685322,0.5750925],"study_design_scores_gemma":[0.0009308129,0.0002210138,0.01987038,0.0001186364,0.00002434796,0.0003467642,0.0004939048,0.3266862,0.5877433,0.00729882,0.05487873,0.001387076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3813691,0.00002166278,0.6170408,0.0002220187,0.000702718,0.0002117689,0.000003043973,0.0001216044,0.0003072852],"genre_scores_gemma":[0.1980235,0.00001028229,0.8015417,0.00001306728,0.0001819388,0.0001256436,0.000001339221,0.00001301964,0.00008948203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5737054,"threshold_uncertainty_score":0.7479625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2522857466","doi":"10.3758/s13428-016-0811-4","title":"Test-based age-of-acquisition norms for 44 thousand English word meanings","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":151,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Age of Acquisition; Word (group theory); Vocabulary; Test (biology); Word list; Psychology; Linguistics; Word recognition; Cognitive psychology; Computer science; Artificial intelligence; Cognition","retraction":null,"screen_n_in":null,"score":{"opus":0.1987628173989918,"gpt":0.5479670901449614,"spread":0.3492042727459695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008806281,0.0001839734,0.0003351095,0.0004635684,0.0001780292,0.00006197498,0.0004044878,0.0001883624,0.001075253],"category_scores_gemma":[0.002220784,0.0001250782,0.0001493922,0.0004614771,0.0002732446,0.0001248756,0.00007546613,0.0002634828,0.00004496482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381901,"about_ca_system_score_gemma":0.0001265394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007307785,"about_ca_topic_score_gemma":0.000003180365,"domain_scores_codex":[0.9964516,0.001250546,0.0004784948,0.0005416475,0.0005199859,0.000757776],"domain_scores_gemma":[0.9929157,0.005448684,0.0001172108,0.0006245878,0.000689805,0.0002039653],"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":[0.0003535952,0.0005248372,0.02990455,0.00005146324,0.00002863457,0.0000432634,0.004389449,1.639827e-7,0.1689642,0.0008952523,0.005315911,0.7895287],"study_design_scores_gemma":[0.006501794,0.001981583,0.3525958,0.0006136408,0.00009718447,0.0000232668,0.001442172,0.00001564344,0.2585849,0.002651404,0.3746382,0.0008544817],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8526614,0.0002476965,0.1350533,0.0004081256,0.001428823,0.002108223,0.0001347449,0.0002226675,0.007735067],"genre_scores_gemma":[0.5207559,0.00001008551,0.457453,0.00006815526,0.0003849814,0.002614522,0.00005258357,0.00009631549,0.01856442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7886742,"threshold_uncertainty_score":0.9998379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210813972","doi":"10.3758/s13428-021-01772-6","title":"Expanding horizons of cross-linguistic research on reading: The Multilingual Eye-movement Corpus (MECO)","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":149,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Universiteit Gent; Saint Petersburg State University; Israel Science Foundation; Fonds Wetenschappelijk Onderzoek; Eesti Teadusagentuur","keywords":"Reading (process); Eye movement; Computer science; Linguistics; Contrast (vision); Eye tracking; Word (group theory); Cognitive psychology; Empirical research; Diversity (politics); Psychology; Artificial intelligence; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.4203943651102048,"gpt":0.6630701278381799,"spread":0.242675762727975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.039213,0.000266043,0.0004312651,0.001214162,0.002484276,0.0002282302,0.001553779,0.0001282138,0.002796064],"category_scores_gemma":[0.003635402,0.0002115334,0.0001888192,0.00195361,0.0008939033,0.00005168513,0.001154974,0.00323271,0.0001076099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007644623,"about_ca_system_score_gemma":0.000365531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008844752,"about_ca_topic_score_gemma":0.000007915012,"domain_scores_codex":[0.9806746,0.01293693,0.0008973368,0.001011994,0.002855756,0.001623343],"domain_scores_gemma":[0.989432,0.007531111,0.0001854938,0.001538994,0.001034626,0.0002777511],"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":[0.002215481,0.004371646,0.1851736,0.0001110449,0.0002557489,0.001115187,0.08762323,0.0001183068,0.09506823,0.0436998,0.008205941,0.5720418],"study_design_scores_gemma":[0.004434876,0.007457343,0.5319771,0.0002858381,0.00009421816,0.00008804435,0.05330151,0.000205802,0.1067616,0.006724412,0.2874003,0.001269044],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744512,0.0004106762,0.0002456634,0.0002260747,0.002274762,0.00160196,0.00007697617,0.00007441071,0.02063825],"genre_scores_gemma":[0.9568652,0.00002050905,0.00862473,0.00005374877,0.0003090437,0.00328234,0.00003254063,0.00008815447,0.03072376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5707728,"threshold_uncertainty_score":0.9990669,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043356813","doi":"10.3758/s13428-012-0299-5","title":"Recurrence quantification analysis of eye movements","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":148,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Recurrence quantification analysis; Gaze; Eye movement; Fixation (population genetics); Computer science; Artificial intelligence; Context (archaeology); Nonlinear system; Geography; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6078203590008676,"gpt":0.6485880780666875,"spread":0.04076771906581989,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003726198,0.00009111444,0.0002093872,0.0008265675,0.0002062371,0.0001159628,0.0004583668,0.00007209662,0.002858568],"category_scores_gemma":[0.001809434,0.00008054548,0.0001000267,0.003305001,0.0002153739,0.0002465075,0.0001110772,0.0002740872,0.0002150097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004076492,"about_ca_system_score_gemma":0.00004981046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001756182,"about_ca_topic_score_gemma":0.000003072337,"domain_scores_codex":[0.9957912,0.002301632,0.0003251058,0.0004448449,0.0008059668,0.0003312799],"domain_scores_gemma":[0.9984849,0.0004326526,0.0001048851,0.0004642892,0.0003793029,0.0001339341],"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":[0.000004585409,0.0001623622,0.001641948,0.000009432312,0.000005111764,4.896889e-7,0.000248646,0.000003267475,0.8173016,0.0005889258,0.00005184191,0.1799817],"study_design_scores_gemma":[0.00009305072,0.00009820579,0.107746,0.0000120099,0.00004533155,2.938091e-7,0.0002639608,0.004884387,0.8852714,0.0009988279,0.0004839964,0.0001026039],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9347575,0.00001891945,0.06318994,0.0001060346,0.0001365098,0.0005288569,0.00001489624,0.00004422791,0.00120312],"genre_scores_gemma":[0.96077,0.00004419114,0.03625403,0.00005885561,0.00001259193,0.0003071806,0.000008748062,0.00001248474,0.002531906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1798791,"threshold_uncertainty_score":0.998053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045733287","doi":"10.3758/s13428-020-01393-5","title":"A thorough evaluation of the Language Environment Analysis (LENA) system","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":140,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; James S. McDonnell Foundation; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Set (abstract data type); Language acquisition; Psychology; Computer science; Key (lock); Natural language processing; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.4149328441978206,"gpt":0.606574171447506,"spread":0.1916413272496855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009325061,0.0001062793,0.0002423948,0.0001732253,0.0001156391,0.00002137187,0.0004650972,0.00009254089,0.003814666],"category_scores_gemma":[0.0004131009,0.00007237838,0.0001965797,0.001331566,0.0001329422,0.00003771754,0.0002070614,0.0002827155,0.0001031601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269687,"about_ca_system_score_gemma":0.00008732427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003540811,"about_ca_topic_score_gemma":0.0000159043,"domain_scores_codex":[0.991183,0.006502504,0.0002804682,0.0003581337,0.001354315,0.000321567],"domain_scores_gemma":[0.998788,0.000271063,0.00009326839,0.0006083421,0.0001334557,0.0001058673],"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":[0.0001808709,0.0005918208,0.1241398,0.0001043068,0.00119249,0.0000558393,0.1094043,0.0001303296,0.04667333,0.002186941,0.002239269,0.7131007],"study_design_scores_gemma":[0.002078376,0.0001789904,0.8350564,0.00002772509,0.003012524,0.000005499387,0.1317963,0.002321493,0.02108593,0.00005349099,0.00399282,0.000390488],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9727211,0.001695193,0.00670972,0.0006033013,0.0001622347,0.001380417,0.00002218591,0.00004534552,0.01666052],"genre_scores_gemma":[0.9871551,0.00000439948,0.01142528,0.00003968914,0.00004553614,0.00050577,0.0000173501,0.00001718669,0.0007896743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7127102,"threshold_uncertainty_score":0.997096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1998828876","doi":"10.3758/s13428-013-0441-z","title":"Error bars in within-subject designs: a comment on Baguley (2012)","year":2014,"lang":"en","type":"letter","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":129,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Plot (graphics); Computer science; Standard error; Set (abstract data type); Subject (documents); Confidence interval; Factor (programming language); Statistics; Data set; Error bar; Algorithm; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8313740192000905,"gpt":0.6323470359685018,"spread":0.1990269832315886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.01748976,0.0009663656,0.00158439,0.00121949,0.0004541254,0.0001633704,0.001866509,0.002879915,0.009969467],"category_scores_gemma":[0.0004919665,0.0007412399,0.0004239717,0.001149093,0.0009840648,0.00008164076,0.0004694631,0.01399221,0.00255783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000501864,"about_ca_system_score_gemma":0.00008629739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002022909,"about_ca_topic_score_gemma":0.0000665793,"domain_scores_codex":[0.9687154,0.02360817,0.001231693,0.002106619,0.001749069,0.00258909],"domain_scores_gemma":[0.9924347,0.004540807,0.000308512,0.002090589,0.0002882374,0.0003371314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003008633,0.001140522,0.001891355,0.00004874796,0.00006282963,0.002660441,0.0008637261,4.25039e-7,0.0001811614,0.0002616376,0.9161835,0.07640484],"study_design_scores_gemma":[0.00119962,0.002297984,0.02664828,0.0002069636,0.00009000023,0.00005997103,0.0003341938,0.000001023663,0.0001057305,0.0007700484,0.9674231,0.0008631029],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.01320969,0.002867739,0.001592834,0.914748,0.007230632,0.008271839,0.0002733527,0.0005177722,0.05128816],"genre_scores_gemma":[0.002199152,0.0001871529,0.04087031,0.8891234,0.004335847,0.01647705,0.000439632,0.0005269493,0.04584053],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.07554173,"threshold_uncertainty_score":0.9995039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067456760","doi":"10.3758/brm.41.2.337","title":"Combined eyetracking and keystroke-logging methods for studying cognitive processes in text production","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":127,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"SR Research (Canada)","funders":"","keywords":"Timeline; Keystroke logging; Computer science; Parsing; Keystroke dynamics; Cognition; Reading (process); Human–computer interaction; Matching (statistics); Identification (biology); Artificial intelligence; Natural language processing; Psychology; Password; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.4066462785331903,"gpt":0.6576008177856255,"spread":0.2509545392524352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03303052,0.0001185557,0.0002360808,0.0005053629,0.001325759,0.0003024104,0.0001792025,0.0001184428,0.00001185968],"category_scores_gemma":[0.02445636,0.0001254119,0.00003475369,0.001097967,0.0003194454,0.0003495173,0.00003858711,0.000468652,0.000001027505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001750845,"about_ca_system_score_gemma":0.000417335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004863352,"about_ca_topic_score_gemma":0.0001607453,"domain_scores_codex":[0.9940004,0.004120094,0.0002962421,0.0005072505,0.0004037014,0.0006723251],"domain_scores_gemma":[0.9945515,0.004203791,0.00008916188,0.000125019,0.0008927106,0.0001378376],"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":[0.00005560343,0.0003230021,0.02116308,0.00008987486,0.000003653589,0.000001635413,0.02693625,5.370619e-7,0.01277368,0.0006432729,0.00003490817,0.9379745],"study_design_scores_gemma":[0.002643288,0.001396701,0.4899414,0.001911051,0.0001415344,0.00001161492,0.4046002,0.0001719137,0.07160008,0.01976644,0.006809471,0.001006302],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9757813,0.0007827566,0.01579596,0.00262981,0.000278733,0.002368206,0.000002815155,0.0001312741,0.002229204],"genre_scores_gemma":[0.7519357,0.0001267329,0.2465495,0.00002126898,0.0002920706,0.0004975033,0.000005070067,0.00001446854,0.0005577095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9369682,"threshold_uncertainty_score":0.9999744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142398106","doi":"10.3758/s13428-012-0203-3","title":"Recognizing vocal emotions in Mandarin Chinese: A validated database of Chinese vocal emotional stimuli","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":123,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Sadness; Disgust; Mandarin Chinese; Anger; Happiness; Surprise; Psychology; Prosody; Audiology; Cognitive psychology; Speech recognition; Social psychology; Computer science; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3763723755228597,"gpt":0.6081377045351003,"spread":0.2317653290122406,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01074727,0.0002786182,0.0004541038,0.001213758,0.0002223852,0.00004105137,0.0003689076,0.0003057935,0.006564787],"category_scores_gemma":[0.001846252,0.0002416175,0.000179672,0.001945296,0.0003781555,0.0004059625,0.0002898743,0.001315596,0.0003306413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000137476,"about_ca_system_score_gemma":0.0001276915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004788173,"about_ca_topic_score_gemma":0.0001082674,"domain_scores_codex":[0.9914575,0.005496685,0.000683083,0.0005475472,0.0007936297,0.00102151],"domain_scores_gemma":[0.9972009,0.001130416,0.0001330463,0.0006473224,0.0004533531,0.0004349517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004143975,0.006666087,0.6332029,0.0001333799,0.00008280495,0.00008653336,0.003942158,0.000004756005,0.06693611,0.001327358,0.001643495,0.2855601],"study_design_scores_gemma":[0.001992991,0.0001866641,0.9941043,0.0001075916,0.00002829112,0.0001206686,0.000616515,0.000138041,0.0009494856,0.0005659063,0.0009260591,0.0002635272],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9612498,0.0002232133,0.02924113,0.0002731441,0.001237901,0.0009274975,0.000249144,0.00008594541,0.006512213],"genre_scores_gemma":[0.92796,0.00002928954,0.06890664,0.00003351326,0.000376197,0.00034204,0.0005989294,0.0000602526,0.001693101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3609014,"threshold_uncertainty_score":0.9943433,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1998133270","doi":"10.3758/brm.40.4.1075","title":"Body—object interaction ratings for 1,618 monosyllabic nouns","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":117,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Northern British Columbia","funders":"","keywords":"Noun; Referent; Set (abstract data type); Generalizability theory; Object (grammar); Word (group theory); Computer science; Psychology; Concreteness; Natural language processing; Artificial intelligence; Cognitive psychology; Mathematics; Linguistics; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.5842658790059307,"gpt":0.6586748091934802,"spread":0.07440893018754946,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003749654,0.0001519171,0.0002212925,0.0004140395,0.0006856381,0.00006135405,0.0002439344,0.0002080943,0.003300281],"category_scores_gemma":[0.001244175,0.0001512054,0.0001277341,0.0007273215,0.000165514,0.0002905029,0.00005408024,0.0005356526,0.0003266608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000239889,"about_ca_system_score_gemma":0.0001383852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002640735,"about_ca_topic_score_gemma":0.00001530863,"domain_scores_codex":[0.9962744,0.001876892,0.0004313408,0.0004818036,0.0004242209,0.0005113587],"domain_scores_gemma":[0.997256,0.001179888,0.0001294591,0.0004713306,0.0008120282,0.0001512322],"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":[0.0008232461,0.001923001,0.07663365,0.00006977173,0.0001248994,0.00007549641,0.01527645,0.00002453065,0.249901,0.00779699,0.1293712,0.5179797],"study_design_scores_gemma":[0.00334706,0.001400275,0.3650401,0.00003900542,0.0000651117,0.0002870931,0.006571887,0.003138335,0.05322015,0.0006937164,0.5654818,0.0007153859],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6953915,0.0001004213,0.2900475,0.0006640728,0.001938454,0.001926419,0.00001894143,0.0002442136,0.009668554],"genre_scores_gemma":[0.7770761,0.0000694359,0.1607807,0.000248422,0.0007812831,0.003419295,0.0001715341,0.0001184319,0.0573348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5172644,"threshold_uncertainty_score":0.9976108,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903145455","doi":"10.3758/s13428-018-1171-z","title":"Quantifying sensorimotor experience: Body–object interaction ratings for more than 9,000 English words","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":116,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexical decision task; Lexicon; Task (project management); Cognitive psychology; Psychology; Computer science; Referent; Semantics (computer science); Object (grammar); Age of Acquisition; Cognition; Natural language processing; Artificial intelligence; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.4921422929899069,"gpt":0.6493498938476473,"spread":0.1572076008577404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004742756,0.0002012221,0.0002556145,0.0004608757,0.0007633396,0.0002033388,0.0003254221,0.0002618693,0.00394796],"category_scores_gemma":[0.003094364,0.0001964529,0.000127634,0.0009271725,0.0003924393,0.0004655226,0.00008996674,0.000556036,0.00009995993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002504784,"about_ca_system_score_gemma":0.00008728699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003471437,"about_ca_topic_score_gemma":0.00003450357,"domain_scores_codex":[0.9956235,0.001967321,0.0005010958,0.0006628557,0.0005785706,0.0006666409],"domain_scores_gemma":[0.9962096,0.001065337,0.0001736814,0.0006045785,0.001760997,0.0001857598],"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":[0.001183931,0.0009981026,0.1540867,0.00008104901,0.00009344069,0.0000206753,0.1606106,0.000002766674,0.2493611,0.004316569,0.02021143,0.4090336],"study_design_scores_gemma":[0.002793881,0.001732829,0.283883,0.0001204633,0.00007116406,0.00004362392,0.1281198,0.004219445,0.1827924,0.0001532836,0.3951525,0.0009176951],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8738052,0.0000346353,0.1166177,0.0002002704,0.004267353,0.001498442,0.00002011941,0.0002567272,0.003299475],"genre_scores_gemma":[0.9079846,0.000008339078,0.07960901,0.0001155935,0.001910159,0.002002538,0.00006593821,0.00008006197,0.008223768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4081159,"threshold_uncertainty_score":0.9969625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809193001","doi":"10.3758/s13428-018-1056-1","title":"The Massive Auditory Lexical Decision (MALD) database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":115,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Killam Trusts; University of Alberta","keywords":"Lexical decision task; Computer science; Lexical database; Lexical access; Natural language processing; Set (abstract data type); Stimulus (psychology); Speech recognition; Artificial intelligence; Database; Psychology; Cognition; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.3306016750896725,"gpt":0.644614645825324,"spread":0.3140129707356515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01445023,0.0001613584,0.0001852954,0.0002380591,0.001108053,0.0001869778,0.0008460202,0.0001540013,0.002792807],"category_scores_gemma":[0.001945002,0.0001037263,0.00008548498,0.0005587573,0.0009521261,0.000104376,0.0004388937,0.0008857825,0.002408463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001380432,"about_ca_system_score_gemma":0.0001702901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001423922,"about_ca_topic_score_gemma":0.000016031,"domain_scores_codex":[0.9931328,0.004077114,0.0003886045,0.0005943849,0.0008853409,0.0009217682],"domain_scores_gemma":[0.992977,0.004902131,0.00006283457,0.001253232,0.0005011001,0.0003037024],"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":[0.0002527057,0.000177161,0.001671103,0.000002545948,0.00002129371,0.0001143165,0.001529331,2.936181e-8,0.005595767,0.004139388,0.1684664,0.81803],"study_design_scores_gemma":[0.0004131903,0.0002750557,0.1018163,0.00004023382,0.00001201705,0.00003320547,0.001065419,0.00001773161,0.003556148,0.001069395,0.8915302,0.000171046],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8070346,0.00158046,0.09116922,0.002160515,0.0165056,0.002114654,0.00006807192,0.0002796916,0.07908719],"genre_scores_gemma":[0.2332735,0.0001482756,0.6481622,0.0002578027,0.005036814,0.002328651,0.00005235698,0.0001484811,0.1105919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8178589,"threshold_uncertainty_score":0.9983683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2288693139","doi":"10.3758/s13428-016-0720-6","title":"The Calgary semantic decision project: concrete/abstract decision data for 10,000 English words","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":101,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Lexical decision task; Computer science; Lexicon; Natural language processing; Semantics (computer science); Semantic memory; Artificial intelligence; Variance (accounting); Word (group theory); Task (project management); Semantic property; Linguistics; Psychology; Cognitive psychology; Cognition","retraction":null,"screen_n_in":null,"score":{"opus":0.4123654394581135,"gpt":0.5860038097873501,"spread":0.1736383703292366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01701584,0.0002666964,0.0003413282,0.0002909276,0.001194354,0.0002752471,0.00314365,0.0002441133,0.0002715105],"category_scores_gemma":[0.07092202,0.0001349949,0.0001418692,0.0006260252,0.00100867,0.0004147593,0.001559095,0.0006203178,0.00005905383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007168174,"about_ca_system_score_gemma":0.0003169574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000891411,"about_ca_topic_score_gemma":0.00004142688,"domain_scores_codex":[0.9932312,0.002546976,0.0006126752,0.001439272,0.0009898095,0.001180034],"domain_scores_gemma":[0.9482292,0.04832654,0.0001344092,0.002688899,0.0004134742,0.000207485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003972859,0.00003537674,0.00005931401,0.000006790058,0.000002543905,0.000226337,0.0001819929,1.709414e-8,0.4277552,0.00005719122,0.006131289,0.5651466],"study_design_scores_gemma":[0.00215048,0.0008184655,0.001126311,0.0002367975,0.00004970259,0.0002606533,0.00045788,0.0001107222,0.5035612,0.002105741,0.488607,0.0005150758],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9785309,0.0004994902,0.01436213,0.0003489308,0.001624024,0.003268327,0.0004717071,0.0001981364,0.0006963962],"genre_scores_gemma":[0.6623589,0.002448513,0.3085629,0.0006799525,0.002663203,0.002552811,0.0001234397,0.0003892111,0.02022108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5646315,"threshold_uncertainty_score":0.936904,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030751416","doi":"10.3758/brm.41.2.546","title":"Subjective frequency and imageability ratings for 3,600 French nouns","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":98,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Noun; Reliability (semiconductor); Psychology; Audiology; Consistency (knowledge bases); Rating scale; Cognitive psychology; Computer science; Statistics; Natural language processing; Artificial intelligence; Developmental psychology; Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2242416127247494,"gpt":0.6053365934815501,"spread":0.3810949807568007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01037657,0.0001864316,0.0003084222,0.0002740973,0.0003756742,0.0001345193,0.0002840193,0.0001623222,0.0004556013],"category_scores_gemma":[0.001468236,0.0001652068,0.0000904788,0.0004361561,0.0002619337,0.0001475245,0.00005730526,0.0005930584,0.00002936752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001488365,"about_ca_system_score_gemma":0.0001278046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007220718,"about_ca_topic_score_gemma":0.0000119321,"domain_scores_codex":[0.9956896,0.002056835,0.0003963248,0.0007307147,0.0003523987,0.0007740958],"domain_scores_gemma":[0.9968026,0.001833078,0.00006743176,0.0005525704,0.0005111367,0.0002331764],"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":[0.00009410157,0.0006599697,0.1082023,0.00002924263,0.00002554232,0.0000400492,0.01750684,4.482363e-8,0.04478716,0.004765504,0.003073318,0.8208159],"study_design_scores_gemma":[0.0006997304,0.0006991251,0.9705245,0.00001908518,0.00001867049,0.0000312575,0.0008267036,0.000008428894,0.004248984,0.0151755,0.007515534,0.0002324857],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.961116,0.0005584164,0.02054078,0.0006375969,0.0003704164,0.001799692,0.00003855497,0.00009814774,0.01484039],"genre_scores_gemma":[0.5326555,0.000008590246,0.4597542,0.00008385901,0.0001252276,0.00104635,0.00001845664,0.00002397855,0.006283817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8623222,"threshold_uncertainty_score":0.673694,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W927394476","doi":"10.3758/s13428-015-0627-7","title":"The influence of base rates on correlations: An evaluation of proposed alternative effect sizes with real-world data","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":95,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ministry of Community Safety and Correctional Services; Royal Ottawa Mental Health Centre; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Mathematics; Correlation; Pearson product-moment correlation coefficient; Base (topology); Sample size determination; Statistic; Polychoric correlation; Econometrics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.8490125083874293,"gpt":0.6913935802776402,"spread":0.1576189281097891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03038406,0.0001625908,0.0003298782,0.0001744455,0.0002231734,0.00003164502,0.0008751809,0.0000652594,0.0001000117],"category_scores_gemma":[0.00232013,0.00008379356,0.00003525503,0.0009227574,0.001245778,0.0001668765,0.0002121317,0.0004930173,0.00001981519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007590417,"about_ca_system_score_gemma":0.0001164478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003883948,"about_ca_topic_score_gemma":0.0007712598,"domain_scores_codex":[0.9836881,0.01365827,0.0003937371,0.0005156975,0.001394305,0.0003499482],"domain_scores_gemma":[0.9926409,0.003980233,0.0002487618,0.001349,0.00163464,0.0001464377],"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":[0.003537518,0.00152983,0.3616383,0.00001280811,0.00009219862,0.00001701023,0.002066965,0.0001585495,0.005177067,0.002104302,0.0006722143,0.6229932],"study_design_scores_gemma":[0.001590312,0.005595521,0.9839983,0.00005955171,0.000159026,0.000002544111,0.001230399,0.0001831828,0.005727621,0.001003801,0.0003194134,0.0001303018],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949218,0.000219261,0.00008762074,0.0001522772,0.0001530457,0.00185459,0.00006580834,0.00002260667,0.002522964],"genre_scores_gemma":[0.9929828,0.00002825071,0.005858491,0.000007672702,0.00004448512,0.0005849286,0.00003905993,0.00001770816,0.0004366102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6228629,"threshold_uncertainty_score":0.9984236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1842016767","doi":"10.3758/s13428-015-0636-6","title":"Ratings of age of acquisition of 299 words across 25 languages: Is there a cross-linguistic order of words?","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":94,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Age of Acquisition; Linguistics; Natural language processing; Computer science; Word order; Psychology; Order (exchange); Artificial intelligence; Cognition; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.3035427565150631,"gpt":0.597421963177566,"spread":0.2938792066625029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006516132,0.0001889423,0.0006067973,0.0002575341,0.00008708284,0.0000260654,0.0007713814,0.0002049793,0.0002287613],"category_scores_gemma":[0.0119699,0.0001558231,0.0001654662,0.001135518,0.001928719,0.00009726376,0.0004196539,0.0004810263,0.000003903889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003071931,"about_ca_system_score_gemma":0.0002378386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007892002,"about_ca_topic_score_gemma":0.00002676607,"domain_scores_codex":[0.9949623,0.0023148,0.0008071538,0.000503736,0.0008789761,0.000533037],"domain_scores_gemma":[0.9956587,0.00184882,0.0004454279,0.0007754334,0.001131925,0.0001396837],"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":[0.000196446,0.000389683,0.007825589,0.0002006516,0.000007864918,0.0002917527,0.02276096,0.000002336343,0.9604589,0.0001159641,0.00002863685,0.007721216],"study_design_scores_gemma":[0.0008125048,0.0006420249,0.005180197,0.0001353053,0.00002296828,0.00004135115,0.003492749,0.00001436809,0.9889147,0.0003811276,0.0002330729,0.0001295986],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968609,0.0004479057,0.0005450896,0.00003629629,0.000152516,0.0005112554,0.0002031989,0.00002394164,0.001218962],"genre_scores_gemma":[0.9794567,0.00002913917,0.01930267,0.00004933878,0.00006753296,0.000037543,0.00001023162,0.00003228422,0.001014586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02845583,"threshold_uncertainty_score":0.9963527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2767253414","doi":"10.3758/s13428-017-0981-8","title":"MorphoLex: A derivational morphological database for 70,000 English words","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":92,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University; Centres Intégré Universitaires de Santé et de Services Sociaux","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Suffix; Computer science; Natural language processing; Lexicon; Word (group theory); Root (linguistics); Artificial intelligence; Lexical decision task; Noun; Linguistics; Cognition; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.4441928567752986,"gpt":0.6216715043181028,"spread":0.1774786475428042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01139074,0.0002254692,0.0003364877,0.0003163584,0.001225723,0.0004395732,0.001293981,0.0002337962,0.003918114],"category_scores_gemma":[0.00557165,0.0001957377,0.0001445055,0.0001897252,0.0005372837,0.0002684227,0.0004829601,0.0007805303,0.0001395065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248196,"about_ca_system_score_gemma":0.0001389822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002907237,"about_ca_topic_score_gemma":0.00000404398,"domain_scores_codex":[0.9955681,0.001465368,0.0004460692,0.0008396989,0.0006734388,0.001007311],"domain_scores_gemma":[0.9953814,0.001719434,0.0001484567,0.001724227,0.0006901525,0.0003363026],"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":[0.0009786937,0.00197592,0.0918581,0.00006377554,0.0001467039,0.0009399522,0.008393152,0.000001014143,0.04384521,0.03254629,0.1286851,0.6905661],"study_design_scores_gemma":[0.002175023,0.0003260967,0.4704172,0.00006643568,0.00003792096,0.00009410323,0.001048003,0.00003799785,0.006151546,0.001478353,0.5176719,0.0004954339],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9223922,0.0002785113,0.04355606,0.0008999029,0.003061233,0.002282411,0.0005519212,0.000197772,0.02677993],"genre_scores_gemma":[0.33219,0.00002090679,0.6294411,0.0001600676,0.001018579,0.006005033,0.0003602867,0.00008166683,0.03072238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6900706,"threshold_uncertainty_score":0.9969925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382502700","doi":"10.3758/s13428-023-02124-2","title":"The Misinformation Susceptibility Test (MIST): A psychometrically validated measure of news veracity discernment","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Economic and Social Research Council; Cambridge Trust; Deutscher Akademischer Austauschdienst; University of Virginia","keywords":"Mist; Misinformation; Psychology; Psychological intervention; Test (biology); Computer science; Social psychology; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.4256537945364519,"gpt":0.6244316175167799,"spread":0.198777822980328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03447419,0.0001108468,0.0001885368,0.0003896973,0.001441287,0.0003436545,0.0006873588,0.0001352653,0.0003543424],"category_scores_gemma":[0.02735897,0.00007737233,0.000117679,0.004532106,0.0006554558,0.0005125549,0.0001401751,0.0004288414,0.0001447759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003583152,"about_ca_system_score_gemma":0.0004782528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001413655,"about_ca_topic_score_gemma":0.0005594238,"domain_scores_codex":[0.9928012,0.00295591,0.0006088096,0.0001926608,0.002731402,0.0007099553],"domain_scores_gemma":[0.9945461,0.003450781,0.0001760343,0.0005794675,0.0008971979,0.0003503969],"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":[0.00007738957,0.0002478152,0.01002821,0.00003251615,0.0000124056,0.000001305547,0.02637503,0.000004037579,0.00728196,0.001791604,0.01537065,0.9387771],"study_design_scores_gemma":[0.001141949,0.000447602,0.6658236,0.00006549358,0.00003283983,0.000001767312,0.08683269,0.0005043628,0.01352292,0.001631367,0.229602,0.0003933866],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9070686,0.00009059431,0.005618371,0.005983389,0.000619108,0.003057199,0.00009120099,0.000346884,0.07712464],"genre_scores_gemma":[0.9860023,0.0005406909,0.007853037,0.00004279699,0.0001011028,0.00007025907,0.00003051289,0.00001724357,0.005342119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9383837,"threshold_uncertainty_score":0.9998587,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2560525638","doi":"10.3758/s13428-016-0830-1","title":"Chronset: An automated tool for detecting speech onset","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"The Scarborough Hospital","funders":"","keywords":"Multitaper; Computer science; Speech recognition; Measure (data warehouse); Artificial intelligence; Natural language processing; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2584792315470756,"gpt":0.5748492312116953,"spread":0.3163699996646197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01124919,0.000179516,0.0002316605,0.0003913275,0.0006299706,0.0004691826,0.00148846,0.0001351933,0.00005428],"category_scores_gemma":[0.002583198,0.0001273074,0.0000951832,0.0008674181,0.0001653152,0.0009791908,0.0004163348,0.0002721785,0.00005035716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000191284,"about_ca_system_score_gemma":0.0004011141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003088256,"about_ca_topic_score_gemma":0.00001263635,"domain_scores_codex":[0.9957505,0.001442136,0.0003248459,0.0007607306,0.0006592491,0.001062511],"domain_scores_gemma":[0.9963647,0.001749454,0.00008242207,0.001005035,0.0005258739,0.0002724918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001144013,0.00005659082,0.0006863081,0.00001062757,0.00000292464,0.0000223006,0.00007749016,1.151931e-7,0.3517207,0.00004275428,0.0002772113,0.6470915],"study_design_scores_gemma":[0.000609931,0.0003957698,0.007362662,0.00007162667,0.000006128614,0.0001045739,0.00004039179,0.002324277,0.9841607,0.001828025,0.00283076,0.0002651287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3424472,0.00006405921,0.6554424,0.0004413371,0.0001814989,0.0005476732,0.00001080421,0.0007877827,0.0000772892],"genre_scores_gemma":[0.1170463,0.000005180058,0.881802,0.0000441158,0.000116906,0.0003901138,0.000001926036,0.00003150584,0.0005619811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6468264,"threshold_uncertainty_score":0.5191444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306655083","doi":"10.3758/s13428-022-01988-0","title":"Questions of value, questions of magnitude: An exploration and application of methods for comparing indirect effects in multiple mediator models","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":88,"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":"Operationalization; Mediation; Computer science; Mechanism (biology); Magnitude (astronomy); Value (mathematics); Psychology; Cognitive psychology; Epistemology; Machine learning; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.4829182336826193,"gpt":0.6283255401611992,"spread":0.14540730647858,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01282301,0.00009924634,0.0004232327,0.0004891308,0.0005153509,0.00001544596,0.0002942853,0.00006914413,0.000005880411],"category_scores_gemma":[0.001138946,0.0001170142,0.0000622267,0.0006509989,0.0005764955,0.0004655033,0.0002796567,0.0002429396,1.068036e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002891625,"about_ca_system_score_gemma":0.000180187,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01011374,"about_ca_topic_score_gemma":0.001750475,"domain_scores_codex":[0.9931031,0.005494628,0.0005062025,0.0003082917,0.0003150213,0.0002727812],"domain_scores_gemma":[0.996796,0.002324068,0.000219699,0.0002499423,0.0003093677,0.0001009371],"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":[0.0001697365,0.001946259,0.115868,0.0001796103,0.00002673811,5.335103e-7,0.04293209,0.00227685,0.5294676,0.09295397,0.000008131958,0.2141705],"study_design_scores_gemma":[0.003947789,0.002736039,0.1128358,0.0001667703,0.0002814893,0.000001840127,0.09898831,0.1140727,0.5543675,0.1110927,0.0006619687,0.0008470147],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8272719,0.0008895069,0.1684389,0.00008265211,0.0001072902,0.002918031,0.0000595508,0.00002751354,0.000204732],"genre_scores_gemma":[0.6096448,0.00008841407,0.386918,0.000001163104,0.00001041113,0.003301679,0.00001512052,0.00001188889,0.000008453202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2184792,"threshold_uncertainty_score":0.996478,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006342589","doi":"10.3758/brm.40.1.263","title":"Rebus puzzles as insight problems","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.4743901324418159,"gpt":0.5834460447021849,"spread":0.1090559122603689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004551849,0.0001518454,0.0002044806,0.0004050762,0.0008068583,0.0001484561,0.002056491,0.0001313159,0.0000845077],"category_scores_gemma":[0.0004909442,0.0001371056,0.00008918101,0.001928739,0.0004707678,0.0004523229,0.0009729812,0.000723174,0.000466364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001765698,"about_ca_system_score_gemma":0.0004669225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005014155,"about_ca_topic_score_gemma":0.00002351169,"domain_scores_codex":[0.9952083,0.001960109,0.0003383353,0.0006859642,0.001113146,0.0006941379],"domain_scores_gemma":[0.9968243,0.0006506666,0.00006584881,0.001666817,0.0004625135,0.0003299145],"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":[0.000009580212,0.001293164,0.001743252,0.00003753549,0.00002942344,0.0003034835,0.005692292,0.0000491457,0.1110344,0.1439786,0.009982412,0.7258468],"study_design_scores_gemma":[0.0009644667,0.0005031059,0.04698858,0.00006422809,0.00002086726,0.00106213,0.000237881,0.006119879,0.1556134,0.03127381,0.7562715,0.0008801506],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01791686,0.000470584,0.9573328,0.002976038,0.0001356474,0.001325464,0.000004210096,0.0003955385,0.01944283],"genre_scores_gemma":[0.0647006,0.0004264548,0.9220502,0.0001234792,0.0001046954,0.002311108,0.00001106202,0.00003969207,0.01023268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7462891,"threshold_uncertainty_score":0.6205783,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087093006","doi":"10.3758/s13428-011-0117-5","title":"Imageability and body–object interaction ratings for 599 multisyllabic nouns","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":85,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Northern British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Noun; Object (grammar); Computer science; Psychology; Cognitive psychology; Linguistics; Natural language processing; Artificial intelligence; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.3464476339350444,"gpt":0.5887497293982573,"spread":0.242302095463213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008242314,0.0001715322,0.0002640351,0.000281527,0.0002905085,0.00007745824,0.0002118365,0.0001811233,0.002315034],"category_scores_gemma":[0.00152128,0.0001515153,0.0001261443,0.0003031773,0.0003054439,0.0002309504,0.0001056954,0.0005722425,0.00008085021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007408386,"about_ca_system_score_gemma":0.00004797875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001929018,"about_ca_topic_score_gemma":0.00009257142,"domain_scores_codex":[0.9951929,0.002954605,0.0003512487,0.0006334206,0.0002829774,0.0005847758],"domain_scores_gemma":[0.9973832,0.001339736,0.00008885537,0.0005170436,0.0004938489,0.0001773653],"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":[0.0007045533,0.0009302904,0.01111824,0.00007189612,0.00005213517,0.0000391982,0.01770953,7.973939e-9,0.1546534,0.001142418,0.0008886658,0.8126896],"study_design_scores_gemma":[0.004717987,0.002934564,0.7043853,0.00009530732,0.0003534522,0.0001995877,0.03661945,0.0001493374,0.2233467,0.01211696,0.0141502,0.0009312294],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590417,0.0003703672,0.02629858,0.0000483308,0.0007732542,0.001922394,0.0000441351,0.0001106705,0.01139058],"genre_scores_gemma":[0.8023677,0.00002772345,0.1911791,0.0000553583,0.0002191422,0.002579609,0.00003678626,0.00005738343,0.00347712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8117584,"threshold_uncertainty_score":0.998597,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148999650","doi":"10.3758/s13428-015-0667-z","title":"Effect size measures in a two-independent-samples case with nonnormal and nonhomogeneous data","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.9138052411701298,"gpt":0.754588885036263,"spread":0.1592163561338669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1264354,0.0003464618,0.001046488,0.0002826908,0.0001730849,0.0002063513,0.0009911794,0.0002107386,0.00009606998],"category_scores_gemma":[0.3338015,0.0002516926,0.00005835327,0.0007451635,0.0007577518,0.0002058742,0.001510773,0.001413254,0.00001281175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001523479,"about_ca_system_score_gemma":0.0003655612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001504564,"about_ca_topic_score_gemma":0.001298548,"domain_scores_codex":[0.963642,0.03142296,0.0009443986,0.001138991,0.001815883,0.001035775],"domain_scores_gemma":[0.7837085,0.2126118,0.0001616978,0.002150407,0.0005286045,0.0008390655],"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":[0.002492505,0.0009369171,0.02821771,0.0003417199,0.00009777203,0.02567615,0.0006471905,0.000003058719,0.002897192,0.003121698,0.0003223643,0.9352458],"study_design_scores_gemma":[0.067055,0.02137593,0.01956941,0.00187649,0.002695784,0.04884278,0.006403408,0.005440572,0.0713721,0.7460118,0.004220456,0.005136246],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8079693,0.0003341074,0.1862997,0.000111468,0.0003173843,0.003517406,0.000383486,0.0001339098,0.0009332243],"genre_scores_gemma":[0.1259147,0.00001558616,0.8732692,0.0000133738,0.0001810149,0.0003919686,0.00000480559,0.00007903844,0.0001302587],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9301095,"threshold_uncertainty_score":0.9999935,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3005165546","doi":"10.3758/s13428-020-01365-9","title":"Longform recordings of everyday life: Ethics for best practices","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":78,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; University of Manitoba","funders":"National Institute of Mental Health; Social Sciences and Humanities Research Council of Canada; Universität Zürich; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Stanford Maternal and Child Health Research Institute; Agence Nationale de la Recherche; James S. McDonnell Foundation","keywords":"Autonomy; Beneficence; Set (abstract data type); Fidelity; Research ethics; Computer science; Everyday life; Data sharing; Informed consent; Economic Justice; Internet privacy; Data science; Psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.8409786516589324,"gpt":0.7069141870663498,"spread":0.1340644645925826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01243043,0.0001538981,0.0003524129,0.0001641385,0.0002713398,0.00005906431,0.0004885244,0.0002766478,0.001315721],"category_scores_gemma":[0.02131858,0.0001397568,0.0001457561,0.0005724652,0.0002167179,0.0001247062,0.0002139471,0.001706315,0.000159829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004721121,"about_ca_system_score_gemma":0.0004115969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003697598,"about_ca_topic_score_gemma":0.000009967154,"domain_scores_codex":[0.9958259,0.001977374,0.0004479068,0.0005645626,0.0006104465,0.0005738263],"domain_scores_gemma":[0.9932242,0.005143038,0.0003365194,0.0003239803,0.0006173758,0.0003548868],"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":[0.00193532,0.001266414,0.05404625,0.0005328383,0.0002254566,0.00006045491,0.04331468,0.000001272322,0.06379101,0.01120032,0.02895097,0.794675],"study_design_scores_gemma":[0.001244239,0.002416881,0.09384999,0.00009951324,0.00009751596,0.00001376761,0.01000948,0.00003330715,0.009053392,0.0002531843,0.8825586,0.0003701616],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8657718,0.002612827,0.0307422,0.04812975,0.00195743,0.004813836,0.0001291633,0.0002954877,0.04554745],"genre_scores_gemma":[0.3776321,0.0002168862,0.6059509,0.001085257,0.0009143194,0.001006593,0.00003955144,0.000141203,0.01301316],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8536076,"threshold_uncertainty_score":0.9995972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2895796529","doi":"10.3758/s13428-018-1147-z","title":"The reliability of attentional biases for emotional images measured using a free-viewing eye-tracking paradigm","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","field":"Psychology","cited_by":76,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Attentional bias; Psychology; Cognitive psychology; Fixation (population genetics); Eye tracking; Anxiety; Reliability (semiconductor); Eye movement; Audiology; Cognition; Artificial intelligence; Computer science; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.5472372277828504,"gpt":0.6384359538892672,"spread":0.09119872610641677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01674007,0.0002768144,0.0004002242,0.0005810653,0.001413275,0.0001492242,0.0008787679,0.0002050858,0.0005847404],"category_scores_gemma":[0.02166639,0.000207785,0.0003300954,0.001608274,0.001747464,0.0002904643,0.0002993591,0.0004933404,0.00002316855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002021033,"about_ca_system_score_gemma":0.0002561415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002784099,"about_ca_topic_score_gemma":0.00001438232,"domain_scores_codex":[0.9919158,0.004266269,0.000720912,0.0009212303,0.001244167,0.0009316399],"domain_scores_gemma":[0.986025,0.008698165,0.0003215373,0.00108659,0.003670648,0.0001980064],"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":[0.0008395831,0.002025425,0.3386176,0.000109306,0.0002291719,0.000007185075,0.001176667,0.000004143404,0.02677967,0.001101113,0.004645304,0.6244649],"study_design_scores_gemma":[0.002193922,0.0006788549,0.9156082,0.0003025284,0.0002256266,0.00002971852,0.001624494,0.0001505435,0.02660146,0.01981926,0.03236176,0.0004035877],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7613046,0.007073173,0.2246107,0.0005890056,0.002268743,0.002561124,0.0004190889,0.0001049737,0.001068603],"genre_scores_gemma":[0.7690204,0.000755786,0.2267709,0.00002420064,0.001003001,0.0012958,0.00004215284,0.00009470151,0.0009930292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6240613,"threshold_uncertainty_score":0.9998868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2592069066","doi":"10.3758/s13428-018-1061-4","title":"Miami University deception detection database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":76,"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":"Deception; Psychology; Lie detection; Social psychology; Statement (logic); Computer science; Applied psychology; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3876640780767517,"gpt":0.6254059579783624,"spread":0.2377418799016107,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004747014,0.0001396897,0.0001664918,0.0008065766,0.0005305985,0.00003537356,0.0003450781,0.0002620838,0.01648728],"category_scores_gemma":[0.0002106797,0.0001493862,0.00009719122,0.001289573,0.0009853838,0.0001681584,0.000144619,0.0006962646,0.005265812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001850469,"about_ca_system_score_gemma":0.00003784587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003685144,"about_ca_topic_score_gemma":0.0002624818,"domain_scores_codex":[0.9941788,0.003985911,0.0002167961,0.0006372465,0.0003756134,0.0006055784],"domain_scores_gemma":[0.998044,0.0002771191,0.00006655052,0.0008540681,0.0005017364,0.0002565784],"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":[0.0003821366,0.0002556934,0.0007508474,0.000002488213,0.00001832324,0.00004556933,0.0005407585,2.733761e-8,0.1320665,0.001234925,0.009974659,0.8547281],"study_design_scores_gemma":[0.001648438,0.001188208,0.1779497,0.00001087004,0.00004006134,0.0002463287,0.003900316,0.00005688996,0.02509911,0.0004175935,0.7891141,0.0003284175],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5576504,0.00005146543,0.3622055,0.0001894701,0.005047924,0.0006660186,0.00003139102,0.000341665,0.07381608],"genre_scores_gemma":[0.8957655,0.00003274429,0.05928388,0.0001300396,0.0009135157,0.00008479477,0.00002837605,0.0000534831,0.04370763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8543997,"threshold_uncertainty_score":0.9955087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}