{"meta":{"query_hash":"49b792a6fb40","filters":{"venue":"Behavior Research Methods"},"cohort_total":304,"direct_labels_cover":3,"predictions_cover":304,"exported":304,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/49b792a6fb40","api":"https://metacan.xera.ac/api/v1/cohort?venue=Behavior+Research+Methods"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.30354275651506313,"score_gpt":0.597421963177566,"score_spread":0.2938792066625029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1842016767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9976864,0.00009881235,0.0002090856,0.000022965609,0.000015300626,0.000016852115,0.00019187853,0.000008669962,0.0017500297],"genre_scores_gemma":[0.99821484,0.00010115419,0.0004027348,0.000032781754,0.000009488534,0.000018509454,0.0003658093,0.000007594947,0.000846992],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99893004,0.00020257104,0.00019041153,0.0001465436,0.0004354666,0.00009492774],"domain_scores_gemma":[0.9790147,0.0067183385,0.0072126216,0.0011867424,0.0038014692,0.002066094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001968344,0.000269418,0.0003482875,0.00087340013,0.00023991826,0.0007278406,0.00028677232,0.0007202396,0.0027565605],"category_scores_gemma":[0.01677413,0.0002589246,0.00046703257,0.00030195547,0.000367731,0.00089623703,0.0005010443,0.0006816841,0.0013217373],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009827248,0.00019980963,0.9784509,0.00004538093,0.00010977593,0.00013059769,0.0011503887,0.00015091528,0.009734675,0.00006171588,0.00029116077,0.008692],"study_design_scores_gemma":[0.000009040359,0.000440015,0.9973189,0.0000079975825,0.000015004109,0.00018211409,0.0004569691,0.00017037959,0.0010905416,0.000040030423,0.00025829775,0.000010573253],"about_ca_topic_score_codex":0.0030204654,"about_ca_topic_score_gemma":0.006126424,"teacher_disagreement_score":0.0030204654,"about_ca_system_score_codex":0.00026317107,"about_ca_system_score_gemma":0.00023723503,"threshold_uncertainty_score":0.010409713},"labels":[],"label_agreement":null},{"id":"W1963917975","doi":"10.3758/brm.38.2.344","title":"An SPSS implementation of the nonrecursive outlier deletion procedure with shiftingz score criterion (Van Selst &amp; Jolicoeur, 1994)","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Outlier; Computer science; Univariate; Popularity; Simple (philosophy); Data mining; Database; Restructuring; Artificial intelligence; Machine learning; Psychology","score_opus":0.11959399906640342,"score_gpt":0.5160720460885306,"score_spread":0.3964780470221272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963917975","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020523973,0.00010877343,0.8693531,0.00039668434,0.00050982635,0.003425103,0.028329184,0.064828545,0.012524868],"genre_scores_gemma":[0.044576358,0.000102764316,0.9090829,0.00016419405,0.00009351659,0.011513834,0.008601119,0.014092394,0.011772979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99336267,0.0027141937,0.0010290336,0.0012019951,0.0011413454,0.0005507741],"domain_scores_gemma":[0.9792077,0.012993602,0.0012471116,0.0034913223,0.0027913162,0.00026893857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076636327,0.0017620678,0.0016016557,0.0024745057,0.0010332261,0.0026315516,0.002103476,0.00086260244,0.09789933],"category_scores_gemma":[0.039793056,0.0012984334,0.0016328099,0.0036798776,0.0007401775,0.0017766961,0.0021241393,0.0030065132,0.022709448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002217506,0.0014510758,0.012140882,0.0013593661,0.0006102997,0.00035427875,0.0044692014,0.0071663796,0.009592465,0.050895065,0.20590998,0.70383346],"study_design_scores_gemma":[0.0018459609,0.0018916568,0.044721518,0.0008071176,0.0011117009,0.0010980897,0.002513367,0.16270913,0.07103035,0.13045773,0.5810112,0.00080212293],"about_ca_topic_score_codex":0.0030581118,"about_ca_topic_score_gemma":0.0048666485,"teacher_disagreement_score":0.09789933,"about_ca_system_score_codex":0.00068547635,"about_ca_system_score_gemma":0.0028818413,"threshold_uncertainty_score":0.3275059},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"German; Valence (chemistry); Psychology; Arousal; Linguistics; Cognitive psychology; Social psychology","score_opus":0.11837886767040291,"score_gpt":0.5231030567677374,"score_spread":0.4047241890973345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968422660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7888965,0.00032226698,0.13214017,0.00033630777,0.00028647578,0.0009805926,0.016825099,0.0021782606,0.05803436],"genre_scores_gemma":[0.9426677,0.00009747211,0.042085573,0.00010826367,0.00006135371,0.0017400817,0.009262244,0.0005548605,0.0034223876],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976895,0.0007147801,0.00027294632,0.00034753903,0.00083485164,0.00014040896],"domain_scores_gemma":[0.99219245,0.0041251713,0.0014636554,0.00060459244,0.0013104616,0.00030371797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002945451,0.0005651332,0.00022414308,0.0014724707,0.0003663649,0.001850795,0.00045909884,0.0004412761,0.008063547],"category_scores_gemma":[0.026739175,0.00020299199,0.0004028086,0.00095924496,0.00069632655,0.0012990835,0.0009190032,0.00075149897,0.0018235424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004540784,0.0011964097,0.32212076,0.0014540303,0.0005376143,0.00052403676,0.017547168,0.0045224475,0.051384356,0.09575064,0.047817204,0.45260465],"study_design_scores_gemma":[0.00030207235,0.000910039,0.83937615,0.00028310303,0.0002694331,0.0011484212,0.0050762035,0.030384533,0.017100146,0.05982702,0.04494742,0.0003754328],"about_ca_topic_score_codex":0.0014426543,"about_ca_topic_score_gemma":0.0025625022,"teacher_disagreement_score":0.008063547,"about_ca_system_score_codex":0.00064011593,"about_ca_system_score_gemma":0.0003377348,"threshold_uncertainty_score":0.026975274},"labels":[],"label_agreement":null},{"id":"W1969265184","doi":"10.3758/s13428-014-0474-y","title":"Comment on Hoffman and Rovine (2007): SPSS MIXED can estimate models with heterogeneous variances","year":2014,"lang":"en","type":"letter","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Syntax; Computer science; Statistics; Homogeneous; Multilevel model; Econometrics; Natural language processing; Mathematics; Machine learning","score_opus":0.35452185905389183,"score_gpt":0.5775459775008415,"score_spread":0.22302411844694964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969265184","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002982939,0.00046772324,0.00063562783,0.9835011,0.013581596,0.000026805285,0.0001353093,0.000105885396,0.0012477075],"genre_scores_gemma":[0.0014792052,0.00021710822,0.00092762825,0.97868437,0.015345791,0.0001096346,0.000029616409,0.00005554205,0.0031511206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9712001,0.010850804,0.0041467,0.00325767,0.008687054,0.0018576643],"domain_scores_gemma":[0.7899403,0.16142394,0.008341124,0.0052742995,0.029839402,0.0051810457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03668896,0.0015542338,0.002674041,0.0021005005,0.005914188,0.007915244,0.004790252,0.06366454,0.010128155],"category_scores_gemma":[0.22280404,0.0021200145,0.0030515695,0.0027235136,0.008867502,0.0068436903,0.0036497046,0.06574862,0.01419322],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059860038,0.000030266501,0.00069174543,0.00006617157,0.000028247096,0.00024621031,0.00032142183,0.00010659672,0.0000861158,0.0036184483,0.9864587,0.008286203],"study_design_scores_gemma":[0.00026988745,0.00013933615,0.005119384,0.0010926346,0.00017910646,0.0007325622,0.0016423974,0.0016800971,0.00055059296,0.03206407,0.956291,0.0002389805],"about_ca_topic_score_codex":0.032039702,"about_ca_topic_score_gemma":0.04748822,"teacher_disagreement_score":0.06366454,"about_ca_system_score_codex":0.0068007326,"about_ca_system_score_gemma":0.008344443,"threshold_uncertainty_score":0.19403213},"labels":[],"label_agreement":null},{"id":"W1970590570","doi":"10.3758/brm.41.3.765","title":"Streams and patterns in behavior as challenges for future technologies","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"STREAMS; Computer science; Operating system","score_opus":0.5247012113643312,"score_gpt":0.6969705412938351,"score_spread":0.17226932992950383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970590570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.446379,0.003793043,0.4042496,0.093679644,0.0012733967,0.0012122161,0.003181909,0.0011818619,0.045049343],"genre_scores_gemma":[0.810349,0.0026523212,0.17470948,0.0033849475,0.0006616682,0.0017192765,0.001282454,0.0002913251,0.0049495846],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.986447,0.009850127,0.0006473846,0.0010416694,0.0017793769,0.00023439116],"domain_scores_gemma":[0.8843047,0.08972419,0.005760083,0.00982474,0.008229326,0.0021570257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025683813,0.00029263395,0.00066526124,0.0018636013,0.001338147,0.0072638267,0.0013715958,0.0014567357,0.0045794253],"category_scores_gemma":[0.10172777,0.00044648896,0.00045404467,0.0018837472,0.0020529637,0.014410713,0.0018340783,0.0027897325,0.0009668906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082832057,0.0010791963,0.20204452,0.0008407291,0.00019289818,0.00024576593,0.022195136,0.0047616423,0.0029338493,0.22322153,0.013164626,0.52849174],"study_design_scores_gemma":[0.00010711562,0.0005721295,0.073451884,0.0008126238,0.00016764789,0.0006577089,0.03255106,0.049723305,0.003337533,0.78059125,0.057879828,0.0001480477],"about_ca_topic_score_codex":0.0017181662,"about_ca_topic_score_gemma":0.0029805498,"teacher_disagreement_score":0.025683813,"about_ca_system_score_codex":0.0016338652,"about_ca_system_score_gemma":0.0022864498,"threshold_uncertainty_score":0.13583058},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2074451318612571,"score_gpt":0.5283622746603649,"score_spread":0.32091714279910777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974991592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922248,0.00025938472,0.0008617724,0.000025865318,0.000029056486,0.000050977244,0.00066954154,0.00005741964,0.0058211233],"genre_scores_gemma":[0.99063885,0.00022077603,0.002554322,0.00004229781,0.0000230585,0.0000819161,0.0017278858,0.00006387766,0.00464705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989207,0.00030821015,0.00021720499,0.00022888774,0.0002666894,0.00005833724],"domain_scores_gemma":[0.98131746,0.013302388,0.0015970798,0.0011104315,0.0019448354,0.00072787184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011726057,0.0002935376,0.00031728606,0.0010853399,0.00030386698,0.00069042336,0.00018675976,0.00062484626,0.009587685],"category_scores_gemma":[0.015695544,0.00021798149,0.00030717324,0.00060372317,0.0003783651,0.00094528624,0.00060221145,0.0004947548,0.0018142004],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0150540015,0.0025657278,0.36908805,0.0023318839,0.0005737377,0.0014256083,0.033450138,0.0013741842,0.3128424,0.0043451963,0.008168549,0.24878062],"study_design_scores_gemma":[0.00014892776,0.003103943,0.96958154,0.000090760215,0.0001521794,0.001296369,0.0025879124,0.0014850227,0.01395151,0.0008970596,0.006613131,0.0000916356],"about_ca_topic_score_codex":0.0005632723,"about_ca_topic_score_gemma":0.0010933153,"teacher_disagreement_score":0.009587685,"about_ca_system_score_codex":0.0001936499,"about_ca_system_score_gemma":0.00010052402,"threshold_uncertainty_score":0.032073975},"labels":[],"label_agreement":null},{"id":"W1977005518","doi":"10.3758/bf03192711","title":"A comparison of the randomization test with theF test when error is skewed","year":2005,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Randomization; Resampling; Statistics; Test (biology); Mathematics; Skew; Type I and type II errors; Restricted randomization; Permutation (music); Computer science; Medicine; Randomized controlled trial; Surgery; Biology","score_opus":0.22585174721536294,"score_gpt":0.5473035776803988,"score_spread":0.3214518304650359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977005518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38591945,0.003748521,0.58447754,0.00339704,0.0032355606,0.0017673625,0.0022543308,0.0031906199,0.012009449],"genre_scores_gemma":[0.8112194,0.00060063985,0.17924076,0.00091656327,0.00084099744,0.0015507911,0.0020428104,0.0010552385,0.0025328165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.74754554,0.2131188,0.006158895,0.016276767,0.014402208,0.0024977708],"domain_scores_gemma":[0.094795376,0.8720709,0.006951395,0.017597472,0.006687056,0.0018978067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17968693,0.0023493883,0.006097958,0.0065348987,0.0024698677,0.0028705292,0.008704313,0.007194445,0.01812955],"category_scores_gemma":[0.5512172,0.0009439128,0.0048982115,0.0056824274,0.008571453,0.011871213,0.004375354,0.004693603,0.0018568637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0796775,0.0033239145,0.09717745,0.003407009,0.011365506,0.0017936236,0.0030775035,0.061979182,0.0040888633,0.156678,0.029208776,0.5482227],"study_design_scores_gemma":[0.018610697,0.029463375,0.089197315,0.0010220418,0.004763146,0.0033291983,0.0030460227,0.6545733,0.009113087,0.1696565,0.015965864,0.0012594718],"about_ca_topic_score_codex":0.00283007,"about_ca_topic_score_gemma":0.0018971404,"teacher_disagreement_score":0.17968693,"about_ca_system_score_codex":0.0031088076,"about_ca_system_score_gemma":0.003682324,"threshold_uncertainty_score":0.9502867},"labels":[],"label_agreement":null},{"id":"W1978406346","doi":"10.3758/bf03192769","title":"Anagram software for cognitive research that enables specification of psycholinguistic variables","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Anagram; Anagrams; Computer science; Task (project management); Software; Cognition; Natural language processing; Artificial intelligence; Programming language; Psychology","score_opus":0.46341037151236264,"score_gpt":0.6295342610735168,"score_spread":0.1661238895611542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978406346","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006886437,0.000073399264,0.81842375,0.00012443935,0.00019406542,0.0011115673,0.014426761,0.14951351,0.009246013],"genre_scores_gemma":[0.057148438,0.00015702323,0.8748867,0.00027848152,0.00012574096,0.011301609,0.011934049,0.028422132,0.015745796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815387,0.000652772,0.00038540867,0.000390664,0.00031060845,0.00010676769],"domain_scores_gemma":[0.9792772,0.016287876,0.00082818477,0.0019067534,0.0014395387,0.0002604963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033961218,0.00153074,0.0010296847,0.0021571652,0.0008215264,0.0018433172,0.0012426511,0.0007611942,0.06974609],"category_scores_gemma":[0.017902935,0.001099353,0.0013178092,0.0014961953,0.0005243969,0.0021812548,0.001998598,0.0018324257,0.014597106],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002201992,0.0008484734,0.009289306,0.003580199,0.000497334,0.0007513474,0.003082593,0.0035185418,0.038155086,0.09710042,0.22733061,0.6136441],"study_design_scores_gemma":[0.0012892743,0.0008571522,0.026240803,0.00067648944,0.000858313,0.0020192943,0.00076505955,0.12124303,0.0867445,0.20498553,0.5539744,0.00034606937],"about_ca_topic_score_codex":0.0010777029,"about_ca_topic_score_gemma":0.0016102003,"teacher_disagreement_score":0.06974609,"about_ca_system_score_codex":0.00055008364,"about_ca_system_score_gemma":0.0015897236,"threshold_uncertainty_score":0.23332393},"labels":[],"label_agreement":null},{"id":"W1979311362","doi":"10.3758/s13428-012-0302-1","title":"ELIA: A software application for integrating spoken language and eye movements","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software; Eye tracking; Eye movement; Process (computing); Gaze; Raw data; Artificial intelligence; Natural language processing; Human–computer interaction; Programming language","score_opus":0.19167298798216587,"score_gpt":0.5646022571054135,"score_spread":0.3729292691232476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979311362","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0115470765,0.00024416597,0.47033364,0.00016714145,0.00018027029,0.000369513,0.0036657397,0.5072543,0.006238185],"genre_scores_gemma":[0.28155884,0.00086093514,0.55759007,0.0019550181,0.00023765775,0.0026413496,0.0150286425,0.08441084,0.05571662],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996635,0.00003319468,0.000036173307,0.00010693875,0.00011861415,0.00004162736],"domain_scores_gemma":[0.99911886,0.00046657087,0.000052152518,0.00012798315,0.00014943207,0.00008496458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007571609,0.0013303485,0.00087724294,0.0012490988,0.0003218131,0.0010704981,0.0018051071,0.00077898556,0.042516682],"category_scores_gemma":[0.002670282,0.0007008086,0.00075966073,0.00049190916,0.00033883515,0.0011245662,0.0022250747,0.0010179145,0.01134793],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031468566,0.00044001,0.009308996,0.0015775611,0.0006345971,0.0012197825,0.0009911666,0.008581346,0.113825805,0.00627517,0.12935202,0.7246467],"study_design_scores_gemma":[0.0015584972,0.0005103894,0.019446988,0.00046274677,0.00060608675,0.0025854853,0.00030837607,0.40454274,0.28744602,0.01880242,0.2632278,0.0005024238],"about_ca_topic_score_codex":0.0018423604,"about_ca_topic_score_gemma":0.0018647531,"teacher_disagreement_score":0.042516682,"about_ca_system_score_codex":0.00044218454,"about_ca_system_score_gemma":0.00060543313,"threshold_uncertainty_score":0.14223248},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2541210475944673,"score_gpt":0.5307494941877987,"score_spread":0.2766284465933314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979532929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928665,0.00015070286,0.00025892895,0.00002423439,0.000044635803,0.00008411236,0.0009470966,0.000029176774,0.0055946424],"genre_scores_gemma":[0.984288,0.00027497517,0.0009805294,0.00008544661,0.00004387606,0.00014438403,0.0026458835,0.0000326668,0.011504188],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884737,0.00021048877,0.00021759374,0.00017132457,0.0004300819,0.00012313465],"domain_scores_gemma":[0.97860706,0.008067862,0.003168167,0.0011242967,0.007026969,0.002005768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021995804,0.00040113862,0.00044783382,0.0010882993,0.0003608512,0.00066949305,0.0002510975,0.0006906432,0.0064243185],"category_scores_gemma":[0.017401328,0.00021569077,0.00049273577,0.00025300146,0.00023455588,0.00097355025,0.0007124637,0.000610126,0.0033210467],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040418063,0.0015110775,0.9128309,0.00021314253,0.00019923267,0.00043394722,0.0049273307,0.00054288766,0.024386179,0.0001883218,0.0033657602,0.04735943],"study_design_scores_gemma":[0.000016935595,0.0013944532,0.99410534,0.0000127934645,0.000028393233,0.00021793663,0.00071691367,0.00024039722,0.0019151584,0.000029770497,0.0013025342,0.00001931144],"about_ca_topic_score_codex":0.002724173,"about_ca_topic_score_gemma":0.008078604,"teacher_disagreement_score":0.0064243185,"about_ca_system_score_codex":0.00024998267,"about_ca_system_score_gemma":0.00019678666,"threshold_uncertainty_score":0.021491468},"labels":[],"label_agreement":null},{"id":"W1979886455","doi":"10.3758/brm.41.2.452","title":"Corroborating biased indicators: Global and local agreement among objective and subjective estimates of printed word frequency","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; University of Ottawa","keywords":"Word lists by frequency; Variance (accounting); Selection (genetic algorithm); Frequency; Word (group theory); Age of Acquisition; Psychology; Variable (mathematics); Statistics; Computer science; Cognitive psychology; Variation (astronomy); Econometrics; Mathematics; Natural language processing; Artificial intelligence; Cognition","score_opus":0.1119647348854283,"score_gpt":0.5289141928556063,"score_spread":0.41694945797017796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979886455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9308753,0.0009737757,0.055741083,0.0004347728,0.00017928139,0.00025812973,0.000607923,0.00014606197,0.010783568],"genre_scores_gemma":[0.9847685,0.000143316,0.013186633,0.00021340017,0.00008150526,0.00032867616,0.0005914268,0.00009832405,0.0005882382],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8734691,0.088832796,0.010586301,0.010329404,0.01526405,0.001518198],"domain_scores_gemma":[0.4132232,0.40319365,0.05590337,0.080445126,0.04545676,0.0017778914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.113537066,0.00069718645,0.0013536498,0.0034613078,0.0016150821,0.003434691,0.0019333041,0.0022198502,0.0017388891],"category_scores_gemma":[0.34751192,0.000750961,0.001054711,0.0033676303,0.004319418,0.0033617297,0.0053675026,0.0018918981,0.00088873],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012002527,0.00035338957,0.8849245,0.00093091454,0.0017305887,0.00023713418,0.03203463,0.0016333634,0.005496439,0.005070771,0.002102814,0.06428514],"study_design_scores_gemma":[0.00013281616,0.00072999374,0.94063455,0.00060499593,0.0009399407,0.00066068536,0.01282534,0.009101369,0.014002445,0.01178807,0.008341097,0.00023869569],"about_ca_topic_score_codex":0.0022532053,"about_ca_topic_score_gemma":0.003800331,"teacher_disagreement_score":0.113537066,"about_ca_system_score_codex":0.00074990117,"about_ca_system_score_gemma":0.0010606388,"threshold_uncertainty_score":0.6004486},"labels":[],"label_agreement":null},{"id":"W1984681595","doi":"10.3758/s13428-014-0544-1","title":"A simple algorithm for the offline recalibration of eye-tracking data through best-fitting linear transformation","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Economic and Social Research Council","keywords":"Computer science; Eye tracking; MATLAB; Artificial intelligence; Transformation (genetics); Computer vision; Algorithm; Eye movement; Tracking (education)","score_opus":0.4242559375345631,"score_gpt":0.5898099072666028,"score_spread":0.16555396973203967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984681595","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080732146,0.000043190244,0.9938624,0.000039286704,0.00004331242,0.00009302032,0.00011748726,0.00463314,0.0003608546],"genre_scores_gemma":[0.009111861,0.000072151044,0.9874293,0.000046462246,0.000020279043,0.00036351217,0.00030263377,0.00054994226,0.0021038412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989686,0.0001113376,0.000103654806,0.00033173556,0.00043014888,0.000054548324],"domain_scores_gemma":[0.99830025,0.000541225,0.00018300048,0.00032260176,0.00059703476,0.00005590255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012119146,0.0020392567,0.0010780729,0.001839671,0.00090574374,0.0015669627,0.0019394784,0.0014836299,0.020231122],"category_scores_gemma":[0.0058811274,0.001105097,0.0009378743,0.0018095572,0.00052515947,0.0012811047,0.0015987394,0.0023511013,0.015096679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021222507,0.000168227,0.00135095,0.00040302213,0.00019410787,0.00021683518,0.00026543142,0.020312998,0.05582824,0.0060733296,0.019462397,0.8955122],"study_design_scores_gemma":[0.00024912145,0.0004798794,0.008636487,0.00016750746,0.00023064105,0.0026007297,0.0002535859,0.68348986,0.1515134,0.015092414,0.13690694,0.00037939724],"about_ca_topic_score_codex":0.0042583966,"about_ca_topic_score_gemma":0.0069669425,"teacher_disagreement_score":0.020231122,"about_ca_system_score_codex":0.0007391343,"about_ca_system_score_gemma":0.0019720194,"threshold_uncertainty_score":0.06767988},"labels":[],"label_agreement":null},{"id":"W1985548644","doi":"10.3758/brm.40.3.858","title":"Recovering data from scanned graphs: Performance of Frantz’s g3data software","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Natural Sciences and Engineering Research Council of Canada; Trent University","keywords":"Computer science; Software; Computer graphics (images); Programming language","score_opus":0.5383671611823693,"score_gpt":0.5695334473161054,"score_spread":0.031166286133736176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985548644","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06837386,0.0003821863,0.35829818,0.00064827024,0.0002712708,0.00036924332,0.0047040842,0.55697566,0.009977165],"genre_scores_gemma":[0.30717042,0.0005522896,0.62175095,0.00035143917,0.000068524474,0.0006417535,0.008754769,0.053677842,0.0070320494],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964569,0.00046510328,0.00032727694,0.0008221129,0.0017092769,0.00021937159],"domain_scores_gemma":[0.98574615,0.008587775,0.0005676819,0.0027079827,0.0020046385,0.00038581755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004661172,0.0029091989,0.0013997676,0.00597395,0.0012824783,0.0030480393,0.0043672454,0.001238661,0.024757762],"category_scores_gemma":[0.026136987,0.0010428176,0.0010807372,0.0042543667,0.00095047185,0.002825774,0.0024392444,0.0018442359,0.009498064],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027708267,0.00080297084,0.011207127,0.0009300862,0.00047028577,0.0012321011,0.00247794,0.038041506,0.0347493,0.009285166,0.119109765,0.7789229],"study_design_scores_gemma":[0.00064481486,0.00046441058,0.0149902105,0.00022483713,0.00020114215,0.0009015989,0.0012701851,0.7373783,0.15752871,0.021015787,0.06488273,0.00049724703],"about_ca_topic_score_codex":0.015150522,"about_ca_topic_score_gemma":0.007961531,"teacher_disagreement_score":0.024757762,"about_ca_system_score_codex":0.0012522092,"about_ca_system_score_gemma":0.0020023524,"threshold_uncertainty_score":0.08282298},"labels":[],"label_agreement":null},{"id":"W1986294108","doi":"10.3758/brm.41.3.833","title":"Using Noldus Observer XT for research on deaf signers learning to read: An innovative methodology","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Speech recognition; Psychology","score_opus":0.9560280300315404,"score_gpt":0.7934256045912061,"score_spread":0.1626024254403342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986294108","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17511983,0.00020228753,0.77908075,0.00033854292,0.00088095496,0.020024987,0.001831264,0.0025250085,0.019996341],"genre_scores_gemma":[0.10346845,0.00030718252,0.8191629,0.00044846002,0.00022448452,0.051781006,0.0005306927,0.00058033573,0.023496471],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9926749,0.0029719456,0.00092627574,0.0016053076,0.0013306893,0.00049085484],"domain_scores_gemma":[0.97977656,0.009562716,0.0015193747,0.0024244208,0.0057975804,0.0009193524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008164604,0.0017297609,0.000968463,0.0018183838,0.0016602563,0.0012243249,0.0010662474,0.0013209287,0.01227668],"category_scores_gemma":[0.013371501,0.0012158239,0.00081056374,0.001470194,0.0019620433,0.0018119522,0.0025858607,0.0026744201,0.0031440237],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005101337,0.005104077,0.032925066,0.002584512,0.00016471934,0.00065220305,0.011510055,0.0010347018,0.5755495,0.011353853,0.007124917,0.34689507],"study_design_scores_gemma":[0.0035451036,0.030986805,0.31051955,0.0009667617,0.0013248095,0.002444227,0.012489987,0.03199967,0.47049776,0.012456342,0.121599235,0.0011697292],"about_ca_topic_score_codex":0.0019154132,"about_ca_topic_score_gemma":0.008782309,"teacher_disagreement_score":0.01227668,"about_ca_system_score_codex":0.00074501237,"about_ca_system_score_gemma":0.0038310965,"threshold_uncertainty_score":0.043179035},"labels":[],"label_agreement":null},{"id":"W1989587788","doi":"10.3758/brm.41.3.699","title":"Web-based image norming: How do object familiarity and visual complexity ratings compare when collected in-lab versus online?","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"University of Toronto Scarborough; University of Toronto","keywords":"Psychology; Web application; Artificial intelligence; Computer science; Cognitive psychology; Statistics; Information retrieval; World Wide Web; Mathematics","score_opus":0.4874111073272016,"score_gpt":0.5725089247469776,"score_spread":0.08509781741977596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989587788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98248833,0.00020658167,0.008897877,0.0001278318,0.00014305128,0.00016799071,0.0004929349,0.00008589804,0.007389548],"genre_scores_gemma":[0.99231124,0.00010728857,0.004590041,0.00020381901,0.00009177394,0.00032668267,0.0006837165,0.0000950032,0.0015904163],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9936154,0.002377673,0.0004484077,0.00097034086,0.0024348984,0.00015324035],"domain_scores_gemma":[0.954612,0.021277532,0.0098121585,0.005082046,0.0075701214,0.0016461731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072219414,0.000325573,0.00045873143,0.0010045015,0.0005171768,0.0021588646,0.0006546111,0.001098877,0.00355957],"category_scores_gemma":[0.054903038,0.00024589876,0.00044708073,0.00069190015,0.00079323835,0.0024986407,0.0008378026,0.0006527907,0.0016394102],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026197704,0.0013157369,0.8885089,0.00021855696,0.00058823056,0.00008456512,0.0033833967,0.00056176534,0.015344693,0.001002271,0.0030274102,0.0833448],"study_design_scores_gemma":[0.000040823183,0.00067110505,0.98826104,0.000036870017,0.000085705666,0.0002441513,0.001241381,0.0024454372,0.0043328125,0.00079480855,0.001779988,0.00006585033],"about_ca_topic_score_codex":0.0020296741,"about_ca_topic_score_gemma":0.003565003,"teacher_disagreement_score":0.0072219414,"about_ca_system_score_codex":0.00036913468,"about_ca_system_score_gemma":0.00020249498,"threshold_uncertainty_score":0.038193703},"labels":[],"label_agreement":null},{"id":"W1990092159","doi":"10.3758/bf03192808","title":"BatMon II: Children’s category norms for 33 categories","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Categorization; Cognitive psychology; Developmental psychology; Linguistics; Computer science; Artificial intelligence","score_opus":0.16915305304255768,"score_gpt":0.545034962112387,"score_spread":0.3758819090698293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990092159","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8022884,0.00027670668,0.04620016,0.0005649421,0.0002910781,0.0009310546,0.02124177,0.0019739103,0.12623204],"genre_scores_gemma":[0.90140456,0.000114982606,0.05516077,0.00013086943,0.00003546907,0.0044670166,0.014741211,0.0014501021,0.022494933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967752,0.0008911099,0.00032822054,0.0005548931,0.0012236789,0.00022697107],"domain_scores_gemma":[0.9805264,0.009761458,0.0026972499,0.0026141994,0.0035685995,0.0008321146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047353595,0.0004785287,0.00036421226,0.0016405617,0.00058332965,0.0020091715,0.00083257793,0.00066476053,0.01507825],"category_scores_gemma":[0.034884654,0.00047111575,0.00049189484,0.00083625247,0.00075965247,0.0020018085,0.0016692509,0.001285459,0.0028463453],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025409104,0.00060015114,0.4965936,0.00044862265,0.00016933805,0.00039648468,0.022872675,0.002885156,0.021451464,0.042641003,0.07432885,0.33507168],"study_design_scores_gemma":[0.000069921414,0.00039633733,0.92350876,0.00022088252,0.000049692477,0.0005777331,0.0057959757,0.004974926,0.010979175,0.0111977905,0.042107616,0.00012116633],"about_ca_topic_score_codex":0.0069156606,"about_ca_topic_score_gemma":0.012338203,"teacher_disagreement_score":0.01507825,"about_ca_system_score_codex":0.001145791,"about_ca_system_score_gemma":0.0008921428,"threshold_uncertainty_score":0.050441742},"labels":[],"label_agreement":null},{"id":"W1991251969","doi":"10.3758/s13428-012-0219-8","title":"Design of a noninvasive face mask for ocular occlusion in rats and assessment in a visual discrimination paradigm","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Neuropharmacology Research","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Monocular; Visual cortex; Neuroscience; Computer science; Monocular deprivation; Computer vision; Artificial intelligence; Psychology; Ocular dominance","score_opus":0.4670633180786287,"score_gpt":0.6305032203990433,"score_spread":0.16343990232041455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991251969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89967185,0.00038455203,0.08970475,0.00066964835,0.00042732118,0.0053711245,0.0014954193,0.0010831179,0.0011923312],"genre_scores_gemma":[0.71506286,0.0013667896,0.2510461,0.0007747082,0.0002639126,0.01903022,0.0013472443,0.0005000934,0.010608111],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913365,0.000055586184,0.000072926174,0.00025442115,0.00024280784,0.00024064597],"domain_scores_gemma":[0.9989685,0.000080345795,0.00023646334,0.00017689473,0.00013472671,0.00040306675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006955396,0.0018917504,0.0008524152,0.0010911692,0.0010764027,0.00042209547,0.0013128665,0.0012767239,0.0023964562],"category_scores_gemma":[0.0007526557,0.0008749782,0.00085411075,0.00024355194,0.0015523466,0.0009166328,0.0009428846,0.0017354798,0.0008286411],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023369833,0.0012135302,0.0004986292,0.00007571085,0.000012183529,0.00009092766,0.0000906002,0.0002731848,0.99000657,0.00035797435,0.00016761008,0.0048760776],"study_design_scores_gemma":[0.0005466075,0.012598101,0.0072832396,0.00002459716,0.00011232318,0.0003640854,0.00009045075,0.0024638562,0.9717148,0.0004249236,0.0042765583,0.00010043496],"about_ca_topic_score_codex":0.0029835254,"about_ca_topic_score_gemma":0.0069389767,"teacher_disagreement_score":0.0029835254,"about_ca_system_score_codex":0.0008415923,"about_ca_system_score_gemma":0.00306644,"threshold_uncertainty_score":0.008016944},"labels":[],"label_agreement":null},{"id":"W1993000953","doi":"10.3758/s13428-013-0373-7","title":"The effective number of parameters in post hoc models","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Post hoc; Simple (philosophy); Computer science; Set (abstract data type); Context (archaeology); Monte Carlo method; Statistics; Mathematics","score_opus":0.34766603907049415,"score_gpt":0.6206011347065685,"score_spread":0.2729350956360744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993000953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0094525,0.00034289534,0.9869004,0.00094106526,0.00009326049,0.00007485328,0.00009547638,0.000096512966,0.0020030085],"genre_scores_gemma":[0.43971646,0.0014258495,0.54860663,0.00091615977,0.0006576637,0.0014582934,0.00039092425,0.00038573734,0.0064422037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96855766,0.023706263,0.0011785298,0.0031900853,0.0028069941,0.0005605111],"domain_scores_gemma":[0.5487536,0.41292843,0.005813951,0.027103357,0.0042458833,0.0011547595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04760501,0.0017663117,0.003351696,0.002260983,0.0017839032,0.0035075794,0.0052827923,0.004020055,0.0067927847],"category_scores_gemma":[0.28110036,0.0020679594,0.0019792458,0.0019319529,0.006748204,0.017529149,0.0034699782,0.007913653,0.00073761767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027907858,0.00014450349,0.00301688,0.00035734204,0.00027059103,0.00018849001,0.00057114207,0.07919453,0.00061614584,0.8484026,0.0022613206,0.064697266],"study_design_scores_gemma":[0.00004423602,0.000060043083,0.00054101896,0.00006357782,0.00008673582,0.00010078865,0.00006502925,0.19227187,0.0003900416,0.8050723,0.0012790106,0.000025270345],"about_ca_topic_score_codex":0.0015569489,"about_ca_topic_score_gemma":0.0020056637,"teacher_disagreement_score":0.04760501,"about_ca_system_score_codex":0.0024667073,"about_ca_system_score_gemma":0.0035394197,"threshold_uncertainty_score":0.25176233},"labels":[],"label_agreement":null},{"id":"W1993078811","doi":"10.3758/brm.42.3.809","title":"Automatic detection and quantification of growth spurts","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Infant Health and Development","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Growth spurt; Computer science; Statistics; Mathematics; Medicine","score_opus":0.41912270103037413,"score_gpt":0.6821904125655601,"score_spread":0.263067711535186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993078811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5441055,0.0032636365,0.4299269,0.00039463158,0.00020757562,0.00035542678,0.007090645,0.0068525146,0.0078031872],"genre_scores_gemma":[0.7613938,0.0008764469,0.22815381,0.00012929503,0.0000979321,0.00031674764,0.0042800913,0.00037122582,0.00438068],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992668,0.00020022618,0.000038462716,0.000219204,0.00018962297,0.0000856853],"domain_scores_gemma":[0.9974765,0.0013679502,0.00030267428,0.000174264,0.00054312096,0.00013543469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001282612,0.0005855355,0.00069256313,0.003231629,0.00024781437,0.0007840699,0.0007425499,0.00068502536,0.002424626],"category_scores_gemma":[0.003279306,0.00032732365,0.00035558842,0.0011159319,0.00021135066,0.0003286852,0.00062273594,0.0004515273,0.001034624],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014579429,0.00029731015,0.13800047,0.00042867652,0.00014877229,0.00021438129,0.0002934395,0.004916054,0.07489931,0.0013835103,0.005457638,0.77250254],"study_design_scores_gemma":[0.00023507363,0.0007576198,0.6201485,0.0001612562,0.0003017821,0.0023079584,0.00055161264,0.30018792,0.06041545,0.004835292,0.009938283,0.00015924896],"about_ca_topic_score_codex":0.00279955,"about_ca_topic_score_gemma":0.0045470893,"teacher_disagreement_score":0.003231629,"about_ca_system_score_codex":0.00022994347,"about_ca_system_score_gemma":0.0005046129,"threshold_uncertainty_score":0.008111179},"labels":[],"label_agreement":null},{"id":"W1995383499","doi":"10.3758/s13428-011-0078-8","title":"Exploiting human sensitivity to gaze for tracking the eyes","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Gaze; Eye movement; Eye tracking; Saccade; Fixation (population genetics); Computer vision; Covert; Computer science; Artificial intelligence; Eye–hand coordination; Visual search; Psychology; Optometry; Cognitive psychology; Medicine; Population","score_opus":0.6849314061675018,"score_gpt":0.6082399704273977,"score_spread":0.07669143574010406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995383499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5578962,0.0031293586,0.4283866,0.00018015532,0.00010000842,0.00016070633,0.00076281244,0.0007178015,0.008666266],"genre_scores_gemma":[0.9366701,0.00093247695,0.060607832,0.00006180415,0.000029002016,0.00007388965,0.00015888544,0.00004761093,0.0014182483],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994777,0.00026189568,0.000020469717,0.00011734749,0.00008207463,0.000040465577],"domain_scores_gemma":[0.998949,0.000613053,0.00012348765,0.00013214952,0.00013970502,0.000042623724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006990343,0.0004241141,0.00032660016,0.001110707,0.00019612335,0.0006811812,0.0002061355,0.0005059232,0.0017410177],"category_scores_gemma":[0.0029977832,0.00022721164,0.0003518231,0.0006752322,0.0002462953,0.00074158434,0.0004887515,0.00028473177,0.0003428516],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062733627,0.00023352435,0.05048997,0.0008145563,0.0004485284,0.00019829125,0.0013049897,0.012702354,0.47200292,0.0032218047,0.0018336382,0.45612204],"study_design_scores_gemma":[0.00012175402,0.0014330937,0.43046194,0.00028434608,0.00076570094,0.002312758,0.0010271149,0.33744007,0.20603497,0.009804151,0.010106002,0.00020813811],"about_ca_topic_score_codex":0.0024157062,"about_ca_topic_score_gemma":0.0036690193,"teacher_disagreement_score":0.0024157062,"about_ca_system_score_codex":0.0002689032,"about_ca_system_score_gemma":0.00027239838,"threshold_uncertainty_score":0.0058243275},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5842658790059307,"score_gpt":0.6586748091934802,"score_spread":0.07440893018754946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998133270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99602133,0.000043685537,0.00023478945,0.00000898989,0.000013979112,0.000037194535,0.00033049795,0.00002000449,0.0032895089],"genre_scores_gemma":[0.99153745,0.00011131834,0.0009754628,0.000041291347,0.000015752774,0.00011139056,0.0008538734,0.000050638806,0.006302841],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994803,0.00012242488,0.00006485519,0.00012007907,0.00016401501,0.00004828595],"domain_scores_gemma":[0.9964964,0.0020716768,0.00052047014,0.0001718564,0.00045505207,0.00028458278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006575261,0.0003295012,0.00044482987,0.00037658168,0.00032163181,0.0004153603,0.00016908525,0.0004397381,0.006279295],"category_scores_gemma":[0.0050437218,0.00016475002,0.00020438059,0.00026006319,0.00029834645,0.00048387048,0.00045936194,0.0002778264,0.0012842745],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013784747,0.0014092216,0.6333958,0.000467458,0.000209366,0.0010954794,0.01193856,0.0003378157,0.26581547,0.00043925407,0.0019333529,0.06917343],"study_design_scores_gemma":[0.000060606893,0.0010080107,0.9918401,0.000008676756,0.000038774535,0.00028958276,0.001000556,0.00035176156,0.004410097,0.000061013543,0.0009141071,0.000016750968],"about_ca_topic_score_codex":0.0021567426,"about_ca_topic_score_gemma":0.005577362,"teacher_disagreement_score":0.006279295,"about_ca_system_score_codex":0.0002194613,"about_ca_system_score_gemma":0.000155174,"threshold_uncertainty_score":0.021006346},"labels":[],"label_agreement":null},{"id":"W1998804905","doi":"10.3758/s13428-013-0315-4","title":"Internal consistency: Reports of its death are premature","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Consistency (knowledge bases); Internal consistency; Reliability (semiconductor); Psychology; Personality; Stability (learning theory); Social psychology; Cognitive psychology; Clinical psychology; Computer science; Psychometrics; Artificial intelligence","score_opus":0.4210199386381068,"score_gpt":0.6174052493332904,"score_spread":0.1963853106951836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998804905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3617416,0.036787458,0.28560743,0.11593688,0.04387105,0.0040064724,0.0074999686,0.0040633064,0.14048584],"genre_scores_gemma":[0.9220238,0.0016733141,0.049693648,0.013214989,0.0029066736,0.0015382207,0.0019942916,0.0008622927,0.0060928906],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8047438,0.09737284,0.02297185,0.017184863,0.055408414,0.002318315],"domain_scores_gemma":[0.3065997,0.5096242,0.030549975,0.068417706,0.08141401,0.0033943395],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18818972,0.0012811896,0.0019225696,0.0056845457,0.003569142,0.005182212,0.0033719267,0.0025711372,0.0036371737],"category_scores_gemma":[0.47171575,0.0014448033,0.0031482277,0.0037859033,0.0069368477,0.0042342567,0.004429223,0.0062062107,0.0015636226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014222882,0.0004737869,0.48835388,0.0034061994,0.00508067,0.00070665166,0.0075944,0.0024761031,0.0016757731,0.08061639,0.08686125,0.32133263],"study_design_scores_gemma":[0.00050495786,0.0017871265,0.5816253,0.008411936,0.0035089855,0.003363416,0.008205712,0.022650976,0.011867485,0.21436676,0.14305714,0.0006502755],"about_ca_topic_score_codex":0.0021366614,"about_ca_topic_score_gemma":0.003376327,"teacher_disagreement_score":0.81181026,"about_ca_system_score_codex":0.0030335896,"about_ca_system_score_gemma":0.0030633367,"threshold_uncertainty_score":0.9952542},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8313740192000905,"score_gpt":0.6323470359685018,"score_spread":0.19902698323158863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998828876","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080474763,0.0034269572,0.009615141,0.84851795,0.13010003,0.00017393063,0.00051918445,0.0013688755,0.0054732026],"genre_scores_gemma":[0.005010795,0.0005475337,0.010161987,0.9267308,0.046547335,0.0006536711,0.000073211006,0.00032578947,0.009948827],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88865113,0.04369676,0.011653186,0.014108903,0.03851938,0.0033705593],"domain_scores_gemma":[0.58453155,0.2880816,0.022503465,0.02711482,0.07295546,0.004813161],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10162669,0.0024368255,0.004661108,0.0032284202,0.0076089473,0.005458322,0.010967327,0.058621716,0.0063706506],"category_scores_gemma":[0.28731054,0.002842764,0.0041166055,0.003584614,0.015269334,0.0048775743,0.0038801502,0.07060553,0.015062105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019971735,0.00008516724,0.0004327175,0.0002873038,0.000063316875,0.00018514838,0.000527587,0.00011792869,0.0005339853,0.009363082,0.97073346,0.017470684],"study_design_scores_gemma":[0.00045615053,0.0002920658,0.010219767,0.0021129986,0.00028124737,0.0005292317,0.0006448379,0.0015556646,0.0024053738,0.04797072,0.93322265,0.00030928894],"about_ca_topic_score_codex":0.016947128,"about_ca_topic_score_gemma":0.037739374,"teacher_disagreement_score":0.8983733,"about_ca_system_score_codex":0.010434269,"about_ca_system_score_gemma":0.00684524,"threshold_uncertainty_score":0.53745973},"labels":[],"label_agreement":null},{"id":"W2000645851","doi":"10.3758/s13428-013-0395-1","title":"Statistical power of latent growth curve models to detect quadratic growth","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Latent growth modeling; Growth curve (statistics); Statistics; Statistical model; Growth model; Quadratic equation; Statistical power; Computer science; Power (physics); Econometrics; Quadratic model; Mathematics; Mathematical economics","score_opus":0.38843895614225343,"score_gpt":0.555385129510922,"score_spread":0.16694617336866857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000645851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19677536,0.0005752774,0.79734623,0.0015723414,0.00010477379,0.00012418818,0.00046175683,0.0007435971,0.002296443],"genre_scores_gemma":[0.95824206,0.00022920086,0.039343145,0.00014558186,0.00009148885,0.00015600774,0.00055306836,0.00022529952,0.0010141036],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97823286,0.016926486,0.00055281934,0.0023574193,0.0013520644,0.0005782755],"domain_scores_gemma":[0.5271928,0.43631002,0.009315804,0.02050081,0.0044863583,0.0021942316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04898122,0.0015248858,0.0019819564,0.0029141812,0.0010275401,0.0035351906,0.0028805125,0.0021914095,0.004550922],"category_scores_gemma":[0.32348427,0.0010607146,0.0020377908,0.0028305384,0.0044515715,0.0060880617,0.004113655,0.004209885,0.0007917763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024684411,0.00068498816,0.16596173,0.0005588222,0.00205694,0.00031404532,0.0021669478,0.38005382,0.0017298458,0.21050823,0.0064040655,0.22709216],"study_design_scores_gemma":[0.0000783582,0.00018085704,0.009309239,0.000043554257,0.000086816384,0.00008789858,0.0001614716,0.8055566,0.00035242768,0.18347473,0.00062448956,0.000043530676],"about_ca_topic_score_codex":0.004898672,"about_ca_topic_score_gemma":0.002614052,"teacher_disagreement_score":0.9510188,"about_ca_system_score_codex":0.0013556528,"about_ca_system_score_gemma":0.0029581462,"threshold_uncertainty_score":0.25904053},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3221110839369203,"score_gpt":0.5182101067454136,"score_spread":0.19609902280849328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002429320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99067664,0.0003593134,0.007726913,0.00003722527,0.000019934108,0.000020125968,0.00035833847,0.00012914228,0.00067235605],"genre_scores_gemma":[0.9937237,0.00020544748,0.0045888484,0.000036957503,0.000016232178,0.000037168273,0.00031842606,0.00011659605,0.00095674885],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99790025,0.00069598615,0.00024536974,0.00049695454,0.0005214575,0.00013983453],"domain_scores_gemma":[0.9720395,0.018816538,0.002908766,0.0020365338,0.0038759862,0.00032275205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021368973,0.00036586908,0.00045144255,0.00080475357,0.00031657933,0.0007371812,0.00045689085,0.0007888126,0.0013294099],"category_scores_gemma":[0.027944643,0.00047957234,0.0003001507,0.0009214173,0.0002219357,0.0010126381,0.00063730666,0.00063090783,0.0006261601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014820078,0.0005556861,0.5415263,0.0006465789,0.00046011095,0.0003458763,0.004105908,0.008297667,0.244157,0.00043257815,0.001726631,0.18292558],"study_design_scores_gemma":[0.00006754803,0.0011648419,0.93721986,0.00006252738,0.00020632002,0.0007106375,0.00037379368,0.013982623,0.0453835,0.00013444078,0.00063774525,0.000056121928],"about_ca_topic_score_codex":0.0049932855,"about_ca_topic_score_gemma":0.0048400024,"teacher_disagreement_score":0.0049932855,"about_ca_system_score_codex":0.00037890062,"about_ca_system_score_gemma":0.00038944752,"threshold_uncertainty_score":0.01130116},"labels":[],"label_agreement":null},{"id":"W2002467630","doi":"10.3758/s13428-014-0502-y","title":"Semantic properties, aptness, familiarity, conventionality, and interpretive diversity scores for 84 metaphors and similes","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; McGill University","funders":"","keywords":"Simile; Salient; Metaphor; Interpretation (philosophy); Psychology; Literal and figurative language; Cognitive psychology; Meaning (existential); Cognition; Diversity (politics); Linguistics; Expression (computer science); Computer science; Artificial intelligence; Sociology; Philosophy","score_opus":0.2521318354855341,"score_gpt":0.5103424258964011,"score_spread":0.258210590410867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002467630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963212,0.00006552141,0.0011725483,0.00002632084,0.000011780033,0.000075892014,0.00032154212,0.000029271732,0.0019758383],"genre_scores_gemma":[0.99515474,0.000045755263,0.0030310887,0.000014017215,0.000011704296,0.00023275251,0.0006625066,0.000024931614,0.00082250335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99868876,0.00030533446,0.00024205504,0.0001985709,0.0004402783,0.00012501967],"domain_scores_gemma":[0.983414,0.011317944,0.0018505573,0.0011119827,0.0013016548,0.0010039055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026318405,0.00060369185,0.0006350895,0.0027340788,0.00051825086,0.0016830019,0.00039773845,0.00082181377,0.0048716296],"category_scores_gemma":[0.027261134,0.00018581728,0.0010024556,0.0012814014,0.00077289203,0.0020990118,0.0010507206,0.0009755856,0.00088630087],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037295872,0.0018768304,0.85974616,0.00030014137,0.0005060772,0.0003827412,0.0096352855,0.0017479181,0.019635582,0.002522655,0.0015813262,0.09833568],"study_design_scores_gemma":[0.00014500417,0.0016628443,0.9684415,0.000058990707,0.00021324785,0.00083664875,0.0047938325,0.009890699,0.0051875156,0.0068535837,0.0018280004,0.000088158245],"about_ca_topic_score_codex":0.0009171776,"about_ca_topic_score_gemma":0.0015652874,"teacher_disagreement_score":0.0048716296,"about_ca_system_score_codex":0.000457713,"about_ca_system_score_gemma":0.00039191323,"threshold_uncertainty_score":0.016297221},"labels":[],"label_agreement":null},{"id":"W2003491767","doi":"10.3758/s13428-011-0158-9","title":"Wayfinding: The effects of large displays and 3-D perception","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Simulator sickness; Perception; Computer science; Landmark; Depth perception; Human–computer interaction; Stereoscopy; Virtual reality; Virtual machine; Stereopsis; Psychology; Computer vision","score_opus":0.19493293637273648,"score_gpt":0.5042521348622732,"score_spread":0.3093191984895367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003491767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9586653,0.0017514239,0.030139139,0.0003569056,0.00012622523,0.000053258358,0.0002667343,0.0002183986,0.008422523],"genre_scores_gemma":[0.9898252,0.0004110465,0.008437776,0.00008118661,0.000055376873,0.000062997555,0.000094164294,0.0001617446,0.00087062456],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99836916,0.0009229015,0.0000734852,0.00027416463,0.00027288124,0.0000874794],"domain_scores_gemma":[0.9403115,0.054506946,0.0020191215,0.0019125716,0.00062534114,0.0006244942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016408468,0.00059139373,0.00036256365,0.0006859341,0.00029750486,0.003179508,0.00059799413,0.0008263895,0.0074898335],"category_scores_gemma":[0.029414823,0.0004774261,0.00048722347,0.0006219177,0.0010309569,0.0027664944,0.0016831686,0.00074277504,0.0002804804],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028533187,0.0039906777,0.08167843,0.0027905607,0.0010639341,0.00077194266,0.011600997,0.032065958,0.38979456,0.0376738,0.0048080375,0.40522796],"study_design_scores_gemma":[0.0023767326,0.010752836,0.67974216,0.000840008,0.0026754555,0.0034880294,0.0077319257,0.10115382,0.08614675,0.08745219,0.016892692,0.00074746285],"about_ca_topic_score_codex":0.002245503,"about_ca_topic_score_gemma":0.0015949763,"teacher_disagreement_score":0.0074898335,"about_ca_system_score_codex":0.0003987529,"about_ca_system_score_gemma":0.00045816068,"threshold_uncertainty_score":0.025056005},"labels":[],"label_agreement":null},{"id":"W2005020967","doi":"10.3758/brm.42.1.109","title":"Subjective frequency norms for 330 Spanish simple and compound words","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Noun; Normative; Psychology; Verb; Consistency (knowledge bases); Reliability (semiconductor); Linguistics; Dependency (UML); Test (biology); Cognitive psychology; Mathematics; Statistics; Social psychology; Natural language processing; Artificial intelligence; Computer science","score_opus":0.22443089424841303,"score_gpt":0.5912289163641797,"score_spread":0.36679802211576673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005020967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98357844,0.00017197398,0.002177367,0.00003510965,0.0000377128,0.00014258176,0.0015255476,0.000040901738,0.012290304],"genre_scores_gemma":[0.98516375,0.0001820383,0.00358175,0.000057717716,0.000038733877,0.0003761816,0.003252581,0.00006451939,0.007282699],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980671,0.0005936696,0.00027337318,0.00028009634,0.00066659256,0.00011913851],"domain_scores_gemma":[0.9840184,0.0067381053,0.002018238,0.0012002735,0.00524002,0.0007851164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022949413,0.00040346538,0.00024966823,0.0017523133,0.00031264144,0.0010354551,0.00024235688,0.00050919654,0.004167485],"category_scores_gemma":[0.01451251,0.0001487474,0.00028223582,0.0007194751,0.00041331808,0.00033786037,0.00051925733,0.00041669086,0.0012465358],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019092968,0.0009238711,0.8924565,0.00023952709,0.00014659856,0.0002405022,0.011911709,0.00041424955,0.020245709,0.0012475139,0.0024597591,0.06780481],"study_design_scores_gemma":[0.000024002911,0.00045741952,0.98981595,0.000028076569,0.000023013981,0.00024806577,0.0027891519,0.00030839094,0.0018324731,0.00027541572,0.0041736397,0.000024400628],"about_ca_topic_score_codex":0.0030970825,"about_ca_topic_score_gemma":0.004955878,"teacher_disagreement_score":0.004167485,"about_ca_system_score_codex":0.000432474,"about_ca_system_score_gemma":0.0002590975,"threshold_uncertainty_score":0.013941646},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Psychology","score_opus":0.47439013244181594,"score_gpt":0.5834460447021849,"score_spread":0.10905591226036893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006342589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28755274,0.0037419768,0.43396354,0.018760962,0.0008025902,0.00051815755,0.0008883246,0.00086458685,0.25290707],"genre_scores_gemma":[0.8907619,0.000941071,0.08085148,0.0008094498,0.00014443042,0.00040283072,0.00035591904,0.00016956161,0.025563259],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973769,0.0014454392,0.00011607768,0.0004919998,0.00043657701,0.00013302283],"domain_scores_gemma":[0.98374313,0.011887862,0.0016164554,0.0016999394,0.00070077245,0.0003517276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030392956,0.0011175574,0.00083273783,0.0021892877,0.0010559397,0.0036312428,0.0012441077,0.002231631,0.027834913],"category_scores_gemma":[0.032533597,0.00064802053,0.00073884847,0.0014760969,0.0045187864,0.008060252,0.0032045129,0.0036147458,0.0010701285],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002181058,0.0001200616,0.0031967505,0.00020238546,0.000037986505,0.00028558268,0.004526748,0.0034795422,0.00068193016,0.9329637,0.005768711,0.04851845],"study_design_scores_gemma":[0.000058206013,0.000060728606,0.002256521,0.00010399753,0.000032934826,0.00035087424,0.0025444045,0.018819097,0.00035321247,0.966305,0.009092701,0.000022233256],"about_ca_topic_score_codex":0.0007113836,"about_ca_topic_score_gemma":0.0008380865,"teacher_disagreement_score":0.027834913,"about_ca_system_score_codex":0.0008530583,"about_ca_system_score_gemma":0.00070502824,"threshold_uncertainty_score":0.09311712},"labels":[],"label_agreement":null},{"id":"W2007579756","doi":"10.3758/brm.41.3.736","title":"An improved screw-free method for electrode implantation and intracranial electroencephalographic recordings in mice","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Neuropharmacology Research","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Western Hospital","funders":"","keywords":"GLUE; Cyanoacrylate; Electrode; Isoflurane; Biomedical engineering; Hippocampal formation; Electroencephalography; Skull; Materials science; Medicine; Surgery; Anesthesia; Chemistry; Layer (electronics); Composite material","score_opus":0.15867781067207018,"score_gpt":0.5680586405988695,"score_spread":0.40938082992679925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007579756","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22967067,0.0027632434,0.74934095,0.001061635,0.0014074018,0.0012766054,0.004907581,0.005941266,0.0036306009],"genre_scores_gemma":[0.24032483,0.0024775406,0.73723733,0.0004028114,0.00021261336,0.002009881,0.0037899774,0.0010425787,0.012502394],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99855405,0.00014537355,0.0002550349,0.00039450036,0.0005174808,0.0001336692],"domain_scores_gemma":[0.9987909,0.0001639635,0.00037764237,0.00035850337,0.00016320281,0.00014576667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012519849,0.0017091858,0.0008815873,0.0016941669,0.0004782177,0.0008994811,0.002277349,0.0017367004,0.0022908563],"category_scores_gemma":[0.000826371,0.0010611346,0.0016767628,0.0005514549,0.00093298306,0.0013653889,0.00087800436,0.0024709136,0.0013978201],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014499761,0.000063127,0.000118346776,0.000041579016,0.000016068114,0.00007721798,0.0000198913,0.000097467564,0.99527115,0.00036477298,0.00021679276,0.0035686851],"study_design_scores_gemma":[0.00013506852,0.0006114694,0.00244647,0.000024313294,0.0001077939,0.0008166045,0.000021328327,0.0023119524,0.98472345,0.00031134702,0.008437268,0.000052998468],"about_ca_topic_score_codex":0.0011060634,"about_ca_topic_score_gemma":0.002906109,"teacher_disagreement_score":0.0022908563,"about_ca_system_score_codex":0.00048719306,"about_ca_system_score_gemma":0.0008411313,"threshold_uncertainty_score":0.007663667},"labels":[],"label_agreement":null},{"id":"W2010248328","doi":"10.3758/brm.42.1.82","title":"Norms for two types of manipulability (graspability and functional usage), familiarity, and age of acquisition for 320 photographs of objects","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Object (grammar); Set (abstract data type); Psychology; Cognitive psychology; Point (geometry); Contrast (vision); Social psychology; Computer science; Artificial intelligence; Mathematics","score_opus":0.2881918808271415,"score_gpt":0.5612557759404353,"score_spread":0.2730638951132938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010248328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690253,0.00018949174,0.015232407,0.00006807022,0.00007718966,0.00031467158,0.0015236968,0.00023196187,0.013337229],"genre_scores_gemma":[0.9767667,0.00010261397,0.0168001,0.000034501394,0.00003514854,0.0010784747,0.0022463189,0.00014696714,0.0027892345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9909204,0.0026183059,0.0018314333,0.0010017187,0.0032608658,0.00036724153],"domain_scores_gemma":[0.8603877,0.0711021,0.02504323,0.010924892,0.029389475,0.0031525695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01084902,0.00041720778,0.00038027548,0.0026021728,0.00050514087,0.001155094,0.00059996656,0.00053661695,0.0032058842],"category_scores_gemma":[0.058990184,0.00030350362,0.0005154089,0.000870603,0.0012108826,0.00087696256,0.0011856672,0.0008606948,0.000977187],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021200713,0.0007332736,0.8763241,0.00028237223,0.00038903035,0.00020451845,0.011504931,0.0008297316,0.023042006,0.0062144585,0.0024375378,0.075918],"study_design_scores_gemma":[0.000030461624,0.0010290344,0.97759116,0.0000582255,0.00006949447,0.0007260555,0.002110782,0.0013576235,0.010806524,0.0019424342,0.0042132484,0.00006516484],"about_ca_topic_score_codex":0.0015666992,"about_ca_topic_score_gemma":0.004139258,"teacher_disagreement_score":0.01084902,"about_ca_system_score_codex":0.00059153355,"about_ca_system_score_gemma":0.00038401378,"threshold_uncertainty_score":0.05737573},"labels":[],"label_agreement":null},{"id":"W2010891396","doi":"10.3758/s13428-010-0030-3","title":"Can computer mice be used as low-cost devices for the acquisition of planar human movement velocity signals?","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Context (archaeology); Movement (music); Data acquisition; Tracking (education); Computer vision; Artificial intelligence; Work (physics); Motion (physics); Human–computer interaction; Planar; Simulation; Acoustics; Computer graphics (images); Psychology; Engineering","score_opus":0.3409888756271376,"score_gpt":0.5554284158859369,"score_spread":0.21443954025879935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010891396","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3163616,0.019341469,0.62941265,0.015179667,0.002541065,0.0005423508,0.0009832017,0.004080768,0.011557188],"genre_scores_gemma":[0.58114874,0.025418673,0.3696936,0.0047621545,0.0006501735,0.0010586511,0.0009737969,0.0007135493,0.015580669],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999258,0.00031209228,0.00003356121,0.00016496105,0.000119159115,0.00011229119],"domain_scores_gemma":[0.9973596,0.0010474444,0.00052808184,0.0004443088,0.00034849762,0.0002720542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025105402,0.0011384506,0.00091003143,0.00051990664,0.00022162845,0.0019295802,0.0019123318,0.0021962435,0.0043325797],"category_scores_gemma":[0.0069957944,0.0007698731,0.00059990055,0.00030179918,0.0012978467,0.0033641767,0.00060345884,0.0012914754,0.0022851415],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00289971,0.0004930209,0.005536762,0.00064900826,0.00017438941,0.00014111311,0.00012304196,0.0005196705,0.8237983,0.008562086,0.0042152004,0.15288763],"study_design_scores_gemma":[0.0005630918,0.006391162,0.018704737,0.00046200876,0.0005506782,0.0016508257,0.00041412874,0.008422186,0.8891761,0.017165257,0.056254756,0.00024510603],"about_ca_topic_score_codex":0.00048675344,"about_ca_topic_score_gemma":0.0006317797,"teacher_disagreement_score":0.0043325797,"about_ca_system_score_codex":0.00023363074,"about_ca_system_score_gemma":0.00050004147,"threshold_uncertainty_score":0.014493883},"labels":[],"label_agreement":null},{"id":"W2012306139","doi":"10.3758/bf03193896","title":"Measuring online volitional response control with a continuous tracking task","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Computer science; Reliability (semiconductor); Context (archaeology); Response time; TRACE (psycholinguistics); Control (management); Tracking (education); Measure (data warehouse); Association (psychology); Human–computer interaction; Simulation; Artificial intelligence; Data mining; Psychology; Engineering; Power (physics)","score_opus":0.6035913841167487,"score_gpt":0.5851437254619571,"score_spread":0.018447658654791588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012306139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9549791,0.00020303542,0.041899428,0.00004543291,0.000057275978,0.0002081095,0.00020623808,0.00016189464,0.0022394778],"genre_scores_gemma":[0.9753601,0.0001610044,0.022125907,0.00012699005,0.00005346239,0.00027194936,0.00023930495,0.00007113314,0.0015900689],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987741,0.00026210246,0.000079499296,0.00032484697,0.00045674792,0.00010267223],"domain_scores_gemma":[0.9964185,0.0022617767,0.00051775225,0.00028543273,0.00026735614,0.00024911348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011609299,0.0006434639,0.0004713269,0.00059676287,0.00023126157,0.00081195025,0.00040325258,0.0007649099,0.0015274711],"category_scores_gemma":[0.00548482,0.00027501443,0.00018281108,0.000546056,0.0003884027,0.0007176002,0.00044887062,0.00073165155,0.00034505973],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005227933,0.0037558915,0.06693544,0.00032502887,0.00028901306,0.0001240864,0.000570225,0.0031361,0.77285814,0.0010782854,0.00068261713,0.1450172],"study_design_scores_gemma":[0.00057875697,0.008754417,0.7449919,0.000065960325,0.0004793353,0.0010770295,0.00021972375,0.06020813,0.18046357,0.0013140346,0.0017259633,0.000121174606],"about_ca_topic_score_codex":0.0010029371,"about_ca_topic_score_gemma":0.0013648792,"teacher_disagreement_score":0.0015274711,"about_ca_system_score_codex":0.000269836,"about_ca_system_score_gemma":0.00044041665,"threshold_uncertainty_score":0.0061396956},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.36229890259229897,"score_gpt":0.5548363531033043,"score_spread":0.1925374505110053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013137720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019688768,0.00057410257,0.97558415,0.0003487482,0.00003790783,0.000034122662,0.000078555844,0.0005010426,0.0031525998],"genre_scores_gemma":[0.5230075,0.0012213594,0.46924752,0.00020080495,0.00008928802,0.0002786193,0.000074069394,0.00030876792,0.0055720382],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997669,0.00009164572,0.0000075070793,0.00007764213,0.000041139814,0.0000152045395],"domain_scores_gemma":[0.9987796,0.0007257901,0.000102171325,0.0002718223,0.0000627452,0.000057941463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012595712,0.0005987347,0.00088277535,0.00063225563,0.00024544646,0.0009071032,0.0012086964,0.0006038262,0.0047897156],"category_scores_gemma":[0.0035498498,0.00044162868,0.0005826798,0.00029273692,0.0011888184,0.0024502466,0.0012529208,0.0009786227,0.00042947166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038421256,0.00036699284,0.0024450948,0.00059740624,0.0003388159,0.00009637125,0.000395524,0.08503953,0.092645645,0.32441312,0.0031286017,0.49014866],"study_design_scores_gemma":[0.00006055244,0.00016083811,0.002615259,0.000035165387,0.000050616138,0.00005333673,0.000051577645,0.69988775,0.0077627217,0.28640425,0.002877858,0.000040207957],"about_ca_topic_score_codex":0.00093159825,"about_ca_topic_score_gemma":0.0009829135,"teacher_disagreement_score":0.0047897156,"about_ca_system_score_codex":0.00042992117,"about_ca_system_score_gemma":0.0003953115,"threshold_uncertainty_score":0.016023159},"labels":[],"label_agreement":null},{"id":"W2014721111","doi":"10.3758/brm.42.2.366","title":"Applying the permutation test to factorial designs","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Permutation (music); Factorial; Fractional factorial design; Parametric statistics; Factorial experiment; Resampling; Mathematics; Computation; Limit (mathematics); Computer science; Test (biology); Algorithm; Statistics","score_opus":0.773946312954811,"score_gpt":0.7301019632369032,"score_spread":0.04384434971790774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014721111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007655429,0.00013176196,0.98767275,0.00025086527,0.00030389254,0.0009139445,0.00014551697,0.00046172348,0.0024640616],"genre_scores_gemma":[0.121462576,0.0002711004,0.8679969,0.000375934,0.00022720108,0.007422553,0.00029229673,0.0002804665,0.0016709485],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8062073,0.17022762,0.003616712,0.008649093,0.010005838,0.0012933688],"domain_scores_gemma":[0.6358897,0.3278871,0.0053013847,0.024400573,0.005680777,0.0008405522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.079630755,0.0023111624,0.0050255186,0.0037640922,0.00216029,0.0030527245,0.003475614,0.002509831,0.018560458],"category_scores_gemma":[0.31866115,0.0015753582,0.004391444,0.0037390117,0.005231129,0.0046518035,0.0027766214,0.0055424166,0.0016985615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036036724,0.0013215948,0.005159355,0.0017783298,0.0021959548,0.00036309144,0.0010851638,0.030224813,0.0027903088,0.2251975,0.006561843,0.7197184],"study_design_scores_gemma":[0.0017218661,0.0048376545,0.0067844805,0.00035027514,0.00065870036,0.00034280284,0.00032279154,0.22306338,0.0044997414,0.7447136,0.01249284,0.00021190464],"about_ca_topic_score_codex":0.0020697895,"about_ca_topic_score_gemma":0.0017638567,"teacher_disagreement_score":0.079630755,"about_ca_system_score_codex":0.0023842438,"about_ca_system_score_gemma":0.006677301,"threshold_uncertainty_score":0.42113274},"labels":[],"label_agreement":null},{"id":"W2016329964","doi":"10.3758/s13428-012-0273-2","title":"Communicative and noncommunicative point-light actions featuring high-resolution representation of the hands and fingers","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Gesture; Computer science; Motion (physics); Representation (politics); Point (geometry); Biological motion; Computer vision; Consistency (knowledge bases); Set (abstract data type); Perception; Artificial intelligence; Motion capture; Action (physics); Position (finance); Frame of reference; Sight; Human–computer interaction; Psychology; Mathematics","score_opus":0.44170687730108377,"score_gpt":0.6120041218654197,"score_spread":0.17029724456433598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016329964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.847309,0.00032095122,0.14155933,0.00009206788,0.000055754077,0.0003123826,0.0003334457,0.00027323724,0.009743899],"genre_scores_gemma":[0.91956514,0.00021478438,0.07532426,0.000049330964,0.000017619162,0.00021226608,0.00019404227,0.000047645066,0.0043749725],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99956685,0.00015013602,0.000019385247,0.00009146674,0.00010839954,0.00006373659],"domain_scores_gemma":[0.9992755,0.0004885605,0.000038704286,0.00008092694,0.000053170712,0.000063135754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006739348,0.00040043026,0.00021991332,0.00043722268,0.00022797198,0.00055102404,0.00043814938,0.00052032334,0.006367778],"category_scores_gemma":[0.0021898379,0.00023171116,0.00024309073,0.00028652145,0.0005273917,0.00047516465,0.00065589696,0.0003208365,0.00045765587],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019874456,0.0004065569,0.0021322728,0.00036483427,0.000044289503,0.00034693498,0.00060642057,0.0071889414,0.8950218,0.0063603506,0.0005383369,0.08500184],"study_design_scores_gemma":[0.00043276566,0.0053310087,0.15503106,0.00025222037,0.00035700493,0.0055060717,0.001785177,0.17334601,0.63167477,0.013390377,0.012606321,0.00028724232],"about_ca_topic_score_codex":0.0006847767,"about_ca_topic_score_gemma":0.0010452011,"teacher_disagreement_score":0.006367778,"about_ca_system_score_codex":0.00022109172,"about_ca_system_score_gemma":0.00023841459,"threshold_uncertainty_score":0.021302342},"labels":[],"label_agreement":null},{"id":"W2017115354","doi":"10.3758/brm.41.3.615","title":"A hybrid approach to experimental control","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Control (management); XML; Set (abstract data type); Programming language; Range (aeronautics); Object (grammar); Operating system; Artificial intelligence","score_opus":0.12827365322053494,"score_gpt":0.5035860982041628,"score_spread":0.3753124449836278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017115354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004451281,0.00007554219,0.99046224,0.000104181345,0.000049652892,0.000050755,0.000033665816,0.00016645464,0.0046061645],"genre_scores_gemma":[0.52218145,0.00024407938,0.46329677,0.00023863115,0.00014785524,0.001259507,0.00016901485,0.00019018768,0.012272647],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974955,0.0012320848,0.00010091341,0.00040257027,0.0006657504,0.00010309431],"domain_scores_gemma":[0.9962025,0.0021244525,0.00019645528,0.0010274141,0.00036384875,0.000085331194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027387594,0.000771201,0.0008610455,0.00091368344,0.00060429913,0.0017631667,0.0026632042,0.0010814922,0.0074134907],"category_scores_gemma":[0.005203495,0.0005246969,0.00069989625,0.0006234308,0.0023638322,0.002200286,0.0023270084,0.0012785889,0.00078636553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056863885,0.0005999543,0.0010088943,0.00033140744,0.00019188516,0.0000828747,0.00033193364,0.09844185,0.03108739,0.6890477,0.0013125469,0.1769949],"study_design_scores_gemma":[0.00012923958,0.00048572794,0.00085194956,0.000041000847,0.00005515526,0.00008669159,0.000116947675,0.70217854,0.011732845,0.27575865,0.008497057,0.00006626722],"about_ca_topic_score_codex":0.001013953,"about_ca_topic_score_gemma":0.0007394581,"teacher_disagreement_score":0.0074134907,"about_ca_system_score_codex":0.0009067195,"about_ca_system_score_gemma":0.0007461207,"threshold_uncertainty_score":0.024800539},"labels":[],"label_agreement":null},{"id":"W2019158162","doi":"10.3758/brm.40.3.744","title":"SayWhen: An automated method for high-accuracy speech onset detection","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Computer science; Latency (audio); Speech recognition; Voice activity detection; Coding (social sciences); Key (lock); Software; Speech processing","score_opus":0.2683079724846872,"score_gpt":0.5790835721226062,"score_spread":0.310775599637919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019158162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01366588,0.0002833305,0.87527895,0.00010786996,0.0003591772,0.00038554784,0.0027317558,0.10488929,0.0022982287],"genre_scores_gemma":[0.06804988,0.00013960611,0.9151918,0.00028221222,0.00018340343,0.0010809524,0.0023464616,0.005162353,0.0075633144],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99840564,0.0002572731,0.00011603872,0.000509845,0.0005788313,0.00013240038],"domain_scores_gemma":[0.99574995,0.001976209,0.0003328406,0.0005245694,0.0011198747,0.00029659012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018698998,0.0023593183,0.0018848042,0.003645159,0.0008286755,0.0014889848,0.0021851894,0.0021904244,0.023569137],"category_scores_gemma":[0.0070961295,0.0011042699,0.0007314779,0.0014422595,0.0003593824,0.0016631981,0.0018537061,0.0010391334,0.015229937],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015411561,0.00024552477,0.004981825,0.00044399005,0.00020410797,0.00021713428,0.00024523458,0.0008917213,0.1656957,0.0013178107,0.045432013,0.77878386],"study_design_scores_gemma":[0.0008874164,0.0007307782,0.04314287,0.00015895955,0.00060050405,0.0027167385,0.000526651,0.45321667,0.40861169,0.009749314,0.07901212,0.0006463071],"about_ca_topic_score_codex":0.0019535266,"about_ca_topic_score_gemma":0.0067454022,"teacher_disagreement_score":0.023569137,"about_ca_system_score_codex":0.00031385513,"about_ca_system_score_gemma":0.0009696429,"threshold_uncertainty_score":0.07884663},"labels":[],"label_agreement":null},{"id":"W2019929444","doi":"10.3758/s13428-012-0204-2","title":"SPSS macros to compare any two fitted values from a regression model","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Applications","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; Lakehead University","funders":"","keywords":"Statistics; Mathematics; Polynomial regression; Regression analysis; Linear regression; Regression; Standard error; Macro; Confidence interval; Design matrix; Segmented regression; Computer science","score_opus":0.7862703712146977,"score_gpt":0.74524494245617,"score_spread":0.04102542875852766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019929444","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12217903,0.00023233102,0.60809004,0.001213189,0.0023394956,0.004995714,0.08861301,0.13477378,0.03756353],"genre_scores_gemma":[0.19581743,0.00020589704,0.66511476,0.0007710724,0.00033356482,0.03906791,0.036246628,0.042730525,0.01971226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98311514,0.008000199,0.002906067,0.0017161231,0.0036108398,0.00065158994],"domain_scores_gemma":[0.791551,0.18324977,0.0072724367,0.009695704,0.007319476,0.00091156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013727026,0.0019305181,0.002403858,0.0055670366,0.0009661396,0.0017371716,0.0018066913,0.0011960035,0.08818178],"category_scores_gemma":[0.11670755,0.0011898482,0.002449777,0.0033292861,0.00092347275,0.0025038358,0.0025482422,0.0041256566,0.014292134],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004672517,0.003400629,0.034292,0.0034357747,0.002046919,0.000887619,0.004899596,0.008412775,0.012082422,0.049604915,0.44453818,0.43172666],"study_design_scores_gemma":[0.002660864,0.005880927,0.14606349,0.0019234908,0.0025072186,0.0019208941,0.0073236106,0.12005592,0.0583364,0.1312073,0.52095926,0.0011607298],"about_ca_topic_score_codex":0.0010330013,"about_ca_topic_score_gemma":0.0017573369,"teacher_disagreement_score":0.08818178,"about_ca_system_score_codex":0.0008487505,"about_ca_system_score_gemma":0.0020590061,"threshold_uncertainty_score":0.29499745},"labels":[],"label_agreement":null},{"id":"W2020571594","doi":"10.3758/s13428-014-0495-6","title":"Manipulability agreement as a predictor of action initiation latency","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute; Université de Moncton","funders":"","keywords":"Agreement; Latency (audio); Computer science; Psychology; Action (physics); Physics; Telecommunications; Linguistics","score_opus":0.5568847796030505,"score_gpt":0.6374625389479308,"score_spread":0.08057775934488032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020571594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946514,0.00009152221,0.0025477547,0.00003224599,0.00001904523,0.00005516688,0.00016688596,0.00007892305,0.0023570205],"genre_scores_gemma":[0.9980221,0.000035938556,0.0011292004,0.000009913914,0.000011701572,0.00005680557,0.00014452648,0.000032891436,0.0005570717],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99820447,0.0005433012,0.00018519,0.00032224302,0.0005798312,0.00016498526],"domain_scores_gemma":[0.9457402,0.03575167,0.012647142,0.0023706553,0.0019508391,0.0015393428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003107277,0.00046640326,0.0004531531,0.001069727,0.00041598242,0.0009473162,0.0004937165,0.0009602001,0.005092947],"category_scores_gemma":[0.04044083,0.00041932537,0.00029303375,0.00070531684,0.0003895734,0.0007381735,0.0006433351,0.0011986592,0.0009237411],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034614855,0.00058108236,0.9477415,0.00008786901,0.0001867325,0.00015861845,0.0011494556,0.0015809033,0.028343856,0.0004624928,0.00026280517,0.015983127],"study_design_scores_gemma":[0.000031541145,0.00062840764,0.9916127,0.000015774805,0.000057401892,0.00021144292,0.00017993666,0.0044552996,0.0023842838,0.00025791625,0.0001468596,0.00001856004],"about_ca_topic_score_codex":0.0017593262,"about_ca_topic_score_gemma":0.002209489,"teacher_disagreement_score":0.005092947,"about_ca_system_score_codex":0.00024338944,"about_ca_system_score_gemma":0.00051806914,"threshold_uncertainty_score":0.01703763},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5571369298902951,"score_gpt":0.6457370586835582,"score_spread":0.08860012879326318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021096528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9619119,0.00054873584,0.009304777,0.0016079238,0.00028531803,0.0002678608,0.00027801952,0.0002411146,0.02555442],"genre_scores_gemma":[0.9878864,0.0003602898,0.007157978,0.00038815473,0.00008843261,0.00034474963,0.00022840776,0.000057198467,0.0034882673],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99431926,0.00197516,0.00057127426,0.00049587106,0.0023701037,0.00026833892],"domain_scores_gemma":[0.94474053,0.028006606,0.014082753,0.0057825907,0.0048975293,0.0024900269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069438484,0.0006325693,0.00090035534,0.0013961118,0.0003773367,0.002106928,0.0010447258,0.001397876,0.0032194776],"category_scores_gemma":[0.059747975,0.0004068115,0.0011358719,0.0008325089,0.0010331357,0.0026573327,0.000988596,0.0015370211,0.001338205],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019265452,0.0052928533,0.7199579,0.00031589626,0.0011425522,0.00015656982,0.0031772614,0.0013859952,0.007994952,0.003178098,0.0045038317,0.25096747],"study_design_scores_gemma":[0.00037008096,0.006285622,0.95601434,0.0003192265,0.00036413866,0.0008555598,0.0029949828,0.0054981066,0.01087114,0.010425546,0.005852143,0.00014908903],"about_ca_topic_score_codex":0.000598535,"about_ca_topic_score_gemma":0.00083301956,"teacher_disagreement_score":0.0069438484,"about_ca_system_score_codex":0.00041680274,"about_ca_system_score_gemma":0.0009255167,"threshold_uncertainty_score":0.036723018},"labels":[],"label_agreement":null},{"id":"W2022055962","doi":"10.3758/s13428-011-0069-9","title":"Response time accuracy in Apple Macintosh computers","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"USB; Computer science; Computer hardware; Significant difference; Response time; Computer graphics (images); Operating system; Statistics; Mathematics; Software","score_opus":0.5416860349608625,"score_gpt":0.5790788147780557,"score_spread":0.037392779817193134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022055962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98563486,0.00019301765,0.0070232498,0.00008684958,0.00007295669,0.000037050588,0.0006422048,0.00086083804,0.005448876],"genre_scores_gemma":[0.98972744,0.00008251888,0.003746256,0.0000716782,0.000023582024,0.000031266172,0.0005691718,0.00028747146,0.0054606665],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984522,0.0003064838,0.00013605792,0.00044520717,0.00052509055,0.00013494324],"domain_scores_gemma":[0.9844602,0.011432641,0.00072580215,0.0009808469,0.002030696,0.00036967488],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010310702,0.00029745747,0.00031736383,0.00065493066,0.00020263153,0.0007198677,0.0004125023,0.0005986257,0.006337081],"category_scores_gemma":[0.022410164,0.000230625,0.00019851024,0.00068201195,0.00016802996,0.0007460471,0.0004372629,0.00047877303,0.0017998539],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03176784,0.0010319374,0.17560361,0.00071061123,0.00026733626,0.0003898982,0.0037893774,0.012055563,0.21622998,0.0032266704,0.011298354,0.5436288],"study_design_scores_gemma":[0.0002417786,0.0025340756,0.80712837,0.00014090762,0.00023283862,0.0007031815,0.0008661076,0.08502278,0.09436317,0.0018563408,0.0067738327,0.0001366169],"about_ca_topic_score_codex":0.005300215,"about_ca_topic_score_gemma":0.004574776,"teacher_disagreement_score":0.99896896,"about_ca_system_score_codex":0.00048514057,"about_ca_system_score_gemma":0.00030441355,"threshold_uncertainty_score":0.021199644},"labels":[],"label_agreement":null},{"id":"W2022075199","doi":"10.3758/brm.42.4.957","title":"Estimating the probability and fidelity of memory","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Fidelity; Variance (accounting); Probability distribution; Algorithm; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.444713486248623,"score_gpt":0.6297663182607204,"score_spread":0.18505283201209738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022075199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21254312,0.0009910592,0.7818425,0.0012980653,0.00006138027,0.00009798722,0.00042565633,0.00020040471,0.002539847],"genre_scores_gemma":[0.9342704,0.0006139945,0.0631065,0.00015456295,0.00009080881,0.00010838344,0.0003573365,0.000041364703,0.0012566962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99351573,0.003689716,0.0003313437,0.001559504,0.00060393434,0.00029973284],"domain_scores_gemma":[0.82975197,0.14688016,0.007527174,0.013060727,0.0020674416,0.0007126119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015266066,0.00070359657,0.0019727985,0.0024942553,0.00066122494,0.0037105053,0.0028922008,0.0027872226,0.0034104977],"category_scores_gemma":[0.17704718,0.00118204,0.0013683954,0.0018315075,0.0036127437,0.007206693,0.0027061878,0.0029248858,0.00036212648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008845615,0.0003908485,0.08879284,0.00071502384,0.0017979135,0.00028881984,0.0013323454,0.35062414,0.002109773,0.33515212,0.0021772324,0.21573438],"study_design_scores_gemma":[0.00009695524,0.00012377619,0.020045128,0.00016237321,0.00029104794,0.0002897184,0.00017492,0.48196667,0.0013413228,0.49428985,0.0011359344,0.00008220931],"about_ca_topic_score_codex":0.006892066,"about_ca_topic_score_gemma":0.0057437513,"teacher_disagreement_score":0.015266066,"about_ca_system_score_codex":0.0016973725,"about_ca_system_score_gemma":0.0013021127,"threshold_uncertainty_score":0.080735624},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Psychology; Valence (chemistry); Stimulus (psychology); Taboo; Cognitive psychology; Arousal; Linguistics; Social psychology; Sociology","score_opus":0.22356297190789665,"score_gpt":0.5275938138999604,"score_spread":0.30403084199206376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023736093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9622657,0.0010968387,0.004144818,0.00014489383,0.0000955308,0.000103037324,0.01928642,0.00013991671,0.012722879],"genre_scores_gemma":[0.977536,0.00037734624,0.0036355972,0.000037866557,0.000034383916,0.00019934522,0.015909923,0.00009917166,0.0021703087],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99774253,0.00087138865,0.00048093247,0.00034285377,0.00044616926,0.00011626762],"domain_scores_gemma":[0.97481596,0.019812955,0.0015335187,0.0006141239,0.0029515722,0.00027193557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019519113,0.00033141414,0.0003496875,0.0020501718,0.00069521985,0.0012936612,0.00023175335,0.00026501468,0.004568661],"category_scores_gemma":[0.017321859,0.00012880542,0.00022622095,0.002466502,0.00053686486,0.0008428483,0.00051354297,0.00034239297,0.0014495137],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057725,0.00038150584,0.6022362,0.0031610243,0.00042348664,0.0018638994,0.030691773,0.0018552078,0.040216953,0.012311819,0.03131493,0.26977077],"study_design_scores_gemma":[0.00013960972,0.0007411871,0.8824816,0.0004344442,0.00033247727,0.001974592,0.013307641,0.0053136228,0.013352892,0.0035907065,0.07820612,0.0001251919],"about_ca_topic_score_codex":0.0035806394,"about_ca_topic_score_gemma":0.0050222194,"teacher_disagreement_score":0.004568661,"about_ca_system_score_codex":0.00067262555,"about_ca_system_score_gemma":0.00045691023,"threshold_uncertainty_score":0.015283704},"labels":[],"label_agreement":null},{"id":"W2025651983","doi":"10.3758/s13428-013-0399-x","title":"Subcutaneous dye injection for marking and identification of individual adult zebrafish (Danio rerio) in behavioral studies","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Zebrafish; Danio; Agonistic behaviour; Simplicity; Fish <Actinopterygii>; Animal behavior; Social behaviour; Psychology; Computer science; Biology; Neuroscience; Aggression; Zoology; Developmental psychology; Fishery; Physics","score_opus":0.16960624862176968,"score_gpt":0.5433258792030013,"score_spread":0.3737196305812317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025651983","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.504166,0.0029517978,0.42414513,0.0012478012,0.0017669691,0.0072736656,0.010510063,0.00869253,0.03924602],"genre_scores_gemma":[0.45733362,0.0037435293,0.3803364,0.0012155983,0.0002827828,0.0106836185,0.0070545482,0.0021195002,0.13723043],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908817,0.00004179612,0.00006461396,0.000353291,0.00020730427,0.0002447298],"domain_scores_gemma":[0.99943477,0.0000715813,0.0001267768,0.00012077749,0.00011908431,0.00012688749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007169245,0.0017970051,0.00087113073,0.002231511,0.0009189734,0.0006240648,0.0012127443,0.0016289109,0.013090274],"category_scores_gemma":[0.0003615492,0.00067977066,0.0010744383,0.00065710326,0.0011507785,0.000878201,0.00079868507,0.0027813984,0.0042055016],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006486571,0.000098533324,0.00015418473,0.000060615414,0.0000061357564,0.00007505942,0.00006150143,0.000031600426,0.9957718,0.00048711078,0.0002953445,0.0028932146],"study_design_scores_gemma":[0.00007751792,0.001147975,0.004467854,0.00004602005,0.00008498079,0.00044314298,0.0000858506,0.0007966368,0.9818071,0.00023635982,0.010772875,0.00003375509],"about_ca_topic_score_codex":0.0028053082,"about_ca_topic_score_gemma":0.01220804,"teacher_disagreement_score":0.013090274,"about_ca_system_score_codex":0.0006749913,"about_ca_system_score_gemma":0.0013183063,"threshold_uncertainty_score":0.043791354},"labels":[],"label_agreement":null},{"id":"W2026427809","doi":"10.3758/s13428-012-0241-x","title":"Bayesian combination of two-dimensional location estimates","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimension (graph theory); Variable (mathematics); Task (project management); Bayesian probability; Computer science; Motion (physics); Artificial intelligence; Value (mathematics); Mathematics; Pattern recognition (psychology); Statistics; Algorithm","score_opus":0.44191674458838565,"score_gpt":0.6149044304039545,"score_spread":0.17298768581556884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026427809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018573547,0.000590201,0.97831535,0.0002850495,0.00006704754,0.000048720616,0.00031249854,0.00039800027,0.0014095574],"genre_scores_gemma":[0.5075459,0.0011594922,0.48155,0.00028019198,0.00033837208,0.0003091389,0.0021562881,0.00025001212,0.006410613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952554,0.0017800551,0.00038134004,0.0011316802,0.0011595452,0.0002920145],"domain_scores_gemma":[0.98760706,0.007732872,0.00078328344,0.0016625331,0.0018599895,0.00035416128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072808946,0.0014630501,0.002606343,0.0032477968,0.000757464,0.0029776434,0.0026126239,0.0022298268,0.0043268898],"category_scores_gemma":[0.031357232,0.0017095967,0.0018958687,0.0027586939,0.0008787602,0.0042049843,0.003347624,0.0022376827,0.002019745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020044737,0.0004779622,0.016237231,0.0006146815,0.0011514259,0.0002298011,0.00037539838,0.2437248,0.012393057,0.036028143,0.007063635,0.6796995],"study_design_scores_gemma":[0.00006555886,0.00010599109,0.006995079,0.0000771387,0.00017266281,0.00018661648,0.000041650055,0.9473468,0.0026385686,0.040360812,0.0019117037,0.00009740464],"about_ca_topic_score_codex":0.0047879545,"about_ca_topic_score_gemma":0.008889532,"teacher_disagreement_score":0.0072808946,"about_ca_system_score_codex":0.0009984429,"about_ca_system_score_gemma":0.0016108864,"threshold_uncertainty_score":0.038505554},"labels":[],"label_agreement":null},{"id":"W2026942731","doi":"10.3758/s13428-011-0090-z","title":"Redefining membership in animal groups","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Animal Behavior and Reproduction","field":"Agricultural and Biological Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SGS (Canada); University of Toronto","funders":"","keywords":"Shoal; Shoaling and schooling; Danio; Group cohesiveness; Herding; Flock; Group (periodic table); Collective motion; Computer science; Geography; Ecology; Zebrafish; Fishery; Artificial intelligence; Psychology; Biology; Social psychology; Geology; Physics; Oceanography","score_opus":0.589806443472049,"score_gpt":0.5161282013694632,"score_spread":0.07367824210258578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026942731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89219314,0.00012789706,0.09421617,0.0012115091,0.000084416366,0.00011441375,0.00012248424,0.00019213965,0.011737759],"genre_scores_gemma":[0.9479979,0.000037670427,0.04902721,0.00008918235,0.000023315648,0.0000925633,0.000114665076,0.000037800124,0.0025796876],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99352854,0.0038438851,0.00031457798,0.0009508079,0.0008817103,0.000480581],"domain_scores_gemma":[0.94688934,0.030867651,0.006345139,0.009956534,0.0035678714,0.0023735415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010423546,0.0003555996,0.0006214923,0.0010549341,0.0013378679,0.0022332123,0.0014985979,0.0010929139,0.005007181],"category_scores_gemma":[0.042236634,0.00030244814,0.00031353993,0.0010338017,0.001970117,0.004182961,0.0033693686,0.0017025888,0.0004715212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024307559,0.0016235776,0.20243846,0.0005341197,0.00016574544,0.00019367979,0.031263158,0.01955496,0.032576974,0.11888646,0.0036845338,0.5866475],"study_design_scores_gemma":[0.00035208632,0.002662836,0.34135297,0.00050444546,0.0004948132,0.00071575143,0.040573087,0.20549291,0.04310655,0.31993046,0.044613864,0.00020020909],"about_ca_topic_score_codex":0.0016294367,"about_ca_topic_score_gemma":0.004858759,"teacher_disagreement_score":0.010423546,"about_ca_system_score_codex":0.0010031367,"about_ca_system_score_gemma":0.0009999274,"threshold_uncertainty_score":0.055125594},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6740604188140626,"score_gpt":0.6686980108350041,"score_spread":0.005362407979058514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027900864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06203182,0.00053608743,0.7245645,0.0011707925,0.0018123717,0.0061466885,0.087614395,0.059270233,0.056853127],"genre_scores_gemma":[0.13183749,0.00059843523,0.7596003,0.00062025705,0.0003519877,0.035034467,0.023255749,0.017792318,0.030908942],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9828996,0.008325999,0.0023126088,0.001525621,0.0042411597,0.0006950343],"domain_scores_gemma":[0.8533656,0.11603436,0.008581193,0.012328855,0.008885411,0.00080461724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012156895,0.0014705089,0.0019912915,0.0046881284,0.00091294554,0.0020284506,0.0016835621,0.00087127934,0.08317594],"category_scores_gemma":[0.10428373,0.0010031,0.0018953164,0.0055128154,0.000821378,0.0018552354,0.0014559231,0.004039407,0.015795061],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021268616,0.002117512,0.030017657,0.004153195,0.0012726962,0.0005226677,0.0039115497,0.0061260643,0.0051931897,0.06703836,0.35280892,0.52471125],"study_design_scores_gemma":[0.0018169316,0.0042452877,0.1324662,0.002435705,0.002171271,0.0018079702,0.0064347973,0.06314035,0.030363498,0.15605482,0.59840935,0.00065385585],"about_ca_topic_score_codex":0.0024625466,"about_ca_topic_score_gemma":0.0043886593,"teacher_disagreement_score":0.08317594,"about_ca_system_score_codex":0.00088404265,"about_ca_system_score_gemma":0.004187015,"threshold_uncertainty_score":0.27825123},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2242416127247494,"score_gpt":0.6053365934815501,"score_spread":0.3810949807568007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030751416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99656963,0.00017317839,0.00019309185,0.000014886634,0.0000094196,0.000013227056,0.00023505585,0.000012505701,0.002778924],"genre_scores_gemma":[0.99460006,0.00019454831,0.0005856318,0.000042244577,0.000026636817,0.000023274359,0.00053977483,0.000016819893,0.003971052],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995983,0.00013104505,0.0000414219,0.000083933875,0.00011150302,0.000033672808],"domain_scores_gemma":[0.9950722,0.0024052903,0.00085465005,0.00021129637,0.0010325115,0.00042406123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007483313,0.00028684232,0.00021706251,0.00090893474,0.00030058742,0.0006819457,0.00011572728,0.00047414596,0.004652371],"category_scores_gemma":[0.006058346,0.00008828961,0.00023502823,0.0003342451,0.00023609822,0.0005187196,0.00022291676,0.00021628737,0.0006697295],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004268935,0.00055075844,0.84921694,0.00031800912,0.00022904463,0.0005566926,0.012562933,0.00024168228,0.065100834,0.00037729164,0.001434875,0.065142035],"study_design_scores_gemma":[0.000010858803,0.0005222662,0.9958696,0.000010420136,0.000021454427,0.00030079274,0.0011145674,0.000109877095,0.001065978,0.000027171342,0.00093542476,0.000011687319],"about_ca_topic_score_codex":0.0042634076,"about_ca_topic_score_gemma":0.0070357304,"teacher_disagreement_score":0.004652371,"about_ca_system_score_codex":0.00026930374,"about_ca_system_score_gemma":0.00009485807,"threshold_uncertainty_score":0.015563786},"labels":[],"label_agreement":null},{"id":"W2034196084","doi":"10.3758/s13428-010-0029-9","title":"A computer-generated face database with ratings on realism, masculinity, race, and stereotypy","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Masculinity; Psychology; Perception; Race (biology); Ethnic group; Set (abstract data type); Face perception; Face (sociological concept); Social psychology; Cognitive psychology; Computer science; Gender studies; Sociology","score_opus":0.358130814821676,"score_gpt":0.5455536191535534,"score_spread":0.18742280433187736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034196084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76551366,0.0005126152,0.042233948,0.00020300374,0.000256822,0.0049746595,0.16527785,0.003940556,0.017086904],"genre_scores_gemma":[0.7090973,0.000513465,0.06841022,0.0003836166,0.00013576656,0.0053600706,0.20162222,0.00033430228,0.014142942],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996001,0.00005211438,0.00005018496,0.00011484518,0.00014949722,0.000033218323],"domain_scores_gemma":[0.9987552,0.00020161961,0.00009521965,0.0002841685,0.00056243734,0.0001013402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041843115,0.0006003155,0.0007881942,0.0016913023,0.00029541668,0.00033755228,0.00058748474,0.00062946306,0.012674177],"category_scores_gemma":[0.0012885316,0.00015509162,0.0003880944,0.000916708,0.00017996966,0.00033332707,0.00050440495,0.00026280773,0.0055915527],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004924329,0.004590935,0.08188561,0.0015098321,0.00043559907,0.0012770154,0.0004759255,0.0064516184,0.23972936,0.001310322,0.08186699,0.5755425],"study_design_scores_gemma":[0.00045055003,0.002018844,0.8099278,0.00011354454,0.00040521493,0.006607513,0.000576751,0.04982056,0.08272402,0.001133959,0.045961123,0.0002600667],"about_ca_topic_score_codex":0.0026483953,"about_ca_topic_score_gemma":0.004492002,"teacher_disagreement_score":0.012674177,"about_ca_system_score_codex":0.0002837129,"about_ca_system_score_gemma":0.0003069967,"threshold_uncertainty_score":0.042399347},"labels":[],"label_agreement":null},{"id":"W2035770374","doi":"10.3758/s13428-014-0488-5","title":"Four types of manipulability ratings and naming latencies for a set of 560 photographs of objects","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Moncton","funders":"","keywords":"Affordance; Comparability; USable; Set (abstract data type); Popularity; Computer science; Cognitive psychology; Psychology; Cognition; Human–computer interaction; Social psychology; Multimedia; Mathematics","score_opus":0.48768210256630884,"score_gpt":0.6016371807737658,"score_spread":0.11395507820745698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035770374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959502,0.00011111971,0.0010692246,0.0000127835865,0.000014821896,0.00012854401,0.0003101714,0.000055078483,0.0023480437],"genre_scores_gemma":[0.99475265,0.000092265975,0.0018636798,0.000022729006,0.000008777064,0.00014439317,0.00044073287,0.000038746246,0.0026359523],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998906,0.00023048604,0.00014155902,0.0002198856,0.00041167025,0.000090393754],"domain_scores_gemma":[0.9839987,0.008526284,0.003238953,0.0017041767,0.0019961451,0.00053575303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014017446,0.0004934796,0.00041116923,0.0011420267,0.00031172266,0.00049388857,0.00038467676,0.00068704435,0.0042047966],"category_scores_gemma":[0.021598382,0.00030603117,0.0004083116,0.0005149247,0.00036510013,0.00071981316,0.00053877407,0.00058892387,0.00080652075],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012021743,0.0017579254,0.5254812,0.000742126,0.00040168266,0.0005076091,0.0049113794,0.00087139715,0.37482026,0.0005142685,0.00076443015,0.077205874],"study_design_scores_gemma":[0.00004216554,0.0008995803,0.98410654,0.000011370095,0.000053113166,0.00015112218,0.00045136892,0.00052032573,0.013291671,0.00009972186,0.0003438185,0.000029164183],"about_ca_topic_score_codex":0.0020717098,"about_ca_topic_score_gemma":0.0040066703,"teacher_disagreement_score":0.0042047966,"about_ca_system_score_codex":0.00041698513,"about_ca_system_score_gemma":0.00021438778,"threshold_uncertainty_score":0.014066517},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"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","score_opus":0.7240286491433732,"score_gpt":0.6707538589519908,"score_spread":0.05327479019138237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037416776","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004188087,0.00012312012,0.97842455,0.00031093013,0.00005518332,0.0021096852,0.004802698,0.008407597,0.0015782702],"genre_scores_gemma":[0.01686679,0.000068596535,0.9706581,0.00011879249,0.000029112767,0.007190875,0.0024396137,0.0016488364,0.0009792296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96155393,0.023156853,0.0048989225,0.0041318797,0.00538222,0.00087614113],"domain_scores_gemma":[0.89184475,0.08152804,0.0048865466,0.013933637,0.00731067,0.0004964182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046019718,0.004963258,0.0028846406,0.006722646,0.0012594279,0.0036104822,0.004279596,0.0019105896,0.020891516],"category_scores_gemma":[0.16253874,0.0030583255,0.006447131,0.0070739263,0.002103312,0.002439942,0.0043028537,0.0038103722,0.013785106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010254371,0.0009109039,0.05400797,0.0050861863,0.003818564,0.0008588733,0.0028219402,0.022943934,0.011804577,0.16043457,0.11671453,0.61957246],"study_design_scores_gemma":[0.0017830153,0.0020393631,0.109816685,0.0025663336,0.0028125034,0.004047345,0.0009959253,0.25107154,0.028520126,0.32403612,0.27107525,0.0012357502],"about_ca_topic_score_codex":0.003787803,"about_ca_topic_score_gemma":0.0036879808,"teacher_disagreement_score":0.046019718,"about_ca_system_score_codex":0.00131742,"about_ca_system_score_gemma":0.0050735315,"threshold_uncertainty_score":0.24337846},"labels":[],"label_agreement":null},{"id":"W2037493627","doi":"10.3758/s13428-011-0182-9","title":"SOS! An algorithm and software for the stochastic optimization of stimuli","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; University of Pittsburgh; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Carnegie Mellon University; University of Pennsylvania","keywords":"Computer science; Generality; Software; Python (programming language); Maximization; Machine learning; Usability; MATLAB; Toolbox; Artificial intelligence; Algorithm; Mathematical optimization; Human–computer interaction; Programming language; Mathematics","score_opus":0.6979840277782209,"score_gpt":0.6476718274083718,"score_spread":0.05031220036984907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037493627","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073069584,0.00003225951,0.9873935,0.00008779964,0.000066014756,0.000028138988,0.00014529515,0.010428674,0.0010876221],"genre_scores_gemma":[0.051127102,0.00016968665,0.9360663,0.0002493516,0.00009924398,0.0004625102,0.0005032163,0.006695447,0.0046270387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992704,0.00022717346,0.000055175573,0.00008812224,0.00029624256,0.00006294761],"domain_scores_gemma":[0.9983935,0.0010759053,0.000094515344,0.000167861,0.00019817984,0.00007010506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013246029,0.001066922,0.00097494025,0.0005653732,0.00059608504,0.0010162793,0.0017257673,0.0013672009,0.023511773],"category_scores_gemma":[0.005228291,0.00095015863,0.0015061235,0.00048450168,0.0009157346,0.001090083,0.0021281415,0.0024143874,0.0067863734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078339904,0.00019937495,0.001487535,0.0009977659,0.00036967776,0.00030408776,0.0002289553,0.34158248,0.017333135,0.15338635,0.06909086,0.41423637],"study_design_scores_gemma":[0.00012131264,0.00004320938,0.00013662927,0.000053999473,0.000021375348,0.00006805282,0.000012303486,0.93987185,0.0043097055,0.037317365,0.018018411,0.0000257788],"about_ca_topic_score_codex":0.0021021522,"about_ca_topic_score_gemma":0.0030439212,"teacher_disagreement_score":0.023511773,"about_ca_system_score_codex":0.00050064,"about_ca_system_score_gemma":0.0013480919,"threshold_uncertainty_score":0.07865471},"labels":[],"label_agreement":null},{"id":"W2038349824","doi":"10.3758/s13428-015-0585-0","title":"Disparity in organizational research: How should we measure it?","year":2015,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Gender Diversity and Inequality","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Program for New Century Excellent Talents in University; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Gini coefficient; Theil index; Statistics; Standard deviation; Econometrics; Inequality; Mathematics; Index (typography); Measure (data warehouse); Sample size determination; Economics; Computer science; Economic inequality","score_opus":0.9601976785276772,"score_gpt":0.72143815920155,"score_spread":0.23875951932612727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038349824","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010592152,0.99079484,0.0004957277,0.0076980665,0.00052094826,0.000015821282,0.00003319778,0.0000049544215,0.00033058343],"genre_scores_gemma":[0.0038040732,0.9855966,0.003302813,0.0056845816,0.00131009,0.000099802295,0.00005507256,0.0000119609285,0.00013508313],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9537036,0.027717598,0.005353257,0.0032054621,0.0093264915,0.000693616],"domain_scores_gemma":[0.7255551,0.2362685,0.011617967,0.0047501153,0.01886137,0.0029469028],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.079471454,0.001853901,0.009446516,0.0137507515,0.0018077821,0.009371336,0.005516296,0.00735072,0.0038431082],"category_scores_gemma":[0.15132077,0.0013609456,0.0020576918,0.01782257,0.013675282,0.013973984,0.006074283,0.009303897,0.0008458256],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007905285,0.00011590686,0.004177537,0.08726688,0.0013423914,0.00007245322,0.0014089557,0.00026588156,0.00011624417,0.042512853,0.036399994,0.82624185],"study_design_scores_gemma":[0.000118251555,0.0002140181,0.0127925435,0.33945706,0.0029567052,0.00054377323,0.004568425,0.00056264544,0.0002662738,0.13085306,0.50742227,0.00024490425],"about_ca_topic_score_codex":0.011215556,"about_ca_topic_score_gemma":0.023462784,"teacher_disagreement_score":0.92052853,"about_ca_system_score_codex":0.008056494,"about_ca_system_score_gemma":0.025646375,"threshold_uncertainty_score":0.42029023},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Generalizability theory; Computer science; Psychology; Developmental psychology","score_opus":0.9596454361401149,"score_gpt":0.7860996307771648,"score_spread":0.17354580536295006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039891070","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036210954,0.00030977486,0.7378261,0.0014938269,0.0013707257,0.014231381,0.07030912,0.06365109,0.074597046],"genre_scores_gemma":[0.07189094,0.0004464766,0.80452347,0.0006020825,0.00032901976,0.048203144,0.023912445,0.015996952,0.034095444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97996247,0.01066444,0.0027378309,0.0017261801,0.004144711,0.0007644312],"domain_scores_gemma":[0.81760377,0.13213956,0.0067840116,0.02571976,0.01696202,0.0007908967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01988859,0.0017899487,0.0022283238,0.0066656373,0.0013061969,0.0031279707,0.0015688714,0.0007923092,0.10878878],"category_scores_gemma":[0.13470078,0.0015313202,0.0023111592,0.006873764,0.0009402372,0.0031179462,0.001928485,0.0054351804,0.025681127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092587504,0.0017974592,0.016160758,0.0029656466,0.0007287257,0.00034721903,0.0057109133,0.0053074886,0.0030495874,0.07330794,0.34576538,0.54393303],"study_design_scores_gemma":[0.0015566398,0.0017307333,0.06264229,0.0022969572,0.0014487315,0.00080981955,0.0064358534,0.05954558,0.022314696,0.23550081,0.60530335,0.00041460543],"about_ca_topic_score_codex":0.0031361026,"about_ca_topic_score_gemma":0.0040100208,"teacher_disagreement_score":0.10878878,"about_ca_system_score_codex":0.0013038359,"about_ca_system_score_gemma":0.0049719457,"threshold_uncertainty_score":0.36393476},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6078203590008676,"score_gpt":0.6485880780666875,"score_spread":0.040767719065819885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043356813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12688765,0.0007072464,0.8682328,0.00009573567,0.000046632078,0.00006270396,0.00082884834,0.0010673869,0.0020710104],"genre_scores_gemma":[0.7773348,0.0003825597,0.21749225,0.000029093919,0.00008263266,0.00011946494,0.0011949765,0.00026813045,0.0030960734],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995185,0.00012543681,0.000036547593,0.0001412332,0.00013516133,0.000043134944],"domain_scores_gemma":[0.9979634,0.00099987,0.0003201722,0.0002761913,0.00037781382,0.00006255478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000695197,0.0004247103,0.00048841664,0.0019049285,0.0002700656,0.00052779174,0.00044902516,0.000308802,0.0022797883],"category_scores_gemma":[0.004246111,0.00016100834,0.00056504784,0.0013459239,0.00022068292,0.00058455404,0.00040891967,0.00039527117,0.00057093543],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006401871,0.00011580153,0.015739491,0.0004621555,0.00026004828,0.00020651297,0.00057119166,0.03997941,0.17761746,0.020881701,0.00413914,0.73938686],"study_design_scores_gemma":[0.00002475368,0.0001903458,0.053233236,0.000042414376,0.00015906733,0.0004006488,0.00012020919,0.90158504,0.031897645,0.0083754035,0.003905071,0.00006618517],"about_ca_topic_score_codex":0.0029366086,"about_ca_topic_score_gemma":0.0028067145,"teacher_disagreement_score":0.0029366086,"about_ca_system_score_codex":0.00029170222,"about_ca_system_score_gemma":0.00044534577,"threshold_uncertainty_score":0.0076266527},"labels":[],"label_agreement":null},{"id":"W2045164651","doi":"10.3758/s13428-013-0370-x","title":"Subjective frequency ratings for 432 ASL signs","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":62,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"American Sign Language; Sign (mathematics); Psychology; Age of Acquisition; Sign language; Audiology; Word lists by frequency; Linguistics; Mathematics; Cognition; Medicine","score_opus":0.5161361651891855,"score_gpt":0.6621774302998505,"score_spread":0.14604126511066506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045164651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98313475,0.00014023208,0.0034598566,0.000040776988,0.000056359517,0.00021050144,0.000828227,0.0000634708,0.0120658055],"genre_scores_gemma":[0.98269445,0.00022083035,0.006165143,0.00012633625,0.000054984543,0.00028529266,0.0008159204,0.000049623068,0.009587436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99883133,0.00028842772,0.00013473777,0.00012569365,0.0005194824,0.000100301404],"domain_scores_gemma":[0.99257916,0.0028984982,0.0010567994,0.0004754049,0.002463808,0.0005264034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000936269,0.0005051917,0.000333038,0.0012648881,0.00025471702,0.0005659442,0.00024020276,0.0007198358,0.010452245],"category_scores_gemma":[0.008908267,0.00013771279,0.00036980145,0.00036015527,0.00025534484,0.00044447527,0.00063501205,0.0005267524,0.0015939622],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009828898,0.0023102164,0.41244084,0.0013871486,0.00029953453,0.0009663174,0.0056687277,0.00085394655,0.38488683,0.00080916524,0.0032593166,0.17728896],"study_design_scores_gemma":[0.00010860148,0.0054833493,0.96075684,0.00008796687,0.00015985093,0.0013670044,0.0018590027,0.0010889743,0.024946079,0.00013872933,0.003921265,0.00008244775],"about_ca_topic_score_codex":0.00073019956,"about_ca_topic_score_gemma":0.0019078854,"teacher_disagreement_score":0.010452245,"about_ca_system_score_codex":0.00018177046,"about_ca_system_score_gemma":0.00015957438,"threshold_uncertainty_score":0.03496623},"labels":[],"label_agreement":null},{"id":"W2046087187","doi":"10.3758/bf03192781","title":"Picture-naming norms for Canadian French: Name agreement, familiarity, visual complexity, and age of acquisition","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Normative; Age of Acquisition; Agreement; Psychology; Age groups; Nomination; Interpretation (philosophy); Age discrimination; Linguistics; Audiology; Demography; Medicine; Cognition; Sociology; Political science; Law","score_opus":0.29682124807064453,"score_gpt":0.535764501236298,"score_spread":0.2389432531656535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046087187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9633075,0.00044652735,0.0048968927,0.00024850835,0.00010018732,0.0003408271,0.009311908,0.00026103624,0.021086628],"genre_scores_gemma":[0.98185205,0.00014545106,0.0062383614,0.00007154332,0.000019015486,0.00035080695,0.006511023,0.00017665261,0.004635261],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948389,0.000898704,0.00069174403,0.00060888333,0.0025667811,0.00039506584],"domain_scores_gemma":[0.9603048,0.007892925,0.0047224234,0.002111352,0.023441195,0.0015273549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006771079,0.0005185473,0.00046559723,0.004311686,0.002184169,0.0015862868,0.0016853053,0.00071710424,0.0061082374],"category_scores_gemma":[0.02918814,0.00024340548,0.0008717684,0.002349811,0.0010328577,0.0010162436,0.0009608232,0.0008001434,0.0009939858],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015662006,0.00030407417,0.86922544,0.00021262729,0.00024680374,0.00055029406,0.018840851,0.0014725236,0.009186234,0.00546609,0.012168769,0.08076001],"study_design_scores_gemma":[0.000027057635,0.0001307477,0.9888783,0.00004059675,0.000031160645,0.00040422578,0.0017488493,0.0009524416,0.0014738162,0.0005708702,0.005677954,0.00006408437],"about_ca_topic_score_codex":0.7222495,"about_ca_topic_score_gemma":0.8468881,"teacher_disagreement_score":0.2777505,"about_ca_system_score_codex":0.008927368,"about_ca_system_score_gemma":0.008365982,"threshold_uncertainty_score":0.55877244},"labels":[],"label_agreement":null},{"id":"W2046573508","doi":"10.3758/brm.40.3.705","title":"WINDSOR: Windsor improved norms of distance and similarity of representations of semantics","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Windsor; Computer science; Similarity (geometry); Word (group theory); Semantic similarity; Semantics (computer science); Meaning (existential); Natural language processing; Lexical semantics; Cognition; Artificial intelligence; Lexical item; Linguistics; Psychology","score_opus":0.27716463127891805,"score_gpt":0.5285698993187112,"score_spread":0.2514052680397932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046573508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014935969,0.00029253305,0.97468036,0.00026404552,0.00022709742,0.00016015202,0.0015513867,0.0046478244,0.0032406887],"genre_scores_gemma":[0.13674758,0.00031725428,0.8463254,0.0001439774,0.00020729404,0.00059425156,0.004571745,0.002953595,0.008138926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935127,0.0022519238,0.0005458059,0.0012885773,0.0021694938,0.00023160805],"domain_scores_gemma":[0.988882,0.0041603097,0.0006012839,0.002549015,0.0033003415,0.00050696725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063635074,0.0013519222,0.0014844524,0.004225905,0.0011421286,0.003657533,0.0022319697,0.0014756564,0.008322127],"category_scores_gemma":[0.032628182,0.0008678781,0.0016044735,0.0034037416,0.0012843221,0.008093067,0.004477959,0.0026557331,0.0027402982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015234284,0.00039660966,0.005001825,0.0006043115,0.00036845877,0.00010554678,0.0016423987,0.039946005,0.008601024,0.26257667,0.039202902,0.6400309],"study_design_scores_gemma":[0.0003703688,0.00047917906,0.0029857892,0.00017054401,0.00019083598,0.0002330642,0.0005489913,0.56727374,0.016136117,0.33271298,0.0787107,0.00018773835],"about_ca_topic_score_codex":0.008511922,"about_ca_topic_score_gemma":0.013523895,"teacher_disagreement_score":0.008511922,"about_ca_system_score_codex":0.0015698277,"about_ca_system_score_gemma":0.0020104914,"threshold_uncertainty_score":0.033653855},"labels":[],"label_agreement":null},{"id":"W2047223150","doi":"10.3758/s13428-013-0378-2","title":"The transitional impact scale: Assessing the material and psychological impact of life transitions","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Hospital Edmonton; University of Alberta","funders":"","keywords":"Varimax rotation; Cronbach's alpha; Psychology; Scale (ratio); Event (particle physics); Statistics; Internal consistency; Factor analysis; Clinical psychology; Psychometrics; Mathematics; Cartography; Physics; Geography","score_opus":0.3562437201120754,"score_gpt":0.6613279935070518,"score_spread":0.30508427339497646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047223150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842717,0.0005561784,0.0018036478,0.00029543455,0.0000916341,0.0009351903,0.0017045746,0.00008470721,0.010257014],"genre_scores_gemma":[0.9872428,0.0006662112,0.0058535133,0.00015915724,0.0000435325,0.00096045545,0.0014566378,0.000028869734,0.0035889135],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999108,0.00021424633,0.00014345255,0.000042998803,0.00040520477,0.00008607411],"domain_scores_gemma":[0.99781716,0.0005296006,0.00079421006,0.00011513667,0.000283088,0.00046078349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011246176,0.00046448683,0.000564963,0.0013816752,0.0005922014,0.00075937307,0.0006742956,0.00041839524,0.004176461],"category_scores_gemma":[0.0055159633,0.00028007795,0.0009988362,0.0007587145,0.00035582716,0.00090933836,0.001809869,0.0011394204,0.00035041204],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026622524,0.004543735,0.68585306,0.0007979456,0.0010039014,0.0004923662,0.005588237,0.0019057405,0.005495163,0.0015013451,0.008760965,0.28139526],"study_design_scores_gemma":[0.00017294577,0.001514862,0.9871377,0.000093076495,0.00016926702,0.0004740104,0.0019768628,0.0010578951,0.001253941,0.0006967269,0.005384602,0.00006815799],"about_ca_topic_score_codex":0.0012641702,"about_ca_topic_score_gemma":0.0031700947,"teacher_disagreement_score":0.004176461,"about_ca_system_score_codex":0.0004407153,"about_ca_system_score_gemma":0.00056805724,"threshold_uncertainty_score":0.013971686},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5923435475429615,"score_gpt":0.5003782614832487,"score_spread":0.09196528605971277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047902775","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009133247,0.00065921183,0.78206015,0.0010546107,0.0019712043,0.003232955,0.06096353,0.12581713,0.01510792],"genre_scores_gemma":[0.026976494,0.00030019227,0.8917078,0.00060805434,0.0003864804,0.019429069,0.00779339,0.041328736,0.011469868],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9840682,0.0068484363,0.0020675322,0.0029789093,0.0026019218,0.0014348452],"domain_scores_gemma":[0.87987596,0.10466774,0.0038688828,0.0070867157,0.0034758367,0.0010249441],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025392909,0.00582036,0.0068687955,0.0059718094,0.002156839,0.0055834902,0.007426024,0.0038669491,0.32714435],"category_scores_gemma":[0.12195454,0.0040045283,0.0074395966,0.007195283,0.002488752,0.007545924,0.0049332124,0.007514189,0.042596396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070739845,0.0020780594,0.008901776,0.010829982,0.0061887084,0.0022346037,0.0036822786,0.020148074,0.007101854,0.12413809,0.53576183,0.27186075],"study_design_scores_gemma":[0.005469358,0.0023820046,0.018786518,0.0032081406,0.0038853725,0.0016179284,0.00094178674,0.14536038,0.017721677,0.33080056,0.4684751,0.0013512296],"about_ca_topic_score_codex":0.006102361,"about_ca_topic_score_gemma":0.005154405,"teacher_disagreement_score":0.32714435,"about_ca_system_score_codex":0.0015309389,"about_ca_system_score_gemma":0.0059834574,"threshold_uncertainty_score":0.9597469},"labels":[],"label_agreement":null},{"id":"W2049257061","doi":"10.3758/bf03192854","title":"Word lists for testing cognitive biases toward body shape among men and women","year":2007,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Eating Disorders and Behaviors","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Categorization; Normative; Cognition; Word (group theory); Psychology; Word list; Word lists by frequency; Valence (chemistry); Cognitive psychology; Natural language processing; Computer science; Linguistics; Index (typography); Artificial intelligence","score_opus":0.46739107672332725,"score_gpt":0.6153644590337722,"score_spread":0.147973382310445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049257061","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99205023,0.00014530383,0.0021123092,0.00010165195,0.00023180479,0.0006051129,0.0005200749,0.00008419194,0.0041493326],"genre_scores_gemma":[0.9679156,0.00027715391,0.011472443,0.0005794453,0.00017324176,0.0050201435,0.0017667753,0.00019217966,0.012603102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99761415,0.0006858563,0.00037022913,0.00035373477,0.0007874781,0.00018852724],"domain_scores_gemma":[0.96760434,0.02485412,0.0034179166,0.0014466133,0.0018239164,0.0008531845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040763295,0.0009816684,0.0010051577,0.0013171203,0.00096978055,0.0014954575,0.00084675127,0.0016218625,0.018916536],"category_scores_gemma":[0.032340452,0.0004944906,0.0008290084,0.0006643492,0.00086185645,0.0031811646,0.0010829779,0.0011435269,0.003033432],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.071038306,0.015603427,0.5043477,0.0018976686,0.0011263969,0.0012144262,0.017377274,0.0012562168,0.107033804,0.006202901,0.013055942,0.259846],"study_design_scores_gemma":[0.0063592377,0.034252703,0.90184027,0.0003800651,0.0010848788,0.0017646154,0.008255078,0.005185593,0.021109235,0.0072855013,0.012035158,0.00044764916],"about_ca_topic_score_codex":0.00077868864,"about_ca_topic_score_gemma":0.0013082151,"teacher_disagreement_score":0.018916536,"about_ca_system_score_codex":0.00044295657,"about_ca_system_score_gemma":0.00058832666,"threshold_uncertainty_score":0.06328213},"labels":[],"label_agreement":null},{"id":"W2049304476","doi":"10.3758/s13428-011-0184-7","title":"The bank of standardized stimuli (BOSS): comparison between French and English norms","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Categorization, perception, and language","field":"Psychology","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation; Jewish Rehabilitation Hospital; McGill University; Douglas Mental Health University Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boss; Categorization; Linguistics; Psychology; Concordance; Set (abstract data type); Affect (linguistics); Agreement; Social psychology; Object (grammar); Communication; Computer science","score_opus":0.28537434359636293,"score_gpt":0.6022035280019665,"score_spread":0.3168291844056036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049304476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781361,0.00047359258,0.006078478,0.00023292942,0.00018499306,0.0005226198,0.0026316256,0.00018267869,0.011556884],"genre_scores_gemma":[0.98897374,0.00017755711,0.004006323,0.00025528704,0.00006646167,0.0009783931,0.0031909589,0.0002310216,0.0021202534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949309,0.002725853,0.00052578124,0.00054325466,0.001039827,0.00023435445],"domain_scores_gemma":[0.98362744,0.007532151,0.0015539263,0.0018067571,0.004271042,0.0012088045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062336214,0.0005405518,0.00053580763,0.0018678245,0.0008855027,0.0013552997,0.0007481716,0.000907337,0.009633125],"category_scores_gemma":[0.03235039,0.00022883982,0.0003787043,0.0007359725,0.0009526586,0.0011377404,0.0014837098,0.00042381548,0.001477789],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.034267083,0.0037914957,0.466051,0.0015103774,0.0009126375,0.0012071535,0.02214314,0.002618126,0.0825057,0.016290188,0.0360631,0.33263993],"study_design_scores_gemma":[0.00080456486,0.0030023088,0.95914793,0.0002232935,0.00023342714,0.001068345,0.005802648,0.002553729,0.005084541,0.0037596228,0.018174294,0.00014541726],"about_ca_topic_score_codex":0.012671677,"about_ca_topic_score_gemma":0.015353198,"teacher_disagreement_score":0.012671677,"about_ca_system_score_codex":0.0011062435,"about_ca_system_score_gemma":0.00090142054,"threshold_uncertainty_score":0.03296691},"labels":[],"label_agreement":null},{"id":"W2052221032","doi":"10.3758/brm.40.3.735","title":"The noisy-bit method for digital displays: Converting a 256 luminance resolution into a continuous resolution","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Luminance; Computer science; Computer vision; Artificial intelligence; Pixel; Contrast (vision); Dither; Noise (video); Psychophysics; Display device; Flicker; Computer graphics (images); Image (mathematics); Noise shaping; Perception","score_opus":0.3448104394742743,"score_gpt":0.5649020745438365,"score_spread":0.22009163506956214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052221032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021576876,0.0006621084,0.97174203,0.00029083763,0.00020206555,0.0001155722,0.00037387837,0.0010315172,0.0040050326],"genre_scores_gemma":[0.10090093,0.000841602,0.8893173,0.00023246539,0.000072953626,0.0003277381,0.0003692098,0.00049528194,0.0074424907],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993231,0.00016932526,0.000041375126,0.000113838745,0.00031123252,0.000041063086],"domain_scores_gemma":[0.99844533,0.00056386436,0.00012358499,0.00052234175,0.0002721717,0.000072679795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010886042,0.0006801867,0.00042269137,0.00082123006,0.00039895746,0.001148808,0.0012162303,0.0009040035,0.007723064],"category_scores_gemma":[0.0061022514,0.0005359509,0.0004876602,0.00089699443,0.0011085586,0.00179168,0.0009577469,0.0013565666,0.0024345326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013719004,0.00023823156,0.00185779,0.0009133465,0.00008874346,0.0002905823,0.0004203363,0.0043661715,0.4818829,0.087936625,0.0065256716,0.41410765],"study_design_scores_gemma":[0.00014565006,0.00071936444,0.0061089937,0.00023910457,0.00019112664,0.0032677513,0.00016326428,0.14088063,0.75239545,0.053264715,0.042396832,0.00022714672],"about_ca_topic_score_codex":0.00040985394,"about_ca_topic_score_gemma":0.00077795476,"teacher_disagreement_score":0.007723064,"about_ca_system_score_codex":0.00043209404,"about_ca_system_score_gemma":0.00046033598,"threshold_uncertainty_score":0.02583623},"labels":[],"label_agreement":null},{"id":"W2052698354","doi":"10.3758/s13428-013-0442-y","title":"A behavioral database for masked form priming","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Priming (agriculture); Lexical decision task; Computer science; Spelling; Vocabulary; Natural language processing; Word recognition; Task (project management); Reading (process); Orthography; Prime (order theory); Cognitive psychology; Psychology; Artificial intelligence; Cognition; Linguistics; Mathematics","score_opus":0.5022630634511727,"score_gpt":0.6631078933795438,"score_spread":0.16084482992837112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052698354","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07052882,0.0018006936,0.41550562,0.00088411366,0.0005211694,0.009670053,0.32205963,0.06930583,0.10972412],"genre_scores_gemma":[0.22530396,0.0018589734,0.42639813,0.0012250752,0.0004186805,0.026107507,0.2593098,0.014471364,0.04490649],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969085,0.00077475945,0.00060189934,0.0006277,0.0009027647,0.0001843948],"domain_scores_gemma":[0.9727394,0.011919211,0.0013127216,0.009835717,0.0033904323,0.0008024433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004699037,0.00096305995,0.0010674772,0.003306559,0.0008816053,0.001522692,0.0017368534,0.0009708701,0.07389394],"category_scores_gemma":[0.026568715,0.00084262626,0.0006933292,0.0028567992,0.00038491795,0.0022097267,0.0015386487,0.0009937359,0.034230806],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005340213,0.0019228791,0.014389528,0.0019076031,0.00015825796,0.00032490326,0.0008542625,0.0016462682,0.059089325,0.020667158,0.16401517,0.7296844],"study_design_scores_gemma":[0.0013641135,0.001968433,0.08340629,0.0007190347,0.0004263481,0.003641782,0.0005897844,0.025606215,0.13389865,0.05586275,0.69197494,0.00054167566],"about_ca_topic_score_codex":0.0026614505,"about_ca_topic_score_gemma":0.0028234825,"teacher_disagreement_score":0.07389394,"about_ca_system_score_codex":0.0009181922,"about_ca_system_score_gemma":0.0020935177,"threshold_uncertainty_score":0.24719983},"labels":[],"label_agreement":null},{"id":"W2054762775","doi":"10.3758/s13428-012-0201-5","title":"Examining the convergent validity of shared mental model measures","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Team Dynamics and Performance","field":"Psychology","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Convergent validity; Mental model; Psychology; Computer science; Cognitive psychology; Psychometrics; Developmental psychology; Cognitive science; Internal consistency","score_opus":0.7335922008773689,"score_gpt":0.6234797288686424,"score_spread":0.11011247200872643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054762775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783019,0.0004281653,0.011346464,0.00036687593,0.00016802218,0.00039996477,0.00032938964,0.00004988068,0.00860931],"genre_scores_gemma":[0.9913975,0.00015003067,0.006599918,0.00009247274,0.00004985011,0.0006651805,0.00048346785,0.000040098268,0.000521381],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96532005,0.01760348,0.0031437203,0.0035814985,0.009437887,0.00091340754],"domain_scores_gemma":[0.69950837,0.21515177,0.019637212,0.026133072,0.0364945,0.0030751007],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041832842,0.0009819336,0.0010281409,0.004500917,0.00205049,0.0037471077,0.002011005,0.0017726278,0.002767867],"category_scores_gemma":[0.20689918,0.0009826523,0.0022409663,0.0025777195,0.0025498364,0.0038103634,0.005927413,0.0024277824,0.00058640505],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000954941,0.0010258782,0.8933274,0.00037169736,0.0018913154,0.0001250421,0.014817742,0.0017310361,0.0025615622,0.011321144,0.0009005732,0.07097156],"study_design_scores_gemma":[0.0005123628,0.002173352,0.92916524,0.00060242834,0.0012937881,0.0005456706,0.01437957,0.024100324,0.004524077,0.018898966,0.0036220858,0.00018210498],"about_ca_topic_score_codex":0.0026636538,"about_ca_topic_score_gemma":0.005261658,"teacher_disagreement_score":0.95816714,"about_ca_system_score_codex":0.0021322232,"about_ca_system_score_gemma":0.0026582843,"threshold_uncertainty_score":0.22123587},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.46569732647646395,"score_gpt":0.6720252201736696,"score_spread":0.20632789369720567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055350558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19680808,0.017577443,0.73321056,0.0013864012,0.0023606634,0.01210087,0.005909493,0.0039046756,0.026741782],"genre_scores_gemma":[0.3953149,0.0045937346,0.5665694,0.0006975733,0.00024988758,0.017157538,0.0036970458,0.0022361274,0.009483808],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.8821374,0.09381374,0.006066774,0.0049800896,0.012278944,0.00072309555],"domain_scores_gemma":[0.6069658,0.3241727,0.008348016,0.017948214,0.040914893,0.0016504066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09724731,0.0014550525,0.0020400982,0.0063079204,0.0016487435,0.0027109382,0.0036599995,0.0015874766,0.029513316],"category_scores_gemma":[0.3149134,0.0012433153,0.0023184777,0.0049811658,0.0013924105,0.0055936584,0.0038148218,0.0019603989,0.0027115676],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.035396464,0.0012811068,0.038922217,0.007220187,0.0063184067,0.00017558322,0.0047593764,0.0030853203,0.0031080528,0.019371921,0.015826266,0.864535],"study_design_scores_gemma":[0.030640112,0.045913406,0.34343508,0.013787509,0.0146252075,0.003523564,0.016419958,0.19934106,0.027111074,0.14594701,0.157709,0.0015470849],"about_ca_topic_score_codex":0.0033140415,"about_ca_topic_score_gemma":0.006976324,"teacher_disagreement_score":0.09724731,"about_ca_system_score_codex":0.0019877013,"about_ca_system_score_gemma":0.0043736007,"threshold_uncertainty_score":0.51429904},"labels":[],"label_agreement":null},{"id":"W2055627930","doi":"10.3758/s13428-012-0253-6","title":"Recoding and representation in artificial grammar learning","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Encoding (memory); Natural language processing; Representation (politics); Artificial intelligence; Task (project management); Episodic memory; Grammar; Memory model; External Data Representation; Semantic memory; Machine learning; Cognition; Psychology; Linguistics; Shared memory","score_opus":0.5400207676779264,"score_gpt":0.6517631461762786,"score_spread":0.11174237849835222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055627930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41076398,0.00039228797,0.57467526,0.00081548525,0.000096114316,0.00007123657,0.00012907473,0.00071937806,0.012337208],"genre_scores_gemma":[0.84535885,0.0001559639,0.14908695,0.00010912902,0.000023605913,0.000095418414,0.00017457087,0.00025089728,0.0047446475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976108,0.0014424961,0.00012778728,0.00044787902,0.00026368248,0.00010731048],"domain_scores_gemma":[0.98896956,0.007347582,0.00063619955,0.0021833153,0.0006541013,0.00020932728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022179836,0.00029473956,0.00046645734,0.0006695396,0.00030319332,0.002887617,0.0014005969,0.0012749267,0.0035720125],"category_scores_gemma":[0.02100879,0.00051148795,0.00047376196,0.0006498784,0.0027293751,0.005436823,0.0015378754,0.0014879481,0.0004523639],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040276026,0.00032361384,0.009163333,0.0003391788,0.00009406704,0.00031451532,0.004776645,0.038275324,0.034220498,0.54826254,0.0011688013,0.3626588],"study_design_scores_gemma":[0.00006210845,0.00023054422,0.004587456,0.00007945519,0.00006335862,0.00059957115,0.0013247877,0.28961056,0.021445004,0.6763319,0.005579969,0.0000852238],"about_ca_topic_score_codex":0.0010862361,"about_ca_topic_score_gemma":0.00080611627,"teacher_disagreement_score":0.0035720125,"about_ca_system_score_codex":0.0006708161,"about_ca_system_score_gemma":0.0007261784,"threshold_uncertainty_score":0.011949599},"labels":[],"label_agreement":null},{"id":"W2056379117","doi":"10.3758/s13428-015-0564-5","title":"Assessing perceptual change with an ambiguous figures task: Normative data for 40 standard picture sets","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Perception; Normative; Ambiguity; Morphing; Computer science; Cognitive psychology; Object (grammar); Psychology; Artificial intelligence","score_opus":0.8104658419495807,"score_gpt":0.6598050748479091,"score_spread":0.15066076710167164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056379117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9915292,0.00013973682,0.0027393776,0.000018182054,0.000014455493,0.00028217223,0.0014690313,0.00009145873,0.0037163764],"genre_scores_gemma":[0.99247205,0.00011671815,0.002891088,0.00004128748,0.000008977791,0.00037745878,0.002735998,0.00009979292,0.0012567377],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975684,0.00034151514,0.0003926072,0.00048005104,0.0011133578,0.00010413598],"domain_scores_gemma":[0.9865682,0.00541343,0.001032238,0.0035428798,0.0029682661,0.00047488543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763372,0.0006872519,0.00040741774,0.0018622935,0.0005552129,0.0006090237,0.00083983515,0.00089062424,0.0039858217],"category_scores_gemma":[0.01929779,0.0003283929,0.00043834595,0.00059105846,0.0010911552,0.00087475684,0.0008934256,0.00066947006,0.0012914194],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012566769,0.012685425,0.53461236,0.0011456847,0.00077115506,0.003330202,0.009650942,0.0066993176,0.23304547,0.0022004566,0.0076560173,0.17563625],"study_design_scores_gemma":[0.00016807119,0.0028878022,0.951262,0.000059707145,0.00013113285,0.0037826244,0.0008430791,0.002845966,0.03293475,0.0011812774,0.0038378614,0.00006572253],"about_ca_topic_score_codex":0.0031265854,"about_ca_topic_score_gemma":0.004523918,"teacher_disagreement_score":0.0039858217,"about_ca_system_score_codex":0.00044717113,"about_ca_system_score_gemma":0.0002588804,"threshold_uncertainty_score":0.014614284},"labels":[],"label_agreement":null},{"id":"W2058117779","doi":"10.3758/bf03192965","title":"Comparing derived and acquired acceleration profiles: 3-D optical electronic data analyses","year":2007,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Acceleration; Trajectory; Accelerometer; Position (finance); Computer science; Root mean square; Mean squared error; Movement (music); Geodesy; Simulation; Mathematics; Statistics; Acoustics; Physics; Geology","score_opus":0.7508497431548431,"score_gpt":0.6347631879419575,"score_spread":0.11608655521288558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058117779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32691836,0.00018152759,0.6633703,0.00014833294,0.00012084838,0.00039323122,0.0017488323,0.0023802645,0.004738312],"genre_scores_gemma":[0.71062464,0.00022412212,0.2849384,0.000077489036,0.000026029966,0.0002560102,0.00094507664,0.00047365006,0.002434648],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99948704,0.00007231333,0.00005027586,0.000109855304,0.000217133,0.00006339936],"domain_scores_gemma":[0.9989427,0.00029972548,0.0001254844,0.00014113044,0.00045327516,0.000037791073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007446053,0.00050147274,0.0003412669,0.001806877,0.00035779207,0.0009442124,0.0004344648,0.0005050506,0.0034908112],"category_scores_gemma":[0.0028674612,0.00029183656,0.0003140482,0.0014352998,0.00030464408,0.0006487728,0.0005657799,0.00037292464,0.00066828565],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011132654,0.0003397788,0.028615352,0.0005463151,0.00017879557,0.0003646668,0.0010593187,0.011178285,0.39601505,0.002490406,0.0028375224,0.55526125],"study_design_scores_gemma":[0.00013081868,0.000598941,0.31840184,0.0001410056,0.00025469426,0.0018950047,0.0012114072,0.22264731,0.43674344,0.0034947265,0.014244703,0.00023603997],"about_ca_topic_score_codex":0.0029109104,"about_ca_topic_score_gemma":0.006412088,"teacher_disagreement_score":0.0034908112,"about_ca_system_score_codex":0.0003223529,"about_ca_system_score_gemma":0.0007703537,"threshold_uncertainty_score":0.011677921},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Psychology; Mathematics education","score_opus":0.4997630286426059,"score_gpt":0.6502886072233989,"score_spread":0.15052557858079296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058821124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774595,0.00010178538,0.016427696,0.00011862672,0.00010737501,0.0014931527,0.00012920711,0.00016459466,0.003998203],"genre_scores_gemma":[0.9160045,0.0002787626,0.06417558,0.00028752867,0.00014035858,0.009024268,0.00032532378,0.00017563875,0.009588078],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99232376,0.0049165855,0.0005784365,0.0008984111,0.0009852457,0.00029752805],"domain_scores_gemma":[0.92759293,0.058926377,0.003091718,0.004608953,0.0032232958,0.0025565838],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010232957,0.0008713976,0.00092375826,0.00078157237,0.00067679357,0.0015621389,0.0014759648,0.0013738275,0.005161557],"category_scores_gemma":[0.04148995,0.00045954372,0.00038013505,0.0005892377,0.0006786809,0.0019007662,0.0014290906,0.0014175936,0.00095786876],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08310872,0.3315613,0.03326537,0.0012698284,0.0005819889,0.00012801924,0.011556043,0.0066565187,0.08541422,0.004448626,0.0020404477,0.43996888],"study_design_scores_gemma":[0.06061847,0.42636013,0.21453479,0.0006427774,0.001972226,0.00053781306,0.008521731,0.10775663,0.13606834,0.020751609,0.021555342,0.000680124],"about_ca_topic_score_codex":0.0010513108,"about_ca_topic_score_gemma":0.0010332911,"teacher_disagreement_score":0.989767,"about_ca_system_score_codex":0.0006937185,"about_ca_system_score_gemma":0.001441833,"threshold_uncertainty_score":0.05411768},"labels":[],"label_agreement":null},{"id":"W2062564842","doi":"10.3758/s13428-012-0283-0","title":"Norms for grip agreement for 296 photographs of objects","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Affordance; Object (grammar); Set (abstract data type); Cognition; Computer science; Artificial intelligence; Psychology; Cognitive psychology","score_opus":0.5991373342195433,"score_gpt":0.6734610464504677,"score_spread":0.07432371223092438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062564842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.948909,0.0002870971,0.021071544,0.00008498844,0.000097378696,0.00045741067,0.0014807151,0.00027339507,0.027338428],"genre_scores_gemma":[0.98670965,0.00005138987,0.009646902,0.00003070757,0.000019920099,0.00053538213,0.0011520264,0.00013939789,0.0017146351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97331595,0.009496218,0.0032303338,0.003655888,0.009373319,0.0009282534],"domain_scores_gemma":[0.77830106,0.13694414,0.018752456,0.027961632,0.035615787,0.0024249505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024298312,0.00046085537,0.0006065785,0.0036920458,0.0010151786,0.0019109714,0.0009970741,0.0010202597,0.0060063708],"category_scores_gemma":[0.16603582,0.00048292335,0.00091269024,0.0012483109,0.0021307536,0.0014991082,0.0024872313,0.0010682243,0.0014390779],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046924357,0.0007334564,0.82880473,0.0006503975,0.0015472866,0.00033136772,0.02005221,0.0023440865,0.028718363,0.015419274,0.004745026,0.091961354],"study_design_scores_gemma":[0.00006418421,0.0005908893,0.9735206,0.00011155964,0.00016325506,0.0006213788,0.0036362852,0.0045172716,0.007840298,0.0056074937,0.0032078049,0.00011894697],"about_ca_topic_score_codex":0.0023362404,"about_ca_topic_score_gemma":0.0052993204,"teacher_disagreement_score":0.024298312,"about_ca_system_score_codex":0.001099796,"about_ca_system_score_gemma":0.00041919987,"threshold_uncertainty_score":0.12850326},"labels":[],"label_agreement":null},{"id":"W2064017523","doi":"10.3758/s13428-012-0266-1","title":"A methodological note on evaluating performance in a sustained-attention-to-response task","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Response time; Stimulus (psychology); Computer science; Task (project management); Cognitive psychology; Response inhibition; Psychology; Audiology; Cognition; Neuroscience; Medicine","score_opus":0.8800142472997852,"score_gpt":0.7255989051982621,"score_spread":0.15441534210152308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064017523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057159472,0.00330469,0.9126753,0.0065139728,0.0031604248,0.0033916256,0.00058786216,0.0005410594,0.012665561],"genre_scores_gemma":[0.2044042,0.0027389205,0.75955576,0.0065632774,0.0017573506,0.011617185,0.00063699787,0.00055902515,0.012167305],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9646204,0.016025592,0.0064632897,0.0030153382,0.00934114,0.00053417246],"domain_scores_gemma":[0.9364285,0.035397187,0.0050867544,0.012499394,0.009566707,0.0010214747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048638806,0.0011998707,0.0012307938,0.0010715205,0.001746989,0.0027991468,0.005009633,0.003467084,0.0017165877],"category_scores_gemma":[0.10100575,0.00094064575,0.001062401,0.0009338537,0.0035220173,0.0017598438,0.0021224925,0.0048103235,0.0009706749],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036691134,0.0015148689,0.03768943,0.0030862505,0.0007542064,0.0011047677,0.0023469082,0.0016279488,0.6445065,0.057062447,0.0070838467,0.23955375],"study_design_scores_gemma":[0.0012660302,0.0133778965,0.29609692,0.001914243,0.0023788312,0.011731059,0.0018477101,0.019449959,0.465929,0.08623067,0.09916322,0.0006145167],"about_ca_topic_score_codex":0.0026580177,"about_ca_topic_score_gemma":0.007013924,"teacher_disagreement_score":0.048638806,"about_ca_system_score_codex":0.0009159933,"about_ca_system_score_gemma":0.0028726263,"threshold_uncertainty_score":0.2572297},"labels":[],"label_agreement":null},{"id":"W2064232423","doi":"10.3758/bf03192703","title":"Generating complex three-dimensional stimuli (Greebles) for haptic expertise training","year":2005,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; James S. McDonnell Foundation; National Science Foundation","keywords":"Haptic technology; Computer science; Set (abstract data type); Perception; Object (grammar); Training (meteorology); Artificial intelligence; Human–computer interaction; Psychology","score_opus":0.7364569336206933,"score_gpt":0.6112126661609603,"score_spread":0.12524426745973305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064232423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45852494,0.00019122598,0.5335979,0.00020035227,0.00013836817,0.00054354296,0.00024672982,0.0009822994,0.0055747065],"genre_scores_gemma":[0.7714053,0.00020594534,0.22374408,0.000112291564,0.00002609992,0.00053648,0.00014962365,0.00021036825,0.003609815],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99967206,0.00008799563,0.00001870309,0.00006578317,0.00012397602,0.000031521296],"domain_scores_gemma":[0.99863654,0.00094114296,0.0001048112,0.00015259061,0.00007844571,0.00008651746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082283554,0.00047027363,0.00028783813,0.00030800432,0.0001094709,0.0004228516,0.0006217047,0.0006112573,0.0075138127],"category_scores_gemma":[0.0043688715,0.00020788032,0.00021545355,0.00017982641,0.0003110568,0.0005056158,0.0007888024,0.00043364888,0.0008518411],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001088541,0.00075860263,0.00083596277,0.000427766,0.000026388165,0.00013108883,0.00032065797,0.023337299,0.7836958,0.005691734,0.00094888196,0.1827373],"study_design_scores_gemma":[0.000787734,0.0061576534,0.021648956,0.00022686204,0.00012277615,0.001036199,0.00033767358,0.34772417,0.592101,0.016273422,0.01337799,0.00020569962],"about_ca_topic_score_codex":0.00025069297,"about_ca_topic_score_gemma":0.0003861374,"teacher_disagreement_score":0.0075138127,"about_ca_system_score_codex":0.00015189739,"about_ca_system_score_gemma":0.00025929566,"threshold_uncertainty_score":0.025136232},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4066462785331903,"score_gpt":0.6576008177856255,"score_spread":0.2509545392524352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067456760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57754916,0.0034477955,0.4054782,0.00019967683,0.0003296544,0.001715873,0.0021720445,0.0015700137,0.0075375033],"genre_scores_gemma":[0.5512817,0.0016001427,0.43645447,0.00034109395,0.00018224338,0.0036014405,0.00056613376,0.00032249378,0.0056502805],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964504,0.0011760109,0.00022357612,0.0009972246,0.0009836253,0.00016909858],"domain_scores_gemma":[0.9892545,0.0078106113,0.0007188709,0.0008216155,0.0011573697,0.00023699991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002298582,0.0013162675,0.001223767,0.00296236,0.00064037833,0.0015396278,0.0010121313,0.0016673189,0.0028716554],"category_scores_gemma":[0.008497661,0.00081905985,0.00057335396,0.0031619095,0.0005261776,0.0027025137,0.0013517161,0.0012689335,0.0006804892],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022407894,0.0024795216,0.05869007,0.001619554,0.0006214845,0.00034707828,0.002938609,0.0024196962,0.44815347,0.0012944464,0.0016508889,0.4775444],"study_design_scores_gemma":[0.0018569079,0.008092754,0.60246676,0.0006249219,0.002024219,0.0044130757,0.0038007807,0.079015665,0.2783303,0.007912666,0.010685792,0.00077619846],"about_ca_topic_score_codex":0.0037616557,"about_ca_topic_score_gemma":0.010893857,"teacher_disagreement_score":0.0037616557,"about_ca_system_score_codex":0.0004546205,"about_ca_system_score_gemma":0.0011796847,"threshold_uncertainty_score":0.0121561885},"labels":[],"label_agreement":null},{"id":"W2067667602","doi":"10.3758/bf03192772","title":"NUANCE 3.0: Using genetic programming to model variable relationships","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"Government of Canada","keywords":"Computer science; Genetic programming; Set (abstract data type); Artificial intelligence; Machine learning; Human–computer interaction; Cognitive science; Programming language; Psychology","score_opus":0.37795273108280475,"score_gpt":0.5393659313395897,"score_spread":0.1614132002567849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067667602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016893538,0.00011871683,0.9766798,0.0001483911,0.000046489207,0.000092809954,0.0002915329,0.0022122653,0.0035164524],"genre_scores_gemma":[0.12011864,0.00018819666,0.8751826,0.00012035928,0.000020428739,0.00044685727,0.00032764758,0.00049741287,0.0030979083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966276,0.00016224175,0.000014924197,0.00006523379,0.00006838574,0.000026499589],"domain_scores_gemma":[0.9990853,0.0006630489,0.00007609181,0.00006770696,0.00007987575,0.000027895452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013771325,0.00085697253,0.0007324468,0.00077133544,0.00051135925,0.0010594674,0.0020919184,0.0012441629,0.0044010323],"category_scores_gemma":[0.0047557233,0.00058626255,0.0010222602,0.00065916777,0.00061402906,0.0009151315,0.0012039366,0.0015743079,0.0006203543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006464278,0.00007331417,0.0017571213,0.00010435121,0.000107508946,0.00008416468,0.0001671033,0.90536463,0.0013284321,0.04028573,0.0018705655,0.048792474],"study_design_scores_gemma":[0.000016333064,0.000016410162,0.000117783246,0.0000120825425,0.000017048365,0.000020903439,0.000009221477,0.984577,0.0004216629,0.012891182,0.0018932914,0.0000070958586],"about_ca_topic_score_codex":0.007554899,"about_ca_topic_score_gemma":0.009515683,"teacher_disagreement_score":0.007554899,"about_ca_system_score_codex":0.0006230616,"about_ca_system_score_gemma":0.0011419844,"threshold_uncertainty_score":0.015021801},"labels":[],"label_agreement":null},{"id":"W2070372221","doi":"10.3758/s13428-014-0524-5","title":"Response latencies are alive and well for identifying fakers on a self-report personality inventory: A reconsideration of van Hooft and Born (2012)","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Congruence (geometry); Correctness; Personality; Psychology; Personality theory; Personality Assessment Inventory; Test (biology); Personality test; Social psychology; Psychometrics; Computer science; Test validity; Developmental psychology; Algorithm","score_opus":0.41778008388408583,"score_gpt":0.5838089755094042,"score_spread":0.16602889162531842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070372221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6367785,0.008899542,0.26208928,0.02333456,0.007874315,0.0007640243,0.0042012245,0.0009240755,0.055134557],"genre_scores_gemma":[0.9209277,0.0017207547,0.06175402,0.0046191323,0.0011300407,0.00047701856,0.00074920844,0.00029765067,0.008324387],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9865942,0.005326698,0.0013835464,0.0021163472,0.004072947,0.0005061268],"domain_scores_gemma":[0.8445109,0.09245512,0.021433277,0.025178928,0.014765019,0.001656743],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.023081264,0.0008375356,0.0012479246,0.0020614855,0.0010752621,0.003378309,0.0021084393,0.0025651595,0.0025079658],"category_scores_gemma":[0.11502232,0.0005503637,0.0010260923,0.0012686108,0.0019075496,0.007152758,0.0020041028,0.003672031,0.0017977477],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012720212,0.0005084272,0.64638144,0.0007655367,0.00054117077,0.00049177336,0.0041148807,0.0006187034,0.012324615,0.014856456,0.011559233,0.30656576],"study_design_scores_gemma":[0.00006244782,0.0022052035,0.8702006,0.0011917256,0.0007498743,0.003557221,0.004995733,0.0077869846,0.020191034,0.053113077,0.035603847,0.00034230153],"about_ca_topic_score_codex":0.0012053956,"about_ca_topic_score_gemma":0.0029799344,"teacher_disagreement_score":0.99743485,"about_ca_system_score_codex":0.0004148898,"about_ca_system_score_gemma":0.0008872861,"threshold_uncertainty_score":0.122066796},"labels":[],"label_agreement":null},{"id":"W2073248762","doi":"10.3758/brm.41.4.1210","title":"Grounding co-occurrence: Identifying features in a lexical co-occurrence model of semantic memory","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Computer science; Co-occurrence; Feature vector; Word (group theory); Natural language processing; Artificial intelligence; Feature (linguistics); Semantics (computer science); Distributional semantics; Memory model; Vector space model; Space (punctuation); Semantic network; Vector space; Artificial neural network; Semantic similarity; Linguistics; Mathematics; Programming language","score_opus":0.46308618363239945,"score_gpt":0.6144912133150822,"score_spread":0.1514050296826827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073248762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4284495,0.00018031274,0.5666202,0.0004993511,0.000041935466,0.00004073772,0.00018497538,0.0002413171,0.0037417384],"genre_scores_gemma":[0.9804689,0.000066584784,0.018306505,0.00002675901,0.000026618742,0.000033941982,0.00010634527,0.000033736418,0.0009305032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995433,0.00013284775,0.00003122619,0.00013992994,0.00007040824,0.00008225233],"domain_scores_gemma":[0.99507153,0.002886557,0.0006055367,0.00085274526,0.000312019,0.00027164916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015623895,0.00039645517,0.0007986679,0.0012428612,0.0005927992,0.0021882474,0.0018969931,0.0011148402,0.00299294],"category_scores_gemma":[0.008469284,0.00040234235,0.0010091686,0.0013071414,0.0016507423,0.005541423,0.0011357556,0.0010697305,0.00033433214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017288303,0.00069415354,0.04562369,0.00023391974,0.00037218895,0.0012074723,0.001524816,0.16903959,0.027363263,0.59104604,0.0018838412,0.15928216],"study_design_scores_gemma":[0.000026478583,0.00007997197,0.004339358,0.000010918541,0.0000524508,0.00022283927,0.00008830092,0.67810595,0.0013630248,0.31541216,0.00027964733,0.000018876239],"about_ca_topic_score_codex":0.002632489,"about_ca_topic_score_gemma":0.0024111795,"teacher_disagreement_score":0.00299294,"about_ca_system_score_codex":0.0005819263,"about_ca_system_score_gemma":0.0007238287,"threshold_uncertainty_score":0.010012329},"labels":[],"label_agreement":null},{"id":"W2074008056","doi":"10.3758/s13428-010-0053-9","title":"Examining workgroup diversity effects: does playing by the (group-retention) rules help or hinder?","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gender Diversity and Inequality","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Guelph","funders":"","keywords":"Workgroup; Diversity (politics); Group (periodic table); Outcome (game theory); Psychology; Social psychology; Retention rate; Computer science; Statistics; Mathematics; Computer security; Political science","score_opus":0.7036334484509716,"score_gpt":0.5292031031139763,"score_spread":0.1744303453369953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074008056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99594563,0.000102631246,0.0009293175,0.00019988908,0.000010333556,0.000038406346,0.000024904832,0.0000051310676,0.0027437322],"genre_scores_gemma":[0.9981711,0.000048508075,0.0012306533,0.000064116575,0.000013297285,0.000075501615,0.00002311675,0.000005028415,0.00036867944],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944806,0.0038299852,0.00011838547,0.0005609218,0.0005832585,0.00042682447],"domain_scores_gemma":[0.93075055,0.054572087,0.009198455,0.0029540325,0.0007615862,0.0017633211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012801734,0.0004612274,0.00069831585,0.00075103866,0.0015364672,0.0019370939,0.0012401509,0.0010877236,0.0044645974],"category_scores_gemma":[0.056300864,0.00044837393,0.00045251878,0.00068242615,0.002426127,0.0026491461,0.00204627,0.0016857481,0.0002217893],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024645317,0.0059344736,0.8690347,0.0003318897,0.0006819488,0.00014010153,0.021046773,0.00072025333,0.005921617,0.0062952354,0.00061515236,0.08681329],"study_design_scores_gemma":[0.00020366386,0.0017269577,0.9743946,0.00015601904,0.0005024837,0.00006904037,0.012978069,0.0019036406,0.0027487976,0.0042718328,0.0010133185,0.0000315443],"about_ca_topic_score_codex":0.0038633232,"about_ca_topic_score_gemma":0.008151655,"teacher_disagreement_score":0.012801734,"about_ca_system_score_codex":0.00052419346,"about_ca_system_score_gemma":0.0010571148,"threshold_uncertainty_score":0.06770289},"labels":[],"label_agreement":null},{"id":"W2074995870","doi":"10.3758/s13428-012-0294-x","title":"Capturing and evaluating blinks from video-based eyetrackers","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Simon Fraser University","funders":"","keywords":"Computer science; Sensitivity (control systems); Computer vision; Artificial intelligence; Pupil; Workload; Contrast (vision); Plot (graphics); Psychology; Mathematics; Statistics","score_opus":0.4686376173035349,"score_gpt":0.6115095745346915,"score_spread":0.14287195723115653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074995870","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90165097,0.0014716996,0.09012025,0.00008461909,0.00007496149,0.0004891928,0.0021368368,0.0009534226,0.0030180616],"genre_scores_gemma":[0.8968323,0.0014410008,0.09577922,0.00014781381,0.00007356449,0.00039726324,0.0015269631,0.00014176994,0.0036601326],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99949324,0.00009969303,0.000042496158,0.00015542611,0.00014932892,0.00005983656],"domain_scores_gemma":[0.99779797,0.000814448,0.00031153345,0.00009767402,0.00085681304,0.000121643796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048137136,0.00056968466,0.00044315675,0.0019963556,0.0003292001,0.0006911113,0.00036093363,0.000787827,0.0014347313],"category_scores_gemma":[0.002687419,0.00023452009,0.00027075084,0.0011270092,0.00014712168,0.0007596741,0.00041534466,0.0002932607,0.000683261],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016579467,0.00036102402,0.051907245,0.0013024902,0.00025829277,0.00033644354,0.0014224596,0.0012118109,0.7054165,0.00018649305,0.0015402017,0.23439899],"study_design_scores_gemma":[0.00027072185,0.002519183,0.68446934,0.00030964028,0.0006144035,0.0021504737,0.0023372932,0.03991425,0.2615032,0.00065326365,0.0051253964,0.0001328163],"about_ca_topic_score_codex":0.00393425,"about_ca_topic_score_gemma":0.008085962,"teacher_disagreement_score":0.00393425,"about_ca_system_score_codex":0.00029834363,"about_ca_system_score_gemma":0.00038292838,"threshold_uncertainty_score":0.007822752},"labels":[],"label_agreement":null},{"id":"W2077834585","doi":"10.3758/brm.40.4.961","title":"Random without replacement is not random: Caveat emptor","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; UC Berkeley College of Chemistry","keywords":"Caveat emptor; Computer science; Selection (genetic algorithm); Simple random sample; Artificial intelligence; Medicine","score_opus":0.7589440560245428,"score_gpt":0.6292991638743772,"score_spread":0.1296448921501656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077834585","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01738975,0.0070445924,0.86594874,0.055311136,0.02079471,0.0067338343,0.0043067634,0.0022483799,0.020222148],"genre_scores_gemma":[0.3670068,0.00318106,0.5134708,0.048415232,0.010956701,0.018012118,0.0009800994,0.0008164536,0.037160624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7417577,0.17990986,0.017006565,0.031838145,0.025101556,0.004386197],"domain_scores_gemma":[0.4348003,0.40032226,0.014188911,0.13487433,0.013561752,0.0022524893],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2708184,0.0047685397,0.012203746,0.0040223673,0.004758997,0.004803145,0.018173974,0.013559241,0.03678542],"category_scores_gemma":[0.5905927,0.0038274024,0.009517931,0.006528197,0.0154423565,0.014252533,0.0068121986,0.022996854,0.007349579],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006148285,0.0010272734,0.01760943,0.004659971,0.009278266,0.004644868,0.006111585,0.008611107,0.0010430705,0.69684595,0.12375189,0.12026832],"study_design_scores_gemma":[0.005211511,0.0006781775,0.007741313,0.0015360513,0.0032718256,0.0029691039,0.0010055942,0.04514937,0.0015127043,0.8834638,0.047054265,0.0004063696],"about_ca_topic_score_codex":0.011786627,"about_ca_topic_score_gemma":0.013284034,"teacher_disagreement_score":0.7291816,"about_ca_system_score_codex":0.003515103,"about_ca_system_score_gemma":0.0072856797,"threshold_uncertainty_score":0.8992107},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1772768251816343,"score_gpt":0.5544826933288824,"score_spread":0.37720586814724816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078894097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6133311,0.0003359562,0.33612767,0.00041575453,0.00012099111,0.00030711415,0.0045233076,0.0011677463,0.043670405],"genre_scores_gemma":[0.92351854,0.000067516965,0.07148205,0.00003922786,0.000042289656,0.00038147357,0.003076779,0.00025657177,0.0011356102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9959953,0.0009823943,0.00052652723,0.0007501225,0.00158701,0.00015864432],"domain_scores_gemma":[0.9695812,0.020392962,0.0015854021,0.0031684763,0.004801111,0.0004708186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044972245,0.00037711806,0.00034924343,0.0013987068,0.0005301875,0.0021633913,0.00075664546,0.0005862678,0.00391911],"category_scores_gemma":[0.030072201,0.00025994368,0.00063507265,0.0005636157,0.0013744497,0.0031034062,0.0012792118,0.00091759715,0.0004501514],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015361246,0.00057706726,0.06118591,0.000733466,0.00019454496,0.0009306757,0.01031891,0.007608554,0.05557561,0.5385011,0.007772257,0.3150659],"study_design_scores_gemma":[0.00020575231,0.00049877824,0.11317153,0.0002572993,0.00019640532,0.003034799,0.004811578,0.097514056,0.041848328,0.7123582,0.025897741,0.0002054823],"about_ca_topic_score_codex":0.00082350895,"about_ca_topic_score_gemma":0.000949683,"teacher_disagreement_score":0.0044972245,"about_ca_system_score_codex":0.0007453681,"about_ca_system_score_gemma":0.00047238747,"threshold_uncertainty_score":0.023783922},"labels":[],"label_agreement":null},{"id":"W2083062973","doi":"10.3758/bf03193037","title":"Assessment of adolescent body perception: Development and characterization of a novel tool for morphing images of adolescent bodies","year":2007,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Eating Disorders and Behaviors","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Body shape; Morphing; Perception; Computer science; Body surface; Artificial intelligence; Computer vision; Psychology; Mathematics","score_opus":0.23983690130810192,"score_gpt":0.5712538266076664,"score_spread":0.3314169252995645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083062973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67106,0.00125427,0.3189594,0.00027572253,0.00014739718,0.0020681014,0.0011039097,0.00071251235,0.004418651],"genre_scores_gemma":[0.6404165,0.0012678497,0.35314423,0.00018692743,0.00005341029,0.0019186767,0.00051074737,0.0002060764,0.0022955178],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993212,0.00020664986,0.000062399726,0.0001234418,0.00023307303,0.000053288175],"domain_scores_gemma":[0.9979942,0.0007937444,0.00034904838,0.00016798393,0.0005514919,0.00014353445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00130887,0.0004214795,0.00037703052,0.0015600096,0.00022337059,0.0005248877,0.0006010019,0.0006383069,0.0018315301],"category_scores_gemma":[0.004485573,0.00034689542,0.00038796902,0.0005693315,0.00028649386,0.00095856935,0.00077550445,0.0006986943,0.00028045793],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001076586,0.00084547914,0.09354354,0.0007703764,0.00011572425,0.00026770428,0.0011061816,0.00086289505,0.5448581,0.0009802203,0.0015194732,0.3540537],"study_design_scores_gemma":[0.00019105744,0.0033745342,0.69839114,0.00021682229,0.00038278216,0.005161149,0.0015454555,0.032449555,0.25024688,0.001099768,0.0067278743,0.00021296949],"about_ca_topic_score_codex":0.0008491664,"about_ca_topic_score_gemma":0.002233443,"teacher_disagreement_score":0.0018315301,"about_ca_system_score_codex":0.00018851557,"about_ca_system_score_gemma":0.00041995625,"threshold_uncertainty_score":0.006922066},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3236072011575465,"score_gpt":0.6104451046833086,"score_spread":0.2868379035257621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084990311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27330053,0.004587307,0.7065342,0.00061091076,0.00037291483,0.0013805925,0.0034550875,0.0037542928,0.006004128],"genre_scores_gemma":[0.29728937,0.0061204797,0.67743284,0.00045227824,0.00016806625,0.0042915116,0.0030095547,0.0013117605,0.009924151],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99544334,0.0007130178,0.0004563066,0.00078250264,0.0022736453,0.00033116786],"domain_scores_gemma":[0.99115855,0.003181918,0.0016497611,0.0010149345,0.0025010342,0.0004937573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004779532,0.0015988704,0.0012490056,0.004818756,0.0008788296,0.0010179499,0.0020335973,0.001356157,0.0021074584],"category_scores_gemma":[0.0061615678,0.0010289806,0.0014186633,0.0013983054,0.00093742314,0.0012061083,0.0015312749,0.0017133639,0.0007794043],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021185032,0.0006811512,0.025268046,0.0012942544,0.000433638,0.00008256039,0.00045651896,0.0014628835,0.7981322,0.0010286724,0.0012042294,0.1678373],"study_design_scores_gemma":[0.00017906346,0.0021576076,0.14559284,0.00016701344,0.0008948204,0.0011446074,0.00031727814,0.016676454,0.8261146,0.0011021825,0.005228768,0.00042482224],"about_ca_topic_score_codex":0.0032251873,"about_ca_topic_score_gemma":0.007212362,"teacher_disagreement_score":0.004818756,"about_ca_system_score_codex":0.0009745674,"about_ca_system_score_gemma":0.00104021,"threshold_uncertainty_score":0.0252769},"labels":[],"label_agreement":null},{"id":"W2086532769","doi":"10.3758/s13428-015-0561-8","title":"The DalHouses: 100 new photographs of houses with ratings of typicality, familiarity, and degree of similarity to faces","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Degree (music); Similarity (geometry); Psychology; Communication; Cognitive psychology; Artificial intelligence; Pattern recognition (psychology); Computer science; Acoustics; Physics","score_opus":0.7083864237377904,"score_gpt":0.5889348991601996,"score_spread":0.11945152457759078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086532769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931098,0.00017160655,0.0006193073,0.000051775667,0.000045005105,0.00040310354,0.0013973932,0.000049271475,0.004152746],"genre_scores_gemma":[0.9913496,0.00018973602,0.002329337,0.000118983706,0.00001934619,0.00012236161,0.0019906505,0.000032741093,0.0038472072],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997377,0.000054282315,0.000028020995,0.00005173587,0.000090973495,0.000037386613],"domain_scores_gemma":[0.9992084,0.00014727144,0.00009538303,0.00029055678,0.00010546287,0.00015302171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049912813,0.00044688626,0.00047702168,0.0007942424,0.0004911572,0.00049971696,0.00042991972,0.0006128267,0.0058589857],"category_scores_gemma":[0.0016319886,0.00035000604,0.00039194964,0.00044609245,0.00044952426,0.00068201136,0.00093317777,0.00039309674,0.00096437306],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019765252,0.00555546,0.5151692,0.0010182047,0.0014011863,0.0032695872,0.007379862,0.0017777758,0.2908476,0.0009864747,0.022241293,0.13058802],"study_design_scores_gemma":[0.00023442427,0.0014157663,0.9681483,0.000027120926,0.00018232552,0.0025990594,0.002221118,0.001265485,0.01594668,0.0002698624,0.00763295,0.00005699466],"about_ca_topic_score_codex":0.0043812464,"about_ca_topic_score_gemma":0.016936392,"teacher_disagreement_score":0.0058589857,"about_ca_system_score_codex":0.00034520318,"about_ca_system_score_gemma":0.00009659819,"threshold_uncertainty_score":0.019600272},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.34644763393504435,"score_gpt":0.5887497293982573,"score_spread":0.24230209546321296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087093006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99661994,0.000028475235,0.00016192817,0.00001258741,0.000009939672,0.000018169329,0.00013850702,0.000008703866,0.0030016012],"genre_scores_gemma":[0.9924233,0.000072452975,0.0006417393,0.000042335105,0.000010718373,0.000055904944,0.00044540013,0.000038729537,0.006269356],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99961346,0.000053445772,0.0000490475,0.000085153006,0.00014582787,0.000053069976],"domain_scores_gemma":[0.99656206,0.0017906135,0.00070741633,0.0001896072,0.0003871419,0.0003631576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005480212,0.00029701652,0.00033922723,0.0004909973,0.0003183056,0.0008888041,0.0002186849,0.0005815277,0.014501399],"category_scores_gemma":[0.006164442,0.00019853428,0.00026990855,0.0002902638,0.00046827854,0.0009585768,0.00064336206,0.00046831756,0.0014420336],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016821178,0.002274275,0.43403795,0.00053480745,0.00025834164,0.0017468014,0.026604606,0.00045392333,0.45351946,0.0020792226,0.0018673951,0.059802134],"study_design_scores_gemma":[0.00009110308,0.0011932234,0.9854982,0.00001626049,0.000047397447,0.00047549227,0.0034422332,0.000643662,0.0069447774,0.00030201598,0.0013131405,0.000032464326],"about_ca_topic_score_codex":0.0030759152,"about_ca_topic_score_gemma":0.004856348,"teacher_disagreement_score":0.014501399,"about_ca_system_score_codex":0.00028424466,"about_ca_system_score_gemma":0.0001619553,"threshold_uncertainty_score":0.048511982},"labels":[],"label_agreement":null},{"id":"W2088635395","doi":"10.3758/brm.42.4.1087","title":"Visual regulation of manual aiming: A comparison of methods","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Kinematics; Trajectory; Computer science; Physical medicine and rehabilitation; Movement (music); Visual control; Artificial intelligence; Outcome (game theory); Medicine; Mathematics","score_opus":0.4759983818703678,"score_gpt":0.6604666333591513,"score_spread":0.18446825148878354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088635395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35474247,0.0106095355,0.59837645,0.00046781782,0.0008209194,0.0034177473,0.0013678127,0.0020758251,0.028121399],"genre_scores_gemma":[0.68242687,0.0063881218,0.28483683,0.00040113972,0.00027351125,0.008602717,0.0007410007,0.0012119224,0.0151178595],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965442,0.0014666049,0.00029286314,0.0005515423,0.0009897478,0.0001551642],"domain_scores_gemma":[0.9934942,0.003971313,0.00047235042,0.00093353045,0.0009389179,0.00018969024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045378287,0.00078042253,0.0009132587,0.0012819256,0.00032556834,0.0009697408,0.0012338919,0.00054704165,0.0056872335],"category_scores_gemma":[0.013034923,0.00042189856,0.00056165084,0.0005630221,0.0005287714,0.0006779401,0.0007489485,0.00070521835,0.0008878062],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019440131,0.0022694038,0.008992398,0.0023402367,0.0004840831,0.000053710763,0.001834303,0.0021092182,0.12554014,0.0055532935,0.0021969902,0.8291862],"study_design_scores_gemma":[0.009836489,0.020240692,0.49108988,0.0018423025,0.0035784047,0.0028307308,0.002075607,0.085222766,0.30234817,0.026919486,0.05295701,0.001058405],"about_ca_topic_score_codex":0.0018508557,"about_ca_topic_score_gemma":0.0019237092,"teacher_disagreement_score":0.0056872335,"about_ca_system_score_codex":0.0006225443,"about_ca_system_score_gemma":0.0010470903,"threshold_uncertainty_score":0.023998678},"labels":[],"label_agreement":null},{"id":"W2089598428","doi":"10.3758/brm.42.3.733","title":"Self-coded indirect memory associations and","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Coding (social sciences); Psychology; Substance use; Feeling; Social psychology; Cognitive psychology; Developmental psychology; Clinical psychology; Statistics; Mathematics","score_opus":0.23993648627419395,"score_gpt":0.5629900760061969,"score_spread":0.32305358973200293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089598428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97795427,0.00049523806,0.006692262,0.0003196753,0.00020038968,0.0002485162,0.00257296,0.00011046545,0.011406253],"genre_scores_gemma":[0.9863891,0.00017118186,0.0056324066,0.00014325892,0.00008834777,0.00044936626,0.0016387072,0.00006278486,0.005424836],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99437296,0.0023686194,0.00074043084,0.0012191522,0.00090546225,0.00039338786],"domain_scores_gemma":[0.8902292,0.074820034,0.013454756,0.012461309,0.007702759,0.0013318543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008424529,0.00069810165,0.00073809404,0.002289234,0.0011272008,0.00413882,0.0015580188,0.0012673386,0.013315028],"category_scores_gemma":[0.08976931,0.00045488335,0.00092434726,0.0017887683,0.0010272763,0.0030919209,0.002855965,0.0022976801,0.0012432898],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018942715,0.0011034487,0.93721986,0.0002900204,0.00063062855,0.00009108976,0.0018865059,0.0005911621,0.0006212757,0.004238965,0.0014252247,0.05000747],"study_design_scores_gemma":[0.00026535642,0.0016811475,0.9555921,0.00042713794,0.0018529553,0.0011983425,0.0029134473,0.008086776,0.005374759,0.017782718,0.004685099,0.00014009487],"about_ca_topic_score_codex":0.0022900891,"about_ca_topic_score_gemma":0.0044965544,"teacher_disagreement_score":0.013315028,"about_ca_system_score_codex":0.00089268194,"about_ca_system_score_gemma":0.0010712852,"threshold_uncertainty_score":0.044553757},"labels":[],"label_agreement":null},{"id":"W2089800891","doi":"10.3758/s13428-011-0155-z","title":"A test for psychometric function shift","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychometric function; Statistics; Test statistic; Nonparametric statistics; Statistic; Homogeneity (statistics); Contingency table; Mathematics; Psychometrics; Null distribution; Weibull distribution; Statistical hypothesis testing; Psychology","score_opus":0.6640702287473397,"score_gpt":0.5703768996849142,"score_spread":0.09369332906242545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089800891","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79672617,0.00049545267,0.14701284,0.0007290382,0.00066516246,0.0008894862,0.0032842048,0.0018036376,0.048394024],"genre_scores_gemma":[0.97439945,0.00006530936,0.018022414,0.0003590638,0.00008616421,0.0012327797,0.0017417448,0.00030860386,0.003784458],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878225,0.0029878907,0.0013725493,0.002295331,0.0048501287,0.000671722],"domain_scores_gemma":[0.87446666,0.09631515,0.006150819,0.013706909,0.007547861,0.0018125926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014501425,0.0013224946,0.0011846968,0.0037779126,0.000996089,0.0018881721,0.0015041635,0.002284249,0.019283758],"category_scores_gemma":[0.117961586,0.00029401854,0.002210503,0.0019437491,0.002062288,0.0044913557,0.0035742857,0.0020699578,0.004395745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008264266,0.0032594593,0.47062218,0.0007698695,0.0021973967,0.0010396177,0.0028206955,0.006939608,0.032649085,0.030021148,0.01349085,0.42792574],"study_design_scores_gemma":[0.0011458128,0.010977785,0.81697,0.00035849545,0.0008132552,0.0039006667,0.0033573683,0.054669578,0.024405483,0.063330196,0.019686101,0.0003852997],"about_ca_topic_score_codex":0.0007529104,"about_ca_topic_score_gemma":0.0003639322,"teacher_disagreement_score":0.019283758,"about_ca_system_score_codex":0.00075950264,"about_ca_system_score_gemma":0.0011109123,"threshold_uncertainty_score":0.07669175},"labels":[],"label_agreement":null},{"id":"W2090246898","doi":"10.3758/s13428-012-0244-7","title":"Assessing the evidence for response time mixture distributions","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quantile; Multinomial distribution; Statistics; Range (aeronautics); Mathematics; Mixture model; Categorical distribution; Residual; Sample size determination; Econometrics; Computer science; Probability distribution; Inverse-chi-squared distribution; Algorithm; Distribution fitting","score_opus":0.8694633089275018,"score_gpt":0.7394179691682082,"score_spread":0.13004533975929355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090246898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49686348,0.0022240928,0.4799931,0.0027968164,0.0003064079,0.0005695345,0.0010180334,0.000806627,0.015421923],"genre_scores_gemma":[0.9282434,0.00052754977,0.06686169,0.0007009424,0.00026037742,0.0003499303,0.0013627321,0.00040705092,0.0012863989],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93462646,0.038244944,0.005384785,0.011100079,0.00954979,0.0010939541],"domain_scores_gemma":[0.19371177,0.74928576,0.013876309,0.03407668,0.0074134483,0.0016359278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13843821,0.001707088,0.0017069498,0.0039109187,0.0015030032,0.007251705,0.0054629184,0.004938946,0.019934768],"category_scores_gemma":[0.53619283,0.0018924475,0.0032043345,0.00249391,0.006560385,0.011026672,0.0066975225,0.0063759503,0.00252994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020127134,0.001787749,0.46298748,0.0036427774,0.01014684,0.0013542377,0.0060605416,0.02304806,0.043144535,0.1393227,0.0028530806,0.2855249],"study_design_scores_gemma":[0.0015752815,0.0031256115,0.44483635,0.0010331898,0.0055293,0.0067557967,0.0021755402,0.20185296,0.029860979,0.2915389,0.011214828,0.00050124305],"about_ca_topic_score_codex":0.0012434651,"about_ca_topic_score_gemma":0.0008799964,"teacher_disagreement_score":0.13843821,"about_ca_system_score_codex":0.0011708857,"about_ca_system_score_gemma":0.0016312964,"threshold_uncertainty_score":0.73213995},"labels":[],"label_agreement":null},{"id":"W2091525225","doi":"10.3758/bf03192745","title":"NUANCE: Naturalistic University of Alberta Nonlinear Correlation Explorer","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Government of Canada","keywords":"Naturalism; Computer science; Correlation; Nonlinear system; Value (mathematics); Space (punctuation); Java; Selection (genetic algorithm); Artificial intelligence; Machine learning; Mathematics; Programming language; Epistemology; Operating system; Physics","score_opus":0.1288585428441985,"score_gpt":0.46415939054078387,"score_spread":0.33530084769658536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091525225","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55469453,0.0007560924,0.3188064,0.0011976528,0.00023776511,0.0003801614,0.0060461587,0.016942283,0.100938864],"genre_scores_gemma":[0.66914684,0.000236094,0.2954864,0.0001920174,0.000018142508,0.00027211648,0.00279159,0.00088123966,0.030975567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998517,0.000046521895,0.0000033628369,0.00003484249,0.00004123117,0.000022355407],"domain_scores_gemma":[0.9993631,0.0003485266,0.000024557306,0.00008761954,0.000097089454,0.00007905385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005144778,0.00029078618,0.0002879029,0.00041394544,0.0007888524,0.0004900579,0.00087871955,0.0005751772,0.007907344],"category_scores_gemma":[0.0020251512,0.00017665248,0.0002577851,0.00049235806,0.0005592225,0.0005557127,0.00081440085,0.0005632237,0.0008408758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024759131,0.00089044677,0.020554984,0.0008571546,0.00014928947,0.0009300901,0.0019440699,0.30464032,0.04567098,0.13048479,0.113582425,0.3778195],"study_design_scores_gemma":[0.00022850983,0.0002889522,0.007252996,0.000052923064,0.000051508032,0.00043714908,0.00038814952,0.85754156,0.011751713,0.033710092,0.08821698,0.00007941693],"about_ca_topic_score_codex":0.021452306,"about_ca_topic_score_gemma":0.06875789,"teacher_disagreement_score":0.021452306,"about_ca_system_score_codex":0.0006782425,"about_ca_system_score_gemma":0.0011837368,"threshold_uncertainty_score":0.042654872},"labels":[],"label_agreement":null},{"id":"W2092104032","doi":"10.3758/s13428-013-0335-0","title":"Models with discrete latent variables for analysis of categorical data: A framework and a MATLAB MDLV toolbox","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Categorical variable; Toolbox; Latent variable; Computer science; Latent variable model; Data mining; Latent class model; Range (aeronautics); Machine learning; Econometrics; Probabilistic latent semantic analysis; Artificial intelligence; Mathematics","score_opus":0.3903748827202807,"score_gpt":0.5216524745550551,"score_spread":0.13127759183477444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092104032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039640715,0.000040598014,0.9985012,0.00009642877,0.000010213179,0.000025208094,0.00017179095,0.0004996537,0.0002585734],"genre_scores_gemma":[0.027096767,0.00021131498,0.96835226,0.00011443834,0.00004120472,0.0008141051,0.00054687815,0.00031368027,0.0025093714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973514,0.0018566863,0.00013250182,0.0003053065,0.0002772175,0.00007686226],"domain_scores_gemma":[0.99131036,0.0071468977,0.00031418563,0.0006894614,0.0004092551,0.00012981532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006632289,0.0011866337,0.0011784346,0.0011194635,0.00045369187,0.0018503722,0.003981336,0.0015416935,0.014361161],"category_scores_gemma":[0.019954449,0.00086664094,0.0019466737,0.0013332919,0.0008816074,0.0017949329,0.0023025912,0.0030716702,0.0058274884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016844772,0.00018459688,0.0021122831,0.00033730487,0.00025442065,0.0002505185,0.00050586276,0.18939929,0.0014760436,0.5672464,0.016640482,0.22142434],"study_design_scores_gemma":[0.00003001731,0.000038287424,0.00032328052,0.000053640557,0.000034915993,0.00015080508,0.000035370656,0.78408015,0.0004942078,0.20712748,0.0076058363,0.000026000125],"about_ca_topic_score_codex":0.004290122,"about_ca_topic_score_gemma":0.0064134463,"teacher_disagreement_score":0.014361161,"about_ca_system_score_codex":0.0010711846,"about_ca_system_score_gemma":0.0021146638,"threshold_uncertainty_score":0.048042893},"labels":[],"label_agreement":null},{"id":"W209594168","doi":"10.3758/s13428-015-0600-5","title":"PsiMLE: A maximum-likelihood estimation approach to estimating psychophysical scaling and variability more reliably, efficiently, and flexibly","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Bayesian probability; Statistics; Gaussian; Algorithm; Variance (accounting); Artificial intelligence; Mathematics; Pattern recognition (psychology)","score_opus":0.3820229668864004,"score_gpt":0.5778684082558168,"score_spread":0.19584544136941634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W209594168","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00062587496,0.000029905059,0.9979608,0.00003062942,0.00001150579,0.000015113824,0.00005518862,0.0011726508,0.000098253644],"genre_scores_gemma":[0.025788376,0.000080000005,0.9714813,0.00011945183,0.000049362963,0.00018338853,0.00043572907,0.0009938692,0.0008685488],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99756384,0.0012519108,0.00016237798,0.00037181115,0.0005706196,0.00007959417],"domain_scores_gemma":[0.99031675,0.0070123775,0.0005095885,0.0012917819,0.00070977135,0.00015965433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058468473,0.0019607262,0.0016808362,0.001473064,0.00069042336,0.0019887676,0.0034902173,0.0021253182,0.006820472],"category_scores_gemma":[0.027116455,0.0016911478,0.0019122306,0.0013632242,0.0009586553,0.003073464,0.0038778603,0.003819667,0.003051841],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061917375,0.00036491608,0.0040822392,0.00056039786,0.0008818549,0.00027498187,0.00039552173,0.22414942,0.017906532,0.027633708,0.012534563,0.71059656],"study_design_scores_gemma":[0.00003607071,0.00004770556,0.000680001,0.00002307713,0.00003423666,0.00011053384,0.00001761129,0.9700893,0.0033459729,0.022387838,0.0031783374,0.000049170023],"about_ca_topic_score_codex":0.002780838,"about_ca_topic_score_gemma":0.005454513,"teacher_disagreement_score":0.006820472,"about_ca_system_score_codex":0.00047170327,"about_ca_system_score_gemma":0.0017399002,"threshold_uncertainty_score":0.03092146},"labels":[],"label_agreement":null},{"id":"W2097184733","doi":"10.3758/brm.41.3.664","title":"Randomization tests and the unequal-N/unequal-variance problem","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Variance (accounting); Statistics; Value (mathematics); Analysis of variance; Type I and type II errors; Word error rate; Mathematics; Computer science; Econometrics; Algorithm; Speech recognition; Economics","score_opus":0.5240400499227096,"score_gpt":0.6774203494091746,"score_spread":0.15338029948646503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097184733","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00856667,0.0009412034,0.97632015,0.0023247448,0.0011197305,0.0044712275,0.00045350322,0.00046295123,0.0053397813],"genre_scores_gemma":[0.11536841,0.00067431293,0.8476082,0.0017030988,0.00064733793,0.030759064,0.00026783592,0.00020949931,0.0027622846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.42166245,0.5301985,0.00895201,0.019109173,0.01766168,0.0024162778],"domain_scores_gemma":[0.314367,0.6344628,0.012184663,0.031868637,0.005884018,0.001232878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28419727,0.004782096,0.011002441,0.0038659188,0.0034142274,0.004793652,0.008432619,0.010110954,0.024039496],"category_scores_gemma":[0.5419312,0.0029667036,0.004719939,0.0044010277,0.01942963,0.01072504,0.0047995904,0.01009003,0.0022416124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009446756,0.0013526266,0.002242648,0.0025691988,0.0017609597,0.0004489811,0.0016612152,0.013018329,0.0011103564,0.7879118,0.009293205,0.16918406],"study_design_scores_gemma":[0.0060905013,0.0013769935,0.0013428999,0.0006321283,0.00041736843,0.00024792252,0.0001663153,0.049043886,0.0014205008,0.9298002,0.009275757,0.00018546738],"about_ca_topic_score_codex":0.0014372051,"about_ca_topic_score_gemma":0.001286311,"teacher_disagreement_score":0.28419727,"about_ca_system_score_codex":0.005289868,"about_ca_system_score_gemma":0.0066806288,"threshold_uncertainty_score":0.8827122},"labels":[],"label_agreement":null},{"id":"W2102418552","doi":"10.3758/s13428-015-0671-3","title":"Tap Arduino: An Arduino microcontroller for low-latency auditory feedback in sensorimotor synchronization experiments","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; International Laboratory for Brain, Music and Sound Research","funders":"","keywords":"Arduino; Latency (audio); Computer science; Microcontroller; Synchronization (alternating current); Psychology; Computer hardware; Embedded system; Telecommunications","score_opus":0.4710063187495546,"score_gpt":0.5808894954880336,"score_spread":0.10988317673847897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102418552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4144613,0.0007717585,0.5453182,0.00039307558,0.001146102,0.005455928,0.0024371627,0.012725527,0.017290981],"genre_scores_gemma":[0.7288744,0.00051802373,0.24239959,0.000581948,0.00015387358,0.007001485,0.00089139957,0.0017049927,0.017874286],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991161,0.00011350937,0.00008855442,0.00023548304,0.0003249796,0.00012119547],"domain_scores_gemma":[0.9991949,0.00027142596,0.00007330314,0.00012338242,0.0002169137,0.0001201631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007720573,0.0015153354,0.00066948927,0.00068710296,0.0005747999,0.00043926827,0.0012686804,0.0008503379,0.023508715],"category_scores_gemma":[0.002023346,0.00045242172,0.00036242124,0.0003893974,0.0005567741,0.00076464604,0.0006539704,0.0008634844,0.0024285563],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088691973,0.0003598754,0.00042347776,0.00042724158,0.000017382774,0.00016094916,0.00017963654,0.00025254537,0.95018095,0.00050778355,0.0012686396,0.045334652],"study_design_scores_gemma":[0.00033952584,0.0044433344,0.011242458,0.00006938336,0.00014652919,0.00073975604,0.00012330244,0.013454651,0.95185935,0.0011814225,0.01633558,0.00006475528],"about_ca_topic_score_codex":0.00024252679,"about_ca_topic_score_gemma":0.00058314204,"teacher_disagreement_score":0.023508715,"about_ca_system_score_codex":0.00023696151,"about_ca_system_score_gemma":0.0005291417,"threshold_uncertainty_score":0.078644514},"labels":[],"label_agreement":null},{"id":"W2112767951","doi":"10.3758/bf03192797","title":"The use of digital video recorders (DVRs) for capturing digital video files for use in both The Observer and Ethovision","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture Food and Rural Development","funders":"","keywords":"Computer science; Observer (physics); Digital recording; Digital video; Software; Uncompressed video; Data compression; Multimedia; Video capture; Video processing; Real-time computing; Computer vision; Video tracking; Computer graphics (images); Computer hardware; Telecommunications","score_opus":0.34555193713925075,"score_gpt":0.47788746533170984,"score_spread":0.13233552819245908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112767951","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081068285,0.0017973435,0.87992615,0.00059099327,0.0008114488,0.0072489954,0.0015988403,0.003290057,0.023667885],"genre_scores_gemma":[0.13572817,0.003018931,0.8261808,0.00053262553,0.00029983767,0.008315376,0.0010383159,0.00072383514,0.024162028],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99364144,0.0019733412,0.0008889652,0.0014277832,0.001857621,0.00021075444],"domain_scores_gemma":[0.97700864,0.008383093,0.0019640047,0.0060279607,0.0059547764,0.0006614563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063355253,0.001088005,0.00056236243,0.0020794373,0.0009987234,0.0010635204,0.0016027107,0.0009236271,0.015138959],"category_scores_gemma":[0.018192546,0.00086678215,0.0006883682,0.0009430247,0.0010539979,0.0014040398,0.0018297387,0.0016806257,0.003569771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013143485,0.00095727964,0.0073316977,0.0017825066,0.00013640108,0.00040414,0.0013961651,0.0005434713,0.5093813,0.0049353032,0.008115627,0.4637018],"study_design_scores_gemma":[0.00074461475,0.017341925,0.12121403,0.0014521722,0.00089868973,0.009083609,0.0018388206,0.014194603,0.6389979,0.006629841,0.18707688,0.0005269103],"about_ca_topic_score_codex":0.0012601118,"about_ca_topic_score_gemma":0.00447645,"teacher_disagreement_score":0.015138959,"about_ca_system_score_codex":0.0003266783,"about_ca_system_score_gemma":0.001659398,"threshold_uncertainty_score":0.050644875},"labels":[],"label_agreement":null},{"id":"W2115529213","doi":"10.3758/s13428-010-0056-6","title":"SMART-T: A system for novel fully automated anticipatory eye-tracking paradigms","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health","keywords":"Computer science; Eye tracking; Toolbox; Gaze; Generalization; Artificial intelligence; Categorization; Human–computer interaction; Scripting language; BitTorrent tracker; Machine learning","score_opus":0.5290336555325987,"score_gpt":0.6079804468599023,"score_spread":0.07894679132730353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115529213","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021678722,0.00028539138,0.888306,0.00012671352,0.00043302006,0.0008120489,0.004240191,0.0812401,0.0028776927],"genre_scores_gemma":[0.12742124,0.00028291272,0.8495644,0.00065012276,0.00016871402,0.0026912591,0.0032170797,0.006077184,0.0099271145],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890816,0.000089441586,0.00009996036,0.00044975497,0.00037293838,0.000079811485],"domain_scores_gemma":[0.99831367,0.0006472228,0.00017033267,0.00038907188,0.0002830588,0.00019679652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001333706,0.0015205635,0.0012725609,0.0010557646,0.00046784148,0.0010449647,0.003278271,0.0016125245,0.02410383],"category_scores_gemma":[0.003209072,0.0011175713,0.00083893014,0.0006475087,0.00034820152,0.0017177076,0.0019543373,0.0011384077,0.008805027],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018396935,0.00029877666,0.003515858,0.0008423241,0.00030095523,0.00031015754,0.0002729886,0.0021017627,0.67339075,0.0024570453,0.03389434,0.2807752],"study_design_scores_gemma":[0.0006978689,0.0015385089,0.020402456,0.00018113678,0.0004940544,0.002920286,0.0000978162,0.30402312,0.5480675,0.007520148,0.11333458,0.00072248786],"about_ca_topic_score_codex":0.001336821,"about_ca_topic_score_gemma":0.002509307,"teacher_disagreement_score":0.02410383,"about_ca_system_score_codex":0.00052306923,"about_ca_system_score_gemma":0.0010179252,"threshold_uncertainty_score":0.08063531},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8360044474353515,"score_gpt":0.6474662355025267,"score_spread":0.18853821193282483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124006395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30680278,0.0008534086,0.67825013,0.00026839023,0.000058961163,0.00013601239,0.004533009,0.006520036,0.002577222],"genre_scores_gemma":[0.7415824,0.00030403855,0.2483015,0.00003221595,0.00004603372,0.0003547997,0.006355012,0.0005879025,0.0024361596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989353,0.00048173382,0.00007535297,0.0002767375,0.00013269809,0.000098179305],"domain_scores_gemma":[0.99023,0.008671685,0.00027044167,0.0004721046,0.00020736291,0.0001483653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020279305,0.0007241619,0.00095945754,0.0050021945,0.00081386045,0.0021382102,0.00093934935,0.0006348629,0.008626315],"category_scores_gemma":[0.007404076,0.00038591825,0.0012405773,0.0045088613,0.00041890788,0.0023519683,0.0018518426,0.0008358816,0.0012534198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028990381,0.0005948304,0.077313654,0.0011913995,0.0008342651,0.00081938994,0.0066940025,0.02418538,0.033079717,0.027517514,0.0082558235,0.8166149],"study_design_scores_gemma":[0.00018751319,0.00035659643,0.039341494,0.000105392915,0.0004017792,0.0007823943,0.0033098834,0.8764722,0.01065702,0.05063141,0.017643142,0.00011132878],"about_ca_topic_score_codex":0.005194644,"about_ca_topic_score_gemma":0.006613588,"teacher_disagreement_score":0.008626315,"about_ca_system_score_codex":0.00037529672,"about_ca_system_score_gemma":0.0008689869,"threshold_uncertainty_score":0.028857887},"labels":[],"label_agreement":null},{"id":"W2130509954","doi":"10.3758/s13428-011-0067-y","title":"A novel integrative method for analyzing eye and hand behaviour during reaching and grasping in an MRI environment","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Kinematics; Artificial intelligence; Neuroimaging; Computer vision; Gaze; Functional magnetic resonance imaging; Software; Human–computer interaction; Neuroscience; Psychology","score_opus":0.34878348153452177,"score_gpt":0.5227324701129151,"score_spread":0.17394898857839336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130509954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035962835,0.0002616399,0.9615526,0.000057160676,0.000033818495,0.000084191764,0.0001817429,0.00061159383,0.0012543771],"genre_scores_gemma":[0.14382254,0.00038092432,0.8520917,0.0000907784,0.000053062595,0.00032827895,0.00021282541,0.00032443274,0.002695439],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998061,0.000029355215,0.000009136887,0.000065638626,0.00006398032,0.000025715368],"domain_scores_gemma":[0.9996126,0.00014376515,0.00005092731,0.000053940938,0.000084389125,0.00005445569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004333257,0.0006564047,0.0004761801,0.0010272235,0.00034934265,0.0004997822,0.00068949553,0.00058074447,0.0028929901],"category_scores_gemma":[0.0007395127,0.00043762947,0.000291772,0.0007782195,0.00047746568,0.0007244114,0.0008188308,0.00061885524,0.0006400284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013244154,0.000045233788,0.0013653476,0.00010258561,0.000039756756,0.00007585413,0.00009295065,0.0007286133,0.8812806,0.0009809249,0.00041146888,0.114744194],"study_design_scores_gemma":[0.00018209984,0.0012052904,0.067523405,0.000097757096,0.00043341384,0.0049843756,0.0003698946,0.25048977,0.64699954,0.007426032,0.019976094,0.00031235078],"about_ca_topic_score_codex":0.0012943804,"about_ca_topic_score_gemma":0.0036393914,"teacher_disagreement_score":0.0028929901,"about_ca_system_score_codex":0.00020746549,"about_ca_system_score_gemma":0.00056558155,"threshold_uncertainty_score":0.009678066},"labels":[],"label_agreement":null},{"id":"W2131425739","doi":"10.3758/s13428-011-0154-0","title":"The Slip Induction Task: Creating a window into cognitive control failures","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Task (project management); Action (physics); Cognition; sort; Cognitive psychology; Slip (aerodynamics); Psychology; Computer science; Engineering; Neuroscience","score_opus":0.654021635508505,"score_gpt":0.6161776168764262,"score_spread":0.03784401863207876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131425739","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8509031,0.00043339652,0.13044485,0.0008110871,0.00040954308,0.000539776,0.00089032075,0.0008189108,0.014749049],"genre_scores_gemma":[0.9505382,0.0002870472,0.042964008,0.00049847894,0.00016518055,0.00080827175,0.00043233685,0.00043766006,0.003868751],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995617,0.000098487784,0.000027677626,0.00008500532,0.00016477122,0.000062281375],"domain_scores_gemma":[0.9961319,0.0023437077,0.0004046282,0.0006665163,0.00010140306,0.00035187395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001175448,0.00057862204,0.0004020241,0.00042206587,0.00028066846,0.0007959976,0.00062748254,0.0006428221,0.00522342],"category_scores_gemma":[0.00809767,0.0003430965,0.00016015822,0.00022024573,0.00076419045,0.0015264591,0.0011116983,0.0013422641,0.00044576306],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014301493,0.0053426917,0.023575675,0.00067378563,0.000078468394,0.0008011569,0.003076488,0.0023189662,0.6992462,0.027692907,0.0071697603,0.21572237],"study_design_scores_gemma":[0.0028633205,0.017411461,0.3856512,0.0007329202,0.000518816,0.003472107,0.0021319666,0.09049602,0.32965884,0.13525815,0.03145949,0.00034572298],"about_ca_topic_score_codex":0.00026023606,"about_ca_topic_score_gemma":0.00048234093,"teacher_disagreement_score":0.00522342,"about_ca_system_score_codex":0.00020565827,"about_ca_system_score_gemma":0.0006705521,"threshold_uncertainty_score":0.017474115},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5345840841783612,"score_gpt":0.6108165772882865,"score_spread":0.0762324931099253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138172448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83965135,0.0024895214,0.08462793,0.00037447226,0.00039667383,0.015069523,0.025184391,0.0017818892,0.030424379],"genre_scores_gemma":[0.8260823,0.0022027795,0.108140066,0.0010079521,0.00037640828,0.025876751,0.017453928,0.0010848403,0.017774971],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895346,0.00024435887,0.000094336676,0.00016330722,0.0004430882,0.000101456644],"domain_scores_gemma":[0.9983828,0.0004912885,0.00030819466,0.00016067711,0.0004873807,0.00016966223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013431752,0.001027588,0.0004313286,0.0014269529,0.00062226935,0.0007929686,0.00077420153,0.0009266311,0.00569622],"category_scores_gemma":[0.0054229656,0.00023771913,0.00057566614,0.00083947234,0.00055440195,0.00064575416,0.0008482852,0.0003925728,0.0011250194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010035988,0.0013400824,0.14137839,0.0019172478,0.0008134075,0.0011988822,0.0022686895,0.00696279,0.3739638,0.0041907122,0.022416543,0.4335136],"study_design_scores_gemma":[0.0009311925,0.0024237852,0.9279378,0.0001146836,0.000512341,0.0011680884,0.00038258178,0.0055825952,0.032277215,0.0011234264,0.027359337,0.00018686526],"about_ca_topic_score_codex":0.00905499,"about_ca_topic_score_gemma":0.033948585,"teacher_disagreement_score":0.00905499,"about_ca_system_score_codex":0.00078655704,"about_ca_system_score_gemma":0.0008135732,"threshold_uncertainty_score":0.019055724},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.37637237552285974,"score_gpt":0.6081377045351003,"score_spread":0.23176532901224056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142398106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9790598,0.00047533857,0.009309527,0.000055576023,0.00006981067,0.00074101007,0.0063523166,0.0003032813,0.0036333574],"genre_scores_gemma":[0.93810415,0.00057579443,0.021386653,0.00018614624,0.00014701905,0.0023331267,0.03167081,0.000113956594,0.005482403],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996804,0.00006733127,0.00004447538,0.0000884044,0.00008195837,0.00003745863],"domain_scores_gemma":[0.99935037,0.00014048946,0.00006188269,0.00013479273,0.00023716362,0.00007538032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005512817,0.0005925594,0.0004991571,0.0008045891,0.0005009443,0.00040090925,0.00063746213,0.0005507846,0.003976132],"category_scores_gemma":[0.0012001032,0.00012433724,0.0004251277,0.0006945447,0.00030995643,0.0003212656,0.00058496906,0.00022526528,0.0017355616],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026768097,0.0015526515,0.08121336,0.0016182726,0.00041874344,0.0020378432,0.0014058697,0.0026360976,0.5801789,0.0007541495,0.011113779,0.31439355],"study_design_scores_gemma":[0.0002290016,0.0010222619,0.9035565,0.000058624533,0.0005542914,0.002965815,0.00077782676,0.013461667,0.0667596,0.00026508694,0.01023314,0.000116259725],"about_ca_topic_score_codex":0.0045230505,"about_ca_topic_score_gemma":0.008780595,"teacher_disagreement_score":0.0045230505,"about_ca_system_score_codex":0.0003193564,"about_ca_system_score_gemma":0.00053311855,"threshold_uncertainty_score":0.013301492},"labels":[],"label_agreement":null},{"id":"W2143342006","doi":"10.3758/s13428-015-0682-0","title":"Quantifying online visuomotor feedback utilization in the frequency domain","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequency domain; Computer science; Acceleration; Detrended fluctuation analysis; Feedback control; Control (management); Artificial intelligence; Mathematics; Computer vision; Control engineering","score_opus":0.7533497313562453,"score_gpt":0.6120796684353152,"score_spread":0.14127006292093003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143342006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.818204,0.00047792424,0.1769741,0.00004732475,0.00003949706,0.00007073209,0.00043506786,0.00040484738,0.0033465126],"genre_scores_gemma":[0.95259804,0.00027361253,0.045332257,0.000043253818,0.000022603233,0.000082843995,0.00023686865,0.0001081574,0.001302412],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996288,0.0000735688,0.000016725842,0.000114762195,0.00012606049,0.000040092415],"domain_scores_gemma":[0.99918264,0.000492086,0.00010787749,0.000085960615,0.00009472636,0.000036662255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036025196,0.00042745558,0.00039509637,0.0009975615,0.00015436058,0.00050162757,0.00029133062,0.00041760947,0.0020116542],"category_scores_gemma":[0.0027468463,0.00020900363,0.00020806334,0.00060064887,0.00020534614,0.00062774814,0.00039363583,0.00025405464,0.00038090625],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096394663,0.0005602531,0.033277027,0.00041083325,0.00018377884,0.00008889142,0.00023603882,0.010538088,0.5764886,0.00091748184,0.0004872068,0.37584788],"study_design_scores_gemma":[0.00007526275,0.001247685,0.44841188,0.00012397955,0.00031853138,0.0013732509,0.00024777575,0.25346616,0.28881186,0.003432687,0.0023718947,0.00011901264],"about_ca_topic_score_codex":0.0011233006,"about_ca_topic_score_gemma":0.0019782523,"teacher_disagreement_score":0.0020116542,"about_ca_system_score_codex":0.00021224811,"about_ca_system_score_gemma":0.00026280648,"threshold_uncertainty_score":0.0067296624},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Computer science; Mathematics","score_opus":0.9138052411701298,"score_gpt":0.754588885036263,"score_spread":0.15921635613386687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148999650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09298247,0.002651776,0.8912125,0.0045728437,0.0008297262,0.0023965917,0.0014574847,0.00052461145,0.003371977],"genre_scores_gemma":[0.5397519,0.00063286925,0.44853687,0.0012153354,0.00058382936,0.0056337076,0.00062609074,0.00018059509,0.0028387667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6232969,0.31300366,0.015519158,0.027845502,0.017222973,0.0031117843],"domain_scores_gemma":[0.17628142,0.76882213,0.015788864,0.034298323,0.0033003993,0.0015088167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3183872,0.0031891966,0.008255213,0.0050282064,0.0016083195,0.004236157,0.009299617,0.010469673,0.0106107555],"category_scores_gemma":[0.58840996,0.0022477102,0.006073871,0.0039292104,0.015950348,0.011187016,0.004666172,0.0077327234,0.0009995974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018499611,0.003927406,0.0702369,0.0068278094,0.011045526,0.008077673,0.0063237697,0.056430675,0.0039155693,0.5326912,0.010751306,0.2712725],"study_design_scores_gemma":[0.003222388,0.005278976,0.03148673,0.00078456814,0.0035042798,0.0040656035,0.0012402589,0.3545682,0.0027893374,0.58616686,0.0065243808,0.00036840557],"about_ca_topic_score_codex":0.001801185,"about_ca_topic_score_gemma":0.0013240529,"teacher_disagreement_score":0.6816128,"about_ca_system_score_codex":0.0026542067,"about_ca_system_score_gemma":0.0028265924,"threshold_uncertainty_score":0.84054995},"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":"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7699708216302553,"score_gpt":0.5899453915272571,"score_spread":0.1800254301029982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151069696","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012480357,0.0007959336,0.9959857,0.0005129626,0.0002908042,0.00003220968,0.00012309868,0.000378342,0.0017561329],"genre_scores_gemma":[0.0062760827,0.0024574474,0.981403,0.00078687887,0.0011842658,0.000476784,0.00047032008,0.000898093,0.006047069],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938472,0.0036768802,0.0004579603,0.00044882722,0.0014376696,0.00013145254],"domain_scores_gemma":[0.974019,0.022794126,0.00033553995,0.0012090112,0.0014177682,0.00022463671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012370022,0.0025659024,0.002025316,0.0022492625,0.00072231307,0.0026483978,0.003336165,0.0035471458,0.03417751],"category_scores_gemma":[0.0530228,0.0017947331,0.0019739873,0.0023085987,0.0019121653,0.0047605378,0.0031147182,0.006797999,0.015245578],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010320894,0.00012322325,0.00050411193,0.0009810601,0.00017365046,0.0006704489,0.00024473298,0.017957859,0.002039226,0.49602348,0.076087676,0.40509138],"study_design_scores_gemma":[0.00005431615,0.000056255267,0.00026351394,0.00019166002,0.000045824494,0.00078428397,0.000041218744,0.064799435,0.00089859276,0.8596807,0.07311403,0.0000701966],"about_ca_topic_score_codex":0.0015515522,"about_ca_topic_score_gemma":0.0026594377,"teacher_disagreement_score":0.03417751,"about_ca_system_score_codex":0.0010052224,"about_ca_system_score_gemma":0.0018811444,"threshold_uncertainty_score":0.11433518},"labels":[],"label_agreement":null},{"id":"W2167848283","doi":"10.3758/s13428-011-0101-0","title":"The nature of orthographic–phonological and orthographic–semantic relationships for Japanese kana and kanji words","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Kana; Kanji; Linguistics; Word (group theory); Natural language processing; Psychology; Reading (process); Orthographic projection; Artificial intelligence; Computer science; Chinese characters","score_opus":0.3132455091299252,"score_gpt":0.5334611814445118,"score_spread":0.2202156723145866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167848283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877422,0.00019210596,0.0025528094,0.000069658294,0.000013428071,0.000026341882,0.0002200973,0.00002592476,0.009157507],"genre_scores_gemma":[0.9969689,0.00009934551,0.0016128499,0.000022958704,0.0000073574247,0.00003304307,0.00025947441,0.000046667577,0.00094937155],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991278,0.0002733262,0.000085404994,0.00027249,0.00017345644,0.00006758264],"domain_scores_gemma":[0.9854689,0.009144154,0.002037734,0.00070047844,0.0022859492,0.0003626734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001012521,0.00019632356,0.00019090487,0.0012644654,0.000566418,0.0018342485,0.0005095636,0.00035810244,0.0035350884],"category_scores_gemma":[0.01927478,0.0005492135,0.00029358856,0.0009692772,0.00074734003,0.003265077,0.00086409965,0.000777333,0.00047497335],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018538992,0.0005056759,0.40529478,0.0006288199,0.00037178118,0.00083519885,0.023811867,0.001704016,0.39668128,0.027999781,0.0010784816,0.13923447],"study_design_scores_gemma":[0.00003208125,0.00020317301,0.9665083,0.000038339076,0.00021599642,0.00066736137,0.0038585223,0.004954578,0.015742814,0.0062813633,0.0014460044,0.00005144274],"about_ca_topic_score_codex":0.003635572,"about_ca_topic_score_gemma":0.006303247,"teacher_disagreement_score":0.003635572,"about_ca_system_score_codex":0.0003873845,"about_ca_system_score_gemma":0.00066675793,"threshold_uncertainty_score":0.011826038},"labels":[],"label_agreement":null},{"id":"W2188479190","doi":"10.3758/s13428-015-0679-8","title":"Thematic relatedness production norms for 100 object concepts","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Thematic map; Locative case; Attributive; Computer science; Object (grammar); Similarity (geometry); Cognition; Cognitive science; Psychology; Cognitive psychology; Linguistics; Natural language processing; Artificial intelligence","score_opus":0.6433840902575432,"score_gpt":0.6503699384502034,"score_spread":0.006985848192660238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188479190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93325526,0.0002751982,0.02408048,0.00013478314,0.00009338827,0.00035223516,0.0010299187,0.00035000854,0.04042874],"genre_scores_gemma":[0.97843164,0.00008810978,0.01676977,0.000046219237,0.000037937418,0.00060672726,0.0012408294,0.00031977004,0.002459062],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99127495,0.0029339064,0.000872155,0.001362296,0.0032838017,0.0002728504],"domain_scores_gemma":[0.8658892,0.1065552,0.006183805,0.007088768,0.013117567,0.0011655206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013623393,0.00044655282,0.0004157083,0.0019534978,0.00044600727,0.0020502196,0.00077588257,0.0009610146,0.0068947226],"category_scores_gemma":[0.13282572,0.00034758713,0.00048488745,0.000609415,0.0012315812,0.0018138316,0.0017858571,0.00104662,0.0010289439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009149589,0.0017613336,0.30941045,0.0015371065,0.00082568405,0.001210212,0.044296816,0.011341422,0.18521409,0.09027265,0.007945807,0.33703485],"study_design_scores_gemma":[0.0004911001,0.0022784737,0.8011915,0.00038869894,0.00043137747,0.0035140796,0.0065743905,0.041591574,0.052131325,0.075542614,0.015554394,0.00031048027],"about_ca_topic_score_codex":0.0010180867,"about_ca_topic_score_gemma":0.0011890687,"teacher_disagreement_score":0.013623393,"about_ca_system_score_codex":0.0007462473,"about_ca_system_score_gemma":0.0003716135,"threshold_uncertainty_score":0.07204819},"labels":[],"label_agreement":null},{"id":"W2229247805","doi":"10.3758/s13428-015-0699-4","title":"Erratum to: Manipulability agreement as a predictor of action initiation latency","year":2016,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute; Université de Moncton","funders":"","keywords":"Latency (audio); Agreement; Computer science; Action (physics); Psychology; Physics; Telecommunications; Philosophy; Linguistics","score_opus":0.4731936428423508,"score_gpt":0.6126827588171884,"score_spread":0.13948911597483754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2229247805","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041880594,0.0027599127,0.0031353494,0.071114354,0.8960028,0.00012624677,0.0076601435,0.0011513133,0.0138617745],"genre_scores_gemma":[0.09656571,0.012519155,0.019435998,0.07199354,0.081216455,0.00074903975,0.016098287,0.0031982746,0.69822353],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99609864,0.00051012175,0.0012037818,0.00038315327,0.0016045643,0.0001996401],"domain_scores_gemma":[0.96401614,0.012520114,0.0031873598,0.0024636597,0.016832873,0.0009797962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029852663,0.0014696738,0.0010430595,0.0020091361,0.002091761,0.0016044534,0.0015965899,0.0035152647,0.06704479],"category_scores_gemma":[0.07109778,0.0007113595,0.00071047025,0.0014087242,0.0012194988,0.0014346035,0.0013806033,0.0035403362,0.035790477],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019054378,0.00004327704,0.001137336,0.00021164175,0.000014494308,0.0004399922,0.00008498012,0.000073821655,0.00015995953,0.00084759615,0.97926724,0.017529026],"study_design_scores_gemma":[0.0001592698,0.000255848,0.012530816,0.0012140222,0.00011985705,0.0028119844,0.0006952332,0.0009788463,0.0029791947,0.0042228065,0.9739072,0.00012505212],"about_ca_topic_score_codex":0.012570214,"about_ca_topic_score_gemma":0.016939582,"teacher_disagreement_score":0.06704479,"about_ca_system_score_codex":0.002054117,"about_ca_system_score_gemma":0.0037046417,"threshold_uncertainty_score":0.22428715},"labels":[],"label_agreement":null},{"id":"W2260068509","doi":"10.3758/s13428-015-0696-7","title":"A simple technique to study embodied language processes: the grip force sensor","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Centre National de la Recherche Scientifique","keywords":"Embodied cognition; Computer science; Artifact (error); Brain activity and meditation; Modality (human–computer interaction); Perception; Cognition; Action (physics); Human–computer interaction; Measure (data warehouse); Motor cortex; Cognitive psychology; Artificial intelligence; Electroencephalography; Psychology; Neuroscience; Data mining","score_opus":0.4750688339849863,"score_gpt":0.6410319682460859,"score_spread":0.1659631342610996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260068509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10628774,0.0013571299,0.88157123,0.00039274967,0.0004115877,0.00036956798,0.00080077694,0.00071983,0.008089346],"genre_scores_gemma":[0.531374,0.0014742689,0.46173865,0.00032459982,0.00017012983,0.0008225842,0.00031264997,0.00022089666,0.0035622364],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995436,0.00011658752,0.000030775584,0.00012958537,0.00014389458,0.00003545063],"domain_scores_gemma":[0.99918896,0.0004173388,0.00009698129,0.00014556992,0.00007754095,0.000073597956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062169816,0.0006943885,0.00044096197,0.000962882,0.0003999391,0.00059111,0.0008320331,0.0009818316,0.004027379],"category_scores_gemma":[0.0023922236,0.00032754274,0.0003182716,0.00072513777,0.0009509153,0.0012415467,0.0010465607,0.00065353146,0.0005337821],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030501568,0.00024008242,0.004938025,0.0006227184,0.00007769792,0.0001718915,0.00043640257,0.0011966516,0.867611,0.013010291,0.0014323506,0.10995788],"study_design_scores_gemma":[0.0005026197,0.0035378574,0.12103973,0.00036944335,0.00043862022,0.005045653,0.0013390174,0.064399906,0.7027562,0.05408928,0.046037994,0.00044362928],"about_ca_topic_score_codex":0.00048062147,"about_ca_topic_score_gemma":0.0007770964,"teacher_disagreement_score":0.004027379,"about_ca_system_score_codex":0.0001812834,"about_ca_system_score_gemma":0.00040667775,"threshold_uncertainty_score":0.013472855},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4123654394581135,"score_gpt":0.5860038097873501,"score_spread":0.17363837032923662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288693139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93340063,0.0002069791,0.0046857847,0.00023455838,0.00008533761,0.0003099314,0.049963832,0.0004897324,0.010623167],"genre_scores_gemma":[0.8908808,0.00013038448,0.017920231,0.00017535247,0.00005113268,0.0008962292,0.07756211,0.00096692884,0.011416825],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99873966,0.00032979043,0.00012627862,0.00023376301,0.00044297986,0.00012743287],"domain_scores_gemma":[0.9910086,0.0032859687,0.00062917726,0.002141894,0.0019918436,0.0009425778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020601165,0.00056064985,0.00050205115,0.0014870401,0.00071245217,0.0011296172,0.0010013025,0.001053224,0.008131998],"category_scores_gemma":[0.012059356,0.00033790548,0.00039178322,0.0013245032,0.0009877551,0.0012767025,0.0020148847,0.0014148813,0.004192219],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018244175,0.0046966,0.29285514,0.0006700203,0.0006293913,0.0018062993,0.006285411,0.00615792,0.11123189,0.006191524,0.12827395,0.4229576],"study_design_scores_gemma":[0.0007998848,0.0007356165,0.8996921,0.00010408638,0.00015349266,0.0006295501,0.0029857673,0.008316284,0.025897436,0.006738041,0.053747665,0.00020008278],"about_ca_topic_score_codex":0.038310915,"about_ca_topic_score_gemma":0.05766708,"teacher_disagreement_score":0.038310915,"about_ca_system_score_codex":0.0007709548,"about_ca_system_score_gemma":0.0015922935,"threshold_uncertainty_score":0.07617587},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.42588741391414275,"score_gpt":0.6267026890361848,"score_spread":0.200815275122042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290759784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818618,0.00030582637,0.0027768572,0.000059906826,0.0001335659,0.00020965865,0.0022718625,0.00007528769,0.012305226],"genre_scores_gemma":[0.98298544,0.00034403,0.0053280145,0.00008346386,0.00008801328,0.00092423224,0.0051288097,0.00014298041,0.0049749184],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99870956,0.0004451487,0.00020732277,0.00023439464,0.00030632198,0.00009730135],"domain_scores_gemma":[0.99426186,0.0021214706,0.0005990038,0.00037099258,0.0024318167,0.00021493302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020617053,0.0004214594,0.00029362214,0.0009994892,0.0003342735,0.00090200565,0.00020995356,0.00031979757,0.0031674844],"category_scores_gemma":[0.010050831,0.0000908386,0.00027090474,0.0006548779,0.00038232654,0.00034058758,0.00041721595,0.00030098687,0.0010064034],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007105594,0.0007575438,0.71832097,0.0005568151,0.00038826038,0.0003176579,0.009628242,0.00087146944,0.044497795,0.0024512676,0.0060463967,0.20905806],"study_design_scores_gemma":[0.00008208594,0.00064984424,0.9790741,0.00006932313,0.0000670455,0.00026298984,0.00404047,0.00075091654,0.0041654473,0.0011492885,0.009645763,0.000042786443],"about_ca_topic_score_codex":0.0024465686,"about_ca_topic_score_gemma":0.0041746665,"teacher_disagreement_score":0.0031674844,"about_ca_system_score_codex":0.0005148528,"about_ca_system_score_gemma":0.0003021248,"threshold_uncertainty_score":0.010903478},"labels":[],"label_agreement":null},{"id":"W2331470947","doi":"10.3758/bf03192768","title":"Word frequency effects in high-dimensional co-occurrence models: A new approach","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Word lists by frequency; Computer science; Distributional semantics; Lexical decision task; Natural language processing; Orthographic projection; Hyperspace; Space (punctuation); Semantics (computer science); Artificial intelligence; Linguistics; Semantic similarity; Cognition; Psychology","score_opus":0.30327505621301126,"score_gpt":0.5142418890998628,"score_spread":0.21096683288685153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331470947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014414026,0.0005556943,0.98349285,0.00038761727,0.000059274735,0.000076747376,0.00017450147,0.00022502926,0.00061430375],"genre_scores_gemma":[0.44292068,0.0017708899,0.54785246,0.0004375433,0.00084627926,0.0013749358,0.0008602508,0.0004003486,0.0035366644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9770791,0.01650332,0.0011076422,0.0032293936,0.0016705523,0.00040993927],"domain_scores_gemma":[0.80618966,0.17934597,0.0026437226,0.008640738,0.002298601,0.0008812522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028588837,0.0020882634,0.0040076296,0.0056910343,0.0019371593,0.0072782687,0.005906907,0.0036283557,0.0049000666],"category_scores_gemma":[0.08261272,0.0018755605,0.0048767873,0.007410039,0.0037023406,0.008226249,0.0043970305,0.006466056,0.0010546227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012607138,0.0017600077,0.034527764,0.0011385815,0.0049279407,0.0008167482,0.0065555377,0.1699386,0.0051739966,0.47315365,0.0042324606,0.29651415],"study_design_scores_gemma":[0.00013419136,0.00023716052,0.0046564993,0.00009429385,0.00092201645,0.00025591545,0.000444775,0.75058776,0.0006427091,0.23865995,0.0032266274,0.0001380534],"about_ca_topic_score_codex":0.005456197,"about_ca_topic_score_gemma":0.005827234,"teacher_disagreement_score":0.028588837,"about_ca_system_score_codex":0.0015282967,"about_ca_system_score_gemma":0.0022318328,"threshold_uncertainty_score":0.15119398},"labels":[],"label_agreement":null},{"id":"W2469509554","doi":"10.3758/s13428-016-0757-6","title":"Testing the accuracy of timing reports in visual timing tasks with a consumer-grade digital camera","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); CLIPS; Display size; Software; Computer vision; Artificial intelligence; Computer hardware; Real-time computing; Display device","score_opus":0.4994695931328663,"score_gpt":0.5752938594666791,"score_spread":0.07582426633381278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469509554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9553184,0.00021141306,0.03855591,0.000120183555,0.00027603743,0.0003960768,0.00040721524,0.00040483542,0.0043099048],"genre_scores_gemma":[0.9480861,0.00025058739,0.0446477,0.00025369503,0.000082470324,0.00033620337,0.00053100195,0.00020743757,0.00560483],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995843,0.0007567261,0.00049289496,0.0011597263,0.001482959,0.0002647297],"domain_scores_gemma":[0.9772379,0.01121982,0.00435478,0.002219991,0.004214332,0.00075327314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027722623,0.00074308406,0.0003292255,0.0007999704,0.000269756,0.0008281151,0.0010005521,0.00130863,0.004361152],"category_scores_gemma":[0.031628024,0.00043922098,0.00031967746,0.00041975055,0.0004787413,0.00091198,0.0005737424,0.00084052683,0.0013191202],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009001097,0.003175625,0.1415374,0.00039483825,0.00024824127,0.0002779767,0.0012040262,0.0012300212,0.71723294,0.00083046715,0.0016854974,0.12318181],"study_design_scores_gemma":[0.00056406256,0.013438205,0.5812291,0.000095194584,0.00040654896,0.0020011193,0.00070172513,0.028861307,0.36767128,0.00076964905,0.004098132,0.00016371936],"about_ca_topic_score_codex":0.0021596465,"about_ca_topic_score_gemma":0.0032557147,"teacher_disagreement_score":0.004361152,"about_ca_system_score_codex":0.0003070163,"about_ca_system_score_gemma":0.00060004636,"threshold_uncertainty_score":0.0146612525},"labels":[],"label_agreement":null},{"id":"W2498664058","doi":"10.3758/s13428-016-0772-7","title":"One tamed at a time: A new approach for controlling continuous magnitudes in numerical comparison tasks","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"European Research Council; Israel Science Foundation; European Commission","keywords":"Numerosity adaptation effect; Numerical cognition; Convex hull; Cognition; Equating; Computer science; Mathematics; Algorithm; Regular polygon; Statistics; Psychology; Neuroscience; Geometry","score_opus":0.37783024330210274,"score_gpt":0.5580013170808487,"score_spread":0.18017107377874592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498664058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17323455,0.00014186544,0.8159945,0.00034123266,0.00034145062,0.00082284695,0.00046372137,0.00084437133,0.007815432],"genre_scores_gemma":[0.369402,0.00008772612,0.62094885,0.00023203458,0.00010537399,0.00300089,0.00017067844,0.0004260189,0.005626424],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9948407,0.0018332195,0.00024491787,0.0018793528,0.0010712494,0.00013064317],"domain_scores_gemma":[0.984726,0.009737599,0.0017342634,0.002409695,0.0010352727,0.00035712414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046314388,0.0012835824,0.001048749,0.0012156449,0.00081582647,0.0025813251,0.0018025496,0.00091749965,0.0062502446],"category_scores_gemma":[0.029351106,0.0006725201,0.000721732,0.001023213,0.0014746063,0.003111553,0.002081125,0.0018612132,0.0005230772],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007364388,0.004906989,0.043769058,0.0009260435,0.0012361137,0.0001308052,0.006883224,0.021567475,0.17651388,0.13661852,0.005068631,0.59501475],"study_design_scores_gemma":[0.0023404984,0.008767186,0.15157247,0.00021360339,0.002332581,0.0005207381,0.0017283446,0.5280062,0.086861014,0.1827536,0.03402008,0.0008837308],"about_ca_topic_score_codex":0.0024306283,"about_ca_topic_score_gemma":0.004294076,"teacher_disagreement_score":0.0062502446,"about_ca_system_score_codex":0.00092926103,"about_ca_system_score_gemma":0.0013844188,"threshold_uncertainty_score":0.024493694},"labels":[],"label_agreement":null},{"id":"W2509258559","doi":"10.3758/s13428-016-0802-5","title":"Validation of sleep-2-Peak: A smartphone application that can detect fatigue-related changes in reaction times during sleep deprivation","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sleep and Work-Related Fatigue","field":"Psychology","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Clinique Neuro-Outaouais; Cégep de l'Outaouais; Université du Québec en Outaouais","funders":"","keywords":"Sleep deprivation; Alertness; Psychomotor vigilance task; Wakefulness; Psychology; Context (archaeology); Audiology; Vigilance (psychology); Modafinil; Sleep (system call); Medicine; Electroencephalography; Computer science; Cognitive psychology; Cognition; Psychiatry","score_opus":0.16995006484946648,"score_gpt":0.4883889354198899,"score_spread":0.3184388705704234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509258559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90508085,0.0007267442,0.07336906,0.00029588476,0.00036719727,0.002501074,0.008191833,0.0061304225,0.0033369297],"genre_scores_gemma":[0.919166,0.00035842293,0.06697532,0.000644172,0.00014038025,0.003568433,0.0033375986,0.0005191745,0.0052904077],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99958163,0.00012169169,0.000050799328,0.00010001765,0.00010985795,0.000036077807],"domain_scores_gemma":[0.99903035,0.00040239957,0.00013482272,0.00006077573,0.00029820582,0.00007343169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008140842,0.00089264027,0.00038172872,0.0006178472,0.0001559819,0.0003024375,0.00043601362,0.0006866316,0.0035796885],"category_scores_gemma":[0.0019055433,0.00024013109,0.00033648382,0.00022067767,0.0001243715,0.00030798404,0.00037803216,0.00027215513,0.0013529371],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008123638,0.0018063386,0.13531558,0.0022107696,0.0006301209,0.00072401285,0.0012327748,0.0013621403,0.5234377,0.00037817983,0.016250832,0.30852795],"study_design_scores_gemma":[0.0009585269,0.008209434,0.8157716,0.00021425301,0.0008851015,0.0024308064,0.0004810817,0.034571815,0.120997496,0.0003978669,0.014888519,0.0001934537],"about_ca_topic_score_codex":0.000898425,"about_ca_topic_score_gemma":0.001919167,"teacher_disagreement_score":0.0035796885,"about_ca_system_score_codex":0.00010467216,"about_ca_system_score_gemma":0.0002560416,"threshold_uncertainty_score":0.011975229},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1987628173989918,"score_gpt":0.5479670901449614,"score_spread":0.34920427274596955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2522857466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781018,0.000087744214,0.0032626016,0.00006013342,0.000052039803,0.00037149768,0.0018141873,0.000148537,0.016101528],"genre_scores_gemma":[0.9721387,0.000120374505,0.009423642,0.00009035922,0.000018363753,0.0018443004,0.0055158655,0.0001728037,0.0106757535],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955935,0.0007512779,0.0010746933,0.000528144,0.0018151257,0.00023722688],"domain_scores_gemma":[0.96693325,0.010828068,0.0036240737,0.0024584392,0.014695223,0.0014609459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004938351,0.00048698898,0.0003885875,0.0025741493,0.00071370654,0.0014309107,0.0007627957,0.0008343072,0.0050317813],"category_scores_gemma":[0.025597781,0.00033605422,0.0006224945,0.0007589426,0.00068951724,0.0016407024,0.0015656137,0.0007442151,0.0025131914],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017399754,0.003190299,0.81953716,0.00024966893,0.00015802307,0.0005905863,0.019183636,0.0013011287,0.022114241,0.0043832343,0.0059262393,0.1216257],"study_design_scores_gemma":[0.00005495763,0.0017739652,0.97264874,0.00006565634,0.000043499324,0.0006752517,0.003681725,0.0011521756,0.011076204,0.0013304733,0.0074347644,0.00006264118],"about_ca_topic_score_codex":0.0026688296,"about_ca_topic_score_gemma":0.0087907845,"teacher_disagreement_score":0.0050317813,"about_ca_system_score_codex":0.00057398743,"about_ca_system_score_gemma":0.0006608895,"threshold_uncertainty_score":0.026116788},"labels":[],"label_agreement":null},{"id":"W2539586339","doi":"10.3758/s13428-016-0823-0","title":"Performance of growth mixture models in the presence of time-varying covariates","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Statistics Canada","funders":"","keywords":"Akaike information criterion; Bayesian information criterion; Statistics; Covariate; Deviance information criterion; Mathematics; Sample size determination; Contrast (vision); Model selection; Information Criteria; Bayesian probability; Entropy (arrow of time); Mixture model; Standard error; Econometrics; Bayesian inference; Computer science; Artificial intelligence","score_opus":0.0994531219014636,"score_gpt":0.43448942460041307,"score_spread":0.33503630269894946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539586339","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3363722,0.0029263922,0.6453343,0.003688411,0.00035322754,0.0001975295,0.0013357354,0.0062616128,0.00353059],"genre_scores_gemma":[0.8253196,0.00072754035,0.16190575,0.0005682148,0.0001669237,0.00025798968,0.004746234,0.000957754,0.0053499653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98979306,0.008308282,0.00038068046,0.00080420525,0.0003030751,0.00041064684],"domain_scores_gemma":[0.86743146,0.12363062,0.0018969501,0.0030573036,0.0025761176,0.001407492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04668653,0.0026914019,0.0022457712,0.0014116713,0.0014482795,0.002591905,0.003014432,0.004420634,0.0034463317],"category_scores_gemma":[0.068803035,0.0017580154,0.0019312458,0.0010369152,0.0017314727,0.0042961393,0.0036991935,0.0039393813,0.0016478294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030649998,0.00019511831,0.0070402045,0.00015272963,0.00073821243,0.000081268714,0.00024348448,0.9389546,0.00078043685,0.004680654,0.0017559995,0.04231229],"study_design_scores_gemma":[0.000061964085,0.000053163745,0.0007589396,0.00001763418,0.00005589853,0.000015971544,0.000026873404,0.9963386,0.0003563769,0.0021180946,0.00017405741,0.000022460144],"about_ca_topic_score_codex":0.039087836,"about_ca_topic_score_gemma":0.018752834,"teacher_disagreement_score":0.04668653,"about_ca_system_score_codex":0.0015722945,"about_ca_system_score_gemma":0.0034535513,"threshold_uncertainty_score":0.24690491},"labels":[],"label_agreement":null},{"id":"W2553430072","doi":"10.3758/s13428-016-0832-z","title":"Silex: A database for silent-letter endings in French words","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Spelling; Consistency (knowledge bases); Computer science; Reading (process); Orthography; Set (abstract data type); Linguistics; Natural language processing; Artificial intelligence","score_opus":0.3212763358013591,"score_gpt":0.6067207794575348,"score_spread":0.28544444365617566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553430072","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03749412,0.003365897,0.012921113,0.00010944597,0.00012670156,0.00042041225,0.90323657,0.024827838,0.017497886],"genre_scores_gemma":[0.029503087,0.001174175,0.015986081,0.000091449416,0.000057599027,0.00095954177,0.9447102,0.002042463,0.005475413],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908686,0.00019358622,0.00017784371,0.0002341241,0.00020797826,0.00009965297],"domain_scores_gemma":[0.99680746,0.0014070454,0.0003404709,0.00046396334,0.00076574,0.0002153808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007295127,0.0022165934,0.0011259554,0.010896118,0.00071449595,0.0020762496,0.0011458991,0.0014863852,0.03991419],"category_scores_gemma":[0.0060322187,0.00041781555,0.0009605999,0.0050197565,0.00038467092,0.0015682635,0.0013836577,0.00061496056,0.043813493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029227694,0.00052529405,0.024012826,0.007174389,0.00034772657,0.0017343628,0.002565888,0.0026512125,0.019963803,0.0048273513,0.52897733,0.4042971],"study_design_scores_gemma":[0.0003804518,0.00032455416,0.03239535,0.0009101219,0.00028582022,0.0013515034,0.00109662,0.0042030965,0.01068696,0.0028541044,0.9453376,0.00017382574],"about_ca_topic_score_codex":0.013012852,"about_ca_topic_score_gemma":0.012199803,"teacher_disagreement_score":0.03991419,"about_ca_system_score_codex":0.00074599055,"about_ca_system_score_gemma":0.0016235751,"threshold_uncertainty_score":0.13352627},"labels":[],"label_agreement":null},{"id":"W2554172262","doi":"10.3758/s13428-016-0829-7","title":"SyllabO+: A new tool to study sublexical phenomena in spoken Quebec French","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université Laval; Institut Universitaire en Santé Mentale de Québec","funders":"Fonds de Recherche du Québec - Santé; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Université Laval","keywords":"Phonotactics; Computer science; Syllable; Spoken language; Phonology; Psycholinguistics; Speech corpus; Phonetics; Linguistics; Natural language processing; Vocabulary; Artificial intelligence; Psychology; Speech recognition; Cognition; Speech synthesis","score_opus":0.2624615032136157,"score_gpt":0.5939136269055684,"score_spread":0.33145212369195265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554172262","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.866733,0.00046371832,0.063045785,0.00037202568,0.00011325553,0.0014658934,0.01707708,0.0070658647,0.043663327],"genre_scores_gemma":[0.80799353,0.00036727707,0.13439028,0.0002661877,0.000059492868,0.003511591,0.007950488,0.0011424493,0.044318754],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99963856,0.00014138926,0.00001464567,0.00008256306,0.00007751202,0.000045310604],"domain_scores_gemma":[0.998885,0.0006024735,0.00009688525,0.00009114434,0.00019829668,0.00012621934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058047223,0.0005892565,0.00027980973,0.0016768059,0.0007695811,0.00086781644,0.00035922497,0.0003690295,0.01867888],"category_scores_gemma":[0.0015069304,0.00017709062,0.00022121951,0.0007786382,0.00039477693,0.0006466481,0.0008153613,0.00031990337,0.0016652984],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016095884,0.00076440565,0.1207413,0.00077004835,0.00015392304,0.0009029183,0.013571671,0.002097017,0.19356966,0.004804869,0.023762178,0.63725245],"study_design_scores_gemma":[0.00018905954,0.000857558,0.84351724,0.000116539646,0.00014199973,0.001477425,0.0055590454,0.018679155,0.025016384,0.0016173418,0.10262997,0.00019821113],"about_ca_topic_score_codex":0.23951657,"about_ca_topic_score_gemma":0.40381116,"teacher_disagreement_score":0.23951657,"about_ca_system_score_codex":0.0013779398,"about_ca_system_score_gemma":0.00192494,"threshold_uncertainty_score":0.4762448},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2584792315470756,"score_gpt":0.5748492312116953,"score_spread":0.3163699996646197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560525638","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019239362,0.0006931552,0.76319873,0.0001353826,0.00042646303,0.0005890852,0.03622976,0.17464305,0.004845013],"genre_scores_gemma":[0.092937686,0.00047856467,0.83640504,0.00025593815,0.00028891474,0.0028230133,0.048514016,0.008879529,0.009417244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858534,0.00016639824,0.00016321903,0.0004942009,0.0005240886,0.00006675875],"domain_scores_gemma":[0.9955872,0.00199229,0.00067976094,0.00050602935,0.0009931494,0.00024147781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015747463,0.0021129318,0.001353887,0.0054568183,0.00048469266,0.0010897254,0.0018261726,0.0012875366,0.022089813],"category_scores_gemma":[0.007853742,0.0007389298,0.0008900338,0.0019812793,0.00028253978,0.0012035742,0.0015969928,0.00092592643,0.012373251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018036676,0.00036010487,0.009954029,0.0018619112,0.0003406393,0.00047431412,0.00045894808,0.004234981,0.09615938,0.0034072543,0.16607311,0.71487164],"study_design_scores_gemma":[0.0005572612,0.0009405434,0.066731706,0.00038304753,0.000326738,0.0031874056,0.0006055015,0.4444288,0.19956367,0.015679298,0.26688197,0.00071406516],"about_ca_topic_score_codex":0.0018448541,"about_ca_topic_score_gemma":0.0035247314,"teacher_disagreement_score":0.022089813,"about_ca_system_score_codex":0.00045746568,"about_ca_system_score_gemma":0.000950336,"threshold_uncertainty_score":0.07389778},"labels":[],"label_agreement":null},{"id":"W2562201257","doi":"10.3758/s13428-016-0845-7","title":"Q2Stress: A database for multiple cues to stress assignment in Italian","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Stress (linguistics); Lexicon; Orthography; Phonology; Vowel; Natural language processing; Scripting language; Lexical database; Word (group theory); Consonant; Linguistics; Database; Reading (process); Artificial intelligence; Speech recognition","score_opus":0.38679342917853143,"score_gpt":0.623878790254951,"score_spread":0.23708536107641953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562201257","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14529529,0.0014424701,0.01977723,0.00046342044,0.00021633081,0.001194486,0.76852006,0.012668038,0.05042255],"genre_scores_gemma":[0.16291276,0.0011342252,0.033110846,0.0003668975,0.00015453857,0.0041675367,0.78273344,0.0023042427,0.013115594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988733,0.00022028305,0.00026900935,0.00026083604,0.00025738231,0.000119129945],"domain_scores_gemma":[0.99243987,0.002988335,0.0009165048,0.0017277673,0.001378303,0.00054918753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014022066,0.0012785224,0.0009231036,0.0065675997,0.0006148428,0.0014182626,0.0011629714,0.0010419516,0.02422574],"category_scores_gemma":[0.00991645,0.00060065347,0.00055078324,0.0052235266,0.00050925673,0.0021356184,0.0025500597,0.000538091,0.010289059],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036244455,0.00050058175,0.096342064,0.008382802,0.00021722888,0.0016962925,0.010078369,0.0017823004,0.0314006,0.0049503553,0.34566918,0.4953558],"study_design_scores_gemma":[0.00030580742,0.00040240205,0.3210189,0.00043640126,0.0001832841,0.0013265242,0.0020894497,0.0023675426,0.0075060963,0.004042556,0.660018,0.0003029771],"about_ca_topic_score_codex":0.0095440885,"about_ca_topic_score_gemma":0.020079542,"teacher_disagreement_score":0.02422574,"about_ca_system_score_codex":0.00086495106,"about_ca_system_score_gemma":0.0015038026,"threshold_uncertainty_score":0.081043184},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Deception; Psychology; Lie detection; Social psychology; Statement (logic); Computer science; Applied psychology; Linguistics","score_opus":0.3876640780767517,"score_gpt":0.6254059579783624,"score_spread":0.23774187990161072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592069066","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03356159,0.004794057,0.007921842,0.0007871795,0.00028387664,0.0016525036,0.92771935,0.0045503266,0.018729275],"genre_scores_gemma":[0.04409667,0.0016072822,0.010809477,0.00034361274,0.00010309307,0.001972614,0.935697,0.00017906597,0.0051911254],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99942786,0.000080897225,0.00013161406,0.00009982388,0.00019192167,0.000067862406],"domain_scores_gemma":[0.9976084,0.0005212644,0.00034588255,0.0005556221,0.00073474424,0.00023410651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084676297,0.0009339294,0.0007542371,0.003920492,0.0005587267,0.00096405426,0.0016680285,0.0011828853,0.023863457],"category_scores_gemma":[0.0074414876,0.00021787987,0.00032072852,0.0021702193,0.00016941463,0.0012316668,0.001355809,0.00088008697,0.015408311],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077619345,0.00032887465,0.009540844,0.0029170418,0.00006838359,0.0008917954,0.00033568064,0.00090904674,0.0026092036,0.0020491946,0.84179157,0.13778211],"study_design_scores_gemma":[0.00030220483,0.00028682008,0.050644964,0.001060097,0.00012104857,0.0019091192,0.00065492553,0.011185122,0.006023195,0.0036697884,0.9239875,0.00015524248],"about_ca_topic_score_codex":0.006937232,"about_ca_topic_score_gemma":0.010172697,"teacher_disagreement_score":0.023863457,"about_ca_system_score_codex":0.00072144554,"about_ca_system_score_gemma":0.0008513076,"threshold_uncertainty_score":0.07983124},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.5036851353495614,"score_gpt":0.6149425197020493,"score_spread":0.11125738435248789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594456685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9991684,0.00002300604,0.000079445395,0.000035185163,0.0000035020205,0.000043437765,0.000148192,0.0000020016407,0.00049687596],"genre_scores_gemma":[0.9985648,0.000050929848,0.00033002812,0.000053303876,0.000005439879,0.0001063007,0.00038288365,0.000003502095,0.0005027603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995721,0.00010749521,0.000060164188,0.000055251217,0.00014095847,0.00006406124],"domain_scores_gemma":[0.9987465,0.00018049087,0.00037622658,0.000049486058,0.00023335745,0.00041384884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010202719,0.00032868044,0.0003746511,0.0012242578,0.0007616204,0.0005141726,0.00036643058,0.0006697231,0.0015549229],"category_scores_gemma":[0.002629392,0.00023624864,0.00035011716,0.0006184236,0.000372352,0.00060280785,0.0009378336,0.0006782677,0.00040894598],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120324185,0.00039575837,0.99336374,0.000013212563,0.000038164388,0.00019890143,0.0012193918,0.000045594665,0.0015719002,0.00003527956,0.00024321063,0.00275452],"study_design_scores_gemma":[0.000009412405,0.00013957404,0.9984302,0.0000028584268,0.0000060768393,0.0001954175,0.0008213868,0.00010990872,0.000111245965,0.000020487965,0.00014876423,0.0000045698357],"about_ca_topic_score_codex":0.007913302,"about_ca_topic_score_gemma":0.016097918,"teacher_disagreement_score":0.007913302,"about_ca_system_score_codex":0.00050730474,"about_ca_system_score_gemma":0.0005248079,"threshold_uncertainty_score":0.015734434},"labels":[],"label_agreement":null},{"id":"W2596404217","doi":"10.3758/s13428-017-0855-0","title":"Are multiple-trial experiments appropriate for eyewitness identification studies? Accuracy, choosing, and confidence across trials","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Queen Margaret University","keywords":"Eyewitness identification; Psychology; Eyewitness memory; Identification (biology); Confidence interval; Social psychology; Cognitive psychology; Statistics; Computer science; Data mining; Mathematics","score_opus":0.8594029769708219,"score_gpt":0.7296825916912955,"score_spread":0.12972038527952645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596404217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77270806,0.00401631,0.20416555,0.0010987846,0.0016328401,0.0066708024,0.0007124747,0.0004693471,0.008525944],"genre_scores_gemma":[0.80184466,0.0017196378,0.1680163,0.0014568851,0.0005404453,0.02277215,0.0005964644,0.00058500364,0.0024683387],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.87188864,0.09467711,0.012033437,0.007819744,0.012345653,0.001235382],"domain_scores_gemma":[0.64558434,0.24467891,0.051528662,0.046337776,0.00991397,0.0019563595],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.098750606,0.0010338535,0.003450579,0.00084509247,0.0014733361,0.0022092527,0.0022549133,0.0034331603,0.0033147158],"category_scores_gemma":[0.3392801,0.0013237118,0.0013799118,0.0017689797,0.003458539,0.005062003,0.0016921407,0.0026120797,0.00089840835],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.040993832,0.011811708,0.2887201,0.010415955,0.004710446,0.0017915319,0.010625748,0.010945265,0.27254274,0.019471684,0.0057855435,0.32218546],"study_design_scores_gemma":[0.0036884525,0.05203839,0.6993529,0.002154642,0.0018730212,0.0029023937,0.001716333,0.028261313,0.11455218,0.069434896,0.023235114,0.00079030934],"about_ca_topic_score_codex":0.00079819007,"about_ca_topic_score_gemma":0.0023524796,"teacher_disagreement_score":0.9012494,"about_ca_system_score_codex":0.0007723085,"about_ca_system_score_gemma":0.0012656902,"threshold_uncertainty_score":0.52224934},"labels":[],"label_agreement":null},{"id":"W2610034246","doi":"10.3758/s13428-017-0892-8","title":"The Montreal Protocol for Identification of Amusia","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":72,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; International Laboratory for Brain, Music and Sound Research","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Psychology; Neuropsychology; Identification (biology); Protocol (science); Montreal Protocol; Audiology; Neuroscience; Medicine; Cognition; Pathology","score_opus":0.6423844433893441,"score_gpt":0.6825533388179035,"score_spread":0.04016889542855939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610034246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03506372,0.0014404443,0.63503104,0.0015323919,0.0014465089,0.15343612,0.034508422,0.011576022,0.1259654],"genre_scores_gemma":[0.069375224,0.0010924016,0.53746724,0.0015683704,0.00035094016,0.26494884,0.015521631,0.0043539368,0.10532142],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949121,0.0018126401,0.000979265,0.0008221185,0.0009829673,0.00049091125],"domain_scores_gemma":[0.9894225,0.0021776636,0.0005546891,0.0032113416,0.0042786337,0.00035523114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008253913,0.002866574,0.0014644273,0.0037992892,0.0030621951,0.0018648898,0.0019737254,0.002123334,0.1124206],"category_scores_gemma":[0.019223507,0.001055633,0.0017006197,0.0016063811,0.0020765855,0.0014664934,0.00240311,0.002910426,0.028677523],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009988379,0.0025791253,0.010506629,0.0045298743,0.00055398245,0.0031942944,0.00473291,0.003610742,0.06896762,0.065154545,0.26938978,0.55679214],"study_design_scores_gemma":[0.0025036952,0.0027435855,0.047877543,0.0019091791,0.00048765595,0.0034669854,0.0010755584,0.010795152,0.04489689,0.03241475,0.8511002,0.0007287996],"about_ca_topic_score_codex":0.008929566,"about_ca_topic_score_gemma":0.027304636,"teacher_disagreement_score":0.1124206,"about_ca_system_score_codex":0.0013815127,"about_ca_system_score_gemma":0.006975369,"threshold_uncertainty_score":0.3760844},"labels":[],"label_agreement":null},{"id":"W2618664687","doi":"10.3758/s13428-017-0898-2","title":"Scoring best-worst data in unbalanced many-item designs, with applications to crowdsourcing semantic judgments","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Crowdsourcing; Computer science; Set (abstract data type); Rank (graph theory); Scaling; Artificial intelligence; Natural language processing; Scoring rule; Machine learning; Data mining; Quality (philosophy); Information retrieval; Mathematics","score_opus":0.8789947781800274,"score_gpt":0.7240679895118148,"score_spread":0.15492678866821252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618664687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09411725,0.00063828466,0.89841706,0.00053808145,0.00033819606,0.0021509572,0.0005444325,0.00089737435,0.0023584315],"genre_scores_gemma":[0.3825931,0.00015374996,0.6103179,0.00029565283,0.00017477636,0.0040903995,0.0011974854,0.00025442484,0.0009225649],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7003267,0.26524287,0.0069308565,0.016150104,0.0100342315,0.0013152993],"domain_scores_gemma":[0.2824127,0.6634079,0.011052042,0.031165976,0.009726428,0.0022349502],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21904995,0.0040768096,0.0063290056,0.0046851435,0.004283062,0.00647405,0.006368466,0.0055992254,0.005490639],"category_scores_gemma":[0.5381021,0.0024471544,0.0051806387,0.0047824862,0.008037642,0.00556168,0.009930083,0.0053711133,0.000993141],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020048887,0.0043284507,0.05817139,0.004687018,0.0069063343,0.0006883458,0.01451839,0.23922983,0.0053995703,0.12278692,0.010089386,0.51314545],"study_design_scores_gemma":[0.0020664185,0.0019192635,0.010522701,0.00050645316,0.0010013276,0.0001903494,0.0015581211,0.7195421,0.002375032,0.25553143,0.004445189,0.00034157792],"about_ca_topic_score_codex":0.002607078,"about_ca_topic_score_gemma":0.003968242,"teacher_disagreement_score":0.21904995,"about_ca_system_score_codex":0.002589496,"about_ca_system_score_gemma":0.0028709457,"threshold_uncertainty_score":0.9630504},"labels":[],"label_agreement":null},{"id":"W2622780478","doi":"10.3758/s13428-017-0899-1","title":"AGSuite: Software to conduct feature analysis of artificial grammar learning performance","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Natural language processing; Grammaticality; Grammar; Task (project management); Machine learning; String (physics); Levenshtein distance; Linguistics; Mathematics","score_opus":0.4500381688493872,"score_gpt":0.5853024771923007,"score_spread":0.13526430834291348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622780478","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068980776,0.00006974911,0.56876135,0.00013729236,0.00012581509,0.0005848664,0.015561091,0.3408711,0.0049078967],"genre_scores_gemma":[0.34069014,0.00011973164,0.58831143,0.00013223618,0.00009701186,0.005061279,0.02213746,0.03300174,0.010448968],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993569,0.00019688309,0.00006159906,0.00018376671,0.00014898667,0.000051845942],"domain_scores_gemma":[0.99425113,0.004562219,0.0002638361,0.00039420673,0.00042298864,0.00010558844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018403946,0.0011351613,0.0006898814,0.002047289,0.00032607155,0.0009928585,0.0010617888,0.000584409,0.021078838],"category_scores_gemma":[0.0105356565,0.0004788317,0.0009183647,0.0008897942,0.00024014573,0.0011689891,0.0009526664,0.00090550864,0.005469412],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017698004,0.0010273923,0.046640486,0.0010655464,0.00091908063,0.000264365,0.0022538048,0.027063861,0.020611743,0.010078562,0.1740652,0.71424013],"study_design_scores_gemma":[0.0003791347,0.0007295677,0.04796976,0.00010470241,0.00031442672,0.00032441836,0.0003657531,0.83749485,0.03514326,0.019879935,0.05713966,0.00015446988],"about_ca_topic_score_codex":0.0026417898,"about_ca_topic_score_gemma":0.0035229465,"teacher_disagreement_score":0.021078838,"about_ca_system_score_codex":0.0004323713,"about_ca_system_score_gemma":0.0008362896,"threshold_uncertainty_score":0.07051569},"labels":[],"label_agreement":null},{"id":"W2734609056","doi":"10.3758/s13428-017-0941-3","title":"Erratum to: The Montreal Protocol for Identification of Amusia","year":2017,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Nuclear and radioactivity studies","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; International Laboratory for Brain, Music and Sound Research","funders":"","keywords":"Identification (biology); Montreal Protocol; Protocol (science); Psychology; Computer science; Audiology; Medicine; Geography; Biology; Meteorology","score_opus":0.27907645818314236,"score_gpt":0.5741072867000924,"score_spread":0.29503082851695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734609056","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031582452,0.0037233615,0.023433741,0.099459045,0.5924357,0.0064091147,0.06712095,0.004658474,0.19960135],"genre_scores_gemma":[0.009214033,0.003638792,0.025829807,0.043986376,0.012133137,0.007444319,0.028651305,0.0033492697,0.865753],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9899421,0.002490605,0.001903304,0.0006039687,0.0043974617,0.00066269626],"domain_scores_gemma":[0.9507601,0.011271931,0.0015459299,0.004538018,0.030692313,0.0011916476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008155439,0.0014416449,0.0015603951,0.004362964,0.005263965,0.0027010054,0.003522724,0.004764597,0.2232719],"category_scores_gemma":[0.0699967,0.0010159769,0.001065837,0.0019739715,0.0021961222,0.0017823677,0.0025866367,0.006361382,0.11022684],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004666391,0.000018847793,0.00008048557,0.0000795227,0.000002401531,0.000060143208,0.000041228064,0.000011849023,0.00006631317,0.0007814757,0.99197716,0.0068338565],"study_design_scores_gemma":[0.000029819457,0.000024710944,0.0007895333,0.0002949858,0.000009890776,0.00012564534,0.00020013642,0.000060097755,0.00043995533,0.0010344912,0.9969669,0.00002388092],"about_ca_topic_score_codex":0.041795675,"about_ca_topic_score_gemma":0.08853947,"teacher_disagreement_score":0.2232719,"about_ca_system_score_codex":0.0051037977,"about_ca_system_score_gemma":0.012207874,"threshold_uncertainty_score":0.7469189},"labels":[],"label_agreement":null},{"id":"W2743598012","doi":"10.3758/s13428-017-0939-x","title":"Direct-location versus verbal report methods for measuring auditory distance perception in the far field","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; International Laboratory for Brain, Music and Sound Research; Centre for Research on Brain Language and Music; Douglas Mental Health University Institute","funders":"Agencia Nacional de Promoción Científica y Tecnológica; Universidad Nacional de Quilmes; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Perception; Stimulus (psychology); Sound localization; Auditory perception; Modality (human–computer interaction); Psychology; Computer science; Audiology; Set (abstract data type); Cognitive psychology; Artificial intelligence","score_opus":0.5455580172396415,"score_gpt":0.6340813677204105,"score_spread":0.08852335048076898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743598012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7232294,0.0033901923,0.2551931,0.00026819512,0.00063707243,0.0013496473,0.0013186964,0.00047283233,0.014140785],"genre_scores_gemma":[0.80737674,0.0016810185,0.1794335,0.0004263804,0.00027067118,0.0029102338,0.00053147186,0.00021389892,0.0071561877],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98213667,0.010467598,0.001426988,0.0024880765,0.0031064067,0.00037434822],"domain_scores_gemma":[0.9532911,0.03211453,0.0053702225,0.0031271535,0.005384445,0.0007125718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010950345,0.0012180263,0.00067875435,0.0021364803,0.0003959134,0.0016544084,0.0015291469,0.0014279105,0.0052938084],"category_scores_gemma":[0.037038706,0.00050348503,0.0006747613,0.0013067157,0.00088864367,0.0021172403,0.0016502464,0.0009557228,0.0014542456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014241934,0.0029073344,0.33971122,0.0036024568,0.0012717718,0.00034173974,0.006508085,0.0023330343,0.09371227,0.0054034917,0.0025293927,0.5274373],"study_design_scores_gemma":[0.0023686877,0.024777906,0.80860585,0.001424203,0.0022318198,0.0058434745,0.016973617,0.032689728,0.08305499,0.0118479235,0.009209234,0.00097262725],"about_ca_topic_score_codex":0.0014543807,"about_ca_topic_score_gemma":0.0037488402,"teacher_disagreement_score":0.010950345,"about_ca_system_score_codex":0.00039997362,"about_ca_system_score_gemma":0.00063881656,"threshold_uncertainty_score":0.057911634},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Computer science; Cognition; Reflection (computer programming); Psychology; Cognitive psychology; Artificial intelligence; Statistics; Mathematics; Geology; Programming language; Neuroscience","score_opus":0.7821180915133141,"score_gpt":0.736822124123797,"score_spread":0.04529596738951713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747940070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9460854,0.0006967083,0.023522742,0.0010104345,0.00035200943,0.001385583,0.0020899016,0.0005954723,0.024261814],"genre_scores_gemma":[0.97765005,0.0002605048,0.01224771,0.00050711294,0.00011976794,0.0013508389,0.0021556863,0.00017096286,0.005537327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9913571,0.0022767072,0.0012053255,0.0017312554,0.0030239234,0.00040561022],"domain_scores_gemma":[0.96493393,0.012882223,0.009405733,0.006267389,0.005364722,0.0011460276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008213527,0.00074646313,0.0008321976,0.0010363978,0.00053453515,0.0012662038,0.00094480766,0.0012246748,0.0033009474],"category_scores_gemma":[0.06368936,0.0004369469,0.0012626618,0.0007104266,0.0007741544,0.0014505998,0.001626608,0.0021231964,0.0016955095],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003783403,0.0046136603,0.7358806,0.00068217516,0.0017045483,0.0010230753,0.0043789013,0.0020888906,0.015229451,0.0027584916,0.013554043,0.2143028],"study_design_scores_gemma":[0.00013289372,0.0037588673,0.9656218,0.00013527618,0.00020784712,0.0011483604,0.0005847677,0.002429064,0.009443247,0.003673534,0.012737263,0.00012700824],"about_ca_topic_score_codex":0.0012620866,"about_ca_topic_score_gemma":0.0012001873,"teacher_disagreement_score":0.008213527,"about_ca_system_score_codex":0.00034629056,"about_ca_system_score_gemma":0.0007641274,"threshold_uncertainty_score":0.04343778},"labels":[],"label_agreement":null},{"id":"W2751852067","doi":"10.3758/s13428-020-01355-x","title":"Two-stage maximum likelihood approach for item-level missing data in regression","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Imputation (statistics); Statistics; Univariate; Regression; Scale (ratio); Regression analysis; Context (archaeology); Econometrics; Restricted maximum likelihood; Mathematics; Computer science; Maximum likelihood; Multivariate statistics","score_opus":0.9595380073134077,"score_gpt":0.7275446994992708,"score_spread":0.23199330781413685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751852067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019699666,0.00016291556,0.99698156,0.00015692275,0.000019814515,0.00011467636,0.00009407156,0.0002967718,0.0002032097],"genre_scores_gemma":[0.090839125,0.00029894782,0.9053986,0.00018088784,0.00009097347,0.0012390965,0.00060815003,0.00024361485,0.0011005786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9556571,0.03726556,0.0013664345,0.0030407826,0.0020923184,0.0005778572],"domain_scores_gemma":[0.9100125,0.0771713,0.0030988476,0.005193916,0.0040070494,0.0005163616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04936585,0.0017889597,0.0037912433,0.0029172297,0.0013963047,0.0025147519,0.0076553808,0.003670517,0.0058030607],"category_scores_gemma":[0.13754426,0.0022906458,0.0034341686,0.004700605,0.0018836618,0.004051789,0.0038183571,0.0058960887,0.001702246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001212655,0.00052611146,0.020776657,0.0018243126,0.0019174094,0.0009162758,0.0032187675,0.40816456,0.0023407151,0.21119876,0.008187303,0.3397164],"study_design_scores_gemma":[0.00020707291,0.00021805175,0.0015297283,0.00013018354,0.00012404939,0.00018418621,0.000122001744,0.8963305,0.0010023544,0.0958432,0.0042177313,0.00009099168],"about_ca_topic_score_codex":0.0053475252,"about_ca_topic_score_gemma":0.0052342885,"teacher_disagreement_score":0.04936585,"about_ca_system_score_codex":0.001590261,"about_ca_system_score_gemma":0.0051692906,"threshold_uncertainty_score":0.26107466},"labels":[],"label_agreement":null},{"id":"W2756024538","doi":"10.3758/s13428-017-0962-y","title":"Norms for 10,491 Spanish words for five discrete emotions: Happiness, disgust, anger, fear, and sadness","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotions and Moral Behavior","field":"Psychology","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Comunidad de Madrid","keywords":"Sadness; Disgust; Anger; Happiness; Psychology; Emotion classification; Set (abstract data type); Social psychology; Cognitive psychology; Computer science","score_opus":0.4337136039477885,"score_gpt":0.6410584227082299,"score_spread":0.20734481876044136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756024538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87489676,0.0011509992,0.018290317,0.0006741211,0.0008680745,0.0027613672,0.027818786,0.0004616164,0.07307801],"genre_scores_gemma":[0.8603799,0.0014692813,0.046800405,0.0006664385,0.00028800385,0.018776013,0.04542426,0.00073535385,0.025460383],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99494815,0.0017541589,0.0009928782,0.0006500246,0.0014023598,0.00025239718],"domain_scores_gemma":[0.9781885,0.0063049654,0.0018908745,0.0010977592,0.012039492,0.00047847972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055099507,0.00074755447,0.00045507445,0.0023489045,0.00070808287,0.0012530355,0.00043060986,0.0005655578,0.0066270945],"category_scores_gemma":[0.021038309,0.000181815,0.0005295835,0.0014603212,0.00072095863,0.00059130724,0.00088586984,0.00084552413,0.0026167475],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003161256,0.00171299,0.5655939,0.001648046,0.0005178525,0.0006341461,0.030349122,0.0014017157,0.025493251,0.008173948,0.049513448,0.3118003],"study_design_scores_gemma":[0.0002721409,0.0007034115,0.88401383,0.0005150894,0.00018250458,0.0006803007,0.015887046,0.0015099364,0.006099715,0.0034574363,0.08651295,0.00016558224],"about_ca_topic_score_codex":0.0075185467,"about_ca_topic_score_gemma":0.01328776,"teacher_disagreement_score":0.0075185467,"about_ca_system_score_codex":0.001186497,"about_ca_system_score_gemma":0.0011728196,"threshold_uncertainty_score":0.029139817},"labels":[],"label_agreement":null},{"id":"W2759584423","doi":"10.3758/s13428-018-1097-5","title":"Quaddles: A multidimensional 3-D object set with parametrically controlled and customizable features","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Object (grammar); Scripting language; Feature (linguistics); Set (abstract data type); Artificial intelligence; Task (project management); Computer vision; Feature vector; Human–computer interaction; Parametric statistics; Scratch; Pattern recognition (psychology); Programming language; Mathematics","score_opus":0.17297376419914134,"score_gpt":0.5344835669519601,"score_spread":0.36150980275281874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759584423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026925478,0.00020026087,0.962325,0.00015744925,0.00010307139,0.00034857134,0.0018807717,0.0065324074,0.0015269589],"genre_scores_gemma":[0.16361248,0.0003128006,0.82753927,0.00022642256,0.000030887182,0.000843356,0.0032127642,0.0016570264,0.0025650284],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995301,0.00008053537,0.000034021887,0.00013258753,0.00018499487,0.000037702423],"domain_scores_gemma":[0.9991486,0.00032136234,0.00006392952,0.00024695272,0.00009208133,0.00012702766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005794195,0.0010092013,0.0012021965,0.0009735261,0.00038167325,0.001139307,0.0033510525,0.000810534,0.007140902],"category_scores_gemma":[0.0024961862,0.0010809925,0.0017441715,0.00065166096,0.000687153,0.0012829761,0.0038417059,0.0010097394,0.0014965414],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013073735,0.0008110625,0.0054010046,0.0019800416,0.00061189465,0.00089187274,0.0012026369,0.12224598,0.23410541,0.034665667,0.030637216,0.5661398],"study_design_scores_gemma":[0.00023405282,0.000663551,0.006274196,0.00012417392,0.00016449635,0.001325605,0.00016513452,0.856153,0.06357953,0.02649029,0.044607677,0.00021825838],"about_ca_topic_score_codex":0.0024544788,"about_ca_topic_score_gemma":0.003933524,"teacher_disagreement_score":0.007140902,"about_ca_system_score_codex":0.0004913372,"about_ca_system_score_gemma":0.00072663807,"threshold_uncertainty_score":0.023888707},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4441928567752986,"score_gpt":0.6216715043181028,"score_spread":0.17747864754280424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767253414","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1175276,0.0018524932,0.027540125,0.00025846626,0.00015774748,0.00042620016,0.80382663,0.021166699,0.027244024],"genre_scores_gemma":[0.11350437,0.0010436663,0.05133908,0.00014560032,0.00005689753,0.00071057957,0.8212679,0.004663669,0.0072682546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994455,0.000060105533,0.00017054043,0.00016308317,0.00012360394,0.00003729145],"domain_scores_gemma":[0.99833715,0.0006928494,0.00018488054,0.0002860522,0.00040782188,0.00009122771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005345494,0.0013962834,0.0006942178,0.0064527965,0.0007383694,0.001556754,0.0009707836,0.0008658857,0.045254063],"category_scores_gemma":[0.0035619591,0.0007038185,0.0007012055,0.0038373088,0.00039314752,0.002772944,0.002003624,0.00065489195,0.031931136],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024570206,0.0004790391,0.028946225,0.0066138078,0.00032232646,0.0043522813,0.0039861626,0.0017207812,0.07219281,0.0125908125,0.35127386,0.5150648],"study_design_scores_gemma":[0.00042074663,0.00027430957,0.087035924,0.000720069,0.0004026575,0.0065187053,0.0020090928,0.006047578,0.030514374,0.008944221,0.856871,0.00024125546],"about_ca_topic_score_codex":0.0021110605,"about_ca_topic_score_gemma":0.0032979916,"teacher_disagreement_score":0.045254063,"about_ca_system_score_codex":0.0003870396,"about_ca_system_score_gemma":0.0013611944,"threshold_uncertainty_score":0.1513899},"labels":[],"label_agreement":null},{"id":"W2772107854","doi":"10.3758/s13428-017-0983-6","title":"Trajectory analysis of discrete goal-directed pointing movements: How many trials are needed for reliable data?","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Trajectory; Reliability (semiconductor); Clinical trial; Computer science; Movement (music); Statistics; Psychology; Physical medicine and rehabilitation; Mathematics; Medicine","score_opus":0.6192949276183322,"score_gpt":0.5981432500761731,"score_spread":0.021151677542159075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772107854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1763416,0.002900878,0.81308204,0.0011118011,0.00041712032,0.0003546441,0.0015845335,0.0023457347,0.0018616007],"genre_scores_gemma":[0.64117754,0.0012344288,0.35056123,0.00037762334,0.00018860462,0.0011111792,0.00235754,0.0016503287,0.0013415044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99366486,0.0029243054,0.0008245547,0.0010030875,0.0013108739,0.00027229308],"domain_scores_gemma":[0.95469534,0.027098678,0.0023700418,0.009118013,0.005989342,0.0007286543],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011391689,0.00094478735,0.0025004132,0.0009455011,0.0010624191,0.0016581994,0.0017641808,0.0024635098,0.003143435],"category_scores_gemma":[0.075775124,0.00100232,0.00082888006,0.0017070051,0.0013364436,0.0033736452,0.0010862383,0.0020484086,0.0015937027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042308015,0.0008410829,0.04564,0.0023810554,0.00173499,0.00036112167,0.0010127227,0.052844666,0.1754693,0.0077060126,0.009901561,0.69787675],"study_design_scores_gemma":[0.0008262023,0.0023006436,0.23444186,0.0011038146,0.0010913679,0.0016021344,0.0011445642,0.57862514,0.08255262,0.0734829,0.022280216,0.0005485037],"about_ca_topic_score_codex":0.004347091,"about_ca_topic_score_gemma":0.011389696,"teacher_disagreement_score":0.9886083,"about_ca_system_score_codex":0.0004620723,"about_ca_system_score_gemma":0.0012699722,"threshold_uncertainty_score":0.060245693},"labels":[],"label_agreement":null},{"id":"W2783136253","doi":"10.3758/s13428-017-1009-0","title":"When is best-worst best? A comparison of best-worst scaling, numeric estimation, and rating scales for collection of semantic norms","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Computer science; Best practice; Scaling; Generalizability theory; Norm (philosophy); Valence (chemistry); Natural language processing; Psychology; Scale (ratio); Data collection; Cognitive psychology; Artificial intelligence; Statistics; Mathematics","score_opus":0.23785970297431935,"score_gpt":0.5684250069755211,"score_spread":0.33056530400120177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783136253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31936538,0.010819681,0.59551036,0.007026834,0.0042263214,0.003974127,0.0034935435,0.0019138549,0.053669788],"genre_scores_gemma":[0.6797738,0.0018466634,0.30938816,0.0007094188,0.0003797688,0.0038432314,0.0019623586,0.0009348057,0.0011617634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.81375206,0.12372868,0.017980961,0.0081827715,0.034971394,0.001384011],"domain_scores_gemma":[0.49869165,0.3674884,0.025118895,0.044735476,0.06049481,0.003470749],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17326522,0.0010028572,0.002442636,0.0059020254,0.0022076387,0.007149955,0.0032698277,0.0018905398,0.004211255],"category_scores_gemma":[0.52327657,0.0008041553,0.0025420962,0.0051187584,0.005587887,0.010459887,0.0043795146,0.0031677897,0.0009718807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008605566,0.0011115209,0.13802241,0.003499122,0.0021960826,0.00012351987,0.023995973,0.003999493,0.0034988218,0.127174,0.03360535,0.65416807],"study_design_scores_gemma":[0.0017947264,0.0072849183,0.43567502,0.0073429127,0.0032882725,0.0016682344,0.036487322,0.07627588,0.013529755,0.30775,0.106907755,0.0019952636],"about_ca_topic_score_codex":0.0021772615,"about_ca_topic_score_gemma":0.0048033274,"teacher_disagreement_score":0.8267348,"about_ca_system_score_codex":0.0029554737,"about_ca_system_score_gemma":0.00349828,"threshold_uncertainty_score":0.91632503},"labels":[],"label_agreement":null},{"id":"W2785261305","doi":"10.3758/s13428-018-1016-9","title":"Reliability of the sliding scale for collecting affective responses to words","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Color perception and design","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research and Innovation; Social Sciences and Humanities Research Council of Canada; National Institutes of Health; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Reliability (semiconductor); Scale (ratio); Computer science; Psychology; Reliability engineering; Cognitive psychology; Applied psychology; Engineering","score_opus":0.4810218303105388,"score_gpt":0.6599140794620999,"score_spread":0.1788922491515611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785261305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88864785,0.0005746897,0.09378884,0.00020800743,0.0007195421,0.0016590325,0.0008518591,0.00047685378,0.013073336],"genre_scores_gemma":[0.96075153,0.0001585902,0.035039335,0.00014646746,0.00010663959,0.0013732001,0.00085445616,0.00022815765,0.0013417808],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97163445,0.012753866,0.0035796368,0.0028396954,0.008502528,0.0006897341],"domain_scores_gemma":[0.89303374,0.05938467,0.004813546,0.013610145,0.02790283,0.0012550635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029156122,0.0006169872,0.000572459,0.00155344,0.00066118245,0.001131972,0.0006600982,0.0010127733,0.0016504367],"category_scores_gemma":[0.08781897,0.0005329123,0.0012711629,0.00078237447,0.0012413799,0.00088262145,0.0010261001,0.0009851712,0.0011603804],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047532837,0.0013916391,0.7315134,0.000677888,0.0009039817,0.00014881555,0.012521957,0.0034641812,0.05462066,0.0044725467,0.006906331,0.17862535],"study_design_scores_gemma":[0.00017433487,0.00299053,0.96432453,0.0001553531,0.00027851728,0.00041657203,0.001753383,0.009114902,0.01206845,0.001959697,0.006640481,0.0001232865],"about_ca_topic_score_codex":0.0013994477,"about_ca_topic_score_gemma":0.0022195955,"teacher_disagreement_score":0.029156122,"about_ca_system_score_codex":0.0004860103,"about_ca_system_score_gemma":0.0008155676,"threshold_uncertainty_score":0.15419412},"labels":[],"label_agreement":null},{"id":"W2788006214","doi":"10.3758/s13428-018-1020-0","title":"Validating a visual version of the metronome response task","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metronome; Mind-wandering; Task (project management); Modalities; Psychology; Modality (human–computer interaction); Context (archaeology); Cognitive psychology; Stimulus modality; Audiology; Rhythm; Computer science; Cognition; Neuroscience; Artificial intelligence; Medicine; Sensory system","score_opus":0.37594949032883684,"score_gpt":0.604832009901961,"score_spread":0.2288825195731241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788006214","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77579665,0.00015625331,0.20441082,0.00030027083,0.00067143404,0.0020768552,0.0020306841,0.0017610044,0.012796016],"genre_scores_gemma":[0.88419706,0.000120211895,0.10317492,0.00065769214,0.000100458325,0.003345491,0.0017103318,0.00049839565,0.00619543],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968702,0.0013430385,0.00025759253,0.00064705353,0.0007166493,0.00016535299],"domain_scores_gemma":[0.9871701,0.0077851876,0.001066232,0.0013324214,0.00227635,0.0003697366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033380445,0.0007782821,0.00036357882,0.00050290924,0.0002774529,0.0009025258,0.0010206831,0.0013904222,0.004732302],"category_scores_gemma":[0.030195275,0.00026665808,0.00037998433,0.00020694411,0.00050224335,0.0007967743,0.0011365094,0.00054777967,0.0019880608],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010686531,0.0056509916,0.083665684,0.0014983265,0.00046184877,0.00044117184,0.003098581,0.013133656,0.5073678,0.0067105326,0.010952116,0.35633275],"study_design_scores_gemma":[0.0041408553,0.016408574,0.54510653,0.000519085,0.00066332234,0.002818128,0.0019732772,0.15955989,0.22060654,0.013659546,0.03398646,0.00055786065],"about_ca_topic_score_codex":0.001525933,"about_ca_topic_score_gemma":0.0021495833,"teacher_disagreement_score":0.004732302,"about_ca_system_score_codex":0.0002821653,"about_ca_system_score_gemma":0.00058396073,"threshold_uncertainty_score":0.017653465},"labels":[],"label_agreement":null},{"id":"W2788032477","doi":"10.3758/s13428-018-1024-9","title":"Methods for the effective study of collective behavior in a radial arm maze","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Army Research Office; Office of Naval Research; Fonds De La Recherche Scientifique - FNRS; National Science Foundation","keywords":"Categorization; Set (abstract data type); Context (archaeology); Radial arm maze; Computer science; Artificial intelligence; Cohesion (chemistry); Cognitive psychology; Psychology; Machine learning; Cognition; Neuroscience; Working memory","score_opus":0.352439896981346,"score_gpt":0.608060397139158,"score_spread":0.25562050015781207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788032477","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005721383,0.0002226235,0.9923078,0.0000924935,0.000036520138,0.000046477926,0.000054852924,0.00016475059,0.00135297],"genre_scores_gemma":[0.119813286,0.00093430345,0.8727386,0.0001002333,0.000089147725,0.000985902,0.00014942739,0.00022823906,0.0049609053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995827,0.00017888869,0.000020824815,0.00006768734,0.00011919318,0.000030737716],"domain_scores_gemma":[0.99874383,0.00063856895,0.00016946062,0.00027292402,0.00009300724,0.000082295555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001122969,0.00083913,0.00067802117,0.0009304189,0.0004789956,0.0006105609,0.0014002249,0.00077499833,0.0026380068],"category_scores_gemma":[0.00315118,0.00038002236,0.0006595316,0.00041478203,0.0009498156,0.0009260358,0.0014682631,0.0014500481,0.00072354625],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039172132,0.00040820258,0.0020918217,0.00088588306,0.00027470267,0.00017764814,0.00046136268,0.10575127,0.16382214,0.46154562,0.0040134583,0.26017615],"study_design_scores_gemma":[0.00014004712,0.0001845983,0.0013146615,0.000072431336,0.000050117298,0.00017634057,0.000063305524,0.7368517,0.017154016,0.22991093,0.014009112,0.000072736875],"about_ca_topic_score_codex":0.0008181885,"about_ca_topic_score_gemma":0.0010068973,"teacher_disagreement_score":0.0026380068,"about_ca_system_score_codex":0.0003692855,"about_ca_system_score_gemma":0.00055431767,"threshold_uncertainty_score":0.008825004},"labels":[],"label_agreement":null},{"id":"W2788543801","doi":"10.3758/s13428-018-1015-x","title":"iTemplate: A template-based eye movement data analysis approach","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Foundation for the National Institutes of Health","keywords":"Computer science; Eye movement; Consistency (knowledge bases); Eye tracking; Artificial intelligence; Software; Process (computing); Set (abstract data type); Data set; Data mining; Computer vision","score_opus":0.4956475261834326,"score_gpt":0.6034427315023565,"score_spread":0.10779520531892389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788543801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004692495,0.000065172535,0.9743465,0.000055523305,0.000060816812,0.0010143659,0.0049899854,0.013601675,0.0011735634],"genre_scores_gemma":[0.021564946,0.000057120516,0.968031,0.00004199337,0.000014564738,0.0022796288,0.0043557296,0.0012819684,0.0023731599],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99582076,0.0013814614,0.0005018851,0.00112237,0.0009971715,0.00017628033],"domain_scores_gemma":[0.9916163,0.0041860626,0.0004559629,0.0011266317,0.0024551689,0.00015985072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059769102,0.0025644726,0.0013380954,0.0043048845,0.0007610607,0.0026741694,0.0029542237,0.001129813,0.020891853],"category_scores_gemma":[0.017428141,0.0011238701,0.0021632265,0.003639573,0.0003576942,0.0020778882,0.0030120355,0.0013539825,0.009814167],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009805745,0.00054597907,0.01244164,0.0015114351,0.0013311263,0.00015485245,0.0013183104,0.003733129,0.040210254,0.0063899364,0.03433342,0.89704937],"study_design_scores_gemma":[0.0006463669,0.0021569198,0.09902254,0.0006108635,0.0023265504,0.0014424012,0.0029863117,0.5712283,0.1252696,0.03306238,0.16056961,0.0006780951],"about_ca_topic_score_codex":0.004301932,"about_ca_topic_score_gemma":0.009234304,"teacher_disagreement_score":0.020891853,"about_ca_system_score_codex":0.0005680326,"about_ca_system_score_gemma":0.0021325226,"threshold_uncertainty_score":0.0698902},"labels":[],"label_agreement":null},{"id":"W2791802454","doi":"10.3758/s13428-018-1028-5","title":"Picture perfect: A stimulus set of 225 pairs of matched clipart and photographic images normed by Mechanical Turk and laboratory participants","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Multisensory perception and integration","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Normative; Artificial intelligence; Stimulus (psychology); Computer science; Set (abstract data type); Psychology; Modal; Computer vision; Pattern recognition (psychology); Cognitive psychology","score_opus":0.27826937664833906,"score_gpt":0.5845073464812839,"score_spread":0.3062379698329448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791802454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96921176,0.00028166352,0.008547958,0.00009371604,0.00010202958,0.002395839,0.0072319903,0.00024868193,0.011886416],"genre_scores_gemma":[0.9659091,0.00013090913,0.015065904,0.00023522017,0.000060408496,0.0037615637,0.010324506,0.00010938733,0.004402915],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990397,0.00022242626,0.00016333972,0.00025957584,0.00026195575,0.000052909927],"domain_scores_gemma":[0.99769574,0.0005496706,0.00027015194,0.0007718897,0.0004971651,0.00021538204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083897257,0.00059034483,0.00041178783,0.0004779744,0.000616405,0.0006046638,0.0005868141,0.00062826136,0.012766938],"category_scores_gemma":[0.0054243393,0.0002589624,0.00027982547,0.000356502,0.0006405923,0.0005683898,0.001075089,0.00033916466,0.0019041246],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025907528,0.009486727,0.17476656,0.004555875,0.00089576485,0.0038506004,0.015484544,0.0034983596,0.4369663,0.01429804,0.058709282,0.25158048],"study_design_scores_gemma":[0.0008238,0.004513421,0.8631676,0.0001673972,0.0002498189,0.00602918,0.0048130117,0.003809921,0.04931346,0.0050128414,0.06177219,0.00032733296],"about_ca_topic_score_codex":0.0016536595,"about_ca_topic_score_gemma":0.002608259,"teacher_disagreement_score":0.012766938,"about_ca_system_score_codex":0.00039076494,"about_ca_system_score_gemma":0.0002075559,"threshold_uncertainty_score":0.04270965},"labels":[],"label_agreement":null},{"id":"W2805269870","doi":"10.3758/s13428-018-1058-z","title":"Procura-PALavras (P-PAL): A Web-based interface for a new European Portuguese lexical database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Lexical database; Word lists by frequency; Bigram; Unicode; Natural language processing; Pronunciation; Vowel; Syllable; Word (group theory); Speech recognition; Artificial intelligence; Sentence; Linguistics; Trigram; WordNet","score_opus":0.3698592726057386,"score_gpt":0.6163019402785802,"score_spread":0.24644266767284162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805269870","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036869418,0.0021333534,0.44088694,0.0013003738,0.00089335593,0.0018744788,0.12360633,0.3321482,0.06028755],"genre_scores_gemma":[0.22541153,0.0027178219,0.421817,0.0015004,0.00031224787,0.0032752692,0.20765467,0.083487816,0.053823322],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998835,0.0002202284,0.00033240972,0.0002848875,0.00025033808,0.00007718766],"domain_scores_gemma":[0.9952514,0.0026100301,0.00023527947,0.000915611,0.00058013253,0.0004074712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002537746,0.0019074234,0.0015398229,0.0038039829,0.00081254856,0.005258036,0.0018943261,0.0014872993,0.06580779],"category_scores_gemma":[0.011125207,0.0009963575,0.000973202,0.0024658216,0.00046294281,0.009216691,0.0054209246,0.0014879516,0.027280085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039955145,0.0007271412,0.006347975,0.0059578205,0.00030114444,0.0022332186,0.005492201,0.0013113805,0.02884266,0.027837327,0.29922405,0.61772954],"study_design_scores_gemma":[0.00073854293,0.0002746465,0.007867202,0.001066522,0.00024137682,0.0019801175,0.0015079278,0.015541914,0.017478827,0.020597802,0.93237007,0.00033502202],"about_ca_topic_score_codex":0.00243937,"about_ca_topic_score_gemma":0.0028388803,"teacher_disagreement_score":0.06580779,"about_ca_system_score_codex":0.00059111987,"about_ca_system_score_gemma":0.0011860315,"threshold_uncertainty_score":0.22014898},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3306016750896725,"score_gpt":0.644614645825324,"score_spread":0.31401297073565154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809193001","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08666587,0.0017813543,0.03265925,0.0004046365,0.0002642782,0.00070933875,0.8384776,0.01837487,0.020662772],"genre_scores_gemma":[0.14777218,0.00069287966,0.036642708,0.00026159754,0.00012210818,0.0017164504,0.8034151,0.0014075328,0.007969461],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906915,0.0001672714,0.00018721916,0.00024721207,0.00025618004,0.00007296063],"domain_scores_gemma":[0.9958144,0.0015379988,0.00028553134,0.0015019341,0.00052395335,0.0003361862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007960386,0.00090886763,0.0008306974,0.0024647499,0.0004244027,0.0016112659,0.0015352431,0.0009837755,0.037703846],"category_scores_gemma":[0.009585023,0.00043878364,0.00052474614,0.0018964306,0.0003128603,0.0015250985,0.0025390368,0.0007789551,0.026406547],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061171334,0.0011332439,0.028906731,0.0023693414,0.00032326227,0.0010689292,0.00055568555,0.004066481,0.018057896,0.008191705,0.42139417,0.5078155],"study_design_scores_gemma":[0.0020363797,0.0011668846,0.09397151,0.00061102136,0.00050327874,0.0029309958,0.00084490073,0.0391185,0.03798006,0.036613744,0.7838742,0.00034841555],"about_ca_topic_score_codex":0.0027552212,"about_ca_topic_score_gemma":0.0038267334,"teacher_disagreement_score":0.037703846,"about_ca_system_score_codex":0.0002976558,"about_ca_system_score_gemma":0.0011835644,"threshold_uncertainty_score":0.12613189},"labels":[],"label_agreement":null},{"id":"W2810761248","doi":"10.3758/s13428-018-1073-0","title":"Are mind wandering rates an artifact of the probe-caught method? Using self-caught mind wandering in the classroom to test, and reject, this possibility","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mind-wandering; Artifact (error); Consistency (knowledge bases); Psychology; Reliability (semiconductor); Range (aeronautics); Test (biology); Cognitive psychology; Computer science; Artificial intelligence; Ecology; Engineering","score_opus":0.4103673811000614,"score_gpt":0.5647695724099545,"score_spread":0.15440219130989313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810761248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77795106,0.0011095928,0.19835171,0.0016195414,0.0008866733,0.0012319892,0.0004041541,0.0006189074,0.017826343],"genre_scores_gemma":[0.9541953,0.00021427071,0.041016985,0.00090326305,0.00016876028,0.001166094,0.00019209429,0.00021747484,0.0019256145],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97123194,0.014775997,0.0022336582,0.004563055,0.006664486,0.00053089566],"domain_scores_gemma":[0.7921899,0.1356023,0.027966669,0.03531767,0.007729289,0.0011941175],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03389131,0.0007091127,0.0007680521,0.0010040087,0.0008162347,0.0022499615,0.0019192612,0.0014751091,0.0026572226],"category_scores_gemma":[0.25449735,0.00065675925,0.00088522944,0.0006383099,0.0024323252,0.0027112362,0.002332194,0.0023221767,0.0005971987],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054233926,0.0030801115,0.65737253,0.0017978668,0.0025982258,0.0007323403,0.024142675,0.0017747728,0.03794556,0.02704231,0.004228841,0.23386142],"study_design_scores_gemma":[0.0006499716,0.007585106,0.8838405,0.0007216381,0.0022479917,0.0027956385,0.0043122903,0.019598158,0.038375255,0.026883353,0.012719547,0.00027061612],"about_ca_topic_score_codex":0.001441982,"about_ca_topic_score_gemma":0.001428892,"teacher_disagreement_score":0.9661087,"about_ca_system_score_codex":0.0004944359,"about_ca_system_score_gemma":0.0008874591,"threshold_uncertainty_score":0.17923647},"labels":[],"label_agreement":null},{"id":"W2811114800","doi":"10.3758/s13428-018-1072-1","title":"Getting a grip on sensorimotor effects in lexical–semantic processing","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Semantic memory; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Cognition; Neuroscience","score_opus":0.22385796623857343,"score_gpt":0.5820056502941934,"score_spread":0.3581476840556199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811114800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55574006,0.009017367,0.28169087,0.011862116,0.0013751175,0.0004113135,0.0008426086,0.0007557591,0.13830484],"genre_scores_gemma":[0.89554495,0.003704357,0.0831511,0.003091062,0.0012997044,0.0010638403,0.00030452598,0.0008088926,0.011031668],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99700373,0.0014210978,0.00018541017,0.0005733197,0.00065136544,0.00016509999],"domain_scores_gemma":[0.97501296,0.019269004,0.0007356961,0.0037333046,0.0008066425,0.0004423353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008400643,0.0010541787,0.00082713796,0.0020712279,0.00062374404,0.0027198663,0.0012670513,0.0013346843,0.024917917],"category_scores_gemma":[0.046869315,0.0009449264,0.0007020011,0.0008989974,0.00402622,0.0066454075,0.0029828986,0.0030252063,0.0015302546],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032595766,0.0012928997,0.0075905477,0.0028898693,0.00051820575,0.0005084635,0.006265359,0.003212638,0.26203403,0.2663975,0.0063690455,0.43966183],"study_design_scores_gemma":[0.0009262082,0.0021053057,0.15223047,0.001160494,0.00072315935,0.001293245,0.0023916778,0.010050276,0.05359914,0.7488417,0.026352318,0.00032601267],"about_ca_topic_score_codex":0.0006625629,"about_ca_topic_score_gemma":0.0008614345,"teacher_disagreement_score":0.024917917,"about_ca_system_score_codex":0.0004242419,"about_ca_system_score_gemma":0.0005953475,"threshold_uncertainty_score":0.083358765},"labels":[],"label_agreement":null},{"id":"W2883349086","doi":"10.3758/s13428-018-1071-2","title":"Historical evolution of concrete and abstract language revisited","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Concreteness; Semantics (computer science); Cognition; Word (group theory); Computer science; Cognitive psychology; Linguistics; Psychology; Philosophy","score_opus":0.21497517597533058,"score_gpt":0.5804888822575975,"score_spread":0.365513706282267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883349086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49451813,0.057455193,0.04245194,0.07881504,0.0018649687,0.0003055793,0.00079127715,0.00022035885,0.32357758],"genre_scores_gemma":[0.9735782,0.007322509,0.007421401,0.002598908,0.0006981461,0.000120489196,0.0001051541,0.00016304845,0.007992085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9878493,0.0062601287,0.00070478884,0.003185819,0.0013024552,0.0006975035],"domain_scores_gemma":[0.9442058,0.03542651,0.0034818565,0.0035811835,0.0114633115,0.0018412513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024440002,0.0006460524,0.000993432,0.0070859804,0.0030510603,0.0062502623,0.0018914785,0.0030380993,0.01453293],"category_scores_gemma":[0.04601671,0.0008119096,0.0004302582,0.0041648536,0.03573347,0.008926541,0.0030779073,0.005514638,0.0009603921],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030034184,0.00019593463,0.00969754,0.0004556142,0.0000783561,0.0003550399,0.042365294,0.0011601704,0.002355909,0.84652334,0.0024354304,0.094077],"study_design_scores_gemma":[0.00028144903,0.00059838616,0.12585892,0.0031178088,0.00019399094,0.0019213541,0.040401246,0.005010297,0.0076389606,0.3841169,0.4304582,0.00040251864],"about_ca_topic_score_codex":0.02343521,"about_ca_topic_score_gemma":0.022154003,"teacher_disagreement_score":0.024440002,"about_ca_system_score_codex":0.011646784,"about_ca_system_score_gemma":0.0041900277,"threshold_uncertainty_score":0.12925267},"labels":[],"label_agreement":null},{"id":"W2885774321","doi":"10.3758/s13428-018-1083-y","title":"Argus: An open-source and flexible software application for automated quantification of behavior during social interaction in adult zebrafish","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Celiac Association; Université de Montréal; Dairy Farmers of Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Argus; Computer science; Software; Graphical user interface; Zebrafish; Human–computer interaction; Coding (social sciences); Artificial intelligence; Programming language; Biology; Statistics","score_opus":0.15138408359917835,"score_gpt":0.5581043177640113,"score_spread":0.40672023416483294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885774321","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05935037,0.00036445685,0.37948182,0.00023385754,0.00016180257,0.0004301793,0.01942226,0.5363151,0.0042402144],"genre_scores_gemma":[0.296365,0.00054567005,0.6148814,0.0007633815,0.00013272357,0.0034456076,0.024693945,0.044693783,0.014478356],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995602,0.00003073087,0.000034569213,0.0001344674,0.00018825442,0.000051731226],"domain_scores_gemma":[0.9994246,0.00022002283,0.00010789157,0.00008310288,0.000091578004,0.00007280035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007703185,0.0012455875,0.0009611977,0.0015662346,0.0005264879,0.00064083864,0.0018244914,0.0008395947,0.010992431],"category_scores_gemma":[0.0014769766,0.0007339295,0.00086762797,0.0005577517,0.0005160248,0.00086826883,0.001945667,0.00089922274,0.0030790018],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001624437,0.00034141683,0.024324616,0.0017043733,0.000648422,0.00066044397,0.0009249133,0.0114014,0.44521493,0.004470716,0.12143866,0.38724568],"study_design_scores_gemma":[0.00059406605,0.0005011419,0.08857145,0.00035076932,0.00033809582,0.0010528826,0.00022498166,0.3809681,0.38991514,0.008164389,0.1286846,0.00063436606],"about_ca_topic_score_codex":0.004190072,"about_ca_topic_score_gemma":0.0061462102,"teacher_disagreement_score":0.010992431,"about_ca_system_score_codex":0.00061531935,"about_ca_system_score_gemma":0.001191978,"threshold_uncertainty_score":0.036773384},"labels":[],"label_agreement":null},{"id":"W2887699552","doi":"10.3758/s13428-018-1089-5","title":"Probability of bivariate superiority: A non-parametric common-language statistic for detecting bivariate relationships","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Manitoba","funders":"","keywords":"Bivariate analysis; Copula (linguistics); Bivariate data; Nonparametric statistics; Statistic; Statistics; Parametric statistics; Estimator; Mathematics; Parametric model; Monte Carlo method; Correlation; Joint probability distribution; Econometrics; Computer science","score_opus":0.6911867135990772,"score_gpt":0.6567988206342216,"score_spread":0.03438789296485567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887699552","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22700693,0.00054950005,0.7585297,0.00082628144,0.0003673269,0.0010700751,0.0033014996,0.0013663726,0.006982283],"genre_scores_gemma":[0.8344484,0.00017031933,0.15996635,0.00033582211,0.00032326448,0.0023083787,0.0012816874,0.00028296214,0.00088271947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.923877,0.04700973,0.0048846686,0.011982354,0.010899081,0.0013472128],"domain_scores_gemma":[0.38533005,0.56025594,0.019255554,0.027098367,0.005847707,0.0022124383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054431166,0.0012590693,0.0035915386,0.007006001,0.0015429585,0.0031091606,0.004371081,0.003372948,0.01296479],"category_scores_gemma":[0.35192955,0.0006344918,0.003350301,0.006230845,0.0076229805,0.0072859316,0.005052984,0.0039869957,0.0009910049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011446933,0.0015186779,0.3377642,0.0032901068,0.0066975425,0.0020461963,0.0052002543,0.021879783,0.011981751,0.16446413,0.014828411,0.418882],"study_design_scores_gemma":[0.0022060724,0.009749805,0.22062044,0.0006707342,0.0033732413,0.0073477253,0.0046493136,0.28029308,0.013447381,0.43953636,0.017297272,0.00080860907],"about_ca_topic_score_codex":0.00073978864,"about_ca_topic_score_gemma":0.0004732916,"teacher_disagreement_score":0.054431166,"about_ca_system_score_codex":0.00081856677,"about_ca_system_score_gemma":0.0024880392,"threshold_uncertainty_score":0.28786296},"labels":[],"label_agreement":null},{"id":"W2888587255","doi":"10.3758/s13428-018-1106-8","title":"Norms of conceptual familiarity for 3,596 French nouns and their contribution in lexical decision","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Categorization, perception, and language","field":"Psychology","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut Universitaire en Santé Mentale de Québec; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Noun; Linguistics; Lexical decision task; Psychology; Cognitive psychology; Natural language processing; Computer science; Cognition; Philosophy","score_opus":0.24013816053285314,"score_gpt":0.5999140805722225,"score_spread":0.35977592003936937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888587255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99677974,0.00012784617,0.0009853016,0.000028763317,0.0000074301292,0.000014786417,0.00011855091,0.000014116619,0.0019234007],"genre_scores_gemma":[0.9990121,0.00003248028,0.00050604966,0.000011560477,0.0000066479747,0.000016584841,0.00013891458,0.0000111002055,0.00026454008],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947419,0.002845339,0.00045865506,0.00093107746,0.0007866673,0.00023625937],"domain_scores_gemma":[0.9500815,0.035502948,0.0047778194,0.0029256348,0.005714264,0.0009978906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064115594,0.00027954148,0.00029178703,0.001554703,0.00044082134,0.0020476787,0.0002851061,0.00070596446,0.0026203492],"category_scores_gemma":[0.045192894,0.00015333516,0.00029398687,0.000662885,0.0009964149,0.0009159794,0.0005550676,0.00038496472,0.00039913374],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014435856,0.00019151194,0.92161745,0.00007446208,0.00025104554,0.00021863884,0.012622401,0.0005420161,0.010501282,0.0021815563,0.0004684364,0.049887512],"study_design_scores_gemma":[0.000020484433,0.00027563126,0.99307173,0.000018459716,0.000040305502,0.00032223514,0.0021910537,0.0010379279,0.0008826982,0.001139166,0.0009622013,0.000038106515],"about_ca_topic_score_codex":0.010999095,"about_ca_topic_score_gemma":0.012494305,"teacher_disagreement_score":0.010999095,"about_ca_system_score_codex":0.00088193343,"about_ca_system_score_gemma":0.00045105343,"threshold_uncertainty_score":0.03390795},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.679021047517433,"score_gpt":0.7112710266822435,"score_spread":0.03224997916481054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889916852","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66807264,0.0006142022,0.31993645,0.00036324534,0.0001728252,0.0013137569,0.001143344,0.0006004974,0.007783122],"genre_scores_gemma":[0.91301,0.00024389804,0.082065016,0.00015730924,0.000078764635,0.0016375439,0.0005910706,0.0001652478,0.0020510433],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.89895815,0.08764738,0.003214528,0.002925361,0.0065549947,0.00069966033],"domain_scores_gemma":[0.40729684,0.53499246,0.019268343,0.023228643,0.014137178,0.0010764974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.058482308,0.00061705656,0.0009021656,0.00303274,0.000872597,0.0021740608,0.0017831553,0.001200922,0.0064221085],"category_scores_gemma":[0.32767206,0.0006588045,0.0011133633,0.0047244974,0.001551875,0.003251692,0.0028170014,0.00154748,0.0008148063],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067615346,0.002166497,0.58266157,0.00069168484,0.0013330062,0.00010781828,0.0028254224,0.005481711,0.0017897234,0.025317105,0.002557658,0.36830628],"study_design_scores_gemma":[0.0023751515,0.013565911,0.6960325,0.0005286202,0.00269751,0.0020930774,0.0038013246,0.17629497,0.012989802,0.07702013,0.012263047,0.00033784442],"about_ca_topic_score_codex":0.0017308614,"about_ca_topic_score_gemma":0.0021078144,"teacher_disagreement_score":0.9415177,"about_ca_system_score_codex":0.00082379696,"about_ca_system_score_gemma":0.0019997186,"threshold_uncertainty_score":0.30928767},"labels":[],"label_agreement":null},{"id":"W2891563639","doi":"10.3758/s13428-018-1118-4","title":"Conceptualizing syntactic categories as semantic categories: Unifying part-of-speech identification and semantics using co-occurrence vector averaging","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Simple (philosophy); Word (group theory); Replicate; Semantics (computer science); Identification (biology); Class (philosophy); Linguistics; Mathematics; Programming language; Statistics","score_opus":0.3004789857609664,"score_gpt":0.5616148356223938,"score_spread":0.2611358498614274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891563639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052340195,0.0006442369,0.94412893,0.00030503946,0.00006235705,0.00004807522,0.00015494086,0.00046561568,0.00185052],"genre_scores_gemma":[0.7642238,0.0005874538,0.2331649,0.000119453354,0.000091655864,0.00011333769,0.00041650492,0.00017809108,0.0011048161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887556,0.0004464157,0.00006190647,0.0003344019,0.00019863929,0.00008302952],"domain_scores_gemma":[0.9962857,0.0021022405,0.00038717405,0.00079475244,0.00029758175,0.00013251256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002985502,0.00081350957,0.0008982251,0.0040893923,0.0004650927,0.0021504518,0.0014233739,0.0010256164,0.0014024522],"category_scores_gemma":[0.009558542,0.00042050384,0.0009650945,0.0030208174,0.0018341412,0.0066111293,0.001745311,0.0014700678,0.0007108536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003853088,0.0003061462,0.019796807,0.00027069947,0.0004662281,0.0002561851,0.0020761199,0.061850667,0.026372174,0.15855022,0.0026788695,0.7269905],"study_design_scores_gemma":[0.0000117624195,0.000093846415,0.009386844,0.000049346076,0.00007575066,0.00017794048,0.00033113928,0.632684,0.0034912475,0.35120323,0.0024163316,0.00007847729],"about_ca_topic_score_codex":0.0030029807,"about_ca_topic_score_gemma":0.0031329617,"teacher_disagreement_score":0.0040893923,"about_ca_system_score_codex":0.00069232524,"about_ca_system_score_gemma":0.00077411934,"threshold_uncertainty_score":0.015789032},"labels":[],"label_agreement":null},{"id":"W2891614930","doi":"10.3758/s13428-018-1107-7","title":"A comparison of homonym meaning frequency estimates derived from movie and television subtitles, free association, and explicit ratings","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Ambiguity; Meaning (existential); Homonym (biology); Computer science; Consistency (knowledge bases); Context (archaeology); Categorization; Linguistics; Replicate; Interpretation (philosophy); Polysemy; Cognition; Natural language processing; Association (psychology); Cognitive psychology; Psychology; Artificial intelligence; Mathematics; Statistics","score_opus":0.2786611252142364,"score_gpt":0.5546806692884004,"score_spread":0.276019544074164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891614930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753609,0.0003725965,0.018025685,0.000030982046,0.000030322504,0.000043503755,0.00051299756,0.00009921576,0.005523819],"genre_scores_gemma":[0.9925695,0.00012918189,0.005710423,0.00001450332,0.000023888455,0.00002810896,0.0006849587,0.000059456404,0.0007799438],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99792504,0.00075832405,0.00023267393,0.000384201,0.00058529375,0.00011440391],"domain_scores_gemma":[0.9593356,0.031913124,0.0020140354,0.0028069091,0.0034811578,0.0004492138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036215563,0.00025972322,0.00034397436,0.0016442162,0.00025904857,0.0014343645,0.00045992542,0.00061531673,0.0031457192],"category_scores_gemma":[0.044127356,0.00023869755,0.00028604132,0.00070143904,0.00045090512,0.0019695705,0.0011525222,0.0005544553,0.00067587895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011931097,0.00045305377,0.4140272,0.0010752681,0.0011866954,0.0003089915,0.008268732,0.0028762692,0.19778155,0.005323746,0.0014506717,0.35531667],"study_design_scores_gemma":[0.000085727625,0.00057248765,0.9673187,0.00005187761,0.00032470265,0.0008703584,0.0011418192,0.013057468,0.01341257,0.0017376808,0.0013046028,0.000122027835],"about_ca_topic_score_codex":0.0013684279,"about_ca_topic_score_gemma":0.0034828237,"teacher_disagreement_score":0.0036215563,"about_ca_system_score_codex":0.00020392782,"about_ca_system_score_gemma":0.00018711945,"threshold_uncertainty_score":0.01915288},"labels":[],"label_agreement":null},{"id":"W2894255682","doi":"10.3758/s13428-018-1137-1","title":"Beyond subjective judgments: Predicting evaluations of creative writing from computational linguistic features","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Imagination Institute","keywords":"Rubric; Creativity; Fluency; Readability; Psychology; Cohesion (chemistry); Writing assessment; Linguistics; Creativity technique; Context (archaeology); Creative writing; Cognitive psychology; Social psychology; Mathematics education","score_opus":0.32908617477775526,"score_gpt":0.6516848971259406,"score_spread":0.3225987223481853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894255682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871187,0.00014993237,0.009854067,0.000066160486,0.00001725083,0.00005675436,0.0002105429,0.00004611871,0.0024803004],"genre_scores_gemma":[0.9958782,0.000048605485,0.003468588,0.000023181228,0.000014163942,0.0000405026,0.0001525273,0.000015728792,0.00035858087],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809295,0.0010671456,0.00016312175,0.00023153474,0.00037152955,0.0000736231],"domain_scores_gemma":[0.92025477,0.063154675,0.009279333,0.0032187365,0.0026612354,0.0014312373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037903825,0.0005610842,0.00026836435,0.0013883599,0.00022767743,0.0034339323,0.00037821653,0.00093860104,0.0022905204],"category_scores_gemma":[0.074111946,0.00021238171,0.00040363905,0.00074039417,0.0005449745,0.0021774739,0.00082339166,0.00080081355,0.0005381669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002350832,0.0013763995,0.80795354,0.00039240107,0.00055658474,0.00021129622,0.0027719697,0.008719367,0.014385028,0.0022566235,0.0011613445,0.15786465],"study_design_scores_gemma":[0.000094512536,0.0010202352,0.8657655,0.00013747979,0.00021565086,0.00027814542,0.0013652301,0.11359521,0.0061975745,0.010519782,0.0006854132,0.00012531664],"about_ca_topic_score_codex":0.00087620044,"about_ca_topic_score_gemma":0.0016164313,"teacher_disagreement_score":0.0037903825,"about_ca_system_score_codex":0.0002443297,"about_ca_system_score_gemma":0.00024022497,"threshold_uncertainty_score":0.020045698},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.5472372277828504,"score_gpt":0.6384359538892672,"score_spread":0.09119872610641677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895796529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99302715,0.00047075885,0.0035506543,0.00003921829,0.00008168128,0.00010951209,0.00008716672,0.000029257764,0.0026045535],"genre_scores_gemma":[0.9981036,0.00010048021,0.0010816975,0.00007966328,0.00003081189,0.00006852228,0.00011673207,0.000016130633,0.00040242408],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99704784,0.0008958073,0.0002863317,0.00055970607,0.0010809429,0.00012947821],"domain_scores_gemma":[0.97113246,0.019395242,0.0031150964,0.0024265172,0.0035494792,0.00038124027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049567223,0.00043386678,0.00034792197,0.00060535176,0.0002836791,0.0005526988,0.00038562034,0.00065634435,0.0010664804],"category_scores_gemma":[0.034718703,0.00028181795,0.00032308855,0.00027850267,0.00048315772,0.00066172803,0.00044924862,0.00080045493,0.00029945897],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01236405,0.0017356823,0.6743933,0.00038878384,0.001451732,0.00012353239,0.0034974583,0.0010261446,0.19941434,0.000646792,0.00089150865,0.10406673],"study_design_scores_gemma":[0.000114856455,0.0012665396,0.9873713,0.00002832456,0.00017030314,0.00026804153,0.00019309824,0.0016433226,0.008372249,0.00019883532,0.00034843458,0.000024727537],"about_ca_topic_score_codex":0.00130934,"about_ca_topic_score_gemma":0.0015903966,"teacher_disagreement_score":0.0049567223,"about_ca_system_score_codex":0.00027601104,"about_ca_system_score_gemma":0.000245413,"threshold_uncertainty_score":0.026213944},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4921422929899069,"score_gpt":0.6493498938476473,"score_spread":0.15720760085774038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903145455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98571163,0.0004583396,0.0034163643,0.00006766857,0.00006345383,0.00008257083,0.00279994,0.0001312002,0.007268843],"genre_scores_gemma":[0.97756165,0.00045316733,0.005867428,0.00011625082,0.000058685215,0.00020612053,0.002181757,0.00014316302,0.013411656],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995017,0.00009367588,0.00009502229,0.00010347134,0.00017230913,0.000033799657],"domain_scores_gemma":[0.9970963,0.0015351068,0.00051911443,0.00017333817,0.00053864735,0.0001375128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068652857,0.00027131574,0.00028084163,0.000723778,0.0002921375,0.0005439034,0.00020327284,0.00039613838,0.009503619],"category_scores_gemma":[0.0052570035,0.00009453127,0.00021613439,0.0005566587,0.00022226266,0.00079376466,0.0005778028,0.00022120052,0.002168839],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039243046,0.00053584453,0.4307705,0.0018374296,0.00042810573,0.0012799758,0.010510987,0.0011863529,0.1778919,0.0009914048,0.012073806,0.35856944],"study_design_scores_gemma":[0.000021597525,0.00051021687,0.97877425,0.000051611227,0.000080277605,0.00067338994,0.0019072887,0.0009588191,0.0067148153,0.00020387422,0.010069332,0.000034653076],"about_ca_topic_score_codex":0.0009675859,"about_ca_topic_score_gemma":0.0025158788,"teacher_disagreement_score":0.009503619,"about_ca_system_score_codex":0.00010320885,"about_ca_system_score_gemma":0.000113834365,"threshold_uncertainty_score":0.03179282},"labels":[],"label_agreement":null},{"id":"W2909514154","doi":"10.3758/s13428-018-1184-7","title":"The spacing effect stands up to big data","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interval (graph theory); Computer science; Repetition (rhetorical device); Context (archaeology); Relevance (law); Statistics; Psychology; Information retrieval; Mathematics","score_opus":0.6473102502533267,"score_gpt":0.6323547153159895,"score_spread":0.014955534937337145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909514154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019727197,0.012086482,0.78365314,0.12920827,0.018703995,0.0011302767,0.010175067,0.0052444804,0.020071026],"genre_scores_gemma":[0.37690175,0.007098329,0.50140464,0.070799865,0.015636418,0.005573019,0.0069370014,0.0041117757,0.011537269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.84989023,0.1037338,0.0076706884,0.015612361,0.021936145,0.0011567916],"domain_scores_gemma":[0.14872882,0.75255424,0.010635886,0.076955155,0.008774351,0.0023515949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16948494,0.0016545587,0.0041365423,0.004488517,0.003299479,0.0075379466,0.0047535934,0.0042549367,0.01945984],"category_scores_gemma":[0.6601965,0.0020103727,0.004260192,0.0072378777,0.013252203,0.020638557,0.008380845,0.012227866,0.003977643],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018544982,0.00031383842,0.06635463,0.004746347,0.005553966,0.00055798393,0.0028453392,0.0062457155,0.0011023602,0.43246624,0.17349814,0.3044609],"study_design_scores_gemma":[0.00032181398,0.00013188338,0.0063396497,0.0007903177,0.0004892367,0.00030427935,0.00059740257,0.013454768,0.0007702406,0.93212247,0.04457917,0.00009885591],"about_ca_topic_score_codex":0.002594864,"about_ca_topic_score_gemma":0.0037975588,"teacher_disagreement_score":0.16948494,"about_ca_system_score_codex":0.0022856644,"about_ca_system_score_gemma":0.0058613108,"threshold_uncertainty_score":0.89633274},"labels":[],"label_agreement":null},{"id":"W2912822799","doi":"10.3758/s13428-019-01197-2","title":"Development and validation of a high-speed video system for measuring saccadic eye movement","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Traumatic Brain Injury Research","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Saccade; Computer vision; Reliability (semiconductor); Artificial intelligence; Video camera; Eye movement; Simulation; Physics","score_opus":0.43192333207829703,"score_gpt":0.5511577511445754,"score_spread":0.11923441906627841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912822799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25085378,0.0009901967,0.7364827,0.00026352063,0.00035358986,0.004732704,0.0016442286,0.0023611186,0.0023182011],"genre_scores_gemma":[0.294135,0.00077284174,0.6948901,0.0003012691,0.00009192688,0.003889185,0.0023359023,0.00022205622,0.0033616628],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957695,0.001001929,0.00040939392,0.0007532618,0.0018527013,0.00021314876],"domain_scores_gemma":[0.9931276,0.0018727718,0.00039568488,0.0005411882,0.0037961155,0.000266734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064097703,0.0011041078,0.0007359676,0.0022852784,0.00068363297,0.0011388035,0.0022172208,0.0018313141,0.0019637602],"category_scores_gemma":[0.0066698794,0.00056901504,0.0006936035,0.000999916,0.00063495524,0.0011192715,0.001141508,0.00078741944,0.0009864856],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009555259,0.001257319,0.052973103,0.0006598916,0.00025986263,0.00014143018,0.00044865988,0.003534285,0.68697435,0.001033807,0.0019670366,0.24979478],"study_design_scores_gemma":[0.00068239635,0.012953085,0.26234397,0.00027093265,0.0009654084,0.0021880732,0.0006193932,0.09955897,0.5957042,0.0009292351,0.02345785,0.00032644617],"about_ca_topic_score_codex":0.009342884,"about_ca_topic_score_gemma":0.010601688,"teacher_disagreement_score":0.009342884,"about_ca_system_score_codex":0.0010174729,"about_ca_system_score_gemma":0.003277277,"threshold_uncertainty_score":0.033898473},"labels":[],"label_agreement":null},{"id":"W2913504998","doi":"10.3758/s13428-018-1155-z","title":"A thousand studies for the price of one: Accelerating psychological science with Pushkin","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Computer science; The Internet; Transformative learning; Software; Data science; World Wide Web; Mobile device; Range (aeronautics); Population; Computer security; Operating system","score_opus":0.9039247896964424,"score_gpt":0.749324593427155,"score_spread":0.15460019626928745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913504998","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026331758,0.30104637,0.046783727,0.555516,0.03634818,0.00031815845,0.0005740738,0.00046990576,0.032611784],"genre_scores_gemma":[0.31245154,0.20078844,0.14741068,0.2621161,0.036143027,0.0013392754,0.00055204245,0.0013654298,0.037833594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871996,0.0066337003,0.0008118952,0.0013078223,0.003672145,0.00037478065],"domain_scores_gemma":[0.7040974,0.24982457,0.0043637753,0.016389528,0.02112105,0.0042036674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037029345,0.0013223869,0.002206405,0.0057006394,0.0036331394,0.008022586,0.0019243024,0.004848287,0.017017186],"category_scores_gemma":[0.14682744,0.0009294022,0.0018165283,0.0039863423,0.013826571,0.029274361,0.0060046716,0.013452022,0.0020891558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082951697,0.00081244454,0.0068561165,0.0025673732,0.0007090601,0.000421154,0.0027564694,0.001037459,0.00096737413,0.45408055,0.20258942,0.32637313],"study_design_scores_gemma":[0.00034521826,0.00030979564,0.0039526904,0.0038554582,0.00042317278,0.00033002178,0.0030269444,0.0017163148,0.001402662,0.56516755,0.4192329,0.00023733654],"about_ca_topic_score_codex":0.0054245014,"about_ca_topic_score_gemma":0.0067957193,"teacher_disagreement_score":0.9629707,"about_ca_system_score_codex":0.0049201613,"about_ca_system_score_gemma":0.006419328,"threshold_uncertainty_score":0.1958322},"labels":[],"label_agreement":null},{"id":"W2940968901","doi":"10.3758/s13428-019-01254-w","title":"Visual and auditory perceptual strength norms for 3,596 French nouns and their relationship with other psycholinguistic variables","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Perception; Noun; Cognitive psychology; Stimulus modality; Psychology; Modalities; Visual perception; Modality (human–computer interaction); Age of Acquisition; Semantics (computer science); Sensory system; Computer science; Cognition; Natural language processing; Artificial intelligence","score_opus":0.1524743936881985,"score_gpt":0.5181614210583495,"score_spread":0.365687027370151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940968901","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99671644,0.00009267348,0.00032568778,0.00001959886,0.000005804683,0.00001307911,0.00023653131,0.000012034433,0.0025781563],"genre_scores_gemma":[0.99875426,0.000027664184,0.00031866756,0.00001183253,0.0000067713613,0.000020618594,0.00021149957,0.000009308394,0.00063932815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980198,0.0006511314,0.0001864884,0.0004285026,0.00054337195,0.0001707478],"domain_scores_gemma":[0.9813442,0.010941886,0.003366281,0.0007727622,0.002803397,0.000771403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027280166,0.00041002236,0.00023698906,0.0023354825,0.0003690365,0.0010764145,0.00033355912,0.0006047128,0.003191031],"category_scores_gemma":[0.017375339,0.0001395445,0.0003215668,0.00081668084,0.0006993582,0.00053558935,0.0004317169,0.00032170909,0.00042271192],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074320444,0.00020593216,0.96752745,0.000047021982,0.00018019146,0.00023211277,0.003380861,0.00035612984,0.008405895,0.00055282295,0.00026998887,0.018098423],"study_design_scores_gemma":[0.0000055237074,0.00016124515,0.9981852,0.0000036737408,0.00001250999,0.0001556728,0.00053367246,0.00023093335,0.00033217887,0.000100263955,0.00027036102,0.000008689979],"about_ca_topic_score_codex":0.018037738,"about_ca_topic_score_gemma":0.016631605,"teacher_disagreement_score":0.018037738,"about_ca_system_score_codex":0.0008258947,"about_ca_system_score_gemma":0.00035157148,"threshold_uncertainty_score":0.035865486},"labels":[],"label_agreement":null},{"id":"W2955002705","doi":"10.3758/s13428-019-01282-6","title":"LADEC: The Large Database of English Compounds","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Bigram; Lexicon; Computer science; Natural language processing; Lexical database; Morpheme; Compound; WordNet; Parsing; Database; Artificial intelligence; Linguistics; Information retrieval; Trigram","score_opus":0.15682359605961013,"score_gpt":0.5424968809298324,"score_spread":0.38567328487022223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955002705","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062402353,0.0043435446,0.0049047684,0.00046119562,0.0001932975,0.0005077796,0.90130347,0.0038284187,0.022055073],"genre_scores_gemma":[0.050745215,0.0016352145,0.01714166,0.0002584519,0.000080728954,0.00095072755,0.9231363,0.0007269762,0.0053247106],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998579,0.00025741127,0.0003685938,0.00033720362,0.0003713558,0.00008639375],"domain_scores_gemma":[0.995672,0.0014782245,0.000414208,0.00084074895,0.0012265043,0.00036830342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011429812,0.0013645483,0.0012814465,0.0064954353,0.0011662851,0.0024114419,0.0023745708,0.0015516629,0.035250716],"category_scores_gemma":[0.0072111944,0.0007201092,0.00068732724,0.0068577407,0.0005815396,0.005956205,0.0025841505,0.0010587046,0.02419136],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024008916,0.000620743,0.01738151,0.015210469,0.00028757623,0.0028593338,0.0029729134,0.0016396675,0.019033097,0.012659094,0.68718946,0.2377453],"study_design_scores_gemma":[0.00033761785,0.00015254012,0.022741778,0.0005054148,0.00010469332,0.00094027136,0.0013700203,0.0015228242,0.004826951,0.0028278346,0.96452254,0.00014745607],"about_ca_topic_score_codex":0.007225091,"about_ca_topic_score_gemma":0.0135695385,"teacher_disagreement_score":0.035250716,"about_ca_system_score_codex":0.0011268556,"about_ca_system_score_gemma":0.0018594265,"threshold_uncertainty_score":0.117925406},"labels":[],"label_agreement":null},{"id":"W2955707177","doi":"10.3758/s13428-019-01268-4","title":"The Semantic Librarian: A search engine built from vector-space models of semantics","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Computer science; Semantics (computer science); Space (punctuation); Cognition; Semantic space; Information retrieval; Cognitive science; Human–computer interaction; Artificial intelligence; World Wide Web; Data science; Psychology; Programming language","score_opus":0.1924456178434242,"score_gpt":0.5118749448262684,"score_spread":0.3194293269828442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955707177","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015124008,0.00080131035,0.86747366,0.00049633265,0.00007938323,0.00031174635,0.017695254,0.09160772,0.006410657],"genre_scores_gemma":[0.28188378,0.0015578207,0.67131746,0.0004895838,0.00007184114,0.0006348941,0.030296745,0.0058867955,0.007861065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997154,0.000067771056,0.00002860514,0.00007248868,0.000095631134,0.0000201217],"domain_scores_gemma":[0.99927145,0.00042768798,0.000043795288,0.000114893504,0.00010016269,0.00004190873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005917797,0.00082810124,0.0009952191,0.0027915426,0.0003569002,0.0016921777,0.0012225441,0.0008928546,0.010437401],"category_scores_gemma":[0.0049169315,0.00047808484,0.000982731,0.002498026,0.00030413913,0.0040473044,0.0013035552,0.0006345,0.003775123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013187716,0.0004596188,0.008665559,0.0015839295,0.0006541116,0.0004619866,0.00068274816,0.11150115,0.0066500735,0.1320523,0.14731123,0.58865845],"study_design_scores_gemma":[0.000112335496,0.00009034135,0.0010498497,0.000085985426,0.00012931967,0.00020381816,0.00009020928,0.8636282,0.003398329,0.09631175,0.034845203,0.000054693097],"about_ca_topic_score_codex":0.00767375,"about_ca_topic_score_gemma":0.017463198,"teacher_disagreement_score":0.010437401,"about_ca_system_score_codex":0.0007149639,"about_ca_system_score_gemma":0.0013900403,"threshold_uncertainty_score":0.03491658},"labels":[],"label_agreement":null},{"id":"W2960780327","doi":"10.3758/s13428-019-01270-w","title":"The role of number of items per trial in best–worst scaling experiments","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Scaling; Latent semantic analysis; Set (abstract data type); Computer science; Dimension (graph theory); Value (mathematics); Statistics; Cognitive psychology; Natural language processing; Artificial intelligence; Psychology; Machine learning; Mathematics","score_opus":0.5703808539984128,"score_gpt":0.6897069463044384,"score_spread":0.11932609230602564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960780327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7298953,0.0025498609,0.2390453,0.0021248758,0.0011896301,0.0010704701,0.00041851704,0.0012186721,0.022487378],"genre_scores_gemma":[0.8744831,0.0004417762,0.11568946,0.00082844496,0.00032984297,0.001856711,0.00019210162,0.0013235003,0.004855038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9404617,0.043268856,0.0034689428,0.0056497017,0.0063655754,0.000785179],"domain_scores_gemma":[0.44009647,0.49098238,0.018651882,0.0404024,0.005293658,0.004573147],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06697114,0.002759442,0.0048795766,0.0013202475,0.0012510528,0.0054935347,0.003661048,0.0039357995,0.007762854],"category_scores_gemma":[0.37659302,0.0020745837,0.0010771552,0.0009633303,0.0049676658,0.0122537175,0.003261169,0.0048850393,0.0009632568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07480022,0.018824974,0.04559258,0.004247789,0.0021872337,0.0004296805,0.004075731,0.09054357,0.240292,0.08884327,0.0057594334,0.4244036],"study_design_scores_gemma":[0.0045918524,0.0136113865,0.08713251,0.00093345426,0.001484896,0.0006515452,0.0007390938,0.5181142,0.043039802,0.32276562,0.0060553635,0.00088025024],"about_ca_topic_score_codex":0.0008192612,"about_ca_topic_score_gemma":0.00089435955,"teacher_disagreement_score":0.9330289,"about_ca_system_score_codex":0.0012212872,"about_ca_system_score_gemma":0.0015198961,"threshold_uncertainty_score":0.35418147},"labels":[],"label_agreement":null},{"id":"W2963778838","doi":"10.3758/s13428-019-01277-3","title":"A computerized spatial orientation test","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Orientation (vector space); Task (project management); Artificial intelligence; Perspective (graphical); Computer vision; Human–computer interaction; Mathematics","score_opus":0.15379085207640492,"score_gpt":0.5222937646684322,"score_spread":0.36850291259202733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963778838","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9528953,0.00021121274,0.00722259,0.00040124732,0.00024419228,0.0039453357,0.0054171747,0.00084811385,0.028814835],"genre_scores_gemma":[0.8784381,0.00059509865,0.029941011,0.0013052992,0.00014798252,0.010585097,0.0121618835,0.0002465109,0.06657896],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99859756,0.00018624628,0.00024094983,0.00030264305,0.00053258904,0.0001400484],"domain_scores_gemma":[0.9949221,0.0018026364,0.00078999926,0.000554961,0.0013422931,0.00058810244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010779862,0.0016980239,0.0009839545,0.0021139956,0.00068972853,0.0007777491,0.0013531736,0.0011654006,0.016539078],"category_scores_gemma":[0.005762344,0.0004846347,0.00084957544,0.0010254005,0.00064048823,0.0016837545,0.0012230905,0.0011352347,0.0054622423],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011099488,0.035927806,0.5175707,0.000383989,0.00053185393,0.0014695439,0.0018957339,0.006196701,0.03605557,0.0031725774,0.029105285,0.35659087],"study_design_scores_gemma":[0.0025569908,0.01488064,0.93770915,0.000099592005,0.0002471538,0.0014757939,0.00059993175,0.009319054,0.013722074,0.0018161389,0.017386818,0.00018671366],"about_ca_topic_score_codex":0.0069635157,"about_ca_topic_score_gemma":0.0068836864,"teacher_disagreement_score":0.016539078,"about_ca_system_score_codex":0.0005923697,"about_ca_system_score_gemma":0.0014256618,"threshold_uncertainty_score":0.055328667},"labels":[],"label_agreement":null},{"id":"W2970802026","doi":"10.3758/s13428-019-01289-z","title":"The influence of place and time on lexical behavior: A distributional analysis","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Categorization, perception, and language","field":"Psychology","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Lexical choice; Word (group theory); Language model; Experiential learning; Lexical density; Lexical item; Linguistics; Psychology","score_opus":0.1018397194881408,"score_gpt":0.5618026561742797,"score_spread":0.4599629366861389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970802026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937734,0.000050876573,0.0037057365,0.000048052614,0.000012000684,0.000016883987,0.00013598251,0.000025954674,0.002231064],"genre_scores_gemma":[0.9983746,0.000020722586,0.0009030901,0.000012457615,0.0000070543247,0.000016496122,0.00010321096,0.000048517544,0.0005139223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996781,0.0017451098,0.00020209746,0.00057912164,0.000505148,0.00018749911],"domain_scores_gemma":[0.9393508,0.05183787,0.0025294397,0.002810269,0.002216951,0.0012547473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042799353,0.0002209697,0.0005446159,0.0015657836,0.0005080749,0.0020502235,0.0006385679,0.0004717921,0.005307793],"category_scores_gemma":[0.034324836,0.00017340718,0.00062182406,0.0013668181,0.0013167302,0.0014336407,0.001181731,0.00071314024,0.0005121156],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058487896,0.0012612818,0.8081424,0.00021330816,0.00072200247,0.00052367244,0.0067340503,0.0026808614,0.06792837,0.0078036156,0.0008510433,0.097290546],"study_design_scores_gemma":[0.00004018464,0.0007958028,0.970305,0.000017661212,0.00029341664,0.00038589528,0.0023403377,0.016839057,0.0038966124,0.004124053,0.0009070412,0.00005487762],"about_ca_topic_score_codex":0.0025839722,"about_ca_topic_score_gemma":0.002365657,"teacher_disagreement_score":0.005307793,"about_ca_system_score_codex":0.0004899372,"about_ca_system_score_gemma":0.00043725834,"threshold_uncertainty_score":0.022634745},"labels":[],"label_agreement":null},{"id":"W2972188906","doi":"10.3758/s13428-019-01288-0","title":"The Hoosier Vocal Emotions Corpus: A validated set of North American English pseudo-words for evaluating emotion processing","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Psychology; Sadness; Anger; Disgust; Stimulus (psychology); Set (abstract data type); Happiness; Cognitive psychology; Computer science; Social psychology","score_opus":0.3572854909454397,"score_gpt":0.6064557803683746,"score_spread":0.24917028942293484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972188906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8233954,0.0021751,0.022137726,0.00049608236,0.00063846144,0.003341645,0.106252514,0.0024269493,0.0391361],"genre_scores_gemma":[0.6192675,0.001303639,0.045223832,0.0008022292,0.0004562137,0.011462934,0.2881984,0.0023436719,0.0309415],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906856,0.00032441327,0.00014849847,0.00016915156,0.00021980102,0.00006958377],"domain_scores_gemma":[0.9976872,0.0008557728,0.00018782285,0.0002893764,0.0008073042,0.00017252695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011695492,0.0010467442,0.00043907235,0.0014251556,0.0010782141,0.00097486685,0.00074907945,0.0008901822,0.010730094],"category_scores_gemma":[0.003226141,0.0002457469,0.00045418448,0.0008440868,0.00056331494,0.0008331637,0.001475284,0.0007295715,0.0076196236],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052706846,0.002087036,0.058305804,0.0058133113,0.00044728882,0.002858199,0.011583149,0.0018447234,0.2795979,0.0036372563,0.21855018,0.41000447],"study_design_scores_gemma":[0.0006020935,0.0007835903,0.67133206,0.00034826,0.00045262236,0.0052842554,0.005230473,0.00600627,0.038783375,0.0013166718,0.2695474,0.00031294642],"about_ca_topic_score_codex":0.004082597,"about_ca_topic_score_gemma":0.009626003,"teacher_disagreement_score":0.010730094,"about_ca_system_score_codex":0.00039717616,"about_ca_system_score_gemma":0.0007823697,"threshold_uncertainty_score":0.035895705},"labels":[],"label_agreement":null},{"id":"W2986005510","doi":"10.3758/s13428-019-01297-z","title":"MorphoLex-FR: A derivational morphological database for 38,840 French words","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Université Laval","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Suffix; Lexicon; Prefix; Lexical database; Computer science; Natural language processing; Noun; Linguistics; Lexical decision task; Variable (mathematics); Artificial intelligence; Database; Psychology; Mathematics; WordNet; Cognition","score_opus":0.3431572925291088,"score_gpt":0.6009954129180568,"score_spread":0.257838120388948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986005510","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19405429,0.0035404747,0.040829144,0.00035071213,0.00016993078,0.00043554205,0.6833751,0.040175978,0.037068885],"genre_scores_gemma":[0.17211793,0.0012706033,0.050447848,0.00014810149,0.000083286366,0.00051057927,0.76268715,0.0052481787,0.007486414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925345,0.00011198931,0.00013954465,0.00025155363,0.00017619971,0.00006726395],"domain_scores_gemma":[0.99854493,0.00054821506,0.0001415528,0.00025974883,0.00042656146,0.00007910009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006229565,0.0020496987,0.0008789154,0.008816408,0.00092784717,0.0018044234,0.0010036305,0.001239444,0.033099037],"category_scores_gemma":[0.003082137,0.0005859732,0.0010148445,0.003699102,0.0005597179,0.0019854996,0.0013721419,0.0006202015,0.02535108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002331471,0.00042376333,0.028190948,0.0038675768,0.00033283903,0.0038512351,0.0035841563,0.002982786,0.085159756,0.016807416,0.26333952,0.5891286],"study_design_scores_gemma":[0.00034457422,0.00032765188,0.07872949,0.0005215245,0.0003136696,0.005710583,0.0013975435,0.0065532974,0.030614901,0.005944129,0.8692575,0.00028511634],"about_ca_topic_score_codex":0.01370557,"about_ca_topic_score_gemma":0.010410392,"teacher_disagreement_score":0.033099037,"about_ca_system_score_codex":0.000942163,"about_ca_system_score_gemma":0.0018973218,"threshold_uncertainty_score":0.11072725},"labels":[],"label_agreement":null},{"id":"W2998136884","doi":"10.3758/s13428-019-01324-z","title":"Modeling list-strength and spacing effects using version 3 of the retrieving effectively from memory (REM.3) model and its superimposition-of-similar-images assumption","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mnemonic; Engram; Psychology; TRACE (psycholinguistics); Cognitive psychology; Arithmetic; Superimposition; Mathematics; Computer science; Artificial intelligence","score_opus":0.2974948444674319,"score_gpt":0.4911807530646138,"score_spread":0.19368590859718188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998136884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23777471,0.00032747872,0.75185984,0.000575004,0.00019740181,0.0006008511,0.0013206879,0.001466705,0.005877312],"genre_scores_gemma":[0.7781493,0.00032560976,0.20741108,0.0003448259,0.000116686526,0.0014991302,0.00091369636,0.0006535507,0.010586119],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981893,0.0008654055,0.00009620056,0.00040163333,0.00024082811,0.00020666257],"domain_scores_gemma":[0.98453635,0.011214552,0.0011523964,0.0018734608,0.0008897483,0.00033349195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008979681,0.0011861104,0.0016733466,0.0011730498,0.00048347862,0.001359107,0.0046160966,0.0020697538,0.009188795],"category_scores_gemma":[0.026888028,0.00090317865,0.003299553,0.0010765868,0.00091438234,0.0019285163,0.0014681952,0.002674743,0.001377265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025652305,0.0013072753,0.022406826,0.0005456947,0.001258278,0.0005341789,0.000883701,0.76286453,0.011610566,0.12734106,0.004735125,0.06394756],"study_design_scores_gemma":[0.00015486262,0.0003092573,0.0029299988,0.000020313342,0.00028649287,0.000119268756,0.000026422285,0.9734379,0.0012866772,0.020372856,0.0010130379,0.000042924923],"about_ca_topic_score_codex":0.018935274,"about_ca_topic_score_gemma":0.015532007,"teacher_disagreement_score":0.018935274,"about_ca_system_score_codex":0.0013040595,"about_ca_system_score_gemma":0.0019464727,"threshold_uncertainty_score":0.047489643},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8409786516589324,"score_gpt":0.7069141870663498,"score_spread":0.1340644645925826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005165546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01941159,0.012288045,0.72523546,0.11890176,0.008387522,0.0061640916,0.0010853934,0.0010308995,0.1074952],"genre_scores_gemma":[0.24568857,0.009461818,0.60842067,0.03840054,0.0067456258,0.02658844,0.0009523309,0.0012664705,0.06247552],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8375578,0.12603529,0.009947548,0.0044899415,0.020429017,0.0015404257],"domain_scores_gemma":[0.6577632,0.15474628,0.009097488,0.123382024,0.049491324,0.005519768],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.14673801,0.0010729347,0.0013789239,0.001954673,0.0053513995,0.0073778215,0.0038187872,0.010364825,0.0083048185],"category_scores_gemma":[0.25389573,0.0012240799,0.0009615477,0.0017285304,0.0209489,0.0056156334,0.005679331,0.013366268,0.0076819384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020202966,0.00066376757,0.00732713,0.0024779786,0.00019571789,0.0013650013,0.037352618,0.0015232528,0.01674099,0.30642194,0.1864976,0.4374137],"study_design_scores_gemma":[0.0003288462,0.00071085605,0.012891121,0.008850593,0.00015340357,0.0043547363,0.017768413,0.003860006,0.015515303,0.29294837,0.6423278,0.00029068353],"about_ca_topic_score_codex":0.0024008092,"about_ca_topic_score_gemma":0.0057758363,"teacher_disagreement_score":0.98963517,"about_ca_system_score_codex":0.0020985703,"about_ca_system_score_gemma":0.007222397,"threshold_uncertainty_score":0.776034},"labels":[],"label_agreement":null},{"id":"W3008656255","doi":"10.3758/s13428-020-01369-5","title":"Optimizing Detection of True Within-Person Effects for Intensive Measurement Designs: A Comparison of Multilevel SEM and Unit-Weighted Scale Scores","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada; National Institute on Aging; National Institutes of Health","keywords":"Covariate; Statistics; Reliability (semiconductor); Variance (accounting); Scale (ratio); Mathematics; Monte Carlo method; Observational error; Multilevel model; Hierarchical database model; Computer science; Variable (mathematics); Econometrics; Power (physics); Data mining","score_opus":0.736785635071355,"score_gpt":0.630519755261086,"score_spread":0.10626587981026903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008656255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17345187,0.0005320077,0.8204764,0.0003612472,0.00021566838,0.0013263056,0.00034521124,0.00070149143,0.0025898453],"genre_scores_gemma":[0.6336831,0.00013318201,0.36246693,0.0002466717,0.00004501858,0.0023008736,0.00029043085,0.00034109605,0.00049272535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.72292,0.25036624,0.0054509356,0.011076518,0.008999848,0.0011865578],"domain_scores_gemma":[0.2993574,0.6346355,0.0103637595,0.04695436,0.007960426,0.0007285265],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16706538,0.0015078275,0.0027150307,0.0018666373,0.0012415615,0.00280071,0.002080209,0.0022558104,0.0026799582],"category_scores_gemma":[0.50504375,0.0011805085,0.0032648135,0.0018501169,0.0023499026,0.0036934759,0.0035790133,0.0027261479,0.00030940524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015109348,0.0023228517,0.2336339,0.0029575757,0.027900796,0.00021447318,0.0061491476,0.03507348,0.011535237,0.08018302,0.0052857045,0.57963437],"study_design_scores_gemma":[0.0030803813,0.016466137,0.4293988,0.0010691037,0.01328678,0.00066409825,0.0024676525,0.38473332,0.017925201,0.11859077,0.01175431,0.00056348817],"about_ca_topic_score_codex":0.0020656814,"about_ca_topic_score_gemma":0.0038328131,"teacher_disagreement_score":0.8329346,"about_ca_system_score_codex":0.0012074094,"about_ca_system_score_gemma":0.001999596,"threshold_uncertainty_score":0.88353676},"labels":[],"label_agreement":null},{"id":"W30187431","doi":"10.3758/s13428-018-1114-8","title":"Public Health Managers' Perspectives on the Use of Social Marketing Among Public Health Nurses in Saskatchewan","year":2006,"lang":"en","type":"dissertation","venue":"Behavior Research Methods","topic":"Service-Learning and Community Engagement","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Nurses Foundation","keywords":"Public health; Social marketing; Marketing; Business; Public relations; Medicine; Political science; Nursing","score_opus":0.5615402895553624,"score_gpt":0.5857689816748963,"score_spread":0.024228692119533934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30187431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850204,0.0002897359,0.00007264164,0.007197283,0.00001934108,0.000023971263,0.00004140816,0.000004079296,0.0073310696],"genre_scores_gemma":[0.9911143,0.000836379,0.00013788711,0.002461194,0.000016121827,0.00003922982,0.000029102097,0.0000074600225,0.0053584925],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99551624,0.002891139,0.00010616169,0.00018322867,0.00033479233,0.00096837507],"domain_scores_gemma":[0.9925621,0.003935262,0.0010140665,0.0001120287,0.0008608692,0.0015157056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035846278,0.0002732854,0.00020731342,0.0014231097,0.007996614,0.0042932173,0.0010888947,0.001613572,0.0048593124],"category_scores_gemma":[0.0063781375,0.00048455154,0.00014459934,0.0015675371,0.004041533,0.0017337458,0.0035260043,0.0024964819,0.00037996078],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093057424,0.00024737907,0.18765345,0.00018447296,0.000028148504,0.004255763,0.7747085,0.00014628307,0.0030593856,0.0024762324,0.0036540823,0.023493167],"study_design_scores_gemma":[0.0000043518844,0.00005749198,0.08317888,0.000065264794,0.0000063622438,0.000121425786,0.90705276,0.0000871617,0.00021057487,0.00017965364,0.00901802,0.000017981123],"about_ca_topic_score_codex":0.5631638,"about_ca_topic_score_gemma":0.8087843,"teacher_disagreement_score":0.43683618,"about_ca_system_score_codex":0.01966286,"about_ca_system_score_gemma":0.015687538,"threshold_uncertainty_score":0.8788176},"labels":[],"label_agreement":null},{"id":"W3027130718","doi":"10.3758/s13428-020-01403-6","title":"Assessing evidence for replication: A likelihood-based approach","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Replication (statistics); Computer science; Contrast (vision); Statistics; Econometrics; Artificial intelligence; Mathematics","score_opus":0.9916934429120137,"score_gpt":0.8138699872158525,"score_spread":0.1778234556961612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027130718","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020267308,0.033051692,0.86243767,0.0047674812,0.0035514499,0.06398285,0.0043824534,0.0020586457,0.0055004465],"genre_scores_gemma":[0.30815998,0.0026930484,0.6112577,0.0037390396,0.00073999166,0.06896298,0.0017252595,0.0007189353,0.0020031347],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.120700024,0.66915476,0.1069181,0.050927404,0.05021505,0.0020847346],"domain_scores_gemma":[0.054151867,0.84900504,0.026074404,0.057054173,0.012006424,0.0017079631],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7198512,0.01367379,0.036795348,0.039510634,0.0068691494,0.014514999,0.019989258,0.026193164,0.019677587],"category_scores_gemma":[0.8929016,0.008568509,0.06541868,0.01969142,0.021252777,0.020731585,0.016205449,0.017866628,0.003400259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02294235,0.0012240862,0.06659818,0.16946812,0.56226516,0.004688645,0.007059557,0.010168084,0.003848674,0.034728248,0.008665072,0.108343884],"study_design_scores_gemma":[0.028352078,0.009706943,0.0351021,0.040097278,0.4684851,0.0061273607,0.0023322639,0.14073485,0.008085699,0.22741744,0.03131128,0.0022475736],"about_ca_topic_score_codex":0.0037076613,"about_ca_topic_score_gemma":0.0056490265,"teacher_disagreement_score":0.2801488,"about_ca_system_score_codex":0.006557027,"about_ca_system_score_gemma":0.009796602,"threshold_uncertainty_score":0.3454734},"labels":[],"label_agreement":null},{"id":"W3033146654","doi":"10.3758/s13428-020-01418-z","title":"The Metronome Counting Task for measuring meta-awareness","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mind-wandering; Metronome; Task (project management); Cognitive psychology; Psychology; Computer science; Cognition","score_opus":0.8459687191205778,"score_gpt":0.6113941572223104,"score_spread":0.23457456189826742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033146654","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60163224,0.002770702,0.3528994,0.00039988576,0.00086825836,0.004404037,0.007396381,0.0020164438,0.027612599],"genre_scores_gemma":[0.7017299,0.001129042,0.26779357,0.00072381896,0.00024363851,0.01075384,0.0029165426,0.0006426775,0.014067031],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99879384,0.00028008787,0.00016856386,0.00029729822,0.0003809017,0.00007930081],"domain_scores_gemma":[0.99632853,0.0018846744,0.0005844488,0.0005068961,0.0005075135,0.00018787569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016422645,0.0008785613,0.0006002957,0.0016092752,0.0006313993,0.0009344777,0.0008281088,0.0010713807,0.0062733316],"category_scores_gemma":[0.009040061,0.00043499173,0.00056420587,0.0008779236,0.00023207598,0.0011250869,0.0008578006,0.0010756683,0.00094720564],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00556596,0.002140525,0.08590878,0.0019775196,0.0013125774,0.00041195433,0.0015446057,0.0016266096,0.39216477,0.010802418,0.016775735,0.47976848],"study_design_scores_gemma":[0.0010408472,0.0056233816,0.7972128,0.0004952364,0.0012272683,0.00422024,0.00060600665,0.02278388,0.12409311,0.014596922,0.027571915,0.0005283703],"about_ca_topic_score_codex":0.00097122166,"about_ca_topic_score_gemma":0.003058567,"teacher_disagreement_score":0.0062733316,"about_ca_system_score_codex":0.00024200337,"about_ca_system_score_gemma":0.0006473554,"threshold_uncertainty_score":0.020986378},"labels":[],"label_agreement":null},{"id":"W3036211922","doi":"10.3758/s13428-020-01397-1","title":"CompLex: an eye-movement database of compound word reading in English","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; McMaster University","keywords":"Eye movement; Sentence; Reading (process); Population; Natural language processing; Sample (material); Computer science; Word lists by frequency; Set (abstract data type); Word (group theory); Eye tracking; Word recognition; Artificial intelligence; Psychology; Database; Linguistics; Medicine","score_opus":0.46705324781155194,"score_gpt":0.6103505975625049,"score_spread":0.14329734975095293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036211922","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7319723,0.0010538172,0.01762955,0.00017364892,0.00013122016,0.0005367952,0.2220187,0.008794562,0.017689405],"genre_scores_gemma":[0.76384014,0.00055127335,0.030332401,0.00014490506,0.000110376386,0.00064616866,0.18968315,0.0012413438,0.0134503115],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997569,0.00003796277,0.000032521235,0.00008521234,0.00006299946,0.00002442534],"domain_scores_gemma":[0.9986467,0.00046328196,0.000120275065,0.00025466527,0.0003847143,0.00013040018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025648795,0.0004539343,0.0004087626,0.0019798062,0.00023955826,0.00060295494,0.00038810162,0.000573313,0.012563841],"category_scores_gemma":[0.002151503,0.00017235844,0.00027394152,0.0011835126,0.00013512722,0.0008022453,0.0006387353,0.00024235573,0.0053697],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055471747,0.0011723216,0.09798971,0.0022737428,0.0005565233,0.0020531446,0.002711255,0.003351181,0.20306115,0.0017746218,0.114372596,0.5651367],"study_design_scores_gemma":[0.0004086434,0.00080648385,0.8459351,0.00014437936,0.0003189263,0.0035113508,0.0018879881,0.023472663,0.054035563,0.0019528193,0.06730324,0.00022279532],"about_ca_topic_score_codex":0.008351371,"about_ca_topic_score_gemma":0.017886702,"teacher_disagreement_score":0.012563841,"about_ca_system_score_codex":0.00024107759,"about_ca_system_score_gemma":0.00033869018,"threshold_uncertainty_score":0.042030275},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.41493284419782056,"score_gpt":0.606574171447506,"score_spread":0.19164132724968547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045733287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15564106,0.000725964,0.7450889,0.0019048349,0.00036774194,0.002918394,0.0052547147,0.04988752,0.038210895],"genre_scores_gemma":[0.24391274,0.00043137828,0.7280725,0.00059837336,0.00005931856,0.0013708207,0.0032014358,0.005154738,0.017198596],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990364,0.0044900347,0.0008534279,0.00083751074,0.0031878168,0.0002670779],"domain_scores_gemma":[0.97886217,0.009190657,0.00060715433,0.0034745946,0.0074133156,0.00045221022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012273292,0.0009104646,0.0006882803,0.0021774285,0.001106428,0.0025094156,0.0016494327,0.0005090233,0.012192455],"category_scores_gemma":[0.026338594,0.0005625911,0.0006715319,0.00079158094,0.00071172905,0.0022175678,0.0028691455,0.0009081474,0.0044130203],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001205026,0.00056235096,0.04379442,0.0006975476,0.000250141,0.00043262096,0.003221236,0.003968872,0.04896602,0.0143994605,0.020080091,0.86242217],"study_design_scores_gemma":[0.000495243,0.0028930749,0.15589245,0.0012917683,0.0007206909,0.0035813705,0.005551542,0.20108443,0.222513,0.015256797,0.3901994,0.0005202856],"about_ca_topic_score_codex":0.0056827916,"about_ca_topic_score_gemma":0.007858182,"teacher_disagreement_score":0.012273292,"about_ca_system_score_codex":0.0012268673,"about_ca_system_score_gemma":0.0039194915,"threshold_uncertainty_score":0.06490815},"labels":[],"label_agreement":null},{"id":"W3047542501","doi":"10.3758/s13428-020-01437-w","title":"Semi-automated transcription and scoring of autobiographical memory narratives","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Narrative; Computer science; Natural language processing; Python (programming language); Pipeline (software); Autobiographical memory; Software; Transcription (linguistics); World Wide Web; Artificial intelligence; Information retrieval; Cognitive psychology; Psychology; Programming language; Linguistics","score_opus":0.34199784367457753,"score_gpt":0.5841662341372162,"score_spread":0.24216839046263872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047542501","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10619454,0.00064746017,0.82954854,0.0012502379,0.001398594,0.015255286,0.012834392,0.008926821,0.023944072],"genre_scores_gemma":[0.098118216,0.00063993223,0.85241514,0.00032560795,0.00027152285,0.024285696,0.006708208,0.0022497992,0.014985989],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9818211,0.010116159,0.002629991,0.0019255478,0.0031132298,0.00039401324],"domain_scores_gemma":[0.92282444,0.028125513,0.005404166,0.015727036,0.026413098,0.001505703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023029838,0.0015056045,0.0007926732,0.005737475,0.0023799955,0.0023717722,0.0019526725,0.0006608844,0.027507696],"category_scores_gemma":[0.085141994,0.0006408573,0.0007641048,0.0028096708,0.0013951357,0.0019051796,0.0039722696,0.0015016355,0.013069303],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006337881,0.00035762443,0.007916759,0.0029312354,0.000068101675,0.0010809308,0.05362396,0.00185726,0.06553798,0.014370631,0.07186649,0.77975535],"study_design_scores_gemma":[0.0003522166,0.00085939065,0.04172636,0.00286753,0.00014670822,0.0017746188,0.045458764,0.036409467,0.16721785,0.067046106,0.6354779,0.00066308095],"about_ca_topic_score_codex":0.0014098046,"about_ca_topic_score_gemma":0.0043158657,"teacher_disagreement_score":0.027507696,"about_ca_system_score_codex":0.0011857112,"about_ca_system_score_gemma":0.0042077326,"threshold_uncertainty_score":0.12179488},"labels":[],"label_agreement":null},{"id":"W3048953431","doi":"10.3758/s13428-020-01441-0","title":"On metrics for measuring scanpath similarity","year":2020,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Manitoba","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Similarity (geometry); Context (archaeology); Machine learning; Selection (genetic algorithm); Eye tracking; Process (computing); Data mining; Image (mathematics)","score_opus":0.782808445987271,"score_gpt":0.675500207103966,"score_spread":0.10730823888330498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048953431","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016584015,0.9142172,0.076102085,0.001196234,0.0005814667,0.00017158332,0.00077692734,0.0002749881,0.0050211493],"genre_scores_gemma":[0.03461015,0.8107372,0.14541657,0.001062104,0.0014140193,0.00079435454,0.0016819002,0.00015935602,0.0041243737],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99698204,0.0008717016,0.0002714172,0.00057689333,0.0012132372,0.00008472361],"domain_scores_gemma":[0.9833808,0.011918259,0.0010720154,0.00053210557,0.002908559,0.00018827531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053620245,0.0023041328,0.002816064,0.010718262,0.00046498544,0.002717671,0.002526941,0.0019641304,0.0040480774],"category_scores_gemma":[0.023539754,0.0005961586,0.0009669874,0.010377129,0.001606427,0.004143063,0.0012914945,0.0017228303,0.0014855186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050170613,0.000061040715,0.0014757928,0.006333752,0.0002117962,0.000019970426,0.00010147876,0.0011739695,0.00053184177,0.015011456,0.015043844,0.95998496],"study_design_scores_gemma":[0.0001837256,0.000990941,0.041395567,0.034934573,0.0024704516,0.0022540875,0.00094338733,0.046037566,0.007016826,0.20906278,0.6540976,0.00061247713],"about_ca_topic_score_codex":0.010011987,"about_ca_topic_score_gemma":0.010643796,"teacher_disagreement_score":0.010718262,"about_ca_system_score_codex":0.0026030836,"about_ca_system_score_gemma":0.002512202,"threshold_uncertainty_score":0.028357387},"labels":[],"label_agreement":null},{"id":"W3092821006","doi":"10.3758/s13428-020-01497-y","title":"Into a new decade","year":2020,"lang":"en","type":"editorial","venue":"Behavior Research Methods","topic":"Research Data Management Practices","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science","score_opus":0.4932811838024936,"score_gpt":0.656737719488052,"score_spread":0.16345653568555846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092821006","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002223791,0.026028851,0.0004218601,0.124934584,0.83368164,0.000013610202,0.00009759075,0.00013792157,0.014461557],"genre_scores_gemma":[0.005226333,0.043100595,0.0010736726,0.18880142,0.6423062,0.00006079747,0.00031740547,0.0002937764,0.11881983],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968225,0.0006032938,0.00030917846,0.0005401018,0.0013297265,0.00039523604],"domain_scores_gemma":[0.9892792,0.0031154796,0.0005240625,0.00044948127,0.0033981085,0.0032336167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041520954,0.0014671547,0.0008871086,0.0021551943,0.0024779097,0.010716886,0.0012529651,0.005576304,0.045914315],"category_scores_gemma":[0.021328464,0.00033149376,0.0008462189,0.0012637868,0.002842945,0.009035863,0.0036298663,0.0120216645,0.019034296],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038164028,0.000021686144,0.00007265892,0.00023762678,0.000007134397,0.00015496106,0.00016243049,0.00002096974,0.00009635111,0.010448318,0.95384943,0.034890234],"study_design_scores_gemma":[0.000003237529,0.0000049931573,0.000045816665,0.0001134247,0.0000022250467,0.00008216681,0.00008909508,0.000009510292,0.000017938575,0.0011876925,0.9984403,0.000003454084],"about_ca_topic_score_codex":0.0012083517,"about_ca_topic_score_gemma":0.003430587,"teacher_disagreement_score":0.045914315,"about_ca_system_score_codex":0.0029302572,"about_ca_system_score_gemma":0.0051291278,"threshold_uncertainty_score":0.15359873},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.47697900905892937,"score_gpt":0.582458395201068,"score_spread":0.10547938614213864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127637041","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027974343,0.00016618725,0.5029146,0.00014369174,0.00015525923,0.00022715656,0.01753788,0.4691687,0.0068890355],"genre_scores_gemma":[0.07050209,0.00054333283,0.6523693,0.0012714015,0.00015305645,0.0025881696,0.042725258,0.19418696,0.035660468],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99962497,0.000044565,0.0000493061,0.00010271002,0.0001137201,0.000064668035],"domain_scores_gemma":[0.9990314,0.00040281928,0.000065389104,0.00016909865,0.00024080934,0.00009052347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007026048,0.0018424032,0.0008077672,0.001205326,0.0004730176,0.0014265364,0.0024166475,0.00082137296,0.08657658],"category_scores_gemma":[0.0031488636,0.0009830943,0.0011471556,0.0008096228,0.00041726604,0.0012487813,0.0018867896,0.0018718909,0.043018326],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008111011,0.00028471622,0.003089774,0.0023341284,0.00036567613,0.0006709486,0.00045978327,0.014835937,0.031883124,0.015894007,0.58287007,0.3465007],"study_design_scores_gemma":[0.00079005683,0.00020357856,0.008725858,0.0005125254,0.00021740967,0.0014752803,0.00014736365,0.33461756,0.1019801,0.07826226,0.47264856,0.0004195804],"about_ca_topic_score_codex":0.0026810188,"about_ca_topic_score_gemma":0.0054880977,"teacher_disagreement_score":0.08657658,"about_ca_system_score_codex":0.0005101738,"about_ca_system_score_gemma":0.0013546777,"threshold_uncertainty_score":0.2896275},"labels":[],"label_agreement":null},{"id":"W3127812953","doi":"10.3758/s13428-020-01511-3","title":"ASIA: Automated Social Identity Assessment using linguistic style","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health via Writing","field":"Psychology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Population and Public Health; Engineering and Physical Sciences Research Council; European Association of Social Psychology","keywords":"Salient; Social identity theory; Identity (music); Variety (cybernetics); Style (visual arts); Social psychology; Field (mathematics); Computer science; Psychology; Protocol (science); Social media; Natural language processing; Interpretation (philosophy); Artificial intelligence; Social group; Cognitive psychology; Data science; World Wide Web; Mathematics","score_opus":0.5800148776480121,"score_gpt":0.739700750375458,"score_spread":0.15968587272744594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127812953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24210231,0.00038503495,0.6614449,0.00068640814,0.00062542834,0.0026581804,0.020399315,0.046012003,0.02568646],"genre_scores_gemma":[0.34206995,0.0001743134,0.62088567,0.00035189718,0.00016598272,0.0037198374,0.01802001,0.0014145663,0.013197858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948467,0.0020996276,0.00042073766,0.0010918612,0.001335171,0.00020591595],"domain_scores_gemma":[0.98993427,0.0035384344,0.0010724799,0.002142997,0.0027944217,0.0005173135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004793058,0.0012006011,0.0005549478,0.0042274185,0.00077705755,0.002638712,0.0011598316,0.0007915839,0.008409975],"category_scores_gemma":[0.019400612,0.00037667737,0.00062466285,0.0016192549,0.00053815666,0.0028873126,0.0036989793,0.0011939798,0.008577445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006824109,0.0005719238,0.06361479,0.000898191,0.0001846653,0.00051443913,0.010500841,0.003206368,0.051682822,0.0076149423,0.055043276,0.8054854],"study_design_scores_gemma":[0.00031592522,0.001144374,0.19348505,0.00044166608,0.00015575266,0.0016757481,0.014023076,0.46495682,0.09325671,0.057576623,0.17231221,0.0006560165],"about_ca_topic_score_codex":0.0014836688,"about_ca_topic_score_gemma":0.0029679677,"teacher_disagreement_score":0.008409975,"about_ca_system_score_codex":0.0005260073,"about_ca_system_score_gemma":0.00087533094,"threshold_uncertainty_score":0.028134167},"labels":[],"label_agreement":null},{"id":"W3135341785","doi":"10.3758/s13428-020-01528-8","title":"The Musical Ear Test: Norms and correlates from a large sample of Canadian undergraduates","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; General Electric (Canada); University of Toronto; Western University","funders":"Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Audiology; Rhythm; Memory span; Test (biology); Ceiling effect; Musical; Developmental psychology; Recall; Cognitive psychology; Cognition; Working memory; Medicine","score_opus":0.3206795973799662,"score_gpt":0.5131249007507384,"score_spread":0.19244530337077215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135341785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99561214,0.00021192011,0.00023241533,0.00011886813,0.000016467022,0.00013937375,0.0016369891,0.000010176366,0.0020215958],"genre_scores_gemma":[0.99253744,0.0004577864,0.00080095604,0.00021397135,0.0000188943,0.00013956618,0.0033579038,0.000029474575,0.0024440223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99756753,0.00014717437,0.0001736541,0.00037691032,0.0011433659,0.00059141713],"domain_scores_gemma":[0.99235183,0.0004183638,0.0006159093,0.00024683465,0.0051836898,0.0011834545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002179607,0.0007277767,0.0006700455,0.0035778538,0.0050918115,0.001664727,0.0022174055,0.0009146864,0.002578513],"category_scores_gemma":[0.0075936597,0.0004796839,0.0004774832,0.0058481055,0.0016559149,0.0007724282,0.001398324,0.0008484207,0.0008026218],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001408097,0.00020466816,0.9816576,0.000038324317,0.000038256763,0.00013444464,0.0050207134,0.00006864913,0.0007617162,0.00015273996,0.0022718047,0.009510259],"study_design_scores_gemma":[0.000008495175,0.000032058895,0.9967399,0.000010214549,0.000009353931,0.00006872407,0.002010784,0.000055805063,0.00006112141,0.00002588157,0.00096661656,0.000011019417],"about_ca_topic_score_codex":0.9544946,"about_ca_topic_score_gemma":0.9796978,"teacher_disagreement_score":0.045505404,"about_ca_system_score_codex":0.013931925,"about_ca_system_score_gemma":0.016312981,"threshold_uncertainty_score":0.10108364},"labels":[],"label_agreement":null},{"id":"W3140486864","doi":"10.3758/s13428-021-01556-y","title":"Is the author recognition test a useful metric for native and non-native English speakers? An item response theory analysis","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Hebrew University of Jerusalem","keywords":"Test (biology); Psychology; Reading (process); Item response theory; Neuroscience of multilingualism; First language; Foreign language; Language assessment; Linguistics; Cognitive psychology; Mathematics education; Psychometrics; Developmental psychology","score_opus":0.3218624457308632,"score_gpt":0.5860858601608735,"score_spread":0.2642234144300103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140486864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798029,0.0011159785,0.0074255266,0.0018502743,0.00013897731,0.00014286069,0.0011962315,0.0001672608,0.008159994],"genre_scores_gemma":[0.99126863,0.0002623129,0.0063526393,0.00030359725,0.00006119201,0.00013268192,0.0006342448,0.000023598413,0.000961031],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931144,0.0024053429,0.0011459545,0.0008110886,0.002272911,0.00025018895],"domain_scores_gemma":[0.9762725,0.011202212,0.0042591486,0.0014069654,0.0057038134,0.0011553263],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010561057,0.00046538183,0.0011355863,0.003616307,0.00037657487,0.0016931607,0.001008147,0.0011294961,0.0015352527],"category_scores_gemma":[0.036836147,0.0002342859,0.00068126037,0.001652081,0.0009875261,0.0018357324,0.0008260428,0.001050718,0.00069984555],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039565287,0.00019032067,0.9262638,0.00010563927,0.00022660017,0.00022590192,0.001430135,0.00021232615,0.001798947,0.00060251687,0.0016981435,0.06685],"study_design_scores_gemma":[0.00003576989,0.0007404127,0.9883668,0.00011938565,0.000110312,0.00060138694,0.0024086488,0.0024243728,0.0015051666,0.001233067,0.0024086135,0.00004600287],"about_ca_topic_score_codex":0.0028180184,"about_ca_topic_score_gemma":0.003988681,"teacher_disagreement_score":0.98943895,"about_ca_system_score_codex":0.00058672484,"about_ca_system_score_gemma":0.0007679087,"threshold_uncertainty_score":0.05585289},"labels":[],"label_agreement":null},{"id":"W3150425792","doi":"10.3758/s13428-021-01592-8","title":"The good and the bad: Are some attribute words better than others in the Implicit Association Test?","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Psychology; Implicit-association test; Cognitive psychology; Set (abstract data type); Test (biology); Quality (philosophy); Selection (genetic algorithm); Association (psychology); Social psychology; Artificial intelligence; Computer science","score_opus":0.19250705590750736,"score_gpt":0.5669183079270538,"score_spread":0.3744112520195464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150425792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929173,0.00033060988,0.0014410786,0.00073176954,0.00018241182,0.00003228754,0.00012018182,0.000017444918,0.004226924],"genre_scores_gemma":[0.9971034,0.00013512824,0.0013991076,0.000319157,0.00011079712,0.00005369302,0.00020006152,0.000029773551,0.0006489187],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9879772,0.00670376,0.0012793564,0.001788186,0.0017799273,0.0004714975],"domain_scores_gemma":[0.8238712,0.14014152,0.015110513,0.013069156,0.004438447,0.0033692135],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025291173,0.00102906,0.0015634261,0.001952351,0.001120405,0.004342454,0.002441673,0.0045014704,0.0074509955],"category_scores_gemma":[0.1131208,0.00072217407,0.00084638625,0.0014874927,0.003596433,0.010325687,0.0024618416,0.0030807897,0.0019057964],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012943694,0.0025773516,0.8850769,0.0003087201,0.0019155534,0.00027930274,0.005018571,0.0016075675,0.0049138726,0.0053186812,0.002499709,0.07754018],"study_design_scores_gemma":[0.0021828336,0.0043233153,0.8753342,0.0004747216,0.002309255,0.0014644604,0.009168169,0.026044851,0.006285973,0.0677532,0.0042675757,0.00039127818],"about_ca_topic_score_codex":0.0012151159,"about_ca_topic_score_gemma":0.0016852708,"teacher_disagreement_score":0.97470886,"about_ca_system_score_codex":0.00038833552,"about_ca_system_score_gemma":0.0006557904,"threshold_uncertainty_score":0.13375413},"labels":[],"label_agreement":null},{"id":"W3152214984","doi":"10.3758/s13428-021-01558-w","title":"Evaluating the predication model of metaphor comprehension: Using word2vec to model best/worst quality judgments of 622 novel metaphors","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metaphor; Comprehension; Set (abstract data type); Quality (philosophy); Computer science; Cognitive psychology; Cognition; Word2vec; Space (punctuation); Natural language processing; Psychology; Artificial intelligence; Linguistics; Epistemology; Philosophy","score_opus":0.7789337434495036,"score_gpt":0.6764091439089269,"score_spread":0.10252459954057669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152214984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97733307,0.0002939627,0.019282581,0.00025910887,0.00009517585,0.00004724131,0.0009850536,0.00050345383,0.0012003374],"genre_scores_gemma":[0.9882167,0.00005104806,0.009004673,0.00004906693,0.00001957252,0.000039890638,0.002168986,0.000050716775,0.00039934544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999276,0.0003384371,0.000045025,0.00019134703,0.00007144867,0.00007779191],"domain_scores_gemma":[0.99481344,0.004114409,0.0001917805,0.00027650443,0.00044414029,0.00015980916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022285965,0.001045867,0.0005271073,0.00094452134,0.0003728182,0.0017098197,0.000575653,0.0009611255,0.0019872787],"category_scores_gemma":[0.009603028,0.00024909046,0.0009721363,0.000763551,0.000379771,0.0015605221,0.00059664145,0.0014008165,0.0007162279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00966948,0.0040271254,0.2656587,0.00073582114,0.00172789,0.00079614366,0.0028496066,0.25690353,0.02864783,0.0056382725,0.027228087,0.39611745],"study_design_scores_gemma":[0.00005699892,0.00014876922,0.013522399,0.000013680445,0.00006022226,0.000049214315,0.00014071251,0.9823187,0.0014479557,0.0018086601,0.00040883827,0.000023814471],"about_ca_topic_score_codex":0.013306854,"about_ca_topic_score_gemma":0.012898641,"teacher_disagreement_score":0.013306854,"about_ca_system_score_codex":0.0008185464,"about_ca_system_score_gemma":0.00071302813,"threshold_uncertainty_score":0.0264588},"labels":[],"label_agreement":null},{"id":"W3156228691","doi":"10.3758/s13428-021-01570-0","title":"Calculating semantic relatedness of lists of nouns using WordNet path length","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"WordNet; Computer science; Noun; Natural language processing; Path (computing); Artificial intelligence; Semantic similarity; Information retrieval; Programming language","score_opus":0.25866170950767636,"score_gpt":0.5705119817345476,"score_spread":0.3118502722268713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156228691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6859854,0.0022834982,0.26671407,0.00052416924,0.0002518056,0.00071959774,0.021441476,0.003885984,0.018194074],"genre_scores_gemma":[0.7068229,0.0007606354,0.26794037,0.000089624715,0.00007368097,0.00056313956,0.019922763,0.0003894,0.0034374592],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998114,0.00044351604,0.0002847698,0.0005224368,0.0005195858,0.00011575739],"domain_scores_gemma":[0.99222505,0.0044349325,0.0007015261,0.000473049,0.0018570449,0.00030839653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001550246,0.0007088211,0.00064582063,0.011693373,0.0014077071,0.0017518264,0.00081804424,0.00090003107,0.006434465],"category_scores_gemma":[0.013288291,0.00040800148,0.0010087341,0.007976297,0.00057568616,0.0037616056,0.0014208381,0.00077814603,0.0023880987],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020100386,0.0007903472,0.23153761,0.0036017804,0.0010455671,0.0012541697,0.0047144084,0.015607428,0.05689689,0.05108492,0.016955087,0.6145017],"study_design_scores_gemma":[0.00041653548,0.0013048111,0.30616245,0.0008638071,0.0019127843,0.003568239,0.007934524,0.33495486,0.04372477,0.22381403,0.074991934,0.00035131178],"about_ca_topic_score_codex":0.0069666454,"about_ca_topic_score_gemma":0.011605832,"teacher_disagreement_score":0.011693373,"about_ca_system_score_codex":0.0011995004,"about_ca_system_score_gemma":0.0019205031,"threshold_uncertainty_score":0.021525443},"labels":[],"label_agreement":null},{"id":"W3161204446","doi":"10.3758/s13428-021-01583-9","title":"Introducing BITTSy: The Behavioral Infant &amp; Toddler Testing System","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"Graduate School, University of Maryland; National Science Foundation","keywords":"Toddler; Computer science; Software; Set (abstract data type); Fixation (population genetics); Human–computer interaction; Embedded system; Operating system; Programming language; Psychology; Medicine","score_opus":0.4514430033162071,"score_gpt":0.6074659095288819,"score_spread":0.15602290621267478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161204446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07788803,0.00084026693,0.6905244,0.0018205482,0.0007857557,0.0046368404,0.012943255,0.15133269,0.05922825],"genre_scores_gemma":[0.116522856,0.00084260793,0.789509,0.0019171239,0.0002890911,0.006054486,0.0059313034,0.011464271,0.0674692],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988776,0.00039738452,0.000090862304,0.00019276536,0.00036480368,0.00007661179],"domain_scores_gemma":[0.99720484,0.0014022161,0.0001273361,0.0003962634,0.00050753047,0.00036186917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022915702,0.0006928331,0.0004398681,0.00097376644,0.0002200163,0.0006696095,0.0010521425,0.0005193536,0.026747974],"category_scores_gemma":[0.005533283,0.00049634505,0.0004050435,0.00023112049,0.0003134915,0.0006793876,0.0020731387,0.00079997873,0.0098317545],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014483609,0.00079545786,0.037119623,0.00025886085,0.000078398734,0.0008015476,0.00072029815,0.0010712612,0.035512887,0.0035375974,0.09979109,0.81886464],"study_design_scores_gemma":[0.0010233062,0.0025448615,0.14000466,0.00076016004,0.0002445005,0.006774125,0.00052074814,0.051092457,0.07171381,0.008480134,0.7164117,0.000429497],"about_ca_topic_score_codex":0.0022985996,"about_ca_topic_score_gemma":0.0060603763,"teacher_disagreement_score":0.026747974,"about_ca_system_score_codex":0.00028560698,"about_ca_system_score_gemma":0.0009581357,"threshold_uncertainty_score":0.08948088},"labels":[],"label_agreement":null},{"id":"W3165834552","doi":"10.3758/s13428-021-01664-9","title":"OpenMaze: An open-source toolbox for creating virtual navigation experiments","year":2021,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; University of Toronto","funders":"","keywords":"Toolbox; Bespoke; Computer science; Human–computer interaction; Coding (social sciences); Variety (cybernetics); Task (project management); Software; Process (computing); Software engineering; Artificial intelligence; Systems engineering","score_opus":0.5711997562062917,"score_gpt":0.6509840627283027,"score_spread":0.07978430652201096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165834552","genre_codex":"review","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004117384,0.7059668,0.22085413,0.0015441052,0.0018138213,0.0018126013,0.0052983034,0.011049144,0.047543697],"genre_scores_gemma":[0.016908685,0.6829273,0.26520786,0.0016301521,0.0005953118,0.0046699233,0.0065871584,0.002099026,0.019374605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907684,0.00030823806,0.00013870621,0.000083631676,0.00036368537,0.000028801436],"domain_scores_gemma":[0.9967907,0.002188032,0.00022224175,0.00020506328,0.00048140655,0.000112557165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027648401,0.0012610658,0.0013428843,0.0036107718,0.00026216058,0.0011714279,0.0020766251,0.00086526637,0.020762607],"category_scores_gemma":[0.004883825,0.0004453411,0.0011333406,0.0020071473,0.0005538833,0.0016987119,0.0012146826,0.0013460438,0.00840795],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001264468,0.00016902888,0.00019508373,0.030887373,0.00015758545,0.00012704454,0.00020908621,0.0009547278,0.0059481775,0.0094091045,0.042889167,0.9089272],"study_design_scores_gemma":[0.00006749276,0.00016565726,0.00075306115,0.0041169478,0.00013336106,0.0004074183,0.000052616077,0.0004541583,0.0043246686,0.0052006184,0.9842568,0.00006728389],"about_ca_topic_score_codex":0.0005671484,"about_ca_topic_score_gemma":0.001454833,"teacher_disagreement_score":0.020762607,"about_ca_system_score_codex":0.00037859567,"about_ca_system_score_gemma":0.0012927221,"threshold_uncertainty_score":0.06945777},"labels":[],"label_agreement":null},{"id":"W3166385395","doi":"10.3758/s13428-021-01628-z","title":"The Early Social Cognition Inventory (ESCI): An examination of its psychometric properties from birth to 47 months","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cognition; Psychology; Cognitive test; Developmental psychology; Social cognition; Test (biology); Social cognitive theory; Clinical psychology; Pediatrics; Medicine; Psychiatry","score_opus":0.3798399237008766,"score_gpt":0.5371560630070777,"score_spread":0.15731613930620114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166385395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98333967,0.0008299444,0.0012156728,0.00016644564,0.000048249094,0.00040392924,0.0071257576,0.00009631656,0.0067739347],"genre_scores_gemma":[0.97261965,0.0013159586,0.0060972455,0.00013245043,0.000050248742,0.0013813898,0.013957659,0.000037525042,0.0044078394],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99906904,0.000121689845,0.00020057544,0.00009731019,0.0004474253,0.00006394156],"domain_scores_gemma":[0.99665254,0.00055067806,0.0012353857,0.00016133678,0.0010466719,0.00035330653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020794047,0.00050539005,0.00044800952,0.0019596247,0.00040145707,0.00048198822,0.0005631222,0.00028027807,0.0020561833],"category_scores_gemma":[0.005180047,0.00022604804,0.00070456613,0.0013878511,0.0002227712,0.0005765282,0.00091275806,0.00069826294,0.00050551054],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010073884,0.00021514474,0.95392746,0.00007528941,0.00011841219,0.00010513253,0.000672061,0.00019111077,0.0006264954,0.00008746377,0.002176365,0.041704442],"study_design_scores_gemma":[0.0000040847362,0.00009946131,0.9984785,0.000012612158,0.000008930141,0.00009157703,0.00008539891,0.000099633515,0.00012840537,0.000026660275,0.0009588217,0.000006030358],"about_ca_topic_score_codex":0.0063418923,"about_ca_topic_score_gemma":0.010268839,"teacher_disagreement_score":0.0063418923,"about_ca_system_score_codex":0.0005598664,"about_ca_system_score_gemma":0.0005919726,"threshold_uncertainty_score":0.012609959},"labels":[],"label_agreement":null},{"id":"W3166958512","doi":"10.3758/s13428-021-01602-9","title":"Building an intelligent recommendation system for personalized test scheduling in computerized assessments: A reinforcement learning approach","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Pace; Computer science; Test (biology); Scheduling (production processes); Reinforcement learning; Machine learning; Mathematics education; Psychology; Engineering; Operations management","score_opus":0.3273825167922156,"score_gpt":0.5494179913574728,"score_spread":0.22203547456525724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166958512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06510037,0.00013305893,0.91802835,0.000363091,0.000072290604,0.00047706862,0.00020588806,0.013952703,0.0016671567],"genre_scores_gemma":[0.57477504,0.00008438362,0.42181656,0.00017790988,0.000040761453,0.00031864134,0.00038503704,0.00020490607,0.0021966896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988502,0.00033156434,0.00011183582,0.00033948285,0.00027081787,0.00009609603],"domain_scores_gemma":[0.9962065,0.0016499418,0.00025871335,0.0003983351,0.0012620057,0.00022433675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021775402,0.0008142604,0.0013651113,0.001335224,0.0005943567,0.0011046918,0.002168379,0.0013166124,0.0025026584],"category_scores_gemma":[0.00722672,0.0006169715,0.00061355345,0.00068259396,0.00031133063,0.0013408713,0.00064458715,0.0013047004,0.0013221974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008160949,0.0022558477,0.020406151,0.00017306124,0.00035258936,0.00041315146,0.0003013519,0.18764856,0.02219383,0.0023904727,0.009914628,0.75313425],"study_design_scores_gemma":[0.0000351153,0.00005462541,0.00094896584,0.0000048970637,0.000035107198,0.00003527056,0.000016282298,0.9945984,0.0032645739,0.0004972854,0.0004937414,0.000015694473],"about_ca_topic_score_codex":0.018410882,"about_ca_topic_score_gemma":0.019968363,"teacher_disagreement_score":0.018410882,"about_ca_system_score_codex":0.0010532897,"about_ca_system_score_gemma":0.0015515551,"threshold_uncertainty_score":0.036607444},"labels":[],"label_agreement":null},{"id":"W3170480231","doi":"10.3758/s13428-021-01564-y","title":"The RK processor: A program for analysing metaphor and word feature-listing data","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metaphor; Computer science; Feature (linguistics); Ambiguity; Natural language processing; Word (group theory); Coding (social sciences); Artificial intelligence; Consistency (knowledge bases); Similarity (geometry); Information retrieval; Linguistics; Programming language","score_opus":0.4311475053656623,"score_gpt":0.6309512869748113,"score_spread":0.19980378160914897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170480231","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019777851,0.00016283889,0.65788037,0.00017434609,0.00015082241,0.0012478487,0.027803509,0.28745836,0.005343983],"genre_scores_gemma":[0.06658237,0.00017774991,0.87458426,0.00015237562,0.00008702825,0.00532296,0.017788278,0.025586499,0.009718412],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891603,0.00023211405,0.00018563334,0.00039085647,0.00017085989,0.00010453733],"domain_scores_gemma":[0.9940743,0.0044408846,0.00039615555,0.0005458998,0.0003921248,0.00015068515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002841049,0.0021090433,0.00097460405,0.0037797904,0.0006664758,0.0018561798,0.0012934426,0.00060374854,0.056417312],"category_scores_gemma":[0.01220723,0.000947559,0.0014113467,0.0024498631,0.0006129897,0.0023469164,0.0014797252,0.0016716087,0.018731102],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030333803,0.00065619976,0.016317017,0.0027484817,0.00051728013,0.0007201791,0.0028189134,0.002881817,0.03412187,0.013395719,0.16288766,0.7599014],"study_design_scores_gemma":[0.0015317482,0.0012753508,0.075468674,0.0006800554,0.0009190652,0.0023150698,0.0029486192,0.31882265,0.14870809,0.06132792,0.38531038,0.0006923654],"about_ca_topic_score_codex":0.0023130674,"about_ca_topic_score_gemma":0.0029495598,"teacher_disagreement_score":0.056417312,"about_ca_system_score_codex":0.00053983944,"about_ca_system_score_gemma":0.0015316308,"threshold_uncertainty_score":0.18873471},"labels":[],"label_agreement":null},{"id":"W3173672466","doi":"10.3758/s13428-021-01604-7","title":"Troubled past: A critical psychometric assessment of the self-report Survey of Autobiographical Memory (SAM)","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Douglas Mental Health University Institute; McGill University; McGill Genome Centre; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute on Aging; National Institutes of Health","keywords":"Autobiographical memory; Episodic memory; Psychology; Recall; Semantic memory; Childhood memory; Cognitive psychology; Association (psychology); Developmental psychology; Cognition; Psychiatry","score_opus":0.35808866813911666,"score_gpt":0.6406066858722068,"score_spread":0.28251801773309015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173672466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992059,0.00038954444,0.0021895939,0.00024462445,0.00007337963,0.0007083457,0.0007920527,0.000035127072,0.00350837],"genre_scores_gemma":[0.9933698,0.00028638347,0.0039103925,0.00016546239,0.0000363103,0.0004975951,0.0009959266,0.000020889844,0.0007171994],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970304,0.001037084,0.0006572801,0.00014706244,0.0009747625,0.00015344299],"domain_scores_gemma":[0.97338957,0.00820189,0.0054839225,0.0028808208,0.008654278,0.0013894915],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010497256,0.00035996735,0.00040974264,0.0021707376,0.0007805095,0.00094744755,0.000960067,0.00060055475,0.00073528587],"category_scores_gemma":[0.03773353,0.00044977485,0.00079377147,0.0012160498,0.0006600583,0.0010956998,0.0015181828,0.0011735304,0.00028702617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032448364,0.00051555404,0.95439804,0.00010705152,0.00010483889,0.00008750482,0.0020318036,0.00015183404,0.0010810914,0.00035574482,0.0010879892,0.03975402],"study_design_scores_gemma":[0.00002228514,0.0010003236,0.99219936,0.000055782737,0.000054299628,0.0003096543,0.00166883,0.0006771162,0.0009520167,0.0001935726,0.0028507505,0.000016098034],"about_ca_topic_score_codex":0.0029850535,"about_ca_topic_score_gemma":0.0054510892,"teacher_disagreement_score":0.9895027,"about_ca_system_score_codex":0.0007020142,"about_ca_system_score_gemma":0.0014993285,"threshold_uncertainty_score":0.055515468},"labels":[],"label_agreement":null},{"id":"W3174949916","doi":"10.3758/s13428-021-01636-z","title":"Challenging response latencies in faking detection: The case of few items and no warnings","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Lie detection; Computer science; Deception; Cognitive psychology; Applied psychology; Social psychology","score_opus":0.32414565031786513,"score_gpt":0.6050252207614508,"score_spread":0.2808795704435857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174949916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98742896,0.0004174138,0.0088962335,0.00030881423,0.000108977925,0.00011103103,0.00028597278,0.00010115692,0.0023413799],"genre_scores_gemma":[0.9965397,0.000037110476,0.0029109684,0.000050702194,0.000034571574,0.00009595369,0.00014020393,0.000037825168,0.00015299206],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9659186,0.01925457,0.0045057875,0.0038200826,0.0052292454,0.0012716578],"domain_scores_gemma":[0.41621038,0.49845678,0.04602837,0.028456394,0.008318064,0.0025300072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03888246,0.000844329,0.00094807957,0.0028270588,0.00077364105,0.0018357307,0.0009874644,0.0027256333,0.0043997183],"category_scores_gemma":[0.27163875,0.0005938884,0.0012400445,0.0022290598,0.0020738195,0.003505615,0.002370785,0.0026758756,0.0006492408],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008101799,0.00092547946,0.8993436,0.0008291958,0.0005625562,0.0026377572,0.005998457,0.0032475167,0.020520322,0.0017444106,0.0013448821,0.054744177],"study_design_scores_gemma":[0.00014000724,0.0018806608,0.96049553,0.00022385706,0.00034294563,0.0029113928,0.0017672431,0.015306713,0.011059763,0.0036560849,0.0020763692,0.00013941631],"about_ca_topic_score_codex":0.00074647064,"about_ca_topic_score_gemma":0.00084312825,"teacher_disagreement_score":0.03888246,"about_ca_system_score_codex":0.00068951887,"about_ca_system_score_gemma":0.0007140726,"threshold_uncertainty_score":0.20563257},"labels":[],"label_agreement":null},{"id":"W3178744861","doi":"10.3758/s13428-021-01630-5","title":"Scene wheels: Measuring perception and memory of real-world scenes with a continuous stimulus space","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Aesthetic Perception and Analysis","field":"Neuroscience","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perception; Mnemonic; Computer science; Artificial intelligence; Visual perception; Computer vision; Stimulus (psychology); Visual memory; Psychology; Cognitive psychology; Cognition","score_opus":0.3031626478333489,"score_gpt":0.5148994585921086,"score_spread":0.21173681075875972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178744861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9476521,0.00018742406,0.0471483,0.000049380338,0.00007127749,0.00036748484,0.0011035996,0.00035540084,0.0030650808],"genre_scores_gemma":[0.96532816,0.00016244214,0.030688198,0.00007502819,0.00001380745,0.00038190567,0.00059698924,0.00012415428,0.0026294168],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996662,0.00005620382,0.00002433441,0.00006911131,0.00013747795,0.000046680445],"domain_scores_gemma":[0.99887556,0.0003262915,0.00026735215,0.00015845893,0.00016726594,0.0002050263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044383298,0.00029067116,0.00024267206,0.00082709815,0.0002502266,0.00064707163,0.00074368267,0.00041606274,0.0059161256],"category_scores_gemma":[0.0032719418,0.00036626277,0.00036901966,0.0005160435,0.0004035435,0.0008410179,0.0009055017,0.00035022452,0.0005645442],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00630394,0.0017087867,0.0863236,0.0006773946,0.00034156247,0.00013806376,0.0010636125,0.002809449,0.7424806,0.0027575803,0.0030565083,0.15233892],"study_design_scores_gemma":[0.00029226902,0.002323218,0.87772834,0.00007815168,0.00027580973,0.00067563506,0.00069208577,0.026568538,0.0869494,0.0017578227,0.0025121758,0.00014663952],"about_ca_topic_score_codex":0.004585359,"about_ca_topic_score_gemma":0.0072242194,"teacher_disagreement_score":0.0059161256,"about_ca_system_score_codex":0.00035406096,"about_ca_system_score_gemma":0.0005762365,"threshold_uncertainty_score":0.019791365},"labels":[],"label_agreement":null},{"id":"W3195351601","doi":"10.3758/s13428-021-01679-2","title":"The Multiple Object Avoidance (MOA) task measures attention for action: Evidence from driving and sport","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Trent University; Nottingham Trent University","keywords":"Task (project management); Psychology; Cognitive psychology; Action (physics); Object (grammar); Computer science; Artificial intelligence","score_opus":0.48095421207596134,"score_gpt":0.6343246860396539,"score_spread":0.15337047396369252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195351601","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924005,0.0011278256,0.0024584536,0.00008903254,0.000022291892,0.00005700229,0.00017812291,0.000019117699,0.0036475917],"genre_scores_gemma":[0.99528366,0.0008726412,0.0020529788,0.000095945965,0.000029677014,0.000106005384,0.00038138544,0.000015267213,0.0011624192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984028,0.0003936704,0.00015174698,0.00037242385,0.00060495996,0.000074405],"domain_scores_gemma":[0.98977554,0.0040529673,0.0038018702,0.00081705354,0.0010705949,0.00048192946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002228466,0.00050958694,0.00035915102,0.0013760136,0.00043201415,0.0007012321,0.00067483785,0.00069372175,0.0015587363],"category_scores_gemma":[0.009870139,0.00027840922,0.000382968,0.00070179213,0.00087848096,0.000560942,0.0008883304,0.0005084385,0.00033902563],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000922963,0.001524625,0.8680589,0.0008035496,0.0007138414,0.00018110558,0.0030983174,0.0009142059,0.02495772,0.0004844068,0.00057828875,0.0977621],"study_design_scores_gemma":[0.0000058895907,0.00044485208,0.99688256,0.00002482596,0.000030276116,0.00015762796,0.00015151547,0.0002621773,0.0011956863,0.00021057398,0.00062062865,0.000013492494],"about_ca_topic_score_codex":0.0063936077,"about_ca_topic_score_gemma":0.012043426,"teacher_disagreement_score":0.0063936077,"about_ca_system_score_codex":0.0003209402,"about_ca_system_score_gemma":0.00039775798,"threshold_uncertainty_score":0.012712777},"labels":[],"label_agreement":null},{"id":"W3196590458","doi":"10.3758/s13428-022-01919-z","title":"Reliability of the empathy selection task, a novel behavioral measure of empathy avoidance","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Empathy; Psychology; Task (project management); Reliability (semiconductor); Selection (genetic algorithm); Cognitive psychology; Stroop effect; Social psychology; Computer science; Cognition; Artificial intelligence","score_opus":0.3840022036709241,"score_gpt":0.6043703302202744,"score_spread":0.22036812654935034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196590458","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97156245,0.00047002095,0.0159686,0.000112061534,0.00023092488,0.0003117892,0.00046645975,0.00008635009,0.010791313],"genre_scores_gemma":[0.9938261,0.00011812131,0.003361488,0.00011639209,0.000053477357,0.00025599042,0.00050084444,0.0000655182,0.0017021201],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9931075,0.0023244885,0.0005440648,0.001284388,0.0025109255,0.00022868723],"domain_scores_gemma":[0.9691657,0.016914593,0.0032596937,0.0034881942,0.006486846,0.0006850318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00936422,0.00049693865,0.00046615276,0.0007733543,0.00048570277,0.00079021003,0.00040330196,0.00090822787,0.0012146275],"category_scores_gemma":[0.036242183,0.00033745897,0.00059180567,0.00034535542,0.0005818659,0.00048144063,0.00078590703,0.0009796064,0.000844201],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026603588,0.001290721,0.88858485,0.00020846633,0.001115752,0.00013417662,0.004240517,0.0017612192,0.035091326,0.0012456947,0.003130471,0.06053642],"study_design_scores_gemma":[0.00008742741,0.0010631421,0.9895712,0.00003459617,0.0001558742,0.00027278307,0.00030175506,0.0022736616,0.0036196779,0.0005679792,0.0020137848,0.00003798755],"about_ca_topic_score_codex":0.0015595239,"about_ca_topic_score_gemma":0.0023515432,"teacher_disagreement_score":0.00936422,"about_ca_system_score_codex":0.0003008202,"about_ca_system_score_gemma":0.00044940496,"threshold_uncertainty_score":0.049523294},"labels":[],"label_agreement":null},{"id":"W3200105746","doi":"10.3758/s13428-021-01704-4","title":"The Early Humor Survey (EHS): A reliable parent-report measure of humor development for 1- to 47-month-olds","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Humor Studies and Applications","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Developmental psychology; Exploratory factor analysis; Clinical psychology; Psychometrics","score_opus":0.49298477628125853,"score_gpt":0.6242857224602868,"score_spread":0.13130094617902827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200105746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.990166,0.00027085573,0.001796678,0.00010279309,0.000023894694,0.00028741188,0.005266777,0.00009294963,0.0019927],"genre_scores_gemma":[0.98080635,0.00062577904,0.007169643,0.00011906037,0.000046979505,0.0010534112,0.007952498,0.000038002192,0.0021883063],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989164,0.00032763008,0.00020971945,0.00014412859,0.00030897107,0.00009309858],"domain_scores_gemma":[0.99285793,0.0013411022,0.0023829609,0.0005403399,0.0022814362,0.0005961622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024555684,0.0003499455,0.00044272357,0.0015857129,0.00043845188,0.00033958544,0.00033095505,0.00033440767,0.002781311],"category_scores_gemma":[0.0079998905,0.00025915727,0.00040066396,0.0005895796,0.00025392557,0.00056571874,0.00087245734,0.00056106894,0.0009359845],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104413695,0.0001516855,0.9498114,0.00017479267,0.00006695336,0.00021265725,0.004946507,0.000119031596,0.002491722,0.000094263094,0.0043231314,0.037503514],"study_design_scores_gemma":[0.0000053475273,0.00013929998,0.99682814,0.000022514254,0.000009650624,0.0001470542,0.00045882998,0.000049662023,0.00047851415,0.00002276531,0.0018303419,0.000007922324],"about_ca_topic_score_codex":0.0039330767,"about_ca_topic_score_gemma":0.0093049565,"teacher_disagreement_score":0.0039330767,"about_ca_system_score_codex":0.00030551723,"about_ca_system_score_gemma":0.00043710935,"threshold_uncertainty_score":0.012986422},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8389178653384918,"score_gpt":0.783184058779802,"score_spread":0.05573380655868976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200635405","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013164861,0.032772046,0.66576105,0.20098735,0.019718355,0.024378723,0.002326063,0.0032227056,0.037668843],"genre_scores_gemma":[0.022670232,0.007250939,0.933076,0.0119124185,0.0011830822,0.021142257,0.0005320939,0.00037169087,0.0018612621],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.18812072,0.6118799,0.107969716,0.011825754,0.0783514,0.0018524922],"domain_scores_gemma":[0.10182046,0.5111716,0.04191716,0.09307736,0.24721125,0.004802207],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.64079064,0.0033337036,0.004487307,0.017431252,0.007751729,0.011990635,0.010143029,0.012994833,0.00565308],"category_scores_gemma":[0.82798994,0.0047606123,0.0072412053,0.01401043,0.01322294,0.014392553,0.007966874,0.021829799,0.008411207],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010520667,0.0010426975,0.020390345,0.020508578,0.0019466623,0.0005816523,0.022115175,0.0014757819,0.002794451,0.039381582,0.1477341,0.7409769],"study_design_scores_gemma":[0.0022986194,0.0028970002,0.039690316,0.19420958,0.004561956,0.002216223,0.025301337,0.013059852,0.027879609,0.1651826,0.5203677,0.002335305],"about_ca_topic_score_codex":0.0066643246,"about_ca_topic_score_gemma":0.015480665,"teacher_disagreement_score":0.35920936,"about_ca_system_score_codex":0.0072190156,"about_ca_system_score_gemma":0.026389796,"threshold_uncertainty_score":0.44296914},"labels":[],"label_agreement":null},{"id":"W3204429926","doi":"10.3758/s13428-021-01659-6","title":"LIVE-streaming 3D images: A neuroscience approach to full-body illusions","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Transcranial Magnetic Stimulation Studies","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queensland University of Technology; Fonds De La Recherche Scientifique - FNRS; Universität Siegen; Canadian Institute for Advanced Research","keywords":"Illusion; Computer science; Transcranial magnetic stimulation; Set (abstract data type); Neuroscience; Psychology; Stimulation","score_opus":0.4231347299909947,"score_gpt":0.5608453545288526,"score_spread":0.13771062453785793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204429926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030517066,0.0020913293,0.94575983,0.0013120208,0.00021906431,0.000344602,0.00014384028,0.00043452947,0.019177685],"genre_scores_gemma":[0.25626466,0.002467921,0.7335258,0.0008748513,0.0001585242,0.00047684676,0.00010767342,0.000116462266,0.006007248],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997912,0.00006300139,0.000012279632,0.000045695084,0.000071965005,0.000015891721],"domain_scores_gemma":[0.9995432,0.00022758507,0.000044877543,0.0000793765,0.00006254443,0.00004237913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004526469,0.00045153656,0.00021155793,0.00050503056,0.00027879624,0.0012024129,0.0010171875,0.00074970216,0.0036087772],"category_scores_gemma":[0.0013267,0.00025701697,0.0005165898,0.00023343634,0.0019131174,0.0014595906,0.0017406795,0.0012566461,0.00043855404],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002964522,0.00023973593,0.0010317859,0.00085885415,0.000071267306,0.0008920413,0.0020707033,0.014989903,0.339768,0.26077145,0.0039284383,0.37508133],"study_design_scores_gemma":[0.00018321455,0.001321008,0.0059087696,0.00046388723,0.00014393091,0.0074155033,0.001042298,0.22175573,0.2381965,0.42771572,0.095562704,0.00029075454],"about_ca_topic_score_codex":0.00042874497,"about_ca_topic_score_gemma":0.00055755285,"teacher_disagreement_score":0.0036087772,"about_ca_system_score_codex":0.000507129,"about_ca_system_score_gemma":0.00041857734,"threshold_uncertainty_score":0.012072504},"labels":[],"label_agreement":null},{"id":"W360559091","doi":"10.3758/s13428-015-0602-3","title":"Norms for name agreement, familiarity, subjective frequency, and imageability for 348 object names in Tunisian Arabic","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut Universitaire en Santé Mentale de Québec","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Orthography; Word lists by frequency; Reading (process); Age of Acquisition; Arabic; Linguistics; Normative; Computer science; Word (group theory); Semantics (computer science); Phonology; Word recognition; Natural language processing; Psychology; Artificial intelligence; Cognition","score_opus":0.3438291449843307,"score_gpt":0.5920910447842678,"score_spread":0.24826189979993707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W360559091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966196,0.00006518796,0.00047216666,0.000036643512,0.000012046205,0.000026027543,0.00014554705,0.000005169286,0.0026176067],"genre_scores_gemma":[0.9975877,0.00005557899,0.001034715,0.00001725847,0.000007786246,0.000061698825,0.00020530965,0.000006055196,0.0010240157],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975026,0.0010286991,0.00037927233,0.00027712734,0.00066177413,0.00015044883],"domain_scores_gemma":[0.9912981,0.0035314986,0.0015057297,0.0005839924,0.0028132172,0.00026749325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004214405,0.00020742396,0.00020096697,0.0011567544,0.0006868757,0.0007206962,0.00030647675,0.00028355498,0.0023356625],"category_scores_gemma":[0.010580079,0.00017029846,0.00020677391,0.00087954797,0.0008970923,0.00055575476,0.00051841984,0.00035567777,0.0005163717],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004516947,0.00023210904,0.91306525,0.00009505645,0.00008294181,0.00024211529,0.036563747,0.0002188402,0.004826962,0.0009871661,0.001031763,0.042202342],"study_design_scores_gemma":[0.000011278693,0.00018625744,0.98173827,0.00004355323,0.00001773589,0.0003437559,0.0123225,0.0005737828,0.0015661969,0.0004036314,0.0027662278,0.000026892056],"about_ca_topic_score_codex":0.0103766145,"about_ca_topic_score_gemma":0.018134164,"teacher_disagreement_score":0.0103766145,"about_ca_system_score_codex":0.0007750623,"about_ca_system_score_gemma":0.0004758956,"threshold_uncertainty_score":0.022288203},"labels":[],"label_agreement":null},{"id":"W36973636","doi":"10.3758/s13428-023-02088-3","title":"Obesity among Pff-reserve First Nations, Métis, and Inuit Peoples in Canada’s Provinces: Associated Factors and Secular Trends","year":2012,"lang":"en","type":"dissertation","venue":"Behavior Research Methods","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metis; Obesity; Overweight; Demography; Socioeconomic status; Ethnic group; Body mass index; Geography; Odds; Medicine; Gerontology; Population; Political science; Logistic regression; Sociology","score_opus":0.08402551226420661,"score_gpt":0.4493321402713333,"score_spread":0.36530662800712665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36973636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99497557,0.0004893299,0.0002933686,0.00069921324,0.000010069145,0.000036189012,0.0022355479,0.000005454951,0.0012552275],"genre_scores_gemma":[0.99552923,0.0005408998,0.0008264134,0.00008861903,0.000005026948,0.000026867585,0.0014770698,0.000003613517,0.0015023283],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996283,0.00006744164,0.000015312142,0.00005854605,0.00008531766,0.00014514226],"domain_scores_gemma":[0.9991641,0.00014888762,0.00011415349,0.000046829602,0.00031295075,0.00021320781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011243621,0.00026795783,0.00030068945,0.0007041704,0.001702999,0.0008078434,0.0008225976,0.00045837494,0.0020045463],"category_scores_gemma":[0.0030578212,0.00014613154,0.00065689004,0.002124489,0.0003897359,0.00033573402,0.0006328132,0.0008213389,0.00012191135],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012772159,0.00011483642,0.98201776,0.000032568245,0.00009096168,0.00006272715,0.00132078,0.0011647226,0.00009770571,0.0005334477,0.0014526226,0.012984136],"study_design_scores_gemma":[0.000019184645,0.00004460347,0.9903833,0.00006007069,0.000079242054,0.000027648844,0.0032641795,0.004532316,0.00012636269,0.00021950429,0.0012268715,0.00001662205],"about_ca_topic_score_codex":0.99178493,"about_ca_topic_score_gemma":0.99371994,"teacher_disagreement_score":0.012606262,"about_ca_system_score_codex":0.012606262,"about_ca_system_score_gemma":0.021907419,"threshold_uncertainty_score":0.091465294},"labels":[],"label_agreement":null},{"id":"W4200273859","doi":"10.3758/s13428-021-01738-8","title":"Video playback versus live stimuli to assess quantity discrimination in angelfish (Pterophyllum scalare)","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Animal Behavior and Reproduction","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Universidad de Oviedo; Ministerio de Economía y Competitividad","keywords":"Stimulus (psychology); Shoal; Communication; Psychology; Cognitive psychology","score_opus":0.5557374849731176,"score_gpt":0.5590784985018049,"score_spread":0.00334101352868732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200273859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984756,0.00021495487,0.00060097815,0.000016638973,0.000009907944,0.00003835972,0.00015798544,0.000013582171,0.00047211442],"genre_scores_gemma":[0.9910772,0.00029286582,0.00447075,0.00010907463,0.000015435793,0.00023418119,0.00059533655,0.000020932524,0.0031842112],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998272,0.000015108293,0.00001729931,0.00006992803,0.00004050692,0.000029939567],"domain_scores_gemma":[0.9996644,0.00005812579,0.000107734835,0.0000134131815,0.000045842662,0.00011042714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016475127,0.000529921,0.00024604838,0.00057702215,0.00020394337,0.00023994318,0.00022304666,0.0005863919,0.0020774435],"category_scores_gemma":[0.0003870728,0.00022194373,0.00022722615,0.00020319647,0.0002848165,0.00045184378,0.00046517068,0.0005467323,0.00026291376],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044405833,0.00014408794,0.009430306,0.0001236944,0.000010398985,0.00009836144,0.00011631188,0.00004427126,0.9874342,0.000020998817,0.000030319987,0.0021030311],"study_design_scores_gemma":[0.000063869695,0.0075923097,0.7680514,0.000039560593,0.00006719396,0.0006112502,0.0006410513,0.001098778,0.22068232,0.00011449639,0.0010020912,0.000035603294],"about_ca_topic_score_codex":0.0013631891,"about_ca_topic_score_gemma":0.0032908625,"teacher_disagreement_score":0.0020774435,"about_ca_system_score_codex":0.00027891694,"about_ca_system_score_gemma":0.00015921434,"threshold_uncertainty_score":0.0069497228},"labels":[],"label_agreement":null},{"id":"W4200330936","doi":"10.3758/s13428-021-01717-z","title":"PuPl: an open-source tool for processing pupillometry data","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Research Foundation; McMaster University","keywords":"Pupillometry; Open source; Computer science; Human–computer interaction; Psychology; Pupil; Programming language; Neuroscience","score_opus":0.7890012828901644,"score_gpt":0.6870658849593866,"score_spread":0.10193539793077777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200330936","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003655099,0.0003155844,0.2786989,0.00013896411,0.00020253782,0.00032801443,0.04740197,0.66538644,0.0038725294],"genre_scores_gemma":[0.0767231,0.0008930672,0.58073086,0.0009757168,0.00022273757,0.0035794303,0.11304118,0.19901794,0.0248161],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99934536,0.00007338133,0.0000694954,0.00018810199,0.00024747715,0.00007627687],"domain_scores_gemma":[0.99808973,0.00093207345,0.00016273075,0.00037334868,0.0003029586,0.00013916113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013526567,0.0017878464,0.0012747148,0.002098128,0.0005010649,0.0017255396,0.0025462627,0.0010393759,0.097387545],"category_scores_gemma":[0.006259801,0.0010154451,0.0012313495,0.0011447939,0.00038544415,0.0015243276,0.0029302544,0.0015024157,0.036577623],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014075289,0.00029343186,0.00745441,0.0038685752,0.00076318416,0.0009353573,0.000664061,0.0048072757,0.04713666,0.0061920527,0.5436241,0.38285336],"study_design_scores_gemma":[0.0010088332,0.00041702186,0.027016021,0.00071930164,0.00039280218,0.0023675903,0.00036442318,0.14086223,0.15496232,0.034936614,0.6363445,0.0006083354],"about_ca_topic_score_codex":0.0017426452,"about_ca_topic_score_gemma":0.0034866584,"teacher_disagreement_score":0.097387545,"about_ca_system_score_codex":0.0004834602,"about_ca_system_score_gemma":0.0010810312,"threshold_uncertainty_score":0.3257938},"labels":[],"label_agreement":null},{"id":"W4200424524","doi":"10.3758/s13428-021-01735-x","title":"Evaluating the efficacy of an iPad® app in determining a single bout of exercise benefit to executive function","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Smartphone app; Physical medicine and rehabilitation; Session (web analytics); Equivalence (formal languages); Stroop effect; Physical therapy; Audiology; Cognition; Medicine; Computer science; Neuroscience; Mathematics","score_opus":0.7331761601180892,"score_gpt":0.6604872587517003,"score_spread":0.07268890136638884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200424524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99749714,0.00019734661,0.0009396972,0.000041599906,0.000040542764,0.00028259566,0.0001882249,0.000040534796,0.0007723825],"genre_scores_gemma":[0.9913305,0.00035550367,0.0048328303,0.00015234698,0.00007341916,0.00095464,0.00026610665,0.000015644846,0.002019084],"study_design_codex":"randomized_trial","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997224,0.00006477885,0.000023907816,0.00009421196,0.0000610985,0.000033474556],"domain_scores_gemma":[0.9984818,0.0009355616,0.00016799565,0.00006558001,0.00016801232,0.00018106255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009454808,0.00060646515,0.00049845176,0.00024376425,0.00015425964,0.0003672654,0.0002601847,0.00061199814,0.0022135011],"category_scores_gemma":[0.0025520264,0.00021550676,0.0003249962,0.00010192643,0.00018865943,0.00034526817,0.00021292937,0.00051855645,0.0005549923],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.32684594,0.062505215,0.11496721,0.002038204,0.0014409713,0.00031182825,0.000934766,0.0025656584,0.17848581,0.00020143746,0.0024046612,0.30729833],"study_design_scores_gemma":[0.007552683,0.40103528,0.5138098,0.00024053223,0.0027278885,0.00039766112,0.00033940593,0.009298388,0.061561782,0.00026036997,0.002676742,0.00009951299],"about_ca_topic_score_codex":0.00046286272,"about_ca_topic_score_gemma":0.001067591,"teacher_disagreement_score":0.0022135011,"about_ca_system_score_codex":0.00009826737,"about_ca_system_score_gemma":0.00022013632,"threshold_uncertainty_score":0.0074049234},"labels":[],"label_agreement":null},{"id":"W4200504981","doi":"10.3758/s13428-021-01753-9","title":"The Tapping Assay: A Simple Method to Induce Fear Responses in Zebrafish","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Celiac Association; University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Zebrafish; Anxiety; Stimulus (psychology); Neuroscience; Psychology; Computer science; Cognitive psychology; Biology; Psychiatry","score_opus":0.17854596067763234,"score_gpt":0.5785484567686334,"score_spread":0.4000024960910011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200504981","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57590294,0.004271958,0.38967612,0.0016288079,0.0007965111,0.0027298534,0.0047965646,0.0059072585,0.014289957],"genre_scores_gemma":[0.7193554,0.0053131618,0.22498713,0.0014636725,0.0001978496,0.0045557558,0.005076754,0.0012252321,0.03782497],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991493,0.00006884428,0.000072895615,0.00015746069,0.00041560526,0.0001358704],"domain_scores_gemma":[0.9996469,0.00005695174,0.000093574025,0.00005363434,0.00005800627,0.00009087315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000495145,0.0015455701,0.0005980634,0.0012259071,0.0006718926,0.00041435938,0.0010925885,0.00084421475,0.003023232],"category_scores_gemma":[0.0004315992,0.00047873057,0.0010545348,0.00032631474,0.0008625577,0.00063061324,0.0011407487,0.0022241191,0.0012595466],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021740268,0.000014762396,0.00008318634,0.000031655894,0.0000032536327,0.000037628393,0.000012593575,0.000017539427,0.99819547,0.00006472569,0.00014024953,0.0013771803],"study_design_scores_gemma":[0.000027365755,0.00049577636,0.005426299,0.000021373187,0.000034922978,0.0004103488,0.000028652657,0.00060239586,0.9897078,0.00016572129,0.0030411312,0.000038289094],"about_ca_topic_score_codex":0.0033779333,"about_ca_topic_score_gemma":0.0071685724,"teacher_disagreement_score":0.0033779333,"about_ca_system_score_codex":0.00067010394,"about_ca_system_score_gemma":0.0012615715,"threshold_uncertainty_score":0.010113716},"labels":[],"label_agreement":null},{"id":"W4200624835","doi":"10.3758/s13428-021-01740-0","title":"Valence norms for 3,600 English words collected during the COVID-19 pandemic: Effects of age and the pandemic","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Aging and Gerontology Research","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Brock University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Valence (chemistry); Pandemic; Emotional valence; Psychology; Coronavirus disease 2019 (COVID-19); Young adult; Stressor; Developmental psychology; Cognition; Demography; Clinical psychology; Medicine; Psychiatry; Disease; Sociology; Infectious disease (medical specialty)","score_opus":0.31449635730409486,"score_gpt":0.59901345804642,"score_spread":0.28451710074232517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200624835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99461925,0.00013675686,0.00024680595,0.00004805317,0.0000682183,0.000067187706,0.0014451699,0.000006982556,0.003361589],"genre_scores_gemma":[0.9925339,0.00023707618,0.00095881475,0.00016726795,0.000090754525,0.00025811404,0.004054567,0.00005107898,0.0016482949],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963462,0.0012643125,0.0006929559,0.00034412395,0.0011371583,0.00021528463],"domain_scores_gemma":[0.97366285,0.011294345,0.004273105,0.00091849745,0.0089803375,0.0008708953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032592104,0.00031667022,0.0003325529,0.001433993,0.0006841006,0.0021422154,0.00022527411,0.0005587717,0.0022129694],"category_scores_gemma":[0.027464807,0.00016998421,0.00033721136,0.0010701418,0.0006677305,0.0008290886,0.0010421993,0.00060033955,0.00072698935],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037038245,0.00054324523,0.90694153,0.0005865583,0.00036190744,0.00030210512,0.026444936,0.0003162618,0.02199364,0.00071269274,0.0028427052,0.03525061],"study_design_scores_gemma":[0.000019193621,0.00027207058,0.9881356,0.00005714484,0.000046637102,0.00015916115,0.0071148025,0.00017437777,0.0014054821,0.00014888686,0.0024292218,0.000037506066],"about_ca_topic_score_codex":0.0031575689,"about_ca_topic_score_gemma":0.007705707,"teacher_disagreement_score":0.0032592104,"about_ca_system_score_codex":0.0005704907,"about_ca_system_score_gemma":0.0003220924,"threshold_uncertainty_score":0.01723659},"labels":[],"label_agreement":null},{"id":"W4210525855","doi":"10.3758/s13428-021-01774-4","title":"Contrasting domain-general and domain-specific accounts in cognitive neuropsychology: An outline of a new approach with developmental prosopagnosia as a case","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Danmarks Frie Forskningsfond","keywords":"Neuropsychology; Psychology; Cognitive psychology; Cognition; Cognitive neuropsychology; Context (archaeology); Domain (mathematical analysis); Developmental psychology; Mechanism (biology); Cognitive science; Neuroscience; Epistemology","score_opus":0.4460085892567069,"score_gpt":0.549792555383548,"score_spread":0.1037839661268411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210525855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067884415,0.03315695,0.68590254,0.041367922,0.0010790322,0.00037119724,0.00023055768,0.0007361884,0.16927117],"genre_scores_gemma":[0.6748987,0.01810437,0.28744715,0.0045188465,0.0011723606,0.0010085122,0.000246878,0.00029391673,0.012309262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833894,0.0006365705,0.00019510803,0.00026599524,0.0002962737,0.00026719325],"domain_scores_gemma":[0.9972761,0.0015509443,0.00020290562,0.00052219676,0.0002590336,0.00018881344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006025732,0.0013306824,0.0015478934,0.0055819047,0.0020703578,0.009230641,0.0037891837,0.0043097474,0.0022722138],"category_scores_gemma":[0.0038069726,0.00080472487,0.0014565262,0.0023540468,0.028144227,0.020437287,0.006741595,0.0070449146,0.0004877434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015598745,0.000025853997,0.00085146446,0.000061007933,0.000011667332,0.00063568936,0.0022795326,0.0002334172,0.0006022289,0.98646,0.00041040566,0.008413191],"study_design_scores_gemma":[0.000008426389,0.00002532428,0.0012326478,0.000094506955,0.000016310372,0.0018102798,0.0013924164,0.0021477633,0.0005359399,0.9851267,0.0075776894,0.000032054253],"about_ca_topic_score_codex":0.0019196302,"about_ca_topic_score_gemma":0.003115041,"teacher_disagreement_score":0.009230641,"about_ca_system_score_codex":0.002576151,"about_ca_system_score_gemma":0.00198666,"threshold_uncertainty_score":0.031867504},"labels":[],"label_agreement":null},{"id":"W4210535774","doi":"10.3758/s13428-021-01771-7","title":"A Novel Approach for Developing Efficient and Convenient Short Assessments to Approximate a Long Assessment","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Statistics; Mathematics","score_opus":0.6484728603350225,"score_gpt":0.7123271134612921,"score_spread":0.06385425312626958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210535774","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004464782,0.000065605665,0.99347246,0.00007597388,0.00005039313,0.00012195469,0.00011306513,0.0009320445,0.00070377527],"genre_scores_gemma":[0.074466586,0.00009055134,0.9220629,0.00015787357,0.00010624036,0.0006111288,0.00048006748,0.00024065109,0.0017841196],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9940691,0.0021672812,0.0005489856,0.0011453109,0.0018412732,0.00022807538],"domain_scores_gemma":[0.9854783,0.004820763,0.0018175265,0.0032627673,0.0041914782,0.00042914553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005563954,0.001724276,0.0011774449,0.0018052455,0.00071733765,0.0017871021,0.0018964506,0.0009745822,0.00550999],"category_scores_gemma":[0.026446726,0.0007748935,0.0011934867,0.0011798217,0.0006568397,0.0032515593,0.002821392,0.0023835918,0.0032207707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007538981,0.0005950109,0.009407529,0.00028143683,0.00019037521,0.00020373544,0.00053942885,0.04864087,0.021624947,0.019505208,0.007820267,0.8904373],"study_design_scores_gemma":[0.000106913416,0.0010163164,0.009288116,0.00013293984,0.00009615571,0.0005922744,0.00027571715,0.90053153,0.016948538,0.041339643,0.029519433,0.00015244084],"about_ca_topic_score_codex":0.002889831,"about_ca_topic_score_gemma":0.0040741544,"teacher_disagreement_score":0.005563954,"about_ca_system_score_codex":0.0008967125,"about_ca_system_score_gemma":0.00172261,"threshold_uncertainty_score":0.029425383},"labels":[],"label_agreement":null},{"id":"W4210546055","doi":"10.3758/s13428-022-01798-4","title":"Quantifying children’s sensorimotor experience: Child body–object interaction ratings for 3359 English words","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Referent; Psychology; Embodied cognition; Cognitive psychology; Age of Acquisition; Perspective (graphical); Cognition; Object (grammar); Valence (chemistry); Developmental psychology; Linguistics; Computer science; Artificial intelligence","score_opus":0.36302458373415386,"score_gpt":0.6036297274374163,"score_spread":0.24060514370326241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210546055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99086654,0.000117129195,0.0014128102,0.00003569715,0.000015950221,0.00006072093,0.0007025467,0.000057385023,0.0067311567],"genre_scores_gemma":[0.9875958,0.00036038237,0.005249089,0.000042105232,0.000010047387,0.00028727477,0.0007733975,0.000084569605,0.005597338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991991,0.0001379485,0.00012989476,0.00014012541,0.00027806978,0.00011485495],"domain_scores_gemma":[0.99623364,0.0015141766,0.0009371407,0.00021390292,0.0008315674,0.000269604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012209825,0.0004087883,0.0003748871,0.00090715935,0.00029856784,0.0006511956,0.00029565478,0.00040931124,0.008924694],"category_scores_gemma":[0.007017369,0.0002088821,0.00043937613,0.0005137772,0.0004810498,0.000725938,0.00082474964,0.0005028426,0.0012552154],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027770274,0.0004897252,0.57518226,0.0011178034,0.00019387405,0.0017542073,0.02711281,0.0007629477,0.25840184,0.0013382041,0.0041734423,0.12669572],"study_design_scores_gemma":[0.000020482059,0.0006607236,0.9737965,0.000054877215,0.00007046078,0.00060157734,0.0043066805,0.00037876947,0.016624497,0.00011484032,0.0033384347,0.000032336793],"about_ca_topic_score_codex":0.0044209696,"about_ca_topic_score_gemma":0.01165689,"teacher_disagreement_score":0.008924694,"about_ca_system_score_codex":0.00028791497,"about_ca_system_score_gemma":0.000316164,"threshold_uncertainty_score":0.029856086},"labels":[],"label_agreement":null},{"id":"W4210746747","doi":"10.3758/s13428-021-01732-0","title":"Visual and semantic similarity norms for a photographic image stimulus set containing recognizable objects, animals and scenes","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Mental Health; National Institutes of Health; National Science Foundation","keywords":"Multidimensional scaling; Semantic similarity; Similarity (geometry); Artificial intelligence; Computer science; Pattern recognition (psychology); Set (abstract data type); Categorization; Stimulus (psychology); Visual perception; Cognitive psychology; Natural language processing; Psychology; Image (mathematics); Perception; Machine learning","score_opus":0.22452910133432574,"score_gpt":0.5455105804287299,"score_spread":0.32098147909440417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210746747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.964802,0.00016084455,0.027999178,0.000112314476,0.00007410158,0.00021974657,0.0010634634,0.00020262333,0.0053657866],"genre_scores_gemma":[0.9722745,0.00006681853,0.025080234,0.00003065273,0.000023690951,0.00017232979,0.0016098068,0.000057531775,0.0006845797],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99967504,0.000062978026,0.000033119115,0.00007456493,0.00012754968,0.000026808144],"domain_scores_gemma":[0.9979189,0.0010403988,0.00023755748,0.00014393976,0.0005159742,0.00014327308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008362732,0.00018949452,0.00021225418,0.0008742323,0.00016312854,0.0005158881,0.00022150464,0.00024875416,0.0023201394],"category_scores_gemma":[0.0072666495,0.000057472593,0.000260274,0.00037676858,0.0004058333,0.00047647746,0.00038749995,0.00027818952,0.00014432798],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008240556,0.0011192512,0.024894021,0.001156232,0.00021642743,0.0002404349,0.0008898609,0.015103251,0.6966149,0.021768924,0.0043995595,0.22535665],"study_design_scores_gemma":[0.00041577447,0.0034124586,0.5330793,0.00016307837,0.00032644224,0.0022840288,0.0014025727,0.29754695,0.12725092,0.02684742,0.007039969,0.00023106072],"about_ca_topic_score_codex":0.0021107432,"about_ca_topic_score_gemma":0.0027272317,"teacher_disagreement_score":0.0023201394,"about_ca_system_score_codex":0.0006468712,"about_ca_system_score_gemma":0.00029577402,"threshold_uncertainty_score":0.0077616572},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.42039436511020484,"score_gpt":0.6630701278381799,"score_spread":0.24267576272797503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210813972","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7625936,0.019139286,0.02129516,0.0092039425,0.001373139,0.00035589281,0.02006407,0.00051913183,0.16545561],"genre_scores_gemma":[0.9437575,0.00448746,0.02524397,0.0013477461,0.0004316546,0.00066799065,0.01137974,0.00074819394,0.011935702],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978688,0.0009541759,0.00020288161,0.00043365403,0.0003750083,0.00016538119],"domain_scores_gemma":[0.9820478,0.012790433,0.0006048457,0.0020163525,0.0017684218,0.0007720904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004057923,0.00043043378,0.0005312944,0.0054022376,0.0021082768,0.0036942903,0.0008248935,0.000868067,0.007970511],"category_scores_gemma":[0.014534718,0.00021621706,0.00016966811,0.0044950093,0.002113872,0.00307444,0.0065184343,0.0012087667,0.00096156046],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011449124,0.0005394865,0.040084727,0.003392461,0.00015613149,0.0015350047,0.070791796,0.00079362513,0.035931773,0.056406938,0.041822206,0.74740106],"study_design_scores_gemma":[0.00011896388,0.00021305049,0.3084545,0.0025908346,0.00012564598,0.002305059,0.04955725,0.0016539607,0.012911198,0.019930633,0.60193866,0.00020015806],"about_ca_topic_score_codex":0.011628948,"about_ca_topic_score_gemma":0.03822964,"teacher_disagreement_score":0.011628948,"about_ca_system_score_codex":0.0011969125,"about_ca_system_score_gemma":0.002481174,"threshold_uncertainty_score":0.026664019},"labels":[],"label_agreement":null},{"id":"W4212782570","doi":"10.3758/s13428-020-01506-0","title":"Correction to: Editorial: Into a new decade","year":2022,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Information retrieval; Data science","score_opus":0.44132939814837524,"score_gpt":0.6685985257114079,"score_spread":0.22726912756303264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212782570","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017520471,0.00037423623,0.00009332883,0.03999133,0.9584744,0.000010027433,0.000109186985,0.000046979818,0.00088310364],"genre_scores_gemma":[0.0014198736,0.0027217604,0.00084184227,0.1140712,0.82596654,0.00010906158,0.00027137436,0.0004009202,0.054197423],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98448944,0.0028640544,0.002590203,0.0017244668,0.007223958,0.0011077945],"domain_scores_gemma":[0.8924187,0.034727033,0.004732964,0.0050932392,0.05669794,0.0063301926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012886498,0.0028241284,0.0035546145,0.0066491235,0.0067468104,0.011677101,0.004852867,0.01611632,0.051669262],"category_scores_gemma":[0.13137795,0.0015120289,0.0021932735,0.0040944032,0.005045371,0.00469467,0.0034487266,0.020559436,0.036009207],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007853174,0.0000030083152,0.000013192592,0.000046191988,0.000004470939,0.000042311294,0.000009471787,0.0000064454075,0.000006990601,0.00021510226,0.99854773,0.0010971822],"study_design_scores_gemma":[0.000043786047,0.000012652531,0.00028691324,0.00052735704,0.000043889897,0.00015762803,0.00009781441,0.00012336986,0.00008636761,0.0013621429,0.99723107,0.000027071337],"about_ca_topic_score_codex":0.015364583,"about_ca_topic_score_gemma":0.025956398,"teacher_disagreement_score":0.051669262,"about_ca_system_score_codex":0.007857904,"about_ca_system_score_gemma":0.013646435,"threshold_uncertainty_score":0.1728509},"labels":[],"label_agreement":null},{"id":"W4213112533","doi":"10.3758/s13428-022-01801-y","title":"Machine learning to detect invalid text responses: Validation and comparison to existing detection methods","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Coding (social sciences); Word (group theory); Machine learning; Code (set theory); Quality (philosophy); Information retrieval; Linguistics; Statistics","score_opus":0.421437191862916,"score_gpt":0.5856823952146699,"score_spread":0.1642452033517539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213112533","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61498755,0.002327274,0.3637306,0.0006438135,0.00067270943,0.0020355296,0.0028040307,0.0063055595,0.006492964],"genre_scores_gemma":[0.8483266,0.0006065616,0.14284112,0.0002884029,0.00019512931,0.00082459813,0.0026999887,0.0002733419,0.003944223],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9872499,0.006348735,0.0012018725,0.0016495264,0.0031067887,0.00044327206],"domain_scores_gemma":[0.888906,0.08579237,0.0049608843,0.0069124154,0.012433184,0.0009950494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014740348,0.0012825785,0.0012315835,0.0048763086,0.0007867283,0.0014963526,0.0021258956,0.001788404,0.0026610822],"category_scores_gemma":[0.056078736,0.00023186146,0.0007132619,0.0018369692,0.0006271202,0.0020752293,0.0011792284,0.0016254399,0.0022387507],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037381537,0.0051403097,0.10165739,0.0012899712,0.0006364932,0.00023192246,0.00093884626,0.018702846,0.014048349,0.001685065,0.007489231,0.8444415],"study_design_scores_gemma":[0.00033462053,0.002258298,0.052063692,0.00025178154,0.0004196089,0.0007968134,0.00070583617,0.9087516,0.02681953,0.003375618,0.004108669,0.000113866925],"about_ca_topic_score_codex":0.0027526466,"about_ca_topic_score_gemma":0.0022743032,"teacher_disagreement_score":0.014740348,"about_ca_system_score_codex":0.00086031924,"about_ca_system_score_gemma":0.0015895729,"threshold_uncertainty_score":0.077955365},"labels":[],"label_agreement":null},{"id":"W4220858191","doi":"10.3758/s13428-022-01803-w","title":"Audio-Tokens: A toolbox for rating, sorting and comparing audio samples in the browser","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Research on Brain Language and Music; McGill University; Montreal Neurological Institute and Hospital","funders":"Canada First Research Excellence Fund; Centre for Research on Brain, Language and Music; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Toolbox; Computer science; JavaScript; Feature (linguistics); Plug-in; Categorical variable; Speech recognition; Artificial intelligence; Machine learning; World Wide Web","score_opus":0.6559392404991495,"score_gpt":0.5947403805143804,"score_spread":0.06119885998476915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220858191","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020315193,0.0009549057,0.35680377,0.00020233048,0.00027728968,0.0007739632,0.055756636,0.5724443,0.0107553005],"genre_scores_gemma":[0.032644805,0.0017329664,0.6182953,0.0011198117,0.00028575532,0.006239825,0.10253197,0.20233215,0.03481742],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983909,0.00032721707,0.00027583016,0.00035432418,0.0005027005,0.0001489216],"domain_scores_gemma":[0.9934454,0.003108685,0.00038061242,0.0012430513,0.0012649043,0.00055729965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026801967,0.0032212744,0.0018046938,0.0033950503,0.00043605248,0.0028039878,0.0028773355,0.0013399497,0.14934766],"category_scores_gemma":[0.012495128,0.0017747603,0.0014576099,0.0015517037,0.0005519015,0.0028827032,0.003974736,0.0020708444,0.1352705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016145433,0.00035815084,0.0028954425,0.003344483,0.000250866,0.00068262726,0.0005704113,0.0020726924,0.028861783,0.0060191536,0.6119823,0.34134752],"study_design_scores_gemma":[0.000987017,0.00033612,0.01477376,0.0013624706,0.00017713952,0.0022183836,0.00030167264,0.032622505,0.049563237,0.04176807,0.8553191,0.0005704421],"about_ca_topic_score_codex":0.0010326727,"about_ca_topic_score_gemma":0.0022459656,"teacher_disagreement_score":0.14934766,"about_ca_system_score_codex":0.00050733687,"about_ca_system_score_gemma":0.0013461118,"threshold_uncertainty_score":0.4996177},"labels":[],"label_agreement":null},{"id":"W4221022654","doi":"10.3758/s13428-022-01810-x","title":"Quantifying social semantics: An inclusive definition of socialness and ratings for 8388 English words","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada; Mitacs; British Psychological Society; UK Research and Innovation","keywords":"Concreteness; Noun; Psychology; Cognitive psychology; Semantics (computer science); Meaning (existential); Computer science; Natural language processing; Linguistics","score_opus":0.5543549710857866,"score_gpt":0.6303453224183189,"score_spread":0.07599035133253229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221022654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912102,0.00009657062,0.0050587594,0.00002338166,0.0000118275275,0.00010868978,0.00067453884,0.000036630274,0.002779338],"genre_scores_gemma":[0.98945487,0.000069943446,0.007838174,0.00002222534,0.0000210563,0.0003928247,0.001656268,0.000042658718,0.00050204055],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99341077,0.00243718,0.0012655153,0.0006624332,0.0020621738,0.00016184605],"domain_scores_gemma":[0.96395123,0.019664818,0.0074094655,0.0029077074,0.0052051917,0.0008616202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051231044,0.00048226072,0.00046323062,0.0028760443,0.00051006,0.0011858428,0.0003960982,0.00056934217,0.002229518],"category_scores_gemma":[0.037730135,0.00018127389,0.00032532602,0.0019626457,0.0010742858,0.0014108152,0.0021072777,0.0003983194,0.00058024406],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013885755,0.00051216467,0.7120656,0.0010287426,0.00050155347,0.00038258638,0.028560106,0.0016738517,0.046346374,0.004083298,0.0028674693,0.20058976],"study_design_scores_gemma":[0.000040131014,0.00037403277,0.97552943,0.00007246995,0.00006648206,0.00037875047,0.005823152,0.0048631313,0.005154421,0.0029707677,0.0046233884,0.00010385039],"about_ca_topic_score_codex":0.000771859,"about_ca_topic_score_gemma":0.001730742,"teacher_disagreement_score":0.0051231044,"about_ca_system_score_codex":0.00034212903,"about_ca_system_score_gemma":0.0002051958,"threshold_uncertainty_score":0.027093887},"labels":[],"label_agreement":null},{"id":"W4224263986","doi":"10.3758/s13428-022-01845-0","title":"IAT faking indices revisited: Aspects of replicability and differential validity","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Context (archaeology); Block (permutation group theory); Task (project management); Cognitive psychology; Social psychology; Mathematics","score_opus":0.5770403301936822,"score_gpt":0.6674394156831788,"score_spread":0.0903990854894966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224263986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6952352,0.009111567,0.24510054,0.004633338,0.0018833451,0.002370088,0.00088040926,0.0010647936,0.039720643],"genre_scores_gemma":[0.96713144,0.0004631639,0.028862292,0.00048253877,0.00033953146,0.0009595396,0.00035061897,0.00035517936,0.001055704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.81677353,0.113211535,0.0152911665,0.01793218,0.03473208,0.0020595163],"domain_scores_gemma":[0.3130399,0.5236849,0.024770364,0.110560425,0.026420929,0.0015234066],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22317666,0.0017526997,0.0029367928,0.008993589,0.0018027484,0.0043410566,0.0046134265,0.0018609707,0.0031509658],"category_scores_gemma":[0.5018949,0.001321201,0.0038684774,0.005354332,0.013535924,0.0063588624,0.006481575,0.005562901,0.0007289338],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026380918,0.00048524802,0.66247827,0.0018187484,0.0055467584,0.0006168948,0.016217079,0.003472629,0.004942174,0.048500124,0.0034701691,0.24981384],"study_design_scores_gemma":[0.0005316765,0.0027928827,0.7143252,0.001900609,0.0027361629,0.0022201708,0.005282592,0.04926848,0.011967578,0.18965162,0.018870138,0.00045274792],"about_ca_topic_score_codex":0.0028173833,"about_ca_topic_score_gemma":0.0025165107,"teacher_disagreement_score":0.77682334,"about_ca_system_score_codex":0.0016713779,"about_ca_system_score_gemma":0.0022415794,"threshold_uncertainty_score":0.9579615},"labels":[],"label_agreement":null},{"id":"W4225015069","doi":"10.3758/s13428-022-01861-0","title":"Accuracy of paper-and-pencil systematic observation versus computer-aided systems","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Universidad Autónoma de Madrid; University of Auckland","keywords":"Pencil (optics); Computer science; Computer-aided; Computer graphics (images); Artificial intelligence; Programming language; Engineering","score_opus":0.8223134969967072,"score_gpt":0.6146735580251322,"score_spread":0.20763993897157496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225015069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8848554,0.003131823,0.09882665,0.00061646826,0.0003224665,0.0007876658,0.0005609496,0.0006464303,0.010252145],"genre_scores_gemma":[0.96479243,0.0007500268,0.03246757,0.00015126132,0.00006250446,0.00026860528,0.00016138918,0.00008861075,0.0012576581],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9558015,0.027122138,0.005054812,0.003008941,0.008362402,0.0006501624],"domain_scores_gemma":[0.7367765,0.20451166,0.024138631,0.016216343,0.017212473,0.0011443935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0309293,0.0005536611,0.0006661761,0.0010006122,0.00036635966,0.0019865194,0.00074816734,0.0006531302,0.0022603828],"category_scores_gemma":[0.1900405,0.00038696578,0.00059775513,0.00104364,0.0010654218,0.0014493902,0.0015077795,0.0007906913,0.000628586],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012957823,0.00085552793,0.28311703,0.0034764216,0.00093684567,0.00012641744,0.010163522,0.0031557016,0.03137652,0.001400555,0.0019839844,0.6504497],"study_design_scores_gemma":[0.0005972855,0.013047085,0.8828463,0.0015778763,0.00088782504,0.0007953519,0.004952413,0.01982813,0.06256787,0.0032357678,0.009315594,0.0003484188],"about_ca_topic_score_codex":0.0016397419,"about_ca_topic_score_gemma":0.002917235,"teacher_disagreement_score":0.9690707,"about_ca_system_score_codex":0.00061730656,"about_ca_system_score_gemma":0.0009998317,"threshold_uncertainty_score":0.16357172},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7737194927129117,"score_gpt":0.7106257387479584,"score_spread":0.06309375396495331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225749806","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012063116,0.12829249,0.044543687,0.6678098,0.14434817,0.0031279528,0.0036195081,0.00087486027,0.0061772666],"genre_scores_gemma":[0.029082494,0.18795308,0.22278956,0.47423562,0.04996961,0.022980036,0.0046959976,0.0008192372,0.007474436],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.71222705,0.11171349,0.11818059,0.0066222316,0.048637263,0.002619282],"domain_scores_gemma":[0.22909996,0.4860254,0.04812748,0.020619744,0.21201226,0.0041151326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26151618,0.0016058657,0.004242264,0.00925839,0.0033936484,0.007492394,0.009410536,0.013549556,0.006320932],"category_scores_gemma":[0.6604512,0.0020865926,0.004470763,0.0068873246,0.007568468,0.010288505,0.008627469,0.021291455,0.004701696],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019629962,0.00010329979,0.0014983539,0.05308515,0.0004743563,0.00036946728,0.0020443483,0.0003228565,0.00048137765,0.028697802,0.74838376,0.16434295],"study_design_scores_gemma":[0.00019746876,0.0002225581,0.003744021,0.18517093,0.0016343194,0.000753122,0.0014654443,0.0007576901,0.0012575618,0.028417073,0.77617,0.00020986385],"about_ca_topic_score_codex":0.0067255055,"about_ca_topic_score_gemma":0.007824491,"teacher_disagreement_score":0.7384838,"about_ca_system_score_codex":0.0075582885,"about_ca_system_score_gemma":0.039072555,"threshold_uncertainty_score":0.910682},"labels":[],"label_agreement":null},{"id":"W4226366257","doi":"10.3758/s13428-022-01858-9","title":"Waiting for baseline stability in single-case designs: Is it worth the time and effort?","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut universitaire en santé mentale de Montréal; Université de Montréal; Institut Universitaire en Santé Mentale de Québec","funders":"","keywords":"Baseline (sea); Computer science; Classifier (UML); Stability (learning theory); Machine learning; Support vector machine; Multiple baseline design; Monte Carlo method; Artificial intelligence; Graph; Statistics; Mathematics; Psychology; Theoretical computer science","score_opus":0.872368813169848,"score_gpt":0.6139927190547214,"score_spread":0.25837609411512663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226366257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035185404,0.01572693,0.84324145,0.07709104,0.012283665,0.008835361,0.00056868873,0.0019528645,0.005114566],"genre_scores_gemma":[0.24379312,0.0029943972,0.7009397,0.025503764,0.004033473,0.020470522,0.00034735663,0.00053087075,0.0013867808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.4278531,0.47619894,0.04265254,0.017720433,0.033874534,0.001700498],"domain_scores_gemma":[0.09419916,0.7471616,0.057929967,0.06640577,0.031396106,0.0029072769],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.61638993,0.0020231293,0.0063114543,0.003059454,0.0031759134,0.006176334,0.007415993,0.00793362,0.005710357],"category_scores_gemma":[0.83669144,0.0021000626,0.00668268,0.005519268,0.010375582,0.015811823,0.002935665,0.009835789,0.0017661286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011696122,0.0014963497,0.026887195,0.0128197055,0.0066812267,0.00073357474,0.011897496,0.009637808,0.0038912017,0.12901011,0.060991578,0.7242576],"study_design_scores_gemma":[0.011633237,0.020024445,0.04617759,0.027545953,0.005688784,0.0019831841,0.00406708,0.057654276,0.014511516,0.6712124,0.13738184,0.0021197614],"about_ca_topic_score_codex":0.0028373757,"about_ca_topic_score_gemma":0.0053124293,"teacher_disagreement_score":0.38361007,"about_ca_system_score_codex":0.0060815616,"about_ca_system_score_gemma":0.013259037,"threshold_uncertainty_score":0.47305954},"labels":[],"label_agreement":null},{"id":"W4226435591","doi":"10.3758/s13428-022-02029-6","title":"Shennong: A Python toolbox for audio speech features extraction","year":2023,"lang":"en","type":"preprint","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Institut national de recherche en informatique et en automatique (INRIA); Canadian Institute for Advanced Research; Facebook","keywords":"Computer science; Python (programming language); Speech recognition; Toolbox; Normalization (sociology); Software; Scripting language; Mel-frequency cepstrum; Speech processing; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Feature extraction; Programming language","score_opus":0.4835932963510312,"score_gpt":0.6236894237901746,"score_spread":0.14009612743914335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226435591","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030324226,0.00012817337,0.562917,0.00009384082,0.00009659166,0.00017917753,0.017360248,0.4107504,0.0054422636],"genre_scores_gemma":[0.08587504,0.00044353798,0.7226987,0.0007407642,0.00011860391,0.0024576026,0.044307053,0.10069322,0.042665485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997502,0.000031514977,0.000023378661,0.00007167289,0.00007890502,0.00004439068],"domain_scores_gemma":[0.99951756,0.00022634592,0.000031937965,0.00009021572,0.000097132055,0.000036785514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004465669,0.0014994543,0.0006974852,0.0010612741,0.0003569276,0.0010267342,0.0014603839,0.0005476604,0.08064564],"category_scores_gemma":[0.0020631352,0.0008029033,0.0011084926,0.0006994295,0.00030144321,0.0008304917,0.0013323474,0.0012415254,0.036983456],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007119912,0.00023195318,0.003332078,0.0016370224,0.0003060871,0.00044204135,0.00048492567,0.013154927,0.04123142,0.010824511,0.4203069,0.50733614],"study_design_scores_gemma":[0.0005445261,0.00017461073,0.0106395325,0.00026248672,0.00017304244,0.0009915909,0.00022658812,0.43348274,0.10942405,0.056211963,0.3875948,0.0002741319],"about_ca_topic_score_codex":0.0030367088,"about_ca_topic_score_gemma":0.007462854,"teacher_disagreement_score":0.08064564,"about_ca_system_score_codex":0.0004391726,"about_ca_system_score_gemma":0.0009991408,"threshold_uncertainty_score":0.2697866},"labels":[],"label_agreement":null},{"id":"W4229037496","doi":"10.3758/s13428-021-01641-2","title":"Can musical ability be tested online?","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Sophistication; Melody; Musical; Test (biology); Construct validity; Session (web analytics); Openness to experience; Rhythm; Cognition; Cognitive psychology; Cognitive test; Audiology; Developmental psychology; Psychometrics; Social psychology; Computer science; Medicine","score_opus":0.6179878787281432,"score_gpt":0.6237240557554887,"score_spread":0.005736177027345524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229037496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98765403,0.00061565277,0.0024167679,0.0010288124,0.00012810844,0.000054841665,0.00024103516,0.000049818227,0.007810907],"genre_scores_gemma":[0.995307,0.0003742486,0.0022098671,0.0004906867,0.00010297708,0.00008182362,0.00015700301,0.00000868375,0.001267613],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979407,0.00087621715,0.00015270665,0.00033284296,0.0005133346,0.0001841114],"domain_scores_gemma":[0.9845708,0.0092860535,0.0027332641,0.0010833846,0.0013608931,0.0009656069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037884563,0.00057523913,0.0005687721,0.0012345256,0.00029732168,0.0016098307,0.00083668565,0.0010022861,0.0041862694],"category_scores_gemma":[0.03487251,0.00023258281,0.00028559144,0.0008621891,0.00086413504,0.0031674057,0.0012630888,0.00079990475,0.0012148417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048149884,0.0012730027,0.7742149,0.00016623863,0.00011118984,0.00050929456,0.0020735615,0.0001861472,0.0025280998,0.0009063763,0.0012826053,0.21626703],"study_design_scores_gemma":[0.000080356716,0.0025039974,0.9761574,0.0002010226,0.000100221136,0.0014273131,0.002658563,0.0021838367,0.002920664,0.0053775427,0.0063255415,0.00006342781],"about_ca_topic_score_codex":0.0022000994,"about_ca_topic_score_gemma":0.0035926874,"teacher_disagreement_score":0.0041862694,"about_ca_system_score_codex":0.00022970328,"about_ca_system_score_gemma":0.00038706043,"threshold_uncertainty_score":0.020035505},"labels":[],"label_agreement":null},{"id":"W4281285907","doi":"10.3758/s13428-022-01817-4","title":"Planning, conducting, and analyzing a psychophysiological experiment on challenge and threat: A comprehensive tutorial","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"University of Toronto; Social Sciences and Humanities Research Council of Canada; Ontario Ministry of Research, Innovation and Science","keywords":"Biopsychosocial model; Task (project management); Computer science; Data science; Data collection; Psychology; Cognitive psychology; Applied psychology; Engineering","score_opus":0.7294798079183736,"score_gpt":0.6851642411720622,"score_spread":0.04431556674631143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281285907","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013157676,0.00835098,0.97208077,0.0007514497,0.00018182519,0.00508473,0.0012083446,0.0027546694,0.008271535],"genre_scores_gemma":[0.0041740146,0.012491088,0.96869475,0.0003657517,0.00019834303,0.007093247,0.00083266094,0.00053035986,0.005619647],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693394,0.0013368619,0.0003147436,0.0004179531,0.0008496854,0.00014685889],"domain_scores_gemma":[0.99433976,0.0040567564,0.0003093422,0.0005227042,0.0005213893,0.00024994643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007947542,0.0040579285,0.0024336167,0.003896817,0.0011474453,0.002772463,0.0039241635,0.002035213,0.021468068],"category_scores_gemma":[0.012255131,0.0023539595,0.0019423612,0.0019995226,0.001627683,0.0030174947,0.002359518,0.0035673974,0.016352503],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042309763,0.0016557993,0.002898968,0.006623289,0.00017341485,0.00029461438,0.0009130625,0.010149145,0.024701897,0.047774144,0.040600974,0.86379164],"study_design_scores_gemma":[0.00034006688,0.0022939248,0.023265248,0.004913033,0.0003183899,0.0027636276,0.0010816756,0.030662514,0.046114594,0.19924237,0.6883013,0.00070318155],"about_ca_topic_score_codex":0.0045594065,"about_ca_topic_score_gemma":0.010425424,"teacher_disagreement_score":0.021468068,"about_ca_system_score_codex":0.0016270083,"about_ca_system_score_gemma":0.0044032955,"threshold_uncertainty_score":0.071817875},"labels":[],"label_agreement":null},{"id":"W4283690849","doi":"10.3758/s13428-022-01873-w","title":"Evaluating validity properties of 25 race-related scales","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Nomological network; Prejudice (legal term); Scale (ratio); Psychology; Social psychology; Ceiling (cloud); Construct validity; Race (biology); Construct (python library); External validity; Cognitive psychology; Structural equation modeling; Psychometrics; Computer science; Statistics; Mathematics; Developmental psychology; Sociology; Engineering","score_opus":0.7966474623532196,"score_gpt":0.7045809873738367,"score_spread":0.09206647497938292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283690849","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822985,0.000741203,0.0076161954,0.0002035538,0.0001921813,0.0009991336,0.0005020394,0.00005429409,0.0073929727],"genre_scores_gemma":[0.98766136,0.000256389,0.008713952,0.00014201002,0.00007811999,0.0013861686,0.0007694859,0.00005731795,0.00093509303],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9622754,0.021290204,0.00384085,0.0028228783,0.008785843,0.0009848916],"domain_scores_gemma":[0.65575296,0.28519025,0.018909002,0.011985098,0.025649419,0.0025132962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056861266,0.0010203734,0.0009773984,0.0041519967,0.0016377416,0.0018118635,0.0017009582,0.0016851447,0.002817421],"category_scores_gemma":[0.17640986,0.00070711115,0.003492608,0.0022188923,0.0022014105,0.0019704893,0.002277918,0.0011638774,0.0007806062],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004672595,0.0008846582,0.9276646,0.00023411262,0.0014265621,0.00010421599,0.0032292386,0.0017205793,0.0020295482,0.0026619125,0.000883119,0.054488834],"study_design_scores_gemma":[0.0010923756,0.0035879496,0.96907276,0.0003278257,0.00096070307,0.0002930873,0.002405751,0.011137683,0.0034084641,0.0035694516,0.004033305,0.000110584304],"about_ca_topic_score_codex":0.0029680708,"about_ca_topic_score_gemma":0.0042594625,"teacher_disagreement_score":0.9431387,"about_ca_system_score_codex":0.0018156612,"about_ca_system_score_gemma":0.0020978623,"threshold_uncertainty_score":0.30071473},"labels":[],"label_agreement":null},{"id":"W4283825839","doi":"10.3758/s13428-022-01907-3","title":"Head-mounted mobile eye-tracking in the domestic dog: A new method","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Human-Animal Interaction Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Eye tracking; Gaze; Computer science; Tracking (education); Computer vision; Eye movement; Artificial intelligence; Task (project management); Human–computer interaction; Psychology; Engineering","score_opus":0.20730988493526833,"score_gpt":0.6956001090152925,"score_spread":0.4882902240800241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283825839","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18456906,0.003165389,0.8001004,0.00024692956,0.00040072462,0.0004823267,0.0013487465,0.0010307697,0.008655591],"genre_scores_gemma":[0.37978214,0.0022758897,0.60752714,0.00027101,0.00017235958,0.0009736093,0.00046427283,0.00020147476,0.008332106],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999049,0.00029284757,0.000037275873,0.0003379476,0.00022535564,0.000057604753],"domain_scores_gemma":[0.99932337,0.00023875845,0.00006691668,0.00015885202,0.00015620024,0.000055887787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007570469,0.00042561005,0.00047737765,0.0010466909,0.00038644674,0.0005907149,0.0010138588,0.00088642334,0.0025808085],"category_scores_gemma":[0.0012135636,0.0004310659,0.00037829336,0.0006779239,0.00046282215,0.0007543733,0.00090926257,0.0005792566,0.0008192866],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065507885,0.000242939,0.013851815,0.00034753638,0.00019024525,0.0002288831,0.0005148382,0.0010456846,0.6868381,0.001713716,0.0013925798,0.2929785],"study_design_scores_gemma":[0.00049121777,0.0054207817,0.2520474,0.00030187817,0.0013297435,0.009281663,0.0013238037,0.11577438,0.55267227,0.006067801,0.054581534,0.0007075695],"about_ca_topic_score_codex":0.0022911525,"about_ca_topic_score_gemma":0.0059624505,"teacher_disagreement_score":0.0025808085,"about_ca_system_score_codex":0.00034299167,"about_ca_system_score_gemma":0.0005717074,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4284888443","doi":"10.3758/s13428-022-01841-4","title":"r2mlm: An R package calculating R-squared measures for multilevel models","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Association for Psychological Science","keywords":"Multilevel model; Computer science; Graphics; Variance (accounting); R package; Mean squared error; Code (set theory); Computation; Theoretical computer science; Data mining; Statistics; Machine learning; Algorithm; Mathematics; Computational science; Set (abstract data type); Programming language; Computer graphics (images)","score_opus":0.832282820153713,"score_gpt":0.7304257606942206,"score_spread":0.10185705945949242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284888443","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062182103,0.00061612326,0.7075806,0.00063027814,0.0005309132,0.00052021677,0.116787426,0.1619678,0.0051484425],"genre_scores_gemma":[0.047320914,0.00044322014,0.7506048,0.000679424,0.00023814707,0.0046693813,0.059813675,0.12737836,0.008851981],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920671,0.0041035432,0.0008280066,0.0014323067,0.0012127148,0.00035636683],"domain_scores_gemma":[0.95304406,0.035496432,0.0021110778,0.0061548282,0.0027144465,0.00047908598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0111744,0.0036720606,0.0030267714,0.003417031,0.0010399796,0.0035478924,0.004341677,0.0014764667,0.112906635],"category_scores_gemma":[0.105752125,0.002687676,0.004259658,0.0039541903,0.000934776,0.003332704,0.0032112875,0.0038932501,0.056698583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008155706,0.00021944402,0.022610553,0.0038660436,0.0036559498,0.0004028245,0.001074005,0.015195076,0.0028471833,0.052678596,0.71290904,0.18372577],"study_design_scores_gemma":[0.0013774446,0.00044757093,0.02332675,0.001566106,0.0025903247,0.0009403467,0.00035183824,0.13415393,0.010317986,0.20993686,0.61435086,0.00064003444],"about_ca_topic_score_codex":0.0044113593,"about_ca_topic_score_gemma":0.007197825,"teacher_disagreement_score":0.112906635,"about_ca_system_score_codex":0.00082528975,"about_ca_system_score_gemma":0.0029749733,"threshold_uncertainty_score":0.37771034},"labels":[],"label_agreement":null},{"id":"W4286560902","doi":"10.3758/s13428-022-01912-6","title":"Concreteness ratings for 62,000 English multiword expressions","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Computer science; Psychology; Word (group theory); Meaning (existential); Linguistics; Cognitive psychology; Natural language processing","score_opus":0.23104756777532953,"score_gpt":0.5707877905792769,"score_spread":0.33974022280394733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286560902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907775,0.00030765426,0.0010421615,0.000057391684,0.00004491838,0.00008742112,0.000925883,0.000072545045,0.006684556],"genre_scores_gemma":[0.98316956,0.00035757714,0.0043069087,0.00013482978,0.000057449906,0.00022356554,0.0031358795,0.0001231833,0.008491064],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99821186,0.00065103243,0.00032327135,0.00029602618,0.0004347491,0.000083137595],"domain_scores_gemma":[0.978625,0.0152660245,0.0017103668,0.0007969012,0.002962727,0.00063897873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019946196,0.00036532906,0.0004029807,0.00092750514,0.0004148823,0.0005650772,0.00019918122,0.00066817517,0.0075169746],"category_scores_gemma":[0.02251662,0.00018155688,0.00031493057,0.0005529844,0.00030392,0.0009066702,0.0006420516,0.00048021937,0.0016733403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010555004,0.0015807605,0.550047,0.0019378276,0.00052204216,0.0010545402,0.018994877,0.0014422764,0.1376357,0.0021709253,0.012426301,0.2616328],"study_design_scores_gemma":[0.000100887686,0.0012455638,0.9788103,0.00010130699,0.00013036329,0.00070791057,0.0019823601,0.0018516382,0.007671286,0.00042901665,0.0069170906,0.000052302268],"about_ca_topic_score_codex":0.0010464261,"about_ca_topic_score_gemma":0.0018839148,"teacher_disagreement_score":0.0075169746,"about_ca_system_score_codex":0.00023756438,"about_ca_system_score_gemma":0.00014901742,"threshold_uncertainty_score":0.025146782},"labels":[],"label_agreement":null},{"id":"W4289262412","doi":"10.3758/s13428-022-01892-7","title":"Multilevel multivariate meta-analysis made easy: An introduction to MLMVmeta","year":2022,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Multivariate statistics; Computer science; Multilevel model; Multivariate analysis; Meta-analysis; Data mining; Machine learning; Artificial intelligence","score_opus":0.9002596806621552,"score_gpt":0.757045118444534,"score_spread":0.1432145622176212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289262412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010600174,0.2608622,0.68689626,0.011459265,0.009497083,0.0037018112,0.013751861,0.010521771,0.0022497608],"genre_scores_gemma":[0.008871687,0.0503724,0.9112613,0.0041454094,0.0026774376,0.015828166,0.0021177295,0.0027284427,0.0019973454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9190318,0.06325816,0.009175079,0.0026936482,0.005514087,0.00032723957],"domain_scores_gemma":[0.81911534,0.15976816,0.004699115,0.010350169,0.005275277,0.0007919332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07400829,0.0038389622,0.009205838,0.0075361407,0.0008060045,0.005963191,0.004846626,0.0027250722,0.03764605],"category_scores_gemma":[0.2322229,0.003920687,0.027383132,0.008034727,0.0011985581,0.0040958873,0.006089785,0.009733346,0.006502181],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016239412,0.00018017017,0.0016196547,0.11825639,0.07398954,0.00030723776,0.0006909307,0.0051944763,0.0019428247,0.043754287,0.1590836,0.5933569],"study_design_scores_gemma":[0.0042990064,0.00087049813,0.0060672266,0.058326893,0.070777774,0.0010855449,0.00024761708,0.03513541,0.0026912666,0.2820502,0.53729594,0.0011526558],"about_ca_topic_score_codex":0.0036237855,"about_ca_topic_score_gemma":0.007673187,"teacher_disagreement_score":0.9259917,"about_ca_system_score_codex":0.0017557841,"about_ca_system_score_gemma":0.007188555,"threshold_uncertainty_score":0.39139795},"labels":[],"label_agreement":null},{"id":"W4293101458","doi":"10.3758/s13428-022-01926-0","title":"Cognitive and social well-being in older adulthood: The CoSoWELL corpus of written life stories","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Timeline; Narrative; Yesterday; Psychology; Autobiographical memory; Cognition; Cognitive psychology; History; Linguistics","score_opus":0.18600255127345042,"score_gpt":0.5530519446984792,"score_spread":0.36704939342502874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293101458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7809825,0.011298418,0.0139047755,0.0035258012,0.0007444709,0.00095217285,0.16606182,0.00029771213,0.022232294],"genre_scores_gemma":[0.7568091,0.005733418,0.030271437,0.001076117,0.00040638674,0.005490992,0.18767157,0.0004571794,0.012083702],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9984769,0.0007355277,0.00021464113,0.000253609,0.00022918067,0.00009016512],"domain_scores_gemma":[0.9850345,0.010315439,0.0014811124,0.0011185515,0.0015462848,0.00050411467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019619025,0.0004902771,0.0003270831,0.0035787208,0.0016954296,0.0019936394,0.00082026026,0.0008833686,0.0040107733],"category_scores_gemma":[0.016257057,0.00024474703,0.00024256378,0.0056157717,0.0012508044,0.0014642411,0.002695793,0.00081992894,0.0010806539],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006831336,0.0005996516,0.09274868,0.0056694965,0.00020087157,0.0054723523,0.3849422,0.0014308112,0.0078043225,0.019221319,0.2647189,0.21650836],"study_design_scores_gemma":[0.00006759341,0.00006231441,0.1376227,0.00180373,0.000070986745,0.0018145324,0.09668262,0.001380584,0.0025829086,0.0035496948,0.7542318,0.0001305493],"about_ca_topic_score_codex":0.020247146,"about_ca_topic_score_gemma":0.04165965,"teacher_disagreement_score":0.020247146,"about_ca_system_score_codex":0.0012941745,"about_ca_system_score_gemma":0.001597691,"threshold_uncertainty_score":0.040258646},"labels":[],"label_agreement":null},{"id":"W4294146859","doi":"10.3758/s13428-022-01913-5","title":"d$$^{\\prime }_{o}$$: Sensitivity at the optimal criterion location","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Distributed Sensor Networks and Detection Algorithms","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Prime (order theory); Observer (physics); Set (abstract data type); Noise (video); Detection theory; Mathematics; Variance (accounting); Base (topology); Algorithm; Prime number; Range (aeronautics); Statistics; Computer science; SIGNAL (programming language); Artificial intelligence; Discrete mathematics; Combinatorics; Physics; Telecommunications; Mathematical analysis","score_opus":0.16766907625360186,"score_gpt":0.500187781777576,"score_spread":0.3325187055239741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294146859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029194782,0.00047021263,0.93357515,0.0031500256,0.00027239887,0.000058337275,0.00037346044,0.0005251898,0.032380328],"genre_scores_gemma":[0.8308822,0.0008166695,0.13919759,0.0011593656,0.00024578834,0.000195899,0.00033493232,0.0006653966,0.026502216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864835,0.00050895946,0.00003405482,0.00035470343,0.0003161463,0.00013776508],"domain_scores_gemma":[0.9951161,0.003782782,0.00027200844,0.00027240874,0.0003993673,0.00015728595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018782404,0.0007121524,0.00082397007,0.0010922493,0.00041324418,0.0016029173,0.0011641185,0.0013128439,0.013853736],"category_scores_gemma":[0.015841309,0.0004386086,0.00040976645,0.00066902937,0.0016188071,0.0018088813,0.002402412,0.0017335321,0.0014028109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036599208,0.00014006882,0.0017133472,0.00029787753,0.00007372104,0.00017639682,0.00017108026,0.20250605,0.015133227,0.64417756,0.017097993,0.11814666],"study_design_scores_gemma":[0.000024359082,0.000052745698,0.0011370867,0.000056231038,0.000019375912,0.00021886681,0.00005386167,0.7898911,0.005704119,0.19833843,0.0044632736,0.00004045572],"about_ca_topic_score_codex":0.004067396,"about_ca_topic_score_gemma":0.0025809263,"teacher_disagreement_score":0.013853736,"about_ca_system_score_codex":0.0012122749,"about_ca_system_score_gemma":0.0014359683,"threshold_uncertainty_score":0.046345353},"labels":[],"label_agreement":null},{"id":"W4295067019","doi":"10.3758/s13428-022-01958-6","title":"Generating accurate 3D gaze vectors using synchronized eye tracking and motion capture","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women and Children’s Health Research Institute; University of Alberta","funders":"Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer vision; Computer science; Artificial intelligence; Gaze; Eye tracking; Monocular; Motion capture; Motion (physics)","score_opus":0.25227002656806086,"score_gpt":0.5296659863595778,"score_spread":0.277395959791517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295067019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058631476,0.00034223133,0.9353124,0.000087570406,0.000094619114,0.00016668417,0.0012752889,0.0023131534,0.0017765745],"genre_scores_gemma":[0.44586897,0.00067683705,0.5461312,0.000091696245,0.00006909481,0.00039625837,0.0022712525,0.0004127325,0.0040820013],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99961793,0.00006856442,0.000017927869,0.00013059413,0.00012604216,0.000038888807],"domain_scores_gemma":[0.9993788,0.00015443232,0.000082049366,0.00010176765,0.00025334978,0.000029491244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037471042,0.00080891023,0.00051416596,0.0014278397,0.00022287235,0.00066310936,0.00043567538,0.00054396875,0.0023700711],"category_scores_gemma":[0.0019528675,0.0005328694,0.00052671076,0.0011777282,0.00016392797,0.0006048624,0.00087630725,0.0003727013,0.0014413978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004329831,0.00017967516,0.009680601,0.00035739967,0.00021541165,0.00020451599,0.0003679003,0.052544467,0.29026264,0.0023171538,0.008559472,0.63487786],"study_design_scores_gemma":[0.000113270995,0.00031873424,0.048475806,0.00007514173,0.00011313184,0.00047685526,0.00023975856,0.81901234,0.11849232,0.004541335,0.008047832,0.00009334467],"about_ca_topic_score_codex":0.0042511015,"about_ca_topic_score_gemma":0.0072486987,"teacher_disagreement_score":0.0042511015,"about_ca_system_score_codex":0.00035751882,"about_ca_system_score_gemma":0.0007231575,"threshold_uncertainty_score":0.0084527135},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.48291823368261927,"score_gpt":0.6283255401611992,"score_spread":0.14540730647857997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306655083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0148902,0.0030693957,0.97360533,0.0039762203,0.0002511769,0.00059753895,0.00016850277,0.00012210348,0.0033194155],"genre_scores_gemma":[0.335156,0.0018212922,0.6558126,0.0011118529,0.0005112049,0.0041694967,0.00012978402,0.00029789624,0.000989906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.53451407,0.4366938,0.0061369534,0.008671175,0.013218968,0.0007651099],"domain_scores_gemma":[0.0736626,0.8839579,0.010101172,0.026613014,0.0050590923,0.00060615584],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3571735,0.0024184713,0.0047247354,0.0056526326,0.0031544184,0.010942456,0.008594984,0.0050208615,0.006099013],"category_scores_gemma":[0.7681897,0.0020790722,0.004539039,0.006952234,0.022421092,0.021897633,0.009338264,0.011387591,0.00037106994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006455391,0.00037811304,0.012184327,0.0017120923,0.0025729935,0.00014781462,0.0058188294,0.006906825,0.0008413501,0.8544273,0.0013901489,0.11297479],"study_design_scores_gemma":[0.0001760968,0.00026886174,0.0031896336,0.00057532976,0.0004286449,0.0001656651,0.0010463458,0.026330737,0.0007813694,0.9635793,0.00333769,0.00012027808],"about_ca_topic_score_codex":0.002450573,"about_ca_topic_score_gemma":0.0023363882,"teacher_disagreement_score":0.3571735,"about_ca_system_score_codex":0.0039541223,"about_ca_system_score_gemma":0.0054470296,"threshold_uncertainty_score":0.79271954},"labels":[],"label_agreement":null},{"id":"W4307426877","doi":"10.3758/s13428-022-02002-3","title":"The underwood project: A virtual environment for eliciting ambiguous threat","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Media Influence and Health","field":"Arts and Humanities","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Narrative; Cognitive psychology; Psychology; Cognition; Naturalism; Social psychology; Computer science","score_opus":0.5894848696925414,"score_gpt":0.5837338777687398,"score_spread":0.005750991923801685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307426877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82218164,0.0006491279,0.13717303,0.00084490184,0.00026802585,0.003581377,0.0015402554,0.0016773838,0.032084204],"genre_scores_gemma":[0.8655144,0.00045254006,0.123209715,0.00024021686,0.000056589655,0.0031075468,0.00066265435,0.00023469076,0.006521759],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991134,0.0005683456,0.00003166301,0.000072069946,0.00013724293,0.000077332224],"domain_scores_gemma":[0.9984322,0.0008961032,0.00011476898,0.00019296021,0.000054136104,0.00030984762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013196882,0.00069998566,0.00017737706,0.000421275,0.000571718,0.0010865766,0.00073457183,0.00055849855,0.005041377],"category_scores_gemma":[0.0039447774,0.0002606428,0.00031467277,0.00020868622,0.0010887905,0.000891044,0.0028395944,0.0007873662,0.00045339612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009875498,0.008050436,0.03473163,0.0041923756,0.00034787136,0.0036779244,0.06411026,0.01573262,0.315542,0.06569719,0.042496286,0.4355459],"study_design_scores_gemma":[0.00670152,0.042357903,0.10347861,0.001478871,0.00068746513,0.007958491,0.02734948,0.051559262,0.1458535,0.08182308,0.52964985,0.0011019531],"about_ca_topic_score_codex":0.00046683627,"about_ca_topic_score_gemma":0.0010176271,"teacher_disagreement_score":0.005041377,"about_ca_system_score_codex":0.000189691,"about_ca_system_score_gemma":0.00049382827,"threshold_uncertainty_score":0.016865134},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8107478869005017,"score_gpt":0.6970883390979823,"score_spread":0.11365954780251941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308017781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98183066,0.0000906783,0.006999319,0.0012302512,0.000112874215,0.0017800666,0.00037929093,0.00059319224,0.0069836504],"genre_scores_gemma":[0.97564155,0.000058272042,0.01733141,0.000804005,0.00006440888,0.0025353583,0.00062006933,0.0002656564,0.002679162],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.95259124,0.027870523,0.0030093705,0.0041551297,0.010605044,0.0017686891],"domain_scores_gemma":[0.68233436,0.15527739,0.053207155,0.045856178,0.05178805,0.011536841],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06308426,0.00056127436,0.0005866969,0.0014888892,0.0025343697,0.0039079664,0.001991632,0.001395024,0.0046829204],"category_scores_gemma":[0.28513995,0.0004387481,0.00065183267,0.0011903917,0.0030054657,0.0043227174,0.003399157,0.0014518484,0.002559501],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006818337,0.0043005114,0.6717526,0.00074427266,0.00020037961,0.00043906271,0.047734007,0.0012097455,0.008174689,0.006373896,0.023510726,0.22874184],"study_design_scores_gemma":[0.0013253688,0.012256701,0.83527786,0.00051921245,0.0003399206,0.0006016122,0.036241733,0.02110735,0.015565506,0.0067485124,0.069666214,0.00035005258],"about_ca_topic_score_codex":0.005248482,"about_ca_topic_score_gemma":0.0073392373,"teacher_disagreement_score":0.93691576,"about_ca_system_score_codex":0.0024061678,"about_ca_system_score_gemma":0.0041622715,"threshold_uncertainty_score":0.33362544},"labels":[],"label_agreement":null},{"id":"W4313453623","doi":"10.3758/s13428-022-02050-9","title":"The timing database: An open-access, live repository for interval timing studies","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; The Scarborough Hospital; University of Toronto; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database; Task (project management); Interval (graph theory); Range (aeronautics); Data mining","score_opus":0.8729870524749542,"score_gpt":0.720222263704515,"score_spread":0.1527647887704392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313453623","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019801096,0.0009367657,0.05517817,0.0004332666,0.0007851148,0.00021557634,0.83018315,0.094610535,0.015677355],"genre_scores_gemma":[0.020380706,0.0016533773,0.07399645,0.00048709297,0.00059553154,0.0009057895,0.8517765,0.03303349,0.017171111],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846834,0.00014547174,0.00033211915,0.00024836004,0.0006670082,0.00013872898],"domain_scores_gemma":[0.9877225,0.0038754437,0.0011923754,0.003412839,0.0024108272,0.0013859546],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002592154,0.0017442437,0.0021311184,0.008079467,0.000840816,0.0037736958,0.005271228,0.0017460628,0.22857124],"category_scores_gemma":[0.022196563,0.0008500945,0.0008866202,0.01049677,0.0003593524,0.0034650203,0.0040529654,0.0019699717,0.12831423],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009862547,0.00020501463,0.0024123683,0.0025308577,0.00015551552,0.00025084947,0.00022736052,0.0011548928,0.0059005823,0.006183232,0.8629024,0.1170907],"study_design_scores_gemma":[0.00058913307,0.00016030885,0.0081851985,0.00058318925,0.00020022065,0.00049170427,0.00020699539,0.0058981925,0.008964503,0.022587841,0.95184165,0.00029114823],"about_ca_topic_score_codex":0.0024816815,"about_ca_topic_score_gemma":0.0047661434,"teacher_disagreement_score":0.99472874,"about_ca_system_score_codex":0.00054056855,"about_ca_system_score_gemma":0.0023632476,"threshold_uncertainty_score":0.76464695},"labels":[],"label_agreement":null},{"id":"W4317952720","doi":"10.3758/s13428-022-02044-7","title":"Visualization of latent components assessed in O*Net occupations (VOLCANO): A robust method for standardized conversion of occupational labels to ratio scale format","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; Centre for Addiction and Mental Health","funders":"Social Sciences and Humanities Research Council of Canada; Canadian Institutes of Health Research","keywords":"Standardization; Dimension (graph theory); Visualization; Psychology; Scale (ratio); Cognition; Sample (material); Computer science; Space (punctuation); Mathematics education; Data science; Applied psychology; Artificial intelligence; Mathematics; Geography; Cartography","score_opus":0.6037485672332248,"score_gpt":0.6851678499988348,"score_spread":0.08141928276561006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317952720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113454096,0.0008157775,0.47800636,0.0015723084,0.0014032032,0.0016965753,0.26816785,0.10619198,0.028691862],"genre_scores_gemma":[0.24023418,0.0006054188,0.64188915,0.00035985117,0.00032061184,0.0075584236,0.08684816,0.013611177,0.008573004],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985258,0.00047603928,0.00020536441,0.00041296522,0.00027039115,0.00010950178],"domain_scores_gemma":[0.9893526,0.006768377,0.000884365,0.0015681956,0.0011922617,0.00023421888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048759915,0.001372087,0.0007811167,0.0055824555,0.0005835982,0.003353519,0.00088746496,0.00074029254,0.051217336],"category_scores_gemma":[0.021382673,0.0004894443,0.0011510667,0.0042338683,0.00050665333,0.0017636644,0.0041517937,0.0016266303,0.00838224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017227428,0.00043790526,0.047274534,0.0024845426,0.00038885875,0.000490973,0.009100134,0.0027213853,0.012673934,0.026861083,0.37133586,0.52450806],"study_design_scores_gemma":[0.0005758325,0.00050032296,0.2128173,0.0017324628,0.00025971938,0.0007063447,0.008484774,0.086711526,0.02145046,0.07543309,0.5907693,0.00055888144],"about_ca_topic_score_codex":0.0033492835,"about_ca_topic_score_gemma":0.0049057244,"teacher_disagreement_score":0.051217336,"about_ca_system_score_codex":0.0004727395,"about_ca_system_score_gemma":0.0011005506,"threshold_uncertainty_score":0.17133904},"labels":[],"label_agreement":null},{"id":"W4321168228","doi":"10.3758/s13428-023-02066-9","title":"Characterizing the role of impulsivity in costly, reactive aggression using a novel paradigm","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Aggression; Psychology; Temptation; Anger; Impulsivity; Self-control; Rage (emotion); Delay of gratification; Social psychology; Trait; Developmental psychology; Computer science","score_opus":0.5368477379161043,"score_gpt":0.6666851532272852,"score_spread":0.12983741531118087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321168228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770259,0.00015461954,0.016742708,0.0004186549,0.00014032467,0.0005257471,0.00024562847,0.00005242825,0.004694055],"genre_scores_gemma":[0.9483757,0.00041891687,0.041653518,0.0007214696,0.00016169871,0.0024459194,0.000301864,0.00007487786,0.0058460413],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987463,0.00036426054,0.00009189637,0.00035119386,0.00033646115,0.00010988649],"domain_scores_gemma":[0.99831426,0.0005962346,0.0003775302,0.00027111432,0.00013855592,0.00030233714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015948534,0.0009184863,0.0004997779,0.00071256,0.0006246617,0.001027967,0.0009989976,0.00078751845,0.0028703779],"category_scores_gemma":[0.0031428118,0.0004164159,0.00043104228,0.0002711978,0.00074076647,0.00061477424,0.0010388354,0.0021578264,0.00017531913],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019043006,0.04595996,0.050143182,0.00064493145,0.0004912178,0.00039996215,0.0022367097,0.0015007625,0.769011,0.018552141,0.0017050875,0.0903121],"study_design_scores_gemma":[0.0068486505,0.10100411,0.614907,0.00041356724,0.0022604158,0.0032623764,0.0022126855,0.0493933,0.17904554,0.029000035,0.01121749,0.0004347556],"about_ca_topic_score_codex":0.001884808,"about_ca_topic_score_gemma":0.003955127,"teacher_disagreement_score":0.0028703779,"about_ca_system_score_codex":0.00073290203,"about_ca_system_score_gemma":0.0012600068,"threshold_uncertainty_score":0.009602368},"labels":[],"label_agreement":null},{"id":"W4321490378","doi":"10.3758/s13428-023-02079-4","title":"Multilevel mediation analysis in R: A comparison of bootstrap and Bayesian approaches","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Resampling; Bayesian probability; Statistics; Computer science; Mediation; Random effects model; Context (archaeology); Type I and type II errors; Econometrics; Estimator; Multilevel model; Mathematics; Meta-analysis","score_opus":0.7501815697635115,"score_gpt":0.663230774126511,"score_spread":0.08695079563700048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321490378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010685062,0.0012479981,0.98420125,0.0007747342,0.00013643209,0.00033212476,0.00026739025,0.0012121567,0.0011428741],"genre_scores_gemma":[0.1138471,0.0011532822,0.88028055,0.00035479225,0.00013740746,0.0017410971,0.00026682412,0.0016484321,0.00057039637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7770864,0.20494181,0.0030059712,0.005395079,0.008555533,0.0010152146],"domain_scores_gemma":[0.3984038,0.56323963,0.007014685,0.022456117,0.0074980347,0.0013878199],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1423216,0.0017712218,0.0046330066,0.0033701165,0.0013834448,0.0039507207,0.0054821675,0.0027510945,0.011838737],"category_scores_gemma":[0.46538854,0.0016172942,0.004593319,0.005613791,0.0032639632,0.007589564,0.0047013676,0.006379652,0.001919558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007173172,0.001104653,0.015232164,0.004589541,0.012184932,0.00039831732,0.004926884,0.041128203,0.0024944146,0.29150727,0.017920388,0.60134006],"study_design_scores_gemma":[0.00326469,0.0024349962,0.022720326,0.0017624267,0.0064302757,0.0009835066,0.001793443,0.40399632,0.0036663162,0.5274677,0.024811659,0.0006683079],"about_ca_topic_score_codex":0.0054219267,"about_ca_topic_score_gemma":0.007753978,"teacher_disagreement_score":0.8576784,"about_ca_system_score_codex":0.0014347763,"about_ca_system_score_gemma":0.004968137,"threshold_uncertainty_score":0.75267756},"labels":[],"label_agreement":null},{"id":"W4321491505","doi":"10.3758/s13428-023-02076-7","title":"A simple semi-automated home-tank method and procedure to explore classical associative learning in adult zebrafish","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Celiac Association; University of Toronto","funders":"Göteborgs Universitet","keywords":"Zebrafish; Computer science; Mnemonic; Task (project management); Associative learning; Simple (philosophy); Associative property; Artificial intelligence; Animal cognition; Cognition; Cognitive science; Human–computer interaction; Psychology; Cognitive psychology; Neuroscience; Biology","score_opus":0.13491756394403476,"score_gpt":0.5471398362654555,"score_spread":0.4122222723214207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321491505","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23808973,0.0006605259,0.7313156,0.0004840788,0.0002915703,0.009228697,0.0045405226,0.0071671656,0.008222107],"genre_scores_gemma":[0.2009431,0.0006703773,0.7723871,0.0004775092,0.00004690083,0.012419197,0.002117495,0.0005913543,0.010346971],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995857,0.00002663598,0.000037277692,0.00011097479,0.00018140108,0.000058040783],"domain_scores_gemma":[0.99971694,0.00003211888,0.000058633887,0.00008498487,0.00004712223,0.0000601818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049869606,0.0011530987,0.0005319833,0.00077544386,0.0007450758,0.00025924697,0.0013763793,0.0006471382,0.004232735],"category_scores_gemma":[0.0003691692,0.00039901413,0.00074263103,0.00017598974,0.00072918885,0.0003674247,0.000960438,0.0014256149,0.0018354747],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006787273,0.00013592363,0.00048656983,0.00011827577,0.000009085601,0.0001584529,0.00006923933,0.00037692388,0.98347396,0.0004937729,0.00068702863,0.013922982],"study_design_scores_gemma":[0.00013093936,0.0030907937,0.012262858,0.000105449595,0.00007376339,0.0013152512,0.00006528683,0.006641432,0.94781864,0.00091807166,0.027426578,0.00015084817],"about_ca_topic_score_codex":0.002723129,"about_ca_topic_score_gemma":0.00733149,"teacher_disagreement_score":0.004232735,"about_ca_system_score_codex":0.000484756,"about_ca_system_score_gemma":0.0015164186,"threshold_uncertainty_score":0.014159918},"labels":[],"label_agreement":null},{"id":"W4328051526","doi":"10.3758/s13428-023-02080-x","title":"Taking stock of the past: A psychometric evaluation of the Autobiographical Interview","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Concordia University; McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autobiographical memory; Psychology; Recall; Episodic memory; Cognitive psychology; Internal consistency; Reliability (semiconductor); Confirmatory factor analysis; Trait; Psychometrics; Developmental psychology; Clinical psychology; Cognition; Computer science; Structural equation modeling","score_opus":0.6968204307330096,"score_gpt":0.6741826402348429,"score_spread":0.02263779049816672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328051526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985285,0.00028826814,0.005329522,0.00028252002,0.00012891361,0.001632912,0.0003427983,0.000064766966,0.0066452203],"genre_scores_gemma":[0.9825577,0.00047910467,0.011710723,0.00022942785,0.00006676413,0.0018785347,0.0007693865,0.00004658683,0.002261827],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9925269,0.0039686966,0.0010677212,0.00028602316,0.0018861946,0.00026444596],"domain_scores_gemma":[0.9454035,0.02940183,0.00618395,0.0047295173,0.011880915,0.0024003412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019625463,0.00042936028,0.00054453756,0.0029803698,0.0008215135,0.0010892401,0.0009865978,0.0007208298,0.0013387149],"category_scores_gemma":[0.05253228,0.0004643644,0.0009436768,0.0016108435,0.0010187721,0.0015532863,0.0020202363,0.0012578598,0.0004692231],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010683413,0.0023173185,0.8640492,0.00024987475,0.00019805535,0.00016534419,0.013254742,0.00094005826,0.0031892166,0.0013261139,0.0011917345,0.11205002],"study_design_scores_gemma":[0.00018024845,0.0034956643,0.96963227,0.00015961987,0.00015077999,0.0004940779,0.0115244,0.0044712233,0.002829883,0.0010104704,0.005966579,0.00008481593],"about_ca_topic_score_codex":0.0025560826,"about_ca_topic_score_gemma":0.0041897795,"teacher_disagreement_score":0.019625463,"about_ca_system_score_codex":0.001009738,"about_ca_system_score_gemma":0.0020287267,"threshold_uncertainty_score":0.10379064},"labels":[],"label_agreement":null},{"id":"W4380870481","doi":"10.3758/s13428-023-02123-3","title":"Simultaneous estimation of the intermediate correlation matrix for arbitrary marginal densities","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate normal distribution; Correlation; Multivariate statistics; Matrix (chemical analysis); Covariance matrix; Multivariate t-distribution; Distribution (mathematics); Computer science; Data Matrix; Marginal distribution; Mathematics; Statistics; Algorithm; Random variable; Mathematical analysis; Chemistry","score_opus":0.3626131996223184,"score_gpt":0.6157310743641532,"score_spread":0.2531178747418348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380870481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01087002,0.00005588607,0.9882544,0.00007267248,0.0000107325295,0.000026054753,0.00004755753,0.000082463914,0.0005802369],"genre_scores_gemma":[0.48550352,0.0004427034,0.5090486,0.00012919886,0.00008620958,0.00033569592,0.00049206323,0.00017337904,0.0037886535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936566,0.0037670962,0.00022496998,0.0013320282,0.00068198016,0.00033736054],"domain_scores_gemma":[0.9476143,0.043234244,0.0016764824,0.0053537954,0.0015776663,0.0005434393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01182232,0.0009409084,0.001676924,0.0018049182,0.0007426293,0.0030566743,0.0030427317,0.0015423526,0.0036272716],"category_scores_gemma":[0.08034968,0.001543204,0.0019207534,0.0020266,0.0030562733,0.0057847667,0.0044896486,0.0039029988,0.0007664399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032514185,0.00021978075,0.011781385,0.00031146922,0.0003590564,0.0003054619,0.0010097716,0.12452191,0.003262556,0.7115355,0.0018426443,0.14452541],"study_design_scores_gemma":[0.00003049361,0.00006188896,0.003535407,0.00005808682,0.00007837985,0.00016501566,0.00010350652,0.6301208,0.0014322675,0.3631729,0.0011944044,0.00004687056],"about_ca_topic_score_codex":0.0037465931,"about_ca_topic_score_gemma":0.0056410604,"teacher_disagreement_score":0.01182232,"about_ca_system_score_codex":0.0010843907,"about_ca_system_score_gemma":0.0024455437,"threshold_uncertainty_score":0.06252313},"labels":[],"label_agreement":null},{"id":"W4381716880","doi":"10.3758/s13428-023-02098-1","title":"From pre-processing to advanced dynamic modeling of pupil data","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Max-Planck-Gesellschaft; Deutsche Forschungsgemeinschaft","keywords":"Pupillometry; Computer science; Variety (cybernetics); Dynamic time warping; Pupil; Pupil size; Artificial intelligence; Psychology","score_opus":0.5692682817835731,"score_gpt":0.6245009920505697,"score_spread":0.05523271026699661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381716880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005075221,0.0007543541,0.99106616,0.00048301596,0.00006443751,0.000061471226,0.00026183474,0.0008779475,0.0013555397],"genre_scores_gemma":[0.18671429,0.004634922,0.8015989,0.0003778871,0.00031409235,0.000447095,0.0013938561,0.0006405217,0.0038785178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941313,0.0001488986,0.00004222734,0.00016634222,0.00019368934,0.000035789377],"domain_scores_gemma":[0.9984787,0.0008805485,0.000097642456,0.00022488832,0.00028010312,0.000038189304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015778998,0.00088898785,0.0006193937,0.001061761,0.00035365584,0.0019263595,0.0012373273,0.00075184525,0.002523063],"category_scores_gemma":[0.005939126,0.00057551113,0.0009964277,0.001215521,0.00064964994,0.0017566719,0.0010971323,0.0020558517,0.001282513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020507564,0.000101410944,0.0032815952,0.0008059669,0.00021920436,0.0003800733,0.00051300233,0.38342923,0.03504179,0.07264284,0.00967651,0.49370334],"study_design_scores_gemma":[0.000014346197,0.00007692919,0.0017639622,0.00010198335,0.000026417512,0.00012457318,0.00006879512,0.9222748,0.008735365,0.052162144,0.014601102,0.00004949327],"about_ca_topic_score_codex":0.0046286965,"about_ca_topic_score_gemma":0.0037649148,"teacher_disagreement_score":0.0046286965,"about_ca_system_score_codex":0.00060155377,"about_ca_system_score_gemma":0.0011132127,"threshold_uncertainty_score":0.009203494},"labels":[],"label_agreement":null},{"id":"W4382317569","doi":"10.3758/s13428-023-02148-8","title":"Measuring vection: a review and critical evaluation of different methods for quantifying illusory self-motion","year":2023,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; Toronto Metropolitan University; University Health Network","funders":"Australian Research Council; Deakin University","keywords":"Psychology; Comparability; Cognitive psychology; Mathematics","score_opus":0.9385699100556464,"score_gpt":0.7526030079243847,"score_spread":0.18596690213126166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382317569","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068122376,0.99904495,0.000292565,0.00022990687,0.00010577637,0.000016885622,0.000030681214,0.0000064002766,0.00020469804],"genre_scores_gemma":[0.00052339263,0.99832255,0.00070479396,0.00020763572,0.00008254918,0.00004088231,0.00003528358,0.000003941045,0.00007885083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968328,0.00090588134,0.00084809994,0.0004188034,0.00090832915,0.00008612301],"domain_scores_gemma":[0.9784952,0.017108064,0.0011133836,0.00033144784,0.0027980958,0.00015382469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008396299,0.0018431067,0.004118076,0.007000642,0.0005395298,0.0022925877,0.0023805865,0.0020077426,0.0032507495],"category_scores_gemma":[0.01874677,0.0008706299,0.0025034503,0.0046682497,0.001887766,0.0032787512,0.0013928999,0.0024836704,0.001417242],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011700248,0.000054328917,0.00041350635,0.15606228,0.00046745542,0.0000961981,0.00018826233,0.00018963794,0.00082309626,0.0024522152,0.009877873,0.82925826],"study_design_scores_gemma":[0.00007202415,0.0005244533,0.0062092366,0.20172583,0.0038873202,0.0023017481,0.0006406516,0.0003406165,0.0031005426,0.0061706305,0.7747807,0.0002462405],"about_ca_topic_score_codex":0.0036171954,"about_ca_topic_score_gemma":0.0049970043,"teacher_disagreement_score":0.008396299,"about_ca_system_score_codex":0.0017486796,"about_ca_system_score_gemma":0.004598172,"threshold_uncertainty_score":0.044404387},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Economic and Social Research Council; Cambridge Trust; Deutscher Akademischer Austauschdienst; University of Virginia","keywords":"Mist; Misinformation; Psychology; Psychological intervention; Test (biology); Computer science; Social psychology; Computer security","score_opus":0.4256537945364519,"score_gpt":0.6244316175167799,"score_spread":0.19877782298032798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382502700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98794544,0.00012819073,0.004029005,0.00015642533,0.00003864207,0.00022705464,0.0008607817,0.00006328375,0.006551215],"genre_scores_gemma":[0.991719,0.00010020347,0.0060815993,0.000067974506,0.00002701612,0.00029166535,0.0008029924,0.000014934068,0.0008945827],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99705803,0.00078706094,0.0006177038,0.00021840974,0.0011989487,0.00011990452],"domain_scores_gemma":[0.94052815,0.028782476,0.019275704,0.0033669414,0.006201642,0.0018450575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046699606,0.00033484504,0.00039335559,0.0029805538,0.00041073185,0.001258136,0.0007536882,0.0007585533,0.004296676],"category_scores_gemma":[0.045015387,0.00021983386,0.00069583,0.001621746,0.0006336228,0.0019391369,0.001285251,0.0010240405,0.0006716061],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051670155,0.0005648464,0.9124998,0.00023021724,0.00017765444,0.00013237042,0.0024083122,0.0015762701,0.0020498503,0.0014517147,0.0030741242,0.07531821],"study_design_scores_gemma":[0.000043698994,0.00070745,0.9850353,0.00010017998,0.00006154348,0.00036191984,0.001435285,0.005369415,0.0022326375,0.0019498853,0.0026371693,0.00006561109],"about_ca_topic_score_codex":0.00096673495,"about_ca_topic_score_gemma":0.0020891023,"teacher_disagreement_score":0.0046699606,"about_ca_system_score_codex":0.0005173903,"about_ca_system_score_gemma":0.0004909821,"threshold_uncertainty_score":0.024697423},"labels":[],"label_agreement":null},{"id":"W4383711346","doi":"10.3758/s13428-023-02158-6","title":"Reclassifying guesses to increase signal-to-noise ratio in psychological experiments","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Python (programming language); Computer science; Noise (video); MATLAB; Speech recognition; Variable (mathematics); Artificial intelligence; Psychology; Statistics; Data mining; Machine learning; Mathematics; Programming language","score_opus":0.8334514151004707,"score_gpt":0.7131823945226864,"score_spread":0.12026902057778432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383711346","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9437193,0.00020275061,0.05108196,0.0003607468,0.00029255205,0.0007069519,0.00013900762,0.0006869341,0.0028098354],"genre_scores_gemma":[0.93644774,0.00019124053,0.05765865,0.0006803292,0.00011890215,0.001090658,0.00024983796,0.00040149761,0.0031611559],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939067,0.0028613836,0.0006860627,0.0009551836,0.0012856876,0.0003050408],"domain_scores_gemma":[0.94939035,0.03610625,0.004208998,0.0073561175,0.0018875072,0.0010507354],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009305075,0.0012269182,0.0012632399,0.000549075,0.00045062177,0.0015644312,0.0012577676,0.0026322748,0.0044092988],"category_scores_gemma":[0.076196544,0.0006774027,0.00039728108,0.0003425402,0.0010162223,0.0016964313,0.00079316506,0.0026429924,0.0012146778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02412465,0.01332542,0.012335228,0.0009792018,0.0003825138,0.00023791355,0.0015147561,0.010624087,0.7179256,0.0069702948,0.0018957373,0.20968466],"study_design_scores_gemma":[0.0038733678,0.037832472,0.11662124,0.0003485775,0.0009620138,0.0012011407,0.0005210012,0.21559022,0.57862204,0.038209606,0.0056975554,0.00052075426],"about_ca_topic_score_codex":0.00031802533,"about_ca_topic_score_gemma":0.00040185283,"teacher_disagreement_score":0.99069494,"about_ca_system_score_codex":0.0004717982,"about_ca_system_score_gemma":0.00045150385,"threshold_uncertainty_score":0.04921055},"labels":[],"label_agreement":null},{"id":"W4384664207","doi":"10.3758/s13428-023-02170-w","title":"LaDEP: A large database of English pseudo-compounds","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Yorkville University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database; Programming language; Information retrieval; Natural language processing; World Wide Web","score_opus":0.2067183506943114,"score_gpt":0.5583345911829365,"score_spread":0.35161624048862505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384664207","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53962475,0.0038626483,0.013947647,0.00027313692,0.0001498087,0.0012936629,0.42556912,0.002330936,0.012948263],"genre_scores_gemma":[0.20904088,0.0017239655,0.03695416,0.00033497738,0.00008267158,0.0020890683,0.742004,0.0006477303,0.0071226326],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869305,0.0002601543,0.00042458714,0.00026044424,0.00029088504,0.00007101758],"domain_scores_gemma":[0.9949692,0.0021533326,0.00044438607,0.00093317055,0.0011985159,0.00030133067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008996624,0.0010606732,0.0008736182,0.004707865,0.0007026929,0.0013300596,0.0014097905,0.0012124781,0.0128449295],"category_scores_gemma":[0.005451878,0.00042799278,0.00065582164,0.0048269196,0.00043555145,0.0022502749,0.0017913865,0.00069394696,0.009234064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060236566,0.0024403895,0.110394776,0.014069782,0.0008249609,0.016136523,0.0046544285,0.0024230466,0.07304693,0.003883352,0.1778705,0.5882316],"study_design_scores_gemma":[0.00064574246,0.0012387824,0.35906407,0.0006588919,0.00045264297,0.014101582,0.0044493214,0.005004043,0.03469329,0.0023205697,0.57700706,0.0003640305],"about_ca_topic_score_codex":0.001665786,"about_ca_topic_score_gemma":0.0027172782,"teacher_disagreement_score":0.0128449295,"about_ca_system_score_codex":0.00026525636,"about_ca_system_score_gemma":0.00075426913,"threshold_uncertainty_score":0.04297054},"labels":[],"label_agreement":null},{"id":"W4386047445","doi":"10.3758/s13428-023-02190-6","title":"Deep learning models for webcam eye tracking in online experiments","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Max-Planck-Gesellschaft","keywords":"Eye tracking; Computer science; Gaze; Fixation (population genetics); Artificial intelligence; Deep learning; Computer vision; Eye movement; Tracking (education); Task (project management); Psychology","score_opus":0.49091216203907995,"score_gpt":0.610252692821539,"score_spread":0.1193405307824591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386047445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11286483,0.0005927075,0.87961113,0.00027159945,0.000084057465,0.0002004097,0.00062373135,0.002905691,0.0028458263],"genre_scores_gemma":[0.80132306,0.0002491282,0.19301572,0.000219603,0.000039058796,0.00052235497,0.00083641143,0.0001917345,0.0036029366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995326,0.0001578018,0.000025554165,0.00015998475,0.000076406046,0.000047738373],"domain_scores_gemma":[0.9977805,0.001317342,0.00020196932,0.00029180682,0.00034346472,0.000064883716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016915125,0.00062500587,0.0004816766,0.00037893836,0.00019309198,0.00067572336,0.0011105457,0.00095450156,0.0032942365],"category_scores_gemma":[0.008376665,0.0003551216,0.0005272947,0.00033140025,0.00033332166,0.0010688041,0.0007427669,0.0013848586,0.0008796788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078578043,0.0007872885,0.006721588,0.00041252148,0.00022253544,0.00009918432,0.00015970814,0.62893474,0.02914305,0.0048986245,0.004600917,0.3232341],"study_design_scores_gemma":[0.000013968416,0.000061271654,0.0011733137,0.000012768057,0.000008493994,0.000009420718,0.000006155837,0.9944443,0.0023626473,0.0015751334,0.00032592483,0.00000664562],"about_ca_topic_score_codex":0.0057755485,"about_ca_topic_score_gemma":0.006650241,"teacher_disagreement_score":0.0057755485,"about_ca_system_score_codex":0.0008487449,"about_ca_system_score_gemma":0.00057972554,"threshold_uncertainty_score":0.011483848},"labels":[],"label_agreement":null},{"id":"W4386485153","doi":"10.3758/s13428-023-02222-1","title":"Validation of scrambling methods for vocal affect bursts","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Georg-August-Universität Göttingen","keywords":"Scrambling; Affect (linguistics); Computer science; Speech recognition; Psychology; Audiology; Communication; Medicine; Algorithm","score_opus":0.4873390771829146,"score_gpt":0.6633259502545373,"score_spread":0.17598687307162275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386485153","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66585225,0.0028852397,0.32385516,0.00012551964,0.00048069723,0.0023833225,0.00063729,0.0010177719,0.0027627836],"genre_scores_gemma":[0.7478322,0.0018572082,0.24188633,0.000151171,0.00012749982,0.0038662218,0.0010996934,0.0005931501,0.002586533],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970656,0.00094652985,0.00030620178,0.000700836,0.00082704535,0.00015382498],"domain_scores_gemma":[0.9917846,0.004059643,0.00077081297,0.0013600009,0.0018087238,0.00021626892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004089821,0.0009808429,0.0004740703,0.0010497055,0.0004048115,0.0005734584,0.00080632797,0.0006636891,0.002061251],"category_scores_gemma":[0.015771942,0.00031695078,0.00056873605,0.00029598788,0.000697119,0.00044562857,0.0006314724,0.00085318997,0.00090275024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001675432,0.00048066358,0.001996452,0.0004982496,0.00006963289,0.0001014101,0.0005086754,0.0015521969,0.923931,0.00048223618,0.00026327092,0.06844077],"study_design_scores_gemma":[0.00019332212,0.010919113,0.026057485,0.000079039724,0.00023177887,0.00079146004,0.00023110812,0.015206733,0.94016194,0.00044904993,0.0055630277,0.00011585557],"about_ca_topic_score_codex":0.00051731244,"about_ca_topic_score_gemma":0.00047957234,"teacher_disagreement_score":0.004089821,"about_ca_system_score_codex":0.00022879009,"about_ca_system_score_gemma":0.00024307797,"threshold_uncertainty_score":0.021629274},"labels":[],"label_agreement":null},{"id":"W4387392671","doi":"10.3758/s13428-023-02248-5","title":"Negative affective priming: Reliability and associations with depression symptoms in three samples","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Nap; Psychology; Reliability (semiconductor); Priming (agriculture); Audiology; Internal consistency; Task (project management); Analysis of variance; Depression (economics); Clinical psychology; Developmental psychology; Psychometrics; Medicine; Social psychology; Internal medicine","score_opus":0.2972621905165959,"score_gpt":0.5732007862776924,"score_spread":0.27593859576109653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387392671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99941885,0.000046211484,0.00009514318,0.00001233826,0.00000634633,0.000039621842,0.000023655606,0.000002434281,0.00035545934],"genre_scores_gemma":[0.99934775,0.000028642875,0.00019225379,0.000026846512,0.000007838812,0.00009185539,0.000075511074,0.0000047132935,0.00022454099],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99887604,0.000433587,0.00012452426,0.00022192372,0.00022392938,0.00011996482],"domain_scores_gemma":[0.99507207,0.0025475696,0.00075295893,0.0005053021,0.00074124575,0.00038075112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002502063,0.00049173285,0.0004911038,0.00094374333,0.0011754357,0.00074492604,0.00046525052,0.00092413416,0.0017344938],"category_scores_gemma":[0.008931503,0.00038879277,0.00039914896,0.00045769577,0.0010991152,0.0005140922,0.0010517882,0.00086382346,0.00040165562],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034778384,0.003003855,0.9548737,0.00007262922,0.00013299526,0.00023392182,0.011783104,0.0000941858,0.012531751,0.00030981895,0.00029738675,0.01318884],"study_design_scores_gemma":[0.00012585791,0.00094048446,0.99428236,0.000009598486,0.00006925472,0.00041105243,0.0019729408,0.00014605958,0.0014916894,0.00021119833,0.00032713218,0.000012472633],"about_ca_topic_score_codex":0.0013035727,"about_ca_topic_score_gemma":0.00191169,"teacher_disagreement_score":0.002502063,"about_ca_system_score_codex":0.0004295793,"about_ca_system_score_gemma":0.00032676707,"threshold_uncertainty_score":0.01323235},"labels":[],"label_agreement":null},{"id":"W4388706574","doi":"10.3758/s13428-023-02280-5","title":"Author Correction: Can musical ability be tested online?","year":2023,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Diverse Music Education Insights","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Musical; Computer science; Speech recognition; Psychology; Visual arts; Art","score_opus":0.614351461010834,"score_gpt":0.5641746966113369,"score_spread":0.05017676439949714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388706574","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012990643,0.00036126684,0.00050923374,0.07184197,0.91866744,0.000023762184,0.0011822516,0.00030340414,0.0069807824],"genre_scores_gemma":[0.0144438585,0.002926219,0.004075906,0.1545569,0.19371346,0.00036004078,0.0023947023,0.0022511017,0.6252778],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99079365,0.0013453546,0.0013767859,0.0010981564,0.0047024395,0.0006835608],"domain_scores_gemma":[0.9176378,0.021202167,0.0024200603,0.005847087,0.050394733,0.0024980863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008527845,0.0018013897,0.0021142382,0.0034967128,0.0075719613,0.0060908003,0.004175983,0.010084182,0.08303171],"category_scores_gemma":[0.12153277,0.0011530124,0.0012390475,0.0023977733,0.0035093683,0.0029359886,0.0027820426,0.014852013,0.05636228],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010011176,0.0000031529214,0.00004655432,0.00002889295,0.0000024839235,0.00008007303,0.000027302647,0.000010195096,0.000010000918,0.0005059314,0.99724674,0.0020286744],"study_design_scores_gemma":[0.000039473238,0.000012928817,0.0007073168,0.0004443396,0.000028420121,0.00028955145,0.0002643607,0.00020635016,0.00030988443,0.0022879175,0.9953733,0.00003613449],"about_ca_topic_score_codex":0.055112325,"about_ca_topic_score_gemma":0.06340302,"teacher_disagreement_score":0.08303171,"about_ca_system_score_codex":0.0064202715,"about_ca_system_score_gemma":0.010969861,"threshold_uncertainty_score":0.27776873},"labels":[],"label_agreement":null},{"id":"W4388725852","doi":"10.3758/s13428-023-02285-0","title":"Retraction Note: Eye tracking: empirical foundations for a minimal reporting guideline","year":2023,"lang":"en","type":"retraction","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":2,"is_retracted":true,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; SR Research (Canada)","funders":"","keywords":"Guideline; Computer science; Eye tracking; Tracking (education); Artificial intelligence; Optometry; Psychology; Medicine","score_opus":0.6596814002210868,"score_gpt":0.6967781457215364,"score_spread":0.03709674550044961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388725852","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042129643,0.0022259795,0.004391002,0.74879694,0.23841937,0.00016249552,0.000729579,0.00041236528,0.0044409125],"genre_scores_gemma":[0.014646085,0.003919103,0.028676948,0.78856117,0.1291903,0.0024367985,0.0010431599,0.00078198314,0.03074451],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9273135,0.021033736,0.019029502,0.0050026877,0.025346478,0.0022740355],"domain_scores_gemma":[0.5652089,0.2684872,0.020062698,0.018840173,0.122111455,0.005289566],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.061578445,0.0021345802,0.0020461923,0.0035321333,0.005984314,0.009245579,0.008211809,0.0263972,0.017342698],"category_scores_gemma":[0.5609945,0.0013095228,0.0036162746,0.0030335274,0.008335388,0.008118079,0.006768578,0.04142253,0.016515067],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017421786,0.0000072167677,0.00009067178,0.00015269457,0.000011798495,0.00009582065,0.00045068105,0.00003502205,0.000047680347,0.007882142,0.9831533,0.008055537],"study_design_scores_gemma":[0.000044310797,0.000035320336,0.0007526455,0.0022986452,0.000075459284,0.0004047904,0.0006529364,0.00051850785,0.00028084024,0.017907884,0.9769388,0.00008977229],"about_ca_topic_score_codex":0.008001185,"about_ca_topic_score_gemma":0.006911738,"teacher_disagreement_score":0.9736028,"about_ca_system_score_codex":0.0069163544,"about_ca_system_score_gemma":0.015753485,"threshold_uncertainty_score":0.32566178},"labels":[],"label_agreement":null},{"id":"W4388821770","doi":"10.3758/s13428-023-02246-7","title":"Model-agnostic unsupervised detection of bots in a Likert-type questionnaire","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Respondent; Computer science; Likert scale; Permutation (music); Calibration; Sensitivity (control systems); Statistical hypothesis testing; Type I and type II errors; Null hypothesis; Outlier; Relation (database); Artificial intelligence; Data mining; Machine learning; Statistics; Algorithm; Mathematics","score_opus":0.6771024707565433,"score_gpt":0.6449932992528221,"score_spread":0.03210917150372117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388821770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8175158,0.000041496027,0.17496538,0.00016631195,0.000067131274,0.0018777889,0.0013405383,0.0006759753,0.0033495422],"genre_scores_gemma":[0.95542246,0.000020237045,0.040186897,0.0001477711,0.000014076065,0.0013600115,0.0011737933,0.000048997877,0.0016257839],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9874916,0.007991693,0.0006649343,0.0016387398,0.0016517959,0.0005611881],"domain_scores_gemma":[0.9478978,0.035470158,0.0036348708,0.0069466373,0.005329301,0.00072118023],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014545151,0.00045758236,0.00059670064,0.0007037249,0.0004093621,0.00091342104,0.001124292,0.0010578305,0.0022418245],"category_scores_gemma":[0.05279647,0.00033998856,0.00059204514,0.0005702274,0.000500661,0.0011310504,0.0008346754,0.0010180396,0.0015948527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022861317,0.0037586875,0.6993363,0.00084283145,0.00049803517,0.00022275954,0.00602674,0.024222786,0.03328557,0.0071667936,0.010923648,0.21142977],"study_design_scores_gemma":[0.00016271442,0.0023665049,0.50644284,0.0001706324,0.00024303248,0.00043323694,0.0022511592,0.45442006,0.0195056,0.00680122,0.0070587606,0.00014417239],"about_ca_topic_score_codex":0.001229708,"about_ca_topic_score_gemma":0.0020538736,"teacher_disagreement_score":0.98545486,"about_ca_system_score_codex":0.0005942913,"about_ca_system_score_gemma":0.00084152777,"threshold_uncertainty_score":0.07692307},"labels":[],"label_agreement":null},{"id":"W4388913253","doi":"10.3758/s13428-023-02238-7","title":"Disaggregating level-specific effects in cross-classified multilevel models","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Conflation; Multilevel model; Computer science; Cluster (spacecraft); Random effects model; Artificial intelligence; Machine learning; Meta-analysis; Linguistics","score_opus":0.8313128540076932,"score_gpt":0.7245869789737178,"score_spread":0.10672587503397535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388913253","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035864044,0.0007017055,0.95801127,0.00089241244,0.00012505597,0.00017406601,0.0008609545,0.0005675814,0.002802883],"genre_scores_gemma":[0.5532051,0.0008497414,0.43649215,0.0010833645,0.00013694343,0.0009955795,0.001910043,0.00047230732,0.0048547033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9862111,0.00971818,0.0005791385,0.0020773546,0.0008330802,0.0005811488],"domain_scores_gemma":[0.97109723,0.017422404,0.0026246777,0.006581138,0.0017750857,0.00049935566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019803751,0.0016414688,0.002197738,0.0013771921,0.0012065702,0.0039248643,0.004167594,0.0024997974,0.007925529],"category_scores_gemma":[0.048325937,0.0010608268,0.0038836885,0.0023289577,0.002011144,0.0051634572,0.005013411,0.0061871996,0.0016862424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005336762,0.0002529458,0.03804136,0.0006827864,0.0016480807,0.00061948155,0.004777551,0.20187227,0.0016684119,0.6374709,0.005951369,0.1064811],"study_design_scores_gemma":[0.00008754671,0.00020476537,0.007400197,0.00029598866,0.00054171804,0.00017054183,0.0005495448,0.4431134,0.000934104,0.53294384,0.013635019,0.00012335496],"about_ca_topic_score_codex":0.008359596,"about_ca_topic_score_gemma":0.013301603,"teacher_disagreement_score":0.019803751,"about_ca_system_score_codex":0.0019735412,"about_ca_system_score_gemma":0.001834501,"threshold_uncertainty_score":0.10473347},"labels":[],"label_agreement":null},{"id":"W4388927230","doi":"10.3758/s13428-023-02283-2","title":"Denver pain authenticity stimulus set (D-PASS)","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Pain Mechanisms and Treatments","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Institute on Minority Health and Health Disparities","keywords":"Codebook; Stimulus (psychology); Psychology; Facial expression; Perception; Set (abstract data type); Social psychology; Computer science; Cognitive psychology; Artificial intelligence; Communication; Neuroscience","score_opus":0.4863341374594835,"score_gpt":0.6389944832909215,"score_spread":0.15266034583143795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388927230","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4886093,0.0036833056,0.12420875,0.0022560626,0.0031803993,0.052349184,0.123431474,0.0064258697,0.19585565],"genre_scores_gemma":[0.43713966,0.004296015,0.22430812,0.003453715,0.000552303,0.09698992,0.12676576,0.002323784,0.10417067],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994117,0.00014480625,0.00006924914,0.00012301543,0.00020249523,0.000048679234],"domain_scores_gemma":[0.99878746,0.0003278566,0.0000819439,0.00029206843,0.00034379103,0.00016692246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010264696,0.000920247,0.0006975536,0.0005698055,0.00054369064,0.0007250644,0.0010813628,0.00094263395,0.08278],"category_scores_gemma":[0.0028423676,0.00046518378,0.0003291728,0.00038836495,0.0003907314,0.0007575394,0.0013733696,0.0009297871,0.010311448],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021676112,0.0064429417,0.0052915574,0.0056401785,0.00015506137,0.0014377963,0.0013929209,0.0025796972,0.325858,0.020220844,0.23959734,0.36970755],"study_design_scores_gemma":[0.0035794552,0.02021744,0.099009365,0.001646521,0.00042621026,0.0050288453,0.0012805694,0.008751362,0.05790795,0.013665907,0.78795135,0.00053506787],"about_ca_topic_score_codex":0.0010721863,"about_ca_topic_score_gemma":0.0025884323,"teacher_disagreement_score":0.08278,"about_ca_system_score_codex":0.0003586118,"about_ca_system_score_gemma":0.00046670059,"threshold_uncertainty_score":0.2769267},"labels":[],"label_agreement":null},{"id":"W4389075303","doi":"10.3758/s13428-023-02273-4","title":"Attention in hindsight: Using stimulated recall to capture dynamic fluctuations in attentional engagement","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recall; Generalizability theory; Psychology; Cognitive psychology; Hindsight bias; CLIPS; Mnemonic; Developmental psychology; Computer science; Artificial intelligence","score_opus":0.5403413114135511,"score_gpt":0.6165809254192173,"score_spread":0.07623961400566615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389075303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7874974,0.0015987584,0.206179,0.00011570338,0.00013369374,0.00012623113,0.00062880147,0.0006993863,0.003021071],"genre_scores_gemma":[0.94874084,0.0005114449,0.04844185,0.00020430003,0.00010041246,0.000098204066,0.00030445465,0.00012331971,0.0014751987],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99981076,0.00004285798,0.000013376972,0.000057984467,0.000055536977,0.000019588702],"domain_scores_gemma":[0.99900526,0.0005295611,0.00016238341,0.00013321916,0.00009988107,0.00006966321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052810024,0.00034402584,0.00023895738,0.00058181153,0.00012447912,0.0006481836,0.0003079594,0.00044808615,0.0012799901],"category_scores_gemma":[0.003571892,0.0001857914,0.00017479499,0.00044446046,0.00028606015,0.0005379266,0.00047125478,0.00038875482,0.00028337122],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025500178,0.0002045581,0.024669511,0.00038036433,0.00016751925,0.0003710484,0.0005447659,0.0047266097,0.72658503,0.0013467683,0.0014166556,0.23703708],"study_design_scores_gemma":[0.0005135778,0.0033145433,0.4376717,0.00020409317,0.0006312845,0.0054874914,0.00062842347,0.16444062,0.36301735,0.015638767,0.008171758,0.00028037454],"about_ca_topic_score_codex":0.00071647816,"about_ca_topic_score_gemma":0.0019403212,"teacher_disagreement_score":0.0012799901,"about_ca_system_score_codex":0.00013197401,"about_ca_system_score_gemma":0.00023154552,"threshold_uncertainty_score":0.004281938},"labels":[],"label_agreement":null},{"id":"W4389129333","doi":"10.3758/s13428-023-02247-6","title":"Does strict invariance matter? Valid group mean comparisons with ordered-categorical items","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Polytomous Rasch model; Measurement invariance; Categorical variable; Mathematics; Statistics; Scalar (mathematics); Factor analysis; Item response theory; Confirmatory factor analysis; Psychometrics; Structural equation modeling; Geometry","score_opus":0.8548829296835958,"score_gpt":0.6812477469221532,"score_spread":0.17363518276144263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389129333","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16011274,0.0017452593,0.8056434,0.006444657,0.0017668417,0.0019561297,0.0012843809,0.0012274755,0.01981913],"genre_scores_gemma":[0.7590716,0.00054113165,0.22847688,0.0038834226,0.00044579376,0.0044126012,0.0012610572,0.00065708417,0.0012503956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8286572,0.11328383,0.012946929,0.020305784,0.02240442,0.0024018944],"domain_scores_gemma":[0.5650442,0.2801934,0.030121451,0.10122234,0.02164968,0.0017688524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17645526,0.0010875195,0.002092225,0.0016608665,0.0018784988,0.0040504253,0.0036081276,0.0023322082,0.0073016514],"category_scores_gemma":[0.54720473,0.000994476,0.0033837687,0.0032872937,0.0079098055,0.008018663,0.004101764,0.0049866424,0.0016468758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017513244,0.00075618445,0.21308453,0.0027154433,0.0038884988,0.0006005443,0.01695324,0.0037019488,0.012146798,0.20129527,0.020635897,0.5224704],"study_design_scores_gemma":[0.00068471866,0.003171161,0.39101595,0.0016992579,0.0013790898,0.0012817732,0.005428571,0.024417244,0.017476415,0.52005184,0.032938443,0.0004555786],"about_ca_topic_score_codex":0.00211825,"about_ca_topic_score_gemma":0.0025081746,"teacher_disagreement_score":0.17645526,"about_ca_system_score_codex":0.0016098737,"about_ca_system_score_gemma":0.002645914,"threshold_uncertainty_score":0.93319577},"labels":[],"label_agreement":null},{"id":"W4389475103","doi":"10.3758/s13428-023-02293-0","title":"Diversity, equity, and inclusivity in observational ambulatory assessment: Recommendations from two decades of Electronically Activated Recorder (EAR) research","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Institute on Aging; National Cancer Institute; National Institutes of Health; National Institute of Environmental Health Sciences; Mind and Life Institute","keywords":"Observational study; Psychology; Observational methods in psychology; Experience sampling method; Medical education; Applied psychology; Medicine; Social psychology","score_opus":0.967125737717084,"score_gpt":0.8695035739139877,"score_spread":0.0976221638030963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389475103","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10253808,0.20826481,0.07818933,0.57560074,0.01231407,0.002961064,0.0022574835,0.0004751949,0.017399339],"genre_scores_gemma":[0.7175394,0.043796215,0.14551923,0.077345476,0.0076615084,0.0049632066,0.0013037872,0.00020053041,0.0016706544],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.68266195,0.21973349,0.041660327,0.014370828,0.037547924,0.0040254607],"domain_scores_gemma":[0.22033359,0.6447236,0.029400468,0.03486258,0.064702705,0.0059770932],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51574284,0.001962767,0.0068575656,0.007748172,0.006837619,0.017010143,0.011957396,0.011178489,0.0032791593],"category_scores_gemma":[0.5670833,0.0017563283,0.00648125,0.007767274,0.020984778,0.026929555,0.014770294,0.013403483,0.0004516102],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002007838,0.0018514172,0.37590677,0.009729009,0.0043719434,0.00013566737,0.014245293,0.002122126,0.00023801149,0.08489934,0.037577342,0.46691522],"study_design_scores_gemma":[0.0019341552,0.0042184237,0.429839,0.10287615,0.0137570035,0.00035759667,0.059067097,0.019708248,0.0026616533,0.25669256,0.10761898,0.0012691009],"about_ca_topic_score_codex":0.08194915,"about_ca_topic_score_gemma":0.12458238,"teacher_disagreement_score":0.9880426,"about_ca_system_score_codex":0.013482019,"about_ca_system_score_gemma":0.058217913,"threshold_uncertainty_score":0.59717536},"labels":[],"label_agreement":null},{"id":"W4389574735","doi":"10.3758/s13428-023-02299-8","title":"Road Hazard Stimuli: Annotated naturalistic road videos for studying hazard detection and scene perception","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Traffic and Road Safety","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Electric (Canada); University of Toronto","funders":"","keywords":"Computer science; CLIPS; Perception; Replicate; Set (abstract data type); Hazard; Visual perception; Artificial intelligence; Cognitive psychology; Psychology","score_opus":0.23866927227371765,"score_gpt":0.5051115392190106,"score_spread":0.266442266945293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389574735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6633945,0.0026911518,0.05448482,0.00077382155,0.0008795981,0.0054631406,0.23939641,0.0038908857,0.029025659],"genre_scores_gemma":[0.57842374,0.0013369889,0.12501466,0.0005918303,0.00029323302,0.005862284,0.27985486,0.000754949,0.007867484],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99979395,0.000042272928,0.000017343962,0.000054095544,0.000059522015,0.000032828197],"domain_scores_gemma":[0.9993144,0.00020777146,0.00007668514,0.00008822063,0.00019430458,0.0001185352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038403753,0.0006260796,0.00022768397,0.0008495912,0.00034527588,0.00032413413,0.00043934616,0.0005823372,0.008192794],"category_scores_gemma":[0.001612031,0.0001447921,0.00030247236,0.0005123895,0.00026517594,0.00042243276,0.00058830227,0.00050168403,0.0014862445],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036734552,0.0032622633,0.033026386,0.00890961,0.00022303581,0.0019700597,0.0026518905,0.008519274,0.30217978,0.006720029,0.32227048,0.30659372],"study_design_scores_gemma":[0.0007314455,0.0030116804,0.5308291,0.0010484951,0.00028063395,0.006122426,0.0030637702,0.04326849,0.059834845,0.008748711,0.34268332,0.0003771358],"about_ca_topic_score_codex":0.0032488527,"about_ca_topic_score_gemma":0.01370684,"teacher_disagreement_score":0.008192794,"about_ca_system_score_codex":0.00032938813,"about_ca_system_score_gemma":0.00042554995,"threshold_uncertainty_score":0.027407646},"labels":[],"label_agreement":null},{"id":"W4390222853","doi":"10.3758/s13428-023-02242-x","title":"Feats: A database of semantic features for early produced noun concepts","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Institute on Deafness and Other Communication Disorders; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University","keywords":"Computer science; Vocabulary; Natural language processing; Noun; Artificial intelligence; Feature (linguistics); Set (abstract data type); Semantic feature; Semantic network; Linguistics","score_opus":0.35746756208848407,"score_gpt":0.633920496594131,"score_spread":0.2764529345056469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390222853","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13758056,0.0018642044,0.17303108,0.0005383919,0.000247735,0.00056968536,0.61238724,0.04386237,0.029918741],"genre_scores_gemma":[0.2920717,0.0010048804,0.15416199,0.00015032437,0.00007231527,0.001092013,0.53713053,0.0034598156,0.0108564515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995096,0.000040358416,0.0000706879,0.00018341097,0.00015883344,0.000037192473],"domain_scores_gemma":[0.99814737,0.0006935476,0.00020535079,0.00044532923,0.00042890367,0.00007947426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050137093,0.0013672516,0.0005471209,0.004439656,0.0005788402,0.0014919498,0.0012532091,0.0011056467,0.018237792],"category_scores_gemma":[0.0048082233,0.0005848765,0.00086430926,0.0019937058,0.0004149317,0.0040148613,0.0013372768,0.0007498037,0.009023468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023795606,0.0005066135,0.04684937,0.0026628296,0.00037045553,0.0019593248,0.002351692,0.0048106695,0.07738402,0.029982688,0.20956151,0.62118113],"study_design_scores_gemma":[0.00035863963,0.00070332777,0.14680819,0.00077801704,0.00060260703,0.0067440146,0.0022976382,0.062594846,0.081163436,0.0648305,0.6326357,0.00048304885],"about_ca_topic_score_codex":0.0048951516,"about_ca_topic_score_gemma":0.0080512,"teacher_disagreement_score":0.018237792,"about_ca_system_score_codex":0.0007042382,"about_ca_system_score_gemma":0.00092112506,"threshold_uncertainty_score":0.061011493},"labels":[],"label_agreement":null},{"id":"W4390938888","doi":"10.3758/s13428-023-02326-8","title":"What do we manipulate when reminding people of (not) having control? In search of construct validity","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Narodowa Agencja Wymiany Akademickiej; Narodowe Centrum Nauki; Fundacja na rzecz Nauki Polskiej; Uniwersytet Jagielloński w Krakowie; Narodowym Centrum Nauki; Deutsche Forschungsgemeinschaft","keywords":"Construct (python library); Recall; Control (management); Psychology; Comparability; Construct validity; Social psychology; Cognitive psychology; Sense of control; Locus of control; Emotionality; Developmental psychology; Computer science; Psychometrics; Artificial intelligence","score_opus":0.4821986946205014,"score_gpt":0.6286153137827989,"score_spread":0.14641661916229748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390938888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92448807,0.0025808613,0.041082956,0.008723093,0.00079936103,0.0038646725,0.00062168064,0.00023116199,0.017608231],"genre_scores_gemma":[0.962315,0.0007305405,0.025340542,0.0021965795,0.00025857222,0.00801869,0.00028977505,0.00006128441,0.0007889875],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9523851,0.032111473,0.003893561,0.003945275,0.0065919594,0.0010726558],"domain_scores_gemma":[0.7382781,0.19035162,0.030938441,0.02992273,0.0076426887,0.002866439],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055334352,0.0006544452,0.00071674923,0.0009770627,0.0018033844,0.0030086979,0.0013715677,0.0016777456,0.002414059],"category_scores_gemma":[0.2843496,0.0004921624,0.00073632254,0.0007268726,0.004923223,0.0041561252,0.0014327407,0.0017998634,0.0004956434],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069319103,0.00702191,0.30363023,0.004745613,0.0018003787,0.00018167034,0.098811015,0.0011389296,0.012692643,0.01718748,0.00731501,0.53854316],"study_design_scores_gemma":[0.0027953482,0.01349647,0.8069505,0.004183378,0.002720798,0.00039352287,0.030399177,0.0042382046,0.031148724,0.046550196,0.056506924,0.00061676535],"about_ca_topic_score_codex":0.0019993712,"about_ca_topic_score_gemma":0.0018054207,"teacher_disagreement_score":0.9446657,"about_ca_system_score_codex":0.0017418648,"about_ca_system_score_gemma":0.0020671713,"threshold_uncertainty_score":0.2926395},"labels":[],"label_agreement":null},{"id":"W4392446616","doi":"10.3758/s13428-024-02352-0","title":"Lightness constancy in reality, in virtual reality, and on flat-panel displays","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Virtual reality; Achromatic lens; Computer science; Perception; Headset; Lightness; Immersion (mathematics); Depth perception; Virtual machine; Display device; Computer vision; Computer graphics (images); Artificial intelligence; Human–computer interaction; Psychology; Mathematics; Optics; Physics","score_opus":0.5964500043183114,"score_gpt":0.621109479030278,"score_spread":0.02465947471196661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392446616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731126,0.00016168109,0.019634452,0.00007157429,0.000029706824,0.000049885824,0.0004468552,0.00021296403,0.006280277],"genre_scores_gemma":[0.9954365,0.000059008704,0.0034225811,0.000022112401,0.00000894955,0.000016783208,0.00015518106,0.00005977692,0.0008191164],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99947613,0.00014700329,0.000017144213,0.0001115131,0.00015523739,0.000092965434],"domain_scores_gemma":[0.9987174,0.00066526816,0.00013581659,0.0001936557,0.0001384099,0.00014937203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037910292,0.0002683618,0.00021893003,0.0006868456,0.00027950417,0.00068745273,0.00057274575,0.00030417944,0.0041035973],"category_scores_gemma":[0.0032554513,0.00021860798,0.00026122766,0.00045974963,0.00044504082,0.0008320204,0.0008640729,0.0005746298,0.00026824413],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007111401,0.0004788808,0.013535863,0.00025435374,0.000087603126,0.00017127553,0.0010183197,0.0067186514,0.8922019,0.0064617973,0.001367856,0.07059211],"study_design_scores_gemma":[0.00027104723,0.0021168329,0.6006936,0.000093688264,0.00023292215,0.000989557,0.00067440816,0.09515673,0.28860545,0.0073430315,0.003586036,0.00023674768],"about_ca_topic_score_codex":0.0034163455,"about_ca_topic_score_gemma":0.002869072,"teacher_disagreement_score":0.0041035973,"about_ca_system_score_codex":0.00042066042,"about_ca_system_score_gemma":0.00025544275,"threshold_uncertainty_score":0.013727903},"labels":[],"label_agreement":null},{"id":"W4392583385","doi":"10.3758/s13428-024-02363-x","title":"Mobile version of the Battery for the Assessment of Auditory Sensorimotor and Timing Abilities (BAASTA): Implementation and adult norms","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université de Montréal; International Laboratory for Brain, Music and Sound Research; Centre for Research on Brain Language and Music; Bell (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Société d'Accélération du Transfert de Technologies","keywords":"Rhythm; Computer science; Audiology; Finger tapping; Population; Cognitive psychology; Psychology; Normative; Medicine","score_opus":0.25689492300716626,"score_gpt":0.5927734323046927,"score_spread":0.33587850929752644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392583385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55196065,0.0012264871,0.10143664,0.0026526116,0.0020661484,0.07145553,0.13633396,0.010210214,0.12265774],"genre_scores_gemma":[0.35430261,0.0020481616,0.21455078,0.0024823288,0.0007051966,0.19135973,0.09370865,0.0038908,0.1369518],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99557674,0.0010863486,0.0011884907,0.00070025283,0.0011199831,0.00032813617],"domain_scores_gemma":[0.98826516,0.0024342649,0.00093583425,0.0012130644,0.0066227033,0.00052887696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005831329,0.0020825653,0.0014203977,0.0024195495,0.0009628999,0.0014091079,0.0017258,0.0012186221,0.043314494],"category_scores_gemma":[0.013997492,0.000716598,0.0010964042,0.0011839742,0.00073907553,0.0014956774,0.0018410629,0.0015353083,0.02667184],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009859158,0.009330395,0.162814,0.0017198225,0.000322185,0.0010541677,0.0039915973,0.0024735325,0.0154215,0.005417753,0.24182852,0.54576737],"study_design_scores_gemma":[0.0024291207,0.006640999,0.67011625,0.0009874227,0.00026217246,0.0039422284,0.0020535563,0.006280767,0.01724093,0.009590223,0.27983353,0.000622847],"about_ca_topic_score_codex":0.0032249156,"about_ca_topic_score_gemma":0.0070198514,"teacher_disagreement_score":0.043314494,"about_ca_system_score_codex":0.0006161128,"about_ca_system_score_gemma":0.0015243865,"threshold_uncertainty_score":0.1449014},"labels":[],"label_agreement":null},{"id":"W4392947175","doi":"10.3758/s13428-024-02378-4","title":"TAT-HUM: Trajectory analysis toolkit for human movements in Python","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"University of Toronto","keywords":"Python (programming language); Computer science; Scripting language; Human–computer interaction; Hum; Kinematics; Trajectory; Movement (music); Artificial intelligence; Programming language","score_opus":0.5418191110815244,"score_gpt":0.691732494680939,"score_spread":0.14991338359941464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392947175","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003182685,0.000108342145,0.46616456,0.00008955579,0.000113521135,0.00015258175,0.016022978,0.5114204,0.0027453706],"genre_scores_gemma":[0.14833982,0.0005698385,0.61925894,0.0005888243,0.00010377261,0.002505684,0.041920684,0.16532546,0.021386981],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999678,0.000046473993,0.00003605095,0.00010339755,0.000086771965,0.000049290946],"domain_scores_gemma":[0.99937695,0.00029855806,0.000051925614,0.00011167273,0.000103351034,0.00005748617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060965493,0.0015174203,0.0009846381,0.0010393308,0.00063882873,0.001440982,0.001799548,0.0007447663,0.07090046],"category_scores_gemma":[0.0031210245,0.0009843273,0.0014389141,0.0008706295,0.00051269145,0.0011301269,0.002027971,0.001747914,0.02218284],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011719858,0.00022458386,0.007074469,0.0035984276,0.0007478391,0.0008124148,0.0018390621,0.046056096,0.028516814,0.031732228,0.5155054,0.36272067],"study_design_scores_gemma":[0.0005122813,0.0001517048,0.009195299,0.00050834636,0.000251049,0.00092747435,0.0003868232,0.55457693,0.03996202,0.079533435,0.31362888,0.00036574295],"about_ca_topic_score_codex":0.0051501086,"about_ca_topic_score_gemma":0.010527164,"teacher_disagreement_score":0.07090046,"about_ca_system_score_codex":0.00055453327,"about_ca_system_score_gemma":0.001635767,"threshold_uncertainty_score":0.23718572},"labels":[],"label_agreement":null},{"id":"W4393142761","doi":"10.3758/s13428-024-02356-w","title":"Check your outliers! An introduction to identifying statistical outliers in R with easystats","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Outlier; Univariate; Computer science; Anomaly detection; Preprint; Transparency (behavior); Software; Data mining; Statistical analysis; Statistical model; R package; Multivariate statistics; Artificial intelligence; Data science; Machine learning; Statistics; Mathematics; World Wide Web; Programming language; Computer security","score_opus":0.628588452955993,"score_gpt":0.6929784310768745,"score_spread":0.06438997812088154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393142761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013358055,0.0008124857,0.8300873,0.0017325426,0.0010902963,0.00040995024,0.009695032,0.14710751,0.007729213],"genre_scores_gemma":[0.015095961,0.0007684654,0.873734,0.0021803097,0.00086266024,0.0020647522,0.0062275887,0.08111723,0.017949127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98624307,0.0076542106,0.0015510365,0.0010751724,0.003039156,0.00043723464],"domain_scores_gemma":[0.873614,0.09997426,0.005695442,0.011977011,0.007258645,0.0014805975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017272668,0.0026650107,0.002548973,0.003426245,0.001009269,0.0034000585,0.0037033379,0.0019658539,0.16187555],"category_scores_gemma":[0.12406535,0.0027260142,0.0031737972,0.0023320753,0.0016051763,0.0042713587,0.0037815268,0.0043845423,0.116700664],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043446507,0.00014572604,0.0022554654,0.0020577563,0.0002974657,0.0004210793,0.0006181716,0.0034509604,0.0033939492,0.026609428,0.6777395,0.28257605],"study_design_scores_gemma":[0.00061857695,0.00033323103,0.0063200775,0.0023016229,0.00023836056,0.0016067635,0.0003241385,0.046594776,0.015877634,0.16464491,0.7605577,0.0005821909],"about_ca_topic_score_codex":0.0011111108,"about_ca_topic_score_gemma":0.003488211,"teacher_disagreement_score":0.16187555,"about_ca_system_score_codex":0.0005919904,"about_ca_system_score_gemma":0.0020726721,"threshold_uncertainty_score":0.5415276},"labels":[],"label_agreement":null},{"id":"W4393408830","doi":"10.3758/s13428-024-02384-6","title":"Examining the performance of the chi-square difference test when the unrestricted model is slightly misspecified","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nested set model; Context (archaeology); Statistics; Test (biology); Econometrics; Structural equation modeling; Statistical hypothesis testing; Chi-square test; Mean squared error; Mathematics; Computer science; Data mining","score_opus":0.8815597692413241,"score_gpt":0.6416555860264059,"score_spread":0.23990418321491813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393408830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7914643,0.00043170404,0.19872813,0.0009069012,0.0004010672,0.00023048886,0.00061870425,0.0010864128,0.0061322446],"genre_scores_gemma":[0.96944237,0.000047603233,0.029284295,0.00008524666,0.000028347087,0.00008491351,0.00038832697,0.00010830845,0.0005305207],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9491159,0.032041244,0.0036332996,0.007717993,0.005804213,0.001687353],"domain_scores_gemma":[0.48747203,0.48013517,0.006076159,0.018970396,0.0057602525,0.0015860437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.057470623,0.0011594158,0.0012464153,0.0021668444,0.0010715598,0.0025599576,0.0025529005,0.0023429373,0.006288734],"category_scores_gemma":[0.33256823,0.00048222876,0.0023720148,0.0017210755,0.0020173246,0.0040756967,0.0016398889,0.003163166,0.0009834325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056710267,0.0016895403,0.655396,0.0008475376,0.004614229,0.0021526462,0.0037061134,0.023868674,0.011694111,0.013931932,0.00565259,0.27077562],"study_design_scores_gemma":[0.0004970945,0.006716269,0.48330033,0.0004341749,0.0024173828,0.0035021708,0.0076576625,0.43782005,0.024815513,0.024826527,0.0076969033,0.00031596914],"about_ca_topic_score_codex":0.004346375,"about_ca_topic_score_gemma":0.003053395,"teacher_disagreement_score":0.057470623,"about_ca_system_score_codex":0.0009234472,"about_ca_system_score_gemma":0.0024247423,"threshold_uncertainty_score":0.30393732},"labels":[],"label_agreement":null},{"id":"W4394592969","doi":"10.3758/s13428-024-02401-8","title":"Using virtual reality to induce multi-trial inattentional blindness despite trial-by-trial measures of awareness","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tel Aviv University; Milner Foundation; Canadian Institute for Advanced Research","keywords":"Inattentional blindness; Blindness; Virtual reality; Psychology; Computer science; Cognitive psychology; Applied psychology; Human–computer interaction; Perception; Medicine; Optometry; Neuroscience","score_opus":0.9190297617559202,"score_gpt":0.7144993092485171,"score_spread":0.2045304525074031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394592969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92380375,0.0008489526,0.072345324,0.000082385035,0.00015642612,0.00058968714,0.00013788835,0.00035584279,0.0016798992],"genre_scores_gemma":[0.9763173,0.00034290898,0.02106109,0.00010641015,0.00003770767,0.0009631531,0.00015036965,0.00013337572,0.0008876338],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991703,0.00022212717,0.00010408379,0.00022539591,0.00014678377,0.00013140534],"domain_scores_gemma":[0.9981541,0.0008583934,0.00036877656,0.00036713536,0.000122041216,0.00012947485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010197287,0.00061014784,0.0004744568,0.00024775934,0.00021271934,0.0004392446,0.00047431144,0.0003071141,0.0014800049],"category_scores_gemma":[0.003488974,0.00022511244,0.0002475652,0.00013678869,0.0007374932,0.00043120238,0.00091670966,0.0008094164,0.00016920605],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016083546,0.00061281736,0.00070553954,0.0003117813,0.000045126653,0.00006276028,0.0002457668,0.00035106184,0.9799321,0.00056637055,0.00014106552,0.015417354],"study_design_scores_gemma":[0.0007128652,0.02951103,0.05330165,0.00009822685,0.00027122442,0.0010497693,0.00020682505,0.009261639,0.8960469,0.0041046096,0.005309433,0.00012583923],"about_ca_topic_score_codex":0.00018132989,"about_ca_topic_score_gemma":0.0003598378,"teacher_disagreement_score":0.0014800049,"about_ca_system_score_codex":0.00015210596,"about_ca_system_score_gemma":0.00028378863,"threshold_uncertainty_score":0.005392909},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4396558685","doi":"10.3758/s13428-024-02431-2","title":"Author Correction: r2mlm: An R package calculating R-squared measures for multilevel models","year":2024,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Data Analysis with R","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"","keywords":"Statistics; R package; Multilevel model; Mean squared error; Computer science; Mathematics; Econometrics","score_opus":0.5097944911348687,"score_gpt":0.5952947699876017,"score_spread":0.08550027885273292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396558685","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016426455,0.001985057,0.08687067,0.051791135,0.6674035,0.00043520165,0.12911874,0.03608243,0.024670627],"genre_scores_gemma":[0.03475791,0.0025844988,0.20095433,0.032285184,0.045800213,0.0023819604,0.099486776,0.112410516,0.4693386],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98735714,0.0033955323,0.0020561423,0.0019885665,0.004578036,0.0006246096],"domain_scores_gemma":[0.8681969,0.05186673,0.004941164,0.01706346,0.055789497,0.0021422182],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01154635,0.0027186312,0.00279713,0.007290927,0.003421244,0.0050557028,0.005237721,0.004120811,0.39714146],"category_scores_gemma":[0.24192382,0.0021521028,0.0022808437,0.00690072,0.002229606,0.0038108462,0.0047088843,0.008228647,0.17847604],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032601652,0.000004265075,0.00015848075,0.00016842104,0.000022940707,0.00005617497,0.00004096165,0.000092368566,0.000040257815,0.001594196,0.98960084,0.008188577],"study_design_scores_gemma":[0.00013934118,0.000025434912,0.0015584689,0.0008416414,0.00015910593,0.0005613857,0.00015805983,0.0015791722,0.0009021786,0.018273806,0.9756581,0.00014322462],"about_ca_topic_score_codex":0.015843613,"about_ca_topic_score_gemma":0.027060535,"teacher_disagreement_score":0.39714146,"about_ca_system_score_codex":0.0024665876,"about_ca_system_score_gemma":0.008125981,"threshold_uncertainty_score":0.8599045},"labels":[],"label_agreement":null},{"id":"W4396558963","doi":"10.3758/s13428-024-02412-5","title":"Measures of angularity in digital images","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Aesthetic Perception and Analysis","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Curvilinear coordinates; Discriminative model; Artificial intelligence; Scripting language; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.5282680905636027,"score_gpt":0.6166722057195967,"score_spread":0.088404115155994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396558963","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92784995,0.0008305188,0.031601273,0.00011009906,0.00006168934,0.00012549425,0.00074954197,0.00015543686,0.038515966],"genre_scores_gemma":[0.98769146,0.00033792248,0.009285034,0.000038312817,0.000022969405,0.000072390016,0.00025879225,0.000063847176,0.0022292328],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995963,0.00009314159,0.000028556678,0.00008716155,0.00015364437,0.00004121549],"domain_scores_gemma":[0.9977616,0.00081197574,0.0005740872,0.0002441658,0.00043839877,0.00016965809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006271468,0.0002823467,0.00015891009,0.0024520515,0.0003095799,0.0011930071,0.00022479135,0.00021585124,0.009659956],"category_scores_gemma":[0.0072631873,0.00015294907,0.00019609305,0.0014541314,0.00058353844,0.0011952388,0.0007445169,0.0003386196,0.0005669989],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002978246,0.00049417093,0.1522403,0.0010100284,0.00024170254,0.00021114446,0.00271905,0.003697241,0.44554865,0.029607479,0.0024871272,0.35876492],"study_design_scores_gemma":[0.000059574428,0.0006596713,0.926155,0.00017552683,0.00015506211,0.00085740275,0.0024916995,0.0074200826,0.046175133,0.01129836,0.0044664466,0.00008613945],"about_ca_topic_score_codex":0.0015405363,"about_ca_topic_score_gemma":0.0022223133,"teacher_disagreement_score":0.009659956,"about_ca_system_score_codex":0.0005176875,"about_ca_system_score_gemma":0.00020290876,"threshold_uncertainty_score":0.03231573},"labels":[],"label_agreement":null},{"id":"W4396768368","doi":"10.3758/s13428-024-02409-0","title":"Slow and steady: Validating the rhythmic visual response task as a marker for attentional states","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Metronome; Cognitive psychology; Mind-wandering; Rhythm; Psychology; Cognition; Task (project management); Stimulus (psychology); Attentional control; Working memory; Neuroscience","score_opus":0.29499827530801165,"score_gpt":0.5895489115772024,"score_spread":0.2945506362691907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396768368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95532745,0.0001339852,0.037599407,0.00010332132,0.000124468,0.00042525915,0.00053708674,0.00017044459,0.0055784415],"genre_scores_gemma":[0.9708666,0.00008028427,0.023709325,0.0002700807,0.000053785647,0.000982514,0.0004273491,0.00017849832,0.0034314145],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99885356,0.00040772712,0.0000880188,0.0003268886,0.00024090681,0.000082986044],"domain_scores_gemma":[0.9946701,0.0029650803,0.0007472891,0.0006981002,0.00059831725,0.00032114342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024250618,0.00042689056,0.00023649452,0.0005524521,0.00034578846,0.000776229,0.0005209464,0.00083773996,0.0022930033],"category_scores_gemma":[0.013001508,0.0001866332,0.00016775429,0.00022793809,0.000562936,0.0005791001,0.000640306,0.0006048973,0.00070183957],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008119303,0.0037404557,0.09669292,0.00042901162,0.00019214969,0.00023544964,0.002141132,0.001876827,0.739582,0.0034671873,0.0027808743,0.1407428],"study_design_scores_gemma":[0.0007801704,0.015208719,0.8142482,0.00015403483,0.00039722564,0.0014472078,0.0011434192,0.033974573,0.11850011,0.005838491,0.008132152,0.00017567961],"about_ca_topic_score_codex":0.0011266603,"about_ca_topic_score_gemma":0.0020028576,"teacher_disagreement_score":0.0024250618,"about_ca_system_score_codex":0.00017320739,"about_ca_system_score_gemma":0.00039410553,"threshold_uncertainty_score":0.012825072},"labels":[],"label_agreement":null},{"id":"W4396780632","doi":"10.3758/s13428-024-02376-6","title":"Taboo language across the globe: A multi-lab study","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Swearing, Euphemism, Multilingualism","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Agencia Nacional de Investigación y Desarrollo; Ministero dell'Università e della Ricerca; Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja; Università degli Studi di Milano-Bicocca; Banco Bilbao Vizcaya Argentaria; Deutsche Forschungsgemeinschaft; Comunidad de Madrid; Fundación BBVA","keywords":"Taboo; Globe; Linguistics; Sociocultural evolution; Psychology; Speech community; Valence (chemistry); Social psychology; Sociology; Anthropology; Philosophy","score_opus":0.49207033801001115,"score_gpt":0.7252262250210094,"score_spread":0.23315588701099826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396780632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9990953,0.000022001044,0.0003255588,0.000025638337,0.0000064070728,0.0000947563,0.00006774898,0.0000049853998,0.00035765153],"genre_scores_gemma":[0.9962573,0.0001082309,0.0013158629,0.00027698075,0.00003168568,0.0005221657,0.00024532393,0.000016148464,0.0012263075],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99856526,0.0006774376,0.00008289044,0.0002703162,0.00022302098,0.00018106871],"domain_scores_gemma":[0.99649787,0.0009349653,0.000584021,0.000486064,0.0007302971,0.00076678366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025297634,0.00056920707,0.00070730055,0.0009105314,0.002360342,0.0015444204,0.00047166867,0.0007270126,0.0014635163],"category_scores_gemma":[0.004483289,0.00032108068,0.0004569377,0.00053791766,0.0011704842,0.000980337,0.0015271221,0.0011672615,0.00074846967],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022882435,0.038124148,0.62290466,0.00044660855,0.00042535944,0.0033834402,0.21486576,0.00040557917,0.032866232,0.00059633394,0.0032165756,0.08047711],"study_design_scores_gemma":[0.00016584642,0.013946976,0.82412946,0.00009119061,0.00017524559,0.0018758832,0.14498164,0.0009884427,0.0053756386,0.0007680319,0.007320178,0.00018148862],"about_ca_topic_score_codex":0.0019255528,"about_ca_topic_score_gemma":0.0043156203,"teacher_disagreement_score":0.0025297634,"about_ca_system_score_codex":0.000444882,"about_ca_system_score_gemma":0.000502834,"threshold_uncertainty_score":0.013378859},"labels":[],"label_agreement":null},{"id":"W4399117309","doi":"10.3758/s13428-024-02441-0","title":"Shadows of wisdom: Classifying meta-cognitive and morally grounded narrative content via large language models","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychology of Moral and Emotional Judgment","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; John Templeton Foundation","keywords":"Narrative; Categorization; Humility; Classifier (UML); Psychology; Workflow; Coding (social sciences); Computer science; Social psychology; Artificial intelligence; Sociology; Linguistics; Social science","score_opus":0.7650757583834222,"score_gpt":0.5756139618117823,"score_spread":0.18946179657163997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399117309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64324003,0.0008679848,0.3394935,0.0013213577,0.00011813878,0.00071982486,0.0039191497,0.0046364027,0.0056835385],"genre_scores_gemma":[0.8272589,0.000129713,0.16773245,0.00015186159,0.000021641377,0.00035532718,0.0031413683,0.00018921103,0.001019499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971027,0.0018317706,0.00015146614,0.00048190134,0.00032669422,0.00010562279],"domain_scores_gemma":[0.9745763,0.020919414,0.0010550848,0.0015217409,0.0015060761,0.0004213842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069050645,0.0009864329,0.0003900476,0.0021101597,0.00078420626,0.0027111329,0.0014646993,0.0008816893,0.0017056722],"category_scores_gemma":[0.03598443,0.00034360337,0.0009919986,0.0007232739,0.0009404151,0.0030274764,0.0022601064,0.0017595792,0.00078617147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017114853,0.00075502385,0.117785744,0.0015554654,0.00054442364,0.0009519117,0.038158886,0.07284591,0.026539654,0.019375566,0.014236406,0.7055396],"study_design_scores_gemma":[0.00007330141,0.00021015001,0.025221802,0.00029456214,0.00015024187,0.00027024612,0.00634011,0.90622455,0.014152561,0.03514812,0.01176534,0.000149009],"about_ca_topic_score_codex":0.012704884,"about_ca_topic_score_gemma":0.023382772,"teacher_disagreement_score":0.012704884,"about_ca_system_score_codex":0.002172181,"about_ca_system_score_gemma":0.0020084355,"threshold_uncertainty_score":0.036517918},"labels":[],"label_agreement":null},{"id":"W4400940128","doi":"10.3758/s13428-024-02466-5","title":"Body–object interaction ratings for 3600 French nouns","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre for Interdisciplinary Research in Rehabilitation","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Noun; Object (grammar); Psychology; Computer science; Linguistics; Natural language processing; Cognitive psychology; Artificial intelligence","score_opus":0.2720334576754829,"score_gpt":0.6157969862804322,"score_spread":0.3437635286049493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400940128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838579,0.00036580345,0.0009682318,0.00003775512,0.000048545247,0.00007160845,0.0004768759,0.00007568301,0.014097488],"genre_scores_gemma":[0.98062664,0.00038251095,0.0024311105,0.00010334136,0.000034519348,0.00016109803,0.00084766693,0.00008728379,0.015325797],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99933237,0.00029416577,0.000042423762,0.000133458,0.00014640993,0.000051101968],"domain_scores_gemma":[0.9958236,0.002779675,0.0003761321,0.00015848875,0.00066684274,0.00019533996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009547167,0.0005065386,0.00034018734,0.0005844293,0.00029127783,0.0006195499,0.00014828813,0.0006022338,0.009160888],"category_scores_gemma":[0.0066842656,0.00011544192,0.00031857853,0.00026581332,0.00030232503,0.00050877786,0.00033236874,0.00026232435,0.0012153491],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01653536,0.0015180571,0.4054145,0.0013168434,0.00054678356,0.0013369187,0.038140085,0.0009507094,0.31325093,0.0028975056,0.0073504173,0.21074185],"study_design_scores_gemma":[0.00008175199,0.0016092289,0.985261,0.00003933693,0.00008333682,0.00038093113,0.0023259753,0.0006725534,0.004362117,0.00017648496,0.004963467,0.000043806576],"about_ca_topic_score_codex":0.0069977725,"about_ca_topic_score_gemma":0.008221683,"teacher_disagreement_score":0.009160888,"about_ca_system_score_codex":0.00046999415,"about_ca_system_score_gemma":0.00015149254,"threshold_uncertainty_score":0.030646205},"labels":[],"label_agreement":null},{"id":"W4401411007","doi":"10.3758/s13428-024-02482-5","title":"A tutorial: Analyzing eye and head movements in virtual reality","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Virtual reality; Human–computer interaction; Eye movement; Head (geology); Optical head-mounted display; Computer graphics (images); Artificial intelligence; Computer vision; Cognitive psychology; Psychology","score_opus":0.29592612692404874,"score_gpt":0.5960021332841007,"score_spread":0.30007600636005194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401411007","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022773915,0.21995834,0.73723835,0.0023897148,0.007508396,0.00023103833,0.0013071524,0.0070420527,0.022047661],"genre_scores_gemma":[0.013948992,0.21815409,0.5937662,0.0043476373,0.015135686,0.00079868233,0.00246515,0.003359738,0.1480238],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995554,0.00010824903,0.000039719158,0.00010648442,0.00015655928,0.000033593293],"domain_scores_gemma":[0.99781394,0.0014996089,0.000057464065,0.000080634905,0.00036116695,0.00018721787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010523996,0.002598151,0.0013475977,0.0033943001,0.00044762998,0.0018906873,0.0014381545,0.002001419,0.033668887],"category_scores_gemma":[0.0026051297,0.00072827976,0.0011699024,0.0021698817,0.0004853057,0.0025046233,0.0011758853,0.0019004985,0.02512985],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007051477,0.00022533524,0.0006744496,0.0017447282,0.00010722943,0.00025457697,0.00022466299,0.002055361,0.014658622,0.0036624756,0.21356629,0.76275575],"study_design_scores_gemma":[0.00003860815,0.00034137417,0.006703552,0.0015641907,0.00012279417,0.0035284716,0.00034008364,0.008428698,0.008478719,0.017099323,0.95317185,0.00018241433],"about_ca_topic_score_codex":0.0017227615,"about_ca_topic_score_gemma":0.0043426026,"teacher_disagreement_score":0.033668887,"about_ca_system_score_codex":0.00037110547,"about_ca_system_score_gemma":0.0005631021,"threshold_uncertainty_score":0.112633586},"labels":[],"label_agreement":null},{"id":"W4402581411","doi":"10.3758/s13428-024-02508-y","title":"A standardized framework to test event-based experiments","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Templeton World Charity Foundation","keywords":"Computer science; Protocol (science); Snapshot (computer storage); Replication (statistics); Robustness (evolution); Benchmark (surveying); Medical physics; Data science; Cognitive psychology; Psychology; Medicine","score_opus":0.42660021898052125,"score_gpt":0.6289628346652205,"score_spread":0.20236261568469927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402581411","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047651576,0.00090486073,0.9258787,0.0012228381,0.000606307,0.05047814,0.0030316915,0.00340045,0.009711785],"genre_scores_gemma":[0.020090643,0.00074659166,0.8034483,0.00090424047,0.00028502426,0.17007613,0.0023394346,0.00049259595,0.0016170178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.76112443,0.17586748,0.026132012,0.012857173,0.021334842,0.0026840575],"domain_scores_gemma":[0.64011645,0.19858769,0.030394383,0.082396716,0.043515854,0.0049889674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20862077,0.0046022246,0.0023065438,0.0069670114,0.0028663925,0.0076084286,0.0078033633,0.0050093457,0.013737939],"category_scores_gemma":[0.30717048,0.0030613977,0.004914886,0.0037617718,0.0068938313,0.0056526354,0.00829521,0.008214307,0.0071588056],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041550254,0.0035060002,0.012028748,0.013897041,0.0014076048,0.0013397577,0.009760753,0.028047718,0.023659015,0.526555,0.037131846,0.33851153],"study_design_scores_gemma":[0.0046085888,0.011636308,0.01726199,0.010352772,0.0012037136,0.0010988615,0.0024788945,0.044568323,0.031190747,0.43065405,0.44410664,0.0008390727],"about_ca_topic_score_codex":0.0027072292,"about_ca_topic_score_gemma":0.002342438,"teacher_disagreement_score":0.20862077,"about_ca_system_score_codex":0.00431736,"about_ca_system_score_gemma":0.0181631,"threshold_uncertainty_score":0.9759115},"labels":[],"label_agreement":null},{"id":"W4402666573","doi":"10.3758/s13428-024-02493-2","title":"Establishing the reliability of metrics extracted from long-form recordings using LENA and the ACLEW pipeline","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada; James S. McDonnell Foundation; Academy of Finland; Horizon 2020 Framework Programme; Directorate for Engineering; Grand Équipement National De Calcul Intensif; China Scholarship Council; Economic and Social Research Council; European Commission; National Institutes of Health; National Science Foundation; Agence Nationale de la Recherche","keywords":"Pipeline (software); Computer science; Variation (astronomy); Reliability (semiconductor); Intraclass correlation; Natural language processing; Language acquisition; Identity (music); Artificial intelligence; Psychology; Developmental psychology; Mathematics education; Psychometrics","score_opus":0.2585887042868682,"score_gpt":0.5697168966099126,"score_spread":0.31112819232304445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402666573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7238622,0.0013400167,0.24284144,0.00045842514,0.0004896415,0.00071169523,0.009268178,0.009734862,0.011293639],"genre_scores_gemma":[0.7895129,0.00034112058,0.17907491,0.00021814264,0.00013659117,0.0017404299,0.021453759,0.0028324018,0.004689896],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9886856,0.0028599694,0.0016500185,0.003704681,0.0025376147,0.0005620529],"domain_scores_gemma":[0.95722646,0.017144104,0.0031355352,0.005761019,0.015979987,0.0007528529],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014751071,0.0013004699,0.0008817465,0.0039917794,0.0009429245,0.002839735,0.0014725528,0.0011852736,0.0030443177],"category_scores_gemma":[0.061269283,0.00051917025,0.0008308751,0.0020318609,0.0014515595,0.0025939962,0.0034792507,0.0012890501,0.0033034065],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017850257,0.00035012705,0.29076308,0.001985793,0.0012419436,0.00076781196,0.014653097,0.008923571,0.10831061,0.0037241469,0.02262485,0.5448699],"study_design_scores_gemma":[0.00013051955,0.00072209263,0.78993237,0.00053105433,0.00042566468,0.0012173124,0.0066808644,0.08532684,0.056588076,0.0059058447,0.052048124,0.0004912101],"about_ca_topic_score_codex":0.0050544343,"about_ca_topic_score_gemma":0.011152598,"teacher_disagreement_score":0.9852489,"about_ca_system_score_codex":0.00063571846,"about_ca_system_score_gemma":0.001161213,"threshold_uncertainty_score":0.07801211},"labels":[],"label_agreement":null},{"id":"W4405230022","doi":"10.3758/s13428-024-02565-3","title":"DerLex: An eye-movement database of derived word reading in English","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Eye movement; Word (group theory); Computer science; Reading (process); Movement (music); Natural language processing; Artificial intelligence; Linguistics; Art","score_opus":0.25296962608578827,"score_gpt":0.5626719829348331,"score_spread":0.30970235684904485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405230022","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7747279,0.0008171857,0.00868572,0.00008132219,0.00006251515,0.0006156693,0.2002346,0.0046345824,0.010140444],"genre_scores_gemma":[0.575644,0.0006894337,0.01964704,0.00016910565,0.000085472406,0.0012608863,0.38966477,0.0007961678,0.012043039],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99969625,0.000047030568,0.000060685656,0.000110871755,0.00006044053,0.000024812527],"domain_scores_gemma":[0.99860865,0.0004688056,0.00016501901,0.00021503518,0.00041058174,0.00013197305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031009715,0.00064175425,0.00047801924,0.002500985,0.000250487,0.0005934176,0.00039874966,0.0005096569,0.0070777787],"category_scores_gemma":[0.0017704505,0.00017387274,0.00028065508,0.0011255099,0.00013557791,0.00078731286,0.00062039006,0.00021746852,0.0056937924],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006575818,0.0017143915,0.19372709,0.0036053066,0.0007445102,0.0036914004,0.0041697477,0.002213089,0.20308124,0.000898378,0.09302982,0.48654917],"study_design_scores_gemma":[0.0003834127,0.00078187324,0.8972763,0.00011320447,0.00034471738,0.0029672869,0.001530362,0.0066921315,0.034729145,0.00064042286,0.054398384,0.00014281577],"about_ca_topic_score_codex":0.0057278834,"about_ca_topic_score_gemma":0.012775409,"teacher_disagreement_score":0.0070777787,"about_ca_system_score_codex":0.00023055464,"about_ca_system_score_gemma":0.00037316736,"threshold_uncertainty_score":0.023677528},"labels":[],"label_agreement":null},{"id":"W4405273443","doi":"10.3758/s13428-024-02517-x","title":"The PSR corpus: A Persian sentence reading corpus of eye movements","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading (process); Sentence; Eye movement; Persian; Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","score_opus":0.19681685782045238,"score_gpt":0.5401224052394038,"score_spread":0.3433055474189514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405273443","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14767447,0.012748469,0.014218514,0.000875254,0.0008499648,0.0010981219,0.77740854,0.0070918435,0.038034834],"genre_scores_gemma":[0.1558441,0.002696849,0.028970597,0.00041968364,0.0003136178,0.0021390172,0.7974476,0.0011620327,0.011006522],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991615,0.00023096442,0.00015548317,0.00024903668,0.00015701544,0.00004611792],"domain_scores_gemma":[0.9974457,0.0010652993,0.00022973331,0.00043802636,0.00074141,0.0000799325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000833353,0.0011672215,0.0005581314,0.0038546054,0.0007317237,0.000943483,0.00087266596,0.001000533,0.0165498],"category_scores_gemma":[0.0046640444,0.00023894642,0.00037926703,0.0030940142,0.00048171193,0.0007979886,0.0010996273,0.00076521677,0.010317733],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009417737,0.00048538583,0.014111959,0.011434214,0.00023827406,0.0034313956,0.006481342,0.0016815467,0.04130825,0.0045876135,0.5157639,0.39953437],"study_design_scores_gemma":[0.00028480048,0.00021005199,0.16724686,0.00083967973,0.00015145689,0.0033775722,0.0026670273,0.0024093767,0.013369103,0.0025811412,0.8067271,0.00013578619],"about_ca_topic_score_codex":0.0067851613,"about_ca_topic_score_gemma":0.011199475,"teacher_disagreement_score":0.0165498,"about_ca_system_score_codex":0.00054173375,"about_ca_system_score_gemma":0.0009460845,"threshold_uncertainty_score":0.05536461},"labels":[],"label_agreement":null},{"id":"W4406027501","doi":"10.3758/s13428-024-02550-w","title":"Validation of the Emotionally Congruent and Incongruent Face–Body Static Set (ECIFBSS)","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation and Economic Development Trois Rivières; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada; Université du Québec à Trois-Rivières","keywords":"Sadness; Disgust; Psychology; Facial expression; Anger; Valence (chemistry); Surprise; Cognitive psychology; Happiness; Emotion perception; Perception; Arousal; Emotion classification; Stimulus (psychology); Social psychology; Communication","score_opus":0.3302486855200189,"score_gpt":0.5729854020264431,"score_spread":0.2427367165064242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406027501","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93636566,0.00013799837,0.046907246,0.00008120634,0.00022921414,0.0008419092,0.001890706,0.00029396225,0.013252022],"genre_scores_gemma":[0.9678151,0.00006602694,0.024378363,0.00019026654,0.000062787585,0.001775536,0.0032280795,0.00023874738,0.0022451556],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965335,0.0007440092,0.000293315,0.0009008498,0.0013160395,0.00021223459],"domain_scores_gemma":[0.98989254,0.0046527805,0.0007321433,0.0017496624,0.0024673268,0.0005055109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047016577,0.0007713322,0.00048985524,0.0009781483,0.0006902895,0.000739808,0.0010007222,0.0009015683,0.0069839424],"category_scores_gemma":[0.020469053,0.00032599355,0.00063021044,0.00039026796,0.0009477545,0.0005868076,0.0014451776,0.00061709154,0.0017956729],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021461569,0.0043336223,0.24035844,0.0008361851,0.0008563629,0.00039692794,0.0025346193,0.013081128,0.4155664,0.0076483935,0.0044978517,0.28842854],"study_design_scores_gemma":[0.0010297368,0.005445879,0.8672747,0.00016111249,0.0004993805,0.0015443547,0.0008121299,0.031919133,0.07600961,0.004047998,0.011048949,0.00020700454],"about_ca_topic_score_codex":0.0020119022,"about_ca_topic_score_gemma":0.0028082817,"teacher_disagreement_score":0.0069839424,"about_ca_system_score_codex":0.00047407797,"about_ca_system_score_gemma":0.00064585573,"threshold_uncertainty_score":0.024865031},"labels":[],"label_agreement":null},{"id":"W4406119379","doi":"10.3758/s13428-024-02582-2","title":"Expansion of the SyllabO+ corpus and database: Words, lemmas, and morphology","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre de Recherche Industrielle du Québec; Université de Montréal; Université Laval; McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Morpheme; Transparency (behavior); Computer science; Linguistics; Natural language processing; Agreement; Syllabic verse; Artificial intelligence; Speech recognition","score_opus":0.17109214308246842,"score_gpt":0.5626949910866405,"score_spread":0.391602848004172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406119379","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08145742,0.001507343,0.07869572,0.001533593,0.000981691,0.0013160176,0.7616015,0.019867485,0.053039264],"genre_scores_gemma":[0.09196803,0.00069782045,0.101240106,0.0004913612,0.00022364661,0.0024536825,0.7897617,0.005046368,0.008117255],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975285,0.00064601103,0.00059377885,0.0005401883,0.0005783288,0.00011332879],"domain_scores_gemma":[0.98954004,0.005001667,0.00032666884,0.0019057362,0.0026499967,0.00057589094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024128926,0.00095414603,0.0011707235,0.0064606518,0.001368207,0.0023547122,0.0019314297,0.0008495224,0.049848046],"category_scores_gemma":[0.010120853,0.00072797516,0.00066941493,0.004265864,0.00085338793,0.0024976186,0.004047153,0.0019769957,0.029321864],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020339782,0.0005491922,0.00916042,0.005184523,0.000121742385,0.0013945746,0.0028131823,0.0015809822,0.045345064,0.018950982,0.46877685,0.44408852],"study_design_scores_gemma":[0.0002966295,0.00012246953,0.022454923,0.00049169135,0.00012065294,0.0019047662,0.0010303203,0.006197021,0.018700987,0.0052160113,0.94332576,0.00013887149],"about_ca_topic_score_codex":0.008580064,"about_ca_topic_score_gemma":0.013910762,"teacher_disagreement_score":0.049848046,"about_ca_system_score_codex":0.00095400243,"about_ca_system_score_gemma":0.0036586088,"threshold_uncertainty_score":0.16675836},"labels":[],"label_agreement":null},{"id":"W4406652175","doi":"10.3758/s13428-024-02585-z","title":"Eyewitness Lineup Identity (ELI) database: Crime videos and mugshots for eyewitness identification research","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Economic and Social Research Council","keywords":"Eyewitness identification; Psychology; Witness; Culprit; Eyewitness memory; Identification (biology); Eyewitness testimony; Crime scene; Social psychology; Recall; Computer science; Cognitive psychology; Criminology; Database","score_opus":0.5907812189468639,"score_gpt":0.6792687532089515,"score_spread":0.08848753426208766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406652175","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12780878,0.0010905776,0.012740449,0.0004710659,0.00035850235,0.009073696,0.8119083,0.0060222642,0.030526375],"genre_scores_gemma":[0.086656,0.00069645816,0.030251034,0.00035392042,0.000181548,0.019431682,0.8480267,0.0011555301,0.013247162],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989894,0.00020857986,0.00017879719,0.00019335534,0.00033955008,0.00009035759],"domain_scores_gemma":[0.99116725,0.0024852923,0.0012989182,0.001834518,0.002399487,0.0008145125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021134042,0.00061708124,0.00067094015,0.003463509,0.00068137236,0.0008941069,0.0012291061,0.000772518,0.04220048],"category_scores_gemma":[0.011707826,0.00035628147,0.00033222715,0.0019552603,0.00028459064,0.0015550235,0.0017307872,0.0006916255,0.016506813],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024827742,0.0021058044,0.028750975,0.003762091,0.0001261404,0.00049531664,0.0018091832,0.00065182446,0.009590789,0.002654466,0.68564487,0.26192573],"study_design_scores_gemma":[0.0009575591,0.0010822364,0.32799688,0.0013252833,0.00017917808,0.0015349976,0.0022105176,0.0033705148,0.013303913,0.004169304,0.643634,0.000235564],"about_ca_topic_score_codex":0.00410093,"about_ca_topic_score_gemma":0.011559724,"teacher_disagreement_score":0.04220048,"about_ca_system_score_codex":0.00075279846,"about_ca_system_score_gemma":0.0009718141,"threshold_uncertainty_score":0.14117467},"labels":[],"label_agreement":null},{"id":"W4406853484","doi":"10.3758/s13428-024-02553-7","title":"EmoAtlas: An emotional network analyzer of texts that merges psychological lexicons, artificial intelligence, and network science","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Emotional intelligence; Natural language processing; Psychology; Social psychology","score_opus":0.30727787482703395,"score_gpt":0.593795430617827,"score_spread":0.2865175557907931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406853484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10535637,0.0006002088,0.7305434,0.0006651973,0.00025967733,0.0006452197,0.038100813,0.09850231,0.025326928],"genre_scores_gemma":[0.43831807,0.00070173497,0.4898959,0.00043447028,0.00022413959,0.0015990579,0.03925511,0.006681962,0.02288952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996352,0.00013158387,0.000037486956,0.00008497663,0.00009335269,0.000017317509],"domain_scores_gemma":[0.99787724,0.0014342432,0.00021572241,0.00013995952,0.0002620385,0.000070871036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055596296,0.0007910922,0.0002755958,0.0030061372,0.00040276887,0.0012560287,0.00048568376,0.00039276583,0.009389423],"category_scores_gemma":[0.0055879825,0.00023015073,0.00028425033,0.0014891735,0.00022242083,0.002119742,0.0008371996,0.0005976075,0.003891472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010792306,0.0005356174,0.016568918,0.002359377,0.00035776407,0.0007217569,0.0032691013,0.012066037,0.08012586,0.043857746,0.1376643,0.7013943],"study_design_scores_gemma":[0.00014486212,0.00026840088,0.031178333,0.00028896378,0.0003065161,0.0008462794,0.0017505833,0.58667076,0.052869115,0.08984209,0.23567791,0.00015623185],"about_ca_topic_score_codex":0.0010642603,"about_ca_topic_score_gemma":0.00270747,"teacher_disagreement_score":0.009389423,"about_ca_system_score_codex":0.00033158605,"about_ca_system_score_gemma":0.00037656358,"threshold_uncertainty_score":0.031410754},"labels":[],"label_agreement":null},{"id":"W4407688685","doi":"10.3758/s13428-025-02610-9","title":"Open-access network science: Investigating phonological similarity networks based on the SUBTLEX-US lexicon","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Lexicon; Python (programming language); Artificial intelligence; Natural language processing; Clustering coefficient; Adjacency list; Similarity (geometry); Cluster analysis","score_opus":0.4133289132249728,"score_gpt":0.6305229576386698,"score_spread":0.21719404441369705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407688685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7089417,0.0008014012,0.16465817,0.00070397987,0.00016029109,0.00037422494,0.08983741,0.010091853,0.024430923],"genre_scores_gemma":[0.7855477,0.00047803545,0.121525496,0.00015818514,0.00006993784,0.0009333818,0.08387603,0.0016943095,0.005716983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972695,0.00007696683,0.000016961923,0.00009748104,0.00005557974,0.000026163232],"domain_scores_gemma":[0.9974644,0.0016733082,0.00025672014,0.0003308193,0.00018120732,0.000093495015],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005268631,0.00036635096,0.00023340585,0.002103143,0.0006357524,0.0009573162,0.0006762668,0.00043745575,0.008014821],"category_scores_gemma":[0.0069705155,0.00026786383,0.00040852575,0.0020621547,0.0005447953,0.0019698555,0.0013298031,0.00069210754,0.0014414308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013235713,0.0007232107,0.15984327,0.004606803,0.0006405764,0.0019350154,0.014702022,0.077849746,0.054912128,0.22293937,0.17653963,0.28398466],"study_design_scores_gemma":[0.00021813462,0.00030114062,0.12888727,0.00035600283,0.00021109331,0.0013735167,0.0039949953,0.43557382,0.020109124,0.2104987,0.19830242,0.00017385304],"about_ca_topic_score_codex":0.005608143,"about_ca_topic_score_gemma":0.011473323,"teacher_disagreement_score":0.9993237,"about_ca_system_score_codex":0.0004648968,"about_ca_system_score_gemma":0.00045601043,"threshold_uncertainty_score":0.026812255},"labels":[],"label_agreement":null},{"id":"W4408300423","doi":"10.3758/s13428-025-02623-4","title":"The role of individual differences and attitude in willingness to participate in TMS studies","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Transcranial Magnetic Stimulation Studies","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Trent University; Nottingham Trent University","keywords":"Transcranial magnetic stimulation; Psychology; Context (archaeology); Perspective (graphical); Applied psychology; Social psychology","score_opus":0.5495828560905578,"score_gpt":0.6418443354744394,"score_spread":0.09226147938388163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408300423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99624926,0.0003257376,0.0005891914,0.00038975076,0.000020974687,0.000025905665,0.00002766262,0.0000037862944,0.0023676376],"genre_scores_gemma":[0.9993788,0.00007873832,0.00020188908,0.00008893515,0.000008859532,0.000014895035,0.000019358176,0.000001982332,0.00020654728],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943434,0.0033215957,0.00049462897,0.0003723533,0.001086367,0.0003816834],"domain_scores_gemma":[0.9602302,0.02916447,0.0050258604,0.0011062224,0.0020662225,0.002407043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009699102,0.00011548024,0.00023864521,0.00061120605,0.000522358,0.0012782144,0.00029357205,0.00059511,0.0023948776],"category_scores_gemma":[0.039915767,0.00012277722,0.0004008376,0.00045493955,0.0008456059,0.00069910096,0.0007195597,0.00081588316,0.00021642804],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037591287,0.00058572215,0.94604325,0.00019916611,0.00027742708,0.00032410954,0.01997732,0.00014389229,0.0012537806,0.0005698847,0.00035145172,0.029898092],"study_design_scores_gemma":[0.000013394859,0.00032775904,0.98343855,0.00010385277,0.00006226631,0.00042805783,0.013048249,0.00037130082,0.00029526977,0.000808011,0.0010721509,0.000031141422],"about_ca_topic_score_codex":0.00093163236,"about_ca_topic_score_gemma":0.0015074314,"teacher_disagreement_score":0.009699102,"about_ca_system_score_codex":0.00025005272,"about_ca_system_score_gemma":0.00048653033,"threshold_uncertainty_score":0.051294386},"labels":[],"label_agreement":null},{"id":"W4408426509","doi":"10.3758/s13428-025-02636-z","title":"Unraveling other-race face perception with GAN-based image reconstruction","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Race (biology); Similarity (geometry); Artificial intelligence; Face (sociological concept); Pairwise comparison; Computer science; Perception; Face perception; Basis (linear algebra); Pattern recognition (psychology); Cognitive psychology; Computer vision; Psychology; Image (mathematics); Mathematics; Geology; Geometry","score_opus":0.14810278882505917,"score_gpt":0.52501069815385,"score_spread":0.37690790932879087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408426509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045645103,0.0003671104,0.9495021,0.00028884268,0.00011688478,0.000033443113,0.00017127044,0.000602672,0.0032726137],"genre_scores_gemma":[0.69769967,0.0006807186,0.29527026,0.0003621463,0.00011404245,0.000049869945,0.00053891144,0.00022535551,0.0050590546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998286,0.00003851977,0.000003846645,0.000046100897,0.00004824647,0.00003472916],"domain_scores_gemma":[0.999816,0.000053592892,0.000016517213,0.000043734988,0.00005293377,0.00001721789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036347157,0.00051257026,0.00054206094,0.00039921043,0.00014124802,0.00052745827,0.00062107696,0.0005059313,0.0016962426],"category_scores_gemma":[0.0008518777,0.0002705181,0.0005461323,0.00032089886,0.0003580096,0.0006478445,0.0005279771,0.0010489018,0.0005506591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041778715,0.00026691804,0.005116851,0.00023709772,0.00020776578,0.00020410975,0.0002189239,0.23983191,0.17384186,0.017681431,0.008887918,0.5530874],"study_design_scores_gemma":[0.000003489565,0.000023274806,0.0013265621,0.000008018237,0.000010177935,0.000079576035,0.000018536819,0.98736095,0.0070307297,0.0032374018,0.00089252135,0.000008734522],"about_ca_topic_score_codex":0.0025900726,"about_ca_topic_score_gemma":0.0041119303,"teacher_disagreement_score":0.0025900726,"about_ca_system_score_codex":0.00020741427,"about_ca_system_score_gemma":0.00042323914,"threshold_uncertainty_score":0.005674422},"labels":[],"label_agreement":null},{"id":"W4409147508","doi":"10.3758/s13428-025-02628-z","title":"SingleMALD: Investigating practice effects in auditory lexical decision","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Lexical decision task; Stimulus (psychology); Psychology; Computer science; Lexical access; Task (project management); Cognitive psychology; Audiology; Cognition; Medicine","score_opus":0.2294778276926878,"score_gpt":0.6508911712031178,"score_spread":0.42141334351043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409147508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902062,0.0001064422,0.007558572,0.000042432064,0.000040153725,0.00038350758,0.00040274995,0.00012032884,0.0011396739],"genre_scores_gemma":[0.9627176,0.00007657553,0.029361084,0.00024814665,0.000071408795,0.0027475778,0.0008713246,0.00019455903,0.0037117375],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996093,0.0011655077,0.00039830184,0.0012508514,0.00089256273,0.00019984411],"domain_scores_gemma":[0.979761,0.012692846,0.0023798768,0.0029939823,0.0010365834,0.0011357721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033236248,0.00083102396,0.001157079,0.00048459662,0.00045152212,0.001143723,0.0012054524,0.00091071666,0.0043948353],"category_scores_gemma":[0.017638374,0.0007405921,0.00040034918,0.00029598307,0.001001994,0.0012525957,0.0022034056,0.0011961112,0.0009797207],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031090591,0.031961694,0.058893394,0.0022305413,0.00063398964,0.0011949518,0.0099910125,0.003250537,0.64479154,0.002228161,0.0027126328,0.21102093],"study_design_scores_gemma":[0.009139832,0.11611119,0.62115014,0.00022245891,0.0008420433,0.0036147563,0.0030282107,0.025844947,0.18338907,0.01117715,0.024822317,0.00065783795],"about_ca_topic_score_codex":0.0010943334,"about_ca_topic_score_gemma":0.0015429725,"teacher_disagreement_score":0.0043948353,"about_ca_system_score_codex":0.00043043643,"about_ca_system_score_gemma":0.00056396634,"threshold_uncertainty_score":0.01757723},"labels":[],"label_agreement":null},{"id":"W4409148165","doi":"10.3758/s13428-025-02656-9","title":"VOC-ADO: A lexical database for French-speaking adolescents","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation","funders":"Agence Nationale de la Recherche","keywords":"Vocabulary; Computer science; Lemma (botany); Psychology; Linguistics; Lexical database; Mathematics education; Natural language processing","score_opus":0.3489859521934305,"score_gpt":0.6063080813811523,"score_spread":0.25732212918772185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409148165","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09861523,0.0027445403,0.051525313,0.0003241394,0.0002440287,0.0012151548,0.8002009,0.020529646,0.024601156],"genre_scores_gemma":[0.15487191,0.0013390516,0.08095579,0.00020944532,0.000101471116,0.0024119716,0.748798,0.0032509193,0.008061498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991584,0.00019919737,0.00020857358,0.00022636344,0.00014353012,0.000063921245],"domain_scores_gemma":[0.99662447,0.0015238052,0.00025906958,0.00034264452,0.0010193088,0.00023062945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009935801,0.0011011038,0.0011283477,0.007239059,0.00073506095,0.0019875604,0.000883523,0.00085115066,0.028471649],"category_scores_gemma":[0.006494912,0.0003789891,0.00052915554,0.0036370752,0.00025212325,0.0019526762,0.0013594953,0.00045729,0.0132240355],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026960329,0.0005379518,0.032071363,0.006813822,0.00035556377,0.0020073832,0.004333157,0.0017257886,0.034351606,0.009163401,0.34253877,0.56340516],"study_design_scores_gemma":[0.0005558665,0.00038327693,0.062938504,0.0010699388,0.00050684554,0.0022117232,0.003432196,0.008895769,0.012633492,0.006065245,0.9010292,0.00027793803],"about_ca_topic_score_codex":0.01222934,"about_ca_topic_score_gemma":0.012155957,"teacher_disagreement_score":0.028471649,"about_ca_system_score_codex":0.00068295735,"about_ca_system_score_gemma":0.002048468,"threshold_uncertainty_score":0.09524715},"labels":[],"label_agreement":null},{"id":"W4409665275","doi":"10.3758/s13428-025-02658-7","title":"Assessing multiple abilities through process data in computer-based assessments: The multidimensional sequential response model (MSRM)","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Beijing Municipal Social Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Data mining; Machine learning; Artificial intelligence; Programming language","score_opus":0.920767338243147,"score_gpt":0.759212213405075,"score_spread":0.161555124838072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409665275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2317968,0.0005170178,0.75904465,0.0004500307,0.00010464928,0.0028111835,0.0006002063,0.0006915125,0.0039838525],"genre_scores_gemma":[0.6097556,0.0005336435,0.38515055,0.00017758094,0.000031149644,0.0032817952,0.00048183306,0.000075705226,0.0005121925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96350986,0.026187856,0.0019572703,0.0022063022,0.0057825856,0.00035600818],"domain_scores_gemma":[0.89158845,0.08743748,0.008363213,0.0053718835,0.0065983078,0.000640676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033458915,0.0015043282,0.0015413403,0.002661581,0.0005281591,0.0029903087,0.0012925719,0.0012782544,0.0016438751],"category_scores_gemma":[0.12685575,0.0006139149,0.00178405,0.002482528,0.0013327231,0.0036366207,0.0022606214,0.0019112381,0.0005002493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014345534,0.0026564642,0.23997357,0.002260122,0.0015930807,0.00015111743,0.0051926174,0.08537169,0.00465025,0.030000452,0.001944764,0.6247713],"study_design_scores_gemma":[0.0006730272,0.0069132214,0.19830284,0.0017233866,0.0010091191,0.0005620565,0.003039718,0.6354008,0.009005115,0.13648903,0.0062798425,0.00060185295],"about_ca_topic_score_codex":0.0032697283,"about_ca_topic_score_gemma":0.0033862928,"teacher_disagreement_score":0.033458915,"about_ca_system_score_codex":0.0013070015,"about_ca_system_score_gemma":0.0033446215,"threshold_uncertainty_score":0.1769498},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4409720720","doi":"10.3758/s13428-025-02675-6","title":"English verbs semantic norms database: Concreteness, embodiment, imageability, valence and arousal ratings for 3,500 verbs","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Calgary","funders":"","keywords":"Concreteness; Valence (chemistry); Arousal; Psychology; Natural language processing; Computer science; Cognitive psychology; Emotional valence; Artificial intelligence; Cognition; Social psychology","score_opus":0.14195791261475013,"score_gpt":0.5414649967519795,"score_spread":0.39950708413722935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409720720","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62335193,0.00093482045,0.011830295,0.00025887246,0.00013132881,0.0017468526,0.3352363,0.0028628104,0.023646802],"genre_scores_gemma":[0.44581628,0.00038247762,0.015655067,0.00017931333,0.00010757717,0.005485766,0.5231965,0.0008468155,0.00833005],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986105,0.0002464763,0.0004505399,0.00023434657,0.00039870804,0.000059394435],"domain_scores_gemma":[0.9906658,0.0042749825,0.0013894244,0.0011121279,0.0021077709,0.00044994213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017120512,0.00076577923,0.00078850484,0.0026223713,0.00035952803,0.0013060762,0.0008634322,0.0009854612,0.014329626],"category_scores_gemma":[0.012704877,0.00028320996,0.0006032231,0.0017970701,0.00036974996,0.0016605494,0.0010477268,0.00044679208,0.008071847],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011278045,0.003421457,0.30012134,0.0061545004,0.0008271891,0.00090074417,0.0049381144,0.002184893,0.040415894,0.006491258,0.21700847,0.40625814],"study_design_scores_gemma":[0.0009406922,0.0008951349,0.880217,0.00029338044,0.00027922323,0.0014679217,0.0018173433,0.0043812282,0.0068096034,0.004542182,0.09817865,0.00017753504],"about_ca_topic_score_codex":0.002724555,"about_ca_topic_score_gemma":0.004585139,"teacher_disagreement_score":0.014329626,"about_ca_system_score_codex":0.00045227061,"about_ca_system_score_gemma":0.00052046316,"threshold_uncertainty_score":0.047937334},"labels":[],"label_agreement":null},{"id":"W4410091307","doi":"10.3758/s13428-025-02652-z","title":"The Second Database of Emotional Videos from Ottawa (DEVO-2): Over 1300 brief video clips rated on valence, arousal, impact, and familiarity","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Media Influence and Health","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Privy Council Office; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CLIPS; Valence (chemistry); Arousal; Emotional valence; Computer science; Psychology; Cognitive psychology; Multimedia; Artificial intelligence; Cognition; Social psychology","score_opus":0.227521155550353,"score_gpt":0.5381123989237419,"score_spread":0.31059124337338884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410091307","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11227266,0.0017753546,0.0005573545,0.0001302244,0.00012657836,0.00064849877,0.8721627,0.00039387267,0.011932753],"genre_scores_gemma":[0.07110994,0.0012200112,0.0027031738,0.00013886514,0.000076858916,0.0010542268,0.9071167,0.00015986495,0.016420301],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9994081,0.000045641125,0.0000670186,0.00012278667,0.00020093248,0.00015544474],"domain_scores_gemma":[0.99665076,0.00035457558,0.0003088435,0.00034801918,0.001659243,0.0006786174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038639182,0.0013376902,0.0006923005,0.005685629,0.001279628,0.0014751724,0.0012627719,0.0009772866,0.013838904],"category_scores_gemma":[0.0026722488,0.0003844346,0.00057255017,0.004819346,0.0005282487,0.00057741057,0.0014963576,0.0005737238,0.007161713],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005795217,0.001123663,0.12856823,0.008579294,0.0008013848,0.0019127765,0.0039460966,0.0015085696,0.025789177,0.0011707107,0.6251793,0.19562557],"study_design_scores_gemma":[0.00020161211,0.00022333844,0.7083802,0.00073780026,0.00041379165,0.0007163439,0.0029742864,0.00070688355,0.0049748,0.00022297748,0.28020498,0.00024300678],"about_ca_topic_score_codex":0.5362453,"about_ca_topic_score_gemma":0.80102783,"teacher_disagreement_score":0.5362453,"about_ca_system_score_codex":0.0028611775,"about_ca_system_score_gemma":0.0042795087,"threshold_uncertainty_score":0.9329717},"labels":[],"label_agreement":null},{"id":"W4410106284","doi":"10.3758/s13428-025-02690-7","title":"Assessing autobiographical memory consistency: Machine and human approaches","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Autobiographical memory; Consistency (knowledge bases); Computer science; Human memory; Cognitive psychology; Psychology; Artificial intelligence; Natural language processing; Recall; Cognition; Neuroscience","score_opus":0.48539084858012965,"score_gpt":0.629412572268767,"score_spread":0.14402172368863736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410106284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.901934,0.001327501,0.08169499,0.0002764778,0.00008332317,0.00053835136,0.0003170878,0.00022307225,0.013605074],"genre_scores_gemma":[0.9772627,0.0003954491,0.02112879,0.00009049317,0.000043641947,0.00024978508,0.000101965976,0.000019369043,0.0007077221],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99725145,0.0016277483,0.00017104039,0.00032087727,0.00057138054,0.000057451998],"domain_scores_gemma":[0.9821353,0.011102557,0.0033508232,0.001999157,0.001141934,0.0002703257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051777693,0.00032695464,0.00038742478,0.0021004274,0.00028941297,0.0015524337,0.000599094,0.0005957158,0.0022181852],"category_scores_gemma":[0.022909382,0.00021177366,0.00026955135,0.00087925966,0.0008290396,0.001541545,0.0007536404,0.0005371683,0.0002298584],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013215448,0.0013586741,0.4966844,0.0005552758,0.00056863436,0.00008900055,0.0031348036,0.0023311172,0.014683113,0.0077065215,0.0009049073,0.4706621],"study_design_scores_gemma":[0.00014653773,0.002441723,0.9451495,0.00024122324,0.00025774055,0.000725136,0.0026903867,0.021625865,0.009944128,0.012665999,0.0040043276,0.000107477],"about_ca_topic_score_codex":0.00071759743,"about_ca_topic_score_gemma":0.0013499703,"teacher_disagreement_score":0.0051777693,"about_ca_system_score_codex":0.00033669433,"about_ca_system_score_gemma":0.0005357629,"threshold_uncertainty_score":0.02738297},"labels":[],"label_agreement":null},{"id":"W4410345373","doi":"10.3758/s13428-025-02688-1","title":"An equivalent illuminant analysis of lightness constancy with physical objects and in virtual reality","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Standard illuminant; Lightness; Subjective constancy; Color constancy; Virtual reality; Computer science; Computer graphics (images); Artificial intelligence; Computer vision; Perception; Psychology","score_opus":0.13359576943822876,"score_gpt":0.5824340243178263,"score_spread":0.44883825487959755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410345373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19023551,0.00024442672,0.7951837,0.00009629194,0.000037990627,0.000048052276,0.00016641515,0.00022793138,0.013759551],"genre_scores_gemma":[0.94929785,0.00014798625,0.047127996,0.000049354752,0.000021343792,0.00003435224,0.00008886448,0.00013099445,0.003101143],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99958056,0.00011504715,0.000012347402,0.00012820624,0.00011934056,0.00004444113],"domain_scores_gemma":[0.99936277,0.00029532553,0.00005082314,0.000109617504,0.00014500356,0.000036498503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000461969,0.00036786194,0.00025265096,0.0008670436,0.00025835793,0.0009725296,0.00080895924,0.00029480222,0.0045665815],"category_scores_gemma":[0.0022313613,0.00021235863,0.0005395413,0.0005374749,0.0006840416,0.0011086151,0.0007243245,0.00044307782,0.00028738077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011712384,0.00049141457,0.008800056,0.00034127213,0.00019464693,0.00041815927,0.001007604,0.13581634,0.26007345,0.28108415,0.0018702552,0.3087314],"study_design_scores_gemma":[0.000025445033,0.00017193188,0.022725303,0.000020031208,0.00009803364,0.00031188948,0.00019518028,0.90472066,0.024345603,0.04458668,0.0027404728,0.000058742404],"about_ca_topic_score_codex":0.0030832537,"about_ca_topic_score_gemma":0.0017731418,"teacher_disagreement_score":0.0045665815,"about_ca_system_score_codex":0.00041430665,"about_ca_system_score_gemma":0.00031876078,"threshold_uncertainty_score":0.01527673},"labels":[],"label_agreement":null},{"id":"W4410850616","doi":"10.3758/s13428-025-02663-w","title":"Cognition ratings for 8826 english words","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cognition; Cognitive psychology; Psychology; Natural language processing; Computer science","score_opus":0.3474396990473601,"score_gpt":0.6201960024926879,"score_spread":0.2727563034453278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410850616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889264,0.00008650594,0.00022724953,0.000026229112,0.000033456137,0.00008286738,0.00079588883,0.00003094367,0.0097903],"genre_scores_gemma":[0.97243565,0.00017563533,0.0012294994,0.00014536551,0.000042700434,0.00017183922,0.0016205697,0.000058348433,0.024120394],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991755,0.00014220091,0.00009976319,0.00015864808,0.00035292818,0.000070842136],"domain_scores_gemma":[0.9940019,0.0024804547,0.0009811203,0.0005414046,0.0015521573,0.00044289517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010604626,0.000621063,0.00049075653,0.00073537906,0.00037965502,0.0008119212,0.00024214186,0.00057178555,0.012781195],"category_scores_gemma":[0.009743775,0.00015694463,0.00051133416,0.00032245863,0.00030369987,0.000617848,0.00050237717,0.00048907864,0.0029847382],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020215262,0.0070316126,0.6536501,0.00077481335,0.00067388767,0.0012517901,0.010718156,0.0013846159,0.10729085,0.0016380007,0.010563601,0.1848073],"study_design_scores_gemma":[0.0001927231,0.0046316427,0.981293,0.00003324624,0.00013139943,0.00033085802,0.0012564615,0.00070161413,0.0061575575,0.00035952113,0.0048484374,0.000063479674],"about_ca_topic_score_codex":0.0043948623,"about_ca_topic_score_gemma":0.006950539,"teacher_disagreement_score":0.012781195,"about_ca_system_score_codex":0.00042809907,"about_ca_system_score_gemma":0.00021499328,"threshold_uncertainty_score":0.042757392},"labels":[],"label_agreement":null},{"id":"W4411363785","doi":"10.3758/s13428-025-02727-x","title":"Digital questionnaire response time (DQRT): A ubiquitous and low-cost digital assay of cognitive processing speed","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"H2020 European Research Council; Irish Research Council; Science Foundation Ireland; Irish Research eLibrary; Horizon 2020 Framework Programme; Global Brain Health Institute","keywords":"Cognition; Bootstrapping (finance); Measure (data warehouse); Task (project management); Computer science; Reliability (semiconductor); Elementary cognitive task; Range (aeronautics); Psychology; Applied psychology; Data mining; Psychiatry; Mathematics","score_opus":0.2004382962207022,"score_gpt":0.6228393463628408,"score_spread":0.4224010501421386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411363785","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79180694,0.0014744736,0.12355919,0.0010546225,0.00067155657,0.0052453307,0.04213535,0.0019190401,0.032133393],"genre_scores_gemma":[0.80804485,0.0013488156,0.13788003,0.0019040534,0.0005824967,0.014342776,0.024328452,0.00037754787,0.011191032],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99020946,0.004469344,0.0015522736,0.0011695775,0.0022978494,0.00030155285],"domain_scores_gemma":[0.9331989,0.031625394,0.015011656,0.0076486142,0.011052098,0.0014634287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0091575775,0.0008218482,0.0006468032,0.0030768656,0.00042335532,0.0010346835,0.00088136137,0.000872965,0.00868916],"category_scores_gemma":[0.048312943,0.00033917144,0.0010089956,0.0034435077,0.00045122567,0.0013622903,0.0015505597,0.0010939633,0.003142981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013548133,0.0010875444,0.6039976,0.0019000495,0.000699482,0.00018041786,0.0031834685,0.0015965999,0.0094304215,0.0042138286,0.034907855,0.33744788],"study_design_scores_gemma":[0.000183722,0.0017250947,0.94016796,0.00030071082,0.00017339099,0.00061607314,0.0012381537,0.0046720877,0.005737711,0.003478822,0.041525185,0.0001810951],"about_ca_topic_score_codex":0.0014182134,"about_ca_topic_score_gemma":0.0022416252,"teacher_disagreement_score":0.0091575775,"about_ca_system_score_codex":0.00044550415,"about_ca_system_score_gemma":0.00059852586,"threshold_uncertainty_score":0.048430502},"labels":[],"label_agreement":null},{"id":"W4412406583","doi":"10.3758/s13428-025-02743-x","title":"Collecting behavioural data across countries during pandemics: Development of the COVID-19 Risk Assessment Tool","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Blueprint; Pandemic; Government (linguistics); Coronavirus disease 2019 (COVID-19); Public health; Psychological intervention; Risk assessment; Work (physics); Psychology; Business; Public relations; Computer science; Engineering; Medicine; Computer security; Political science; Nursing; Infectious disease (medical specialty)","score_opus":0.6468616321629242,"score_gpt":0.7186630093676086,"score_spread":0.07180137720468438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412406583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3229614,0.0028447087,0.43974167,0.020762071,0.0020760633,0.058390997,0.07086308,0.018623997,0.06373597],"genre_scores_gemma":[0.17227118,0.0013704449,0.776687,0.0016325617,0.00016733246,0.026491685,0.017532922,0.00049564644,0.0033512563],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9703273,0.01676447,0.005902301,0.001818288,0.004323195,0.0008643204],"domain_scores_gemma":[0.904641,0.060632292,0.008623717,0.0064175287,0.016091777,0.0035936113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044990856,0.0012224131,0.0012406766,0.008580616,0.0010795102,0.0035047242,0.0023719706,0.0010525159,0.006336117],"category_scores_gemma":[0.10786145,0.0009176571,0.0020651715,0.0042070914,0.0005602751,0.0049565597,0.0067831115,0.0018796971,0.0026020627],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040821737,0.0012115305,0.16754942,0.004132261,0.00051019166,0.00031920846,0.013389872,0.0027262403,0.0013413773,0.0038012485,0.054725762,0.74988467],"study_design_scores_gemma":[0.00097167643,0.0031649303,0.4624399,0.015905697,0.001092506,0.0015516436,0.035845373,0.036527436,0.009792582,0.0307167,0.40056393,0.0014276183],"about_ca_topic_score_codex":0.0036608793,"about_ca_topic_score_gemma":0.0054303138,"teacher_disagreement_score":0.044990856,"about_ca_system_score_codex":0.0020340532,"about_ca_system_score_gemma":0.0058383388,"threshold_uncertainty_score":0.23793721},"labels":[],"label_agreement":null},{"id":"W4412784629","doi":"10.3758/s13428-025-02762-8","title":"Reward as a facet of word meaning: Ratings of motivation for 8,601 English words","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Concreteness; Cognitive psychology; Valence (chemistry); Pleasure; Semantic memory; Cognition","score_opus":0.22898201203849286,"score_gpt":0.5678840200943505,"score_spread":0.3389020080558576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412784629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99954957,0.000018396915,0.00013689806,0.0000050125727,0.0000016729678,0.000009331411,0.000053522228,0.000003542622,0.0002219586],"genre_scores_gemma":[0.9988722,0.000024000927,0.0005859747,0.000011040599,0.0000042451834,0.000026088712,0.00012622231,0.000005326278,0.00034483458],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99922144,0.00026235217,0.00009665536,0.00013783626,0.00023313556,0.00004866793],"domain_scores_gemma":[0.9933217,0.0034891285,0.0018143255,0.0003223482,0.0006489667,0.00040340054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015841865,0.00031849806,0.0002832853,0.00055091846,0.00020878534,0.0007859359,0.00015436117,0.000480725,0.0011900505],"category_scores_gemma":[0.010400567,0.00014132899,0.00026927085,0.00031928028,0.00036960724,0.0005803079,0.00051380316,0.00043200818,0.000240203],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031539092,0.00077633787,0.83862656,0.0002887777,0.00029760966,0.00037094782,0.009049015,0.0006656179,0.11065313,0.0003030166,0.0004014178,0.035413735],"study_design_scores_gemma":[0.000015244973,0.00070828677,0.99419034,0.000006408169,0.000022006465,0.00017190816,0.0008832788,0.0005974472,0.0030076865,0.0000856717,0.0002877015,0.000024014516],"about_ca_topic_score_codex":0.00048600562,"about_ca_topic_score_gemma":0.001060271,"teacher_disagreement_score":0.0015841865,"about_ca_system_score_codex":0.00015968719,"about_ca_system_score_gemma":0.00007120093,"threshold_uncertainty_score":0.0083780885},"labels":[],"label_agreement":null},{"id":"W4413115497","doi":"10.3758/s13428-025-02768-2","title":"Single point estimation of a decision space","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Computer science; Point estimation; Decision theory; Sensitivity (control systems); Optimal decision; Fisher information; Expected utility hypothesis; A priori and a posteriori; Detection theory; False alarm; Mathematics; Artificial intelligence; Machine learning; Statistics; Decision tree","score_opus":0.2685580400148034,"score_gpt":0.5746600187935892,"score_spread":0.3061019787787858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413115497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014767706,0.00031987956,0.9835698,0.0003896836,0.000032828095,0.00007735773,0.00014076802,0.00008068724,0.0006212081],"genre_scores_gemma":[0.5156464,0.0013525726,0.47589475,0.0002546143,0.00019825938,0.0008024082,0.0007181315,0.0000698409,0.0050629866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98811674,0.008452007,0.00034123834,0.0020540187,0.00075595424,0.00028005405],"domain_scores_gemma":[0.9244565,0.0699668,0.0017717512,0.0023116567,0.0010352685,0.00045800887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016635168,0.0012561537,0.0035471134,0.0034680003,0.0007441573,0.002975982,0.003093516,0.002965804,0.006855702],"category_scores_gemma":[0.06511062,0.0016425749,0.002435568,0.0028657112,0.0026350468,0.0051599047,0.0024212087,0.0036149998,0.0009915215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072605,0.0005194757,0.009526347,0.0005450911,0.000909127,0.00019260088,0.00054848887,0.54991966,0.00074581895,0.29966292,0.0025298218,0.13417462],"study_design_scores_gemma":[0.000054224194,0.00008391153,0.0012275389,0.00006416956,0.00006426742,0.000053263302,0.000055770244,0.7222957,0.0001981975,0.27532133,0.00054917735,0.000032452626],"about_ca_topic_score_codex":0.004942814,"about_ca_topic_score_gemma":0.0042178286,"teacher_disagreement_score":0.016635168,"about_ca_system_score_codex":0.0015151153,"about_ca_system_score_gemma":0.0017927932,"threshold_uncertainty_score":0.08797622},"labels":[],"label_agreement":null},{"id":"W4414698255","doi":"10.3758/s13428-025-02826-9","title":"A year of nouns from English-learning infants’ daily lives: The SEEDLingS-Nouns dataset","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institutes of Health","keywords":"Comprehension; Metadata; Noun; Word (group theory); Reuse","score_opus":0.12907756743695148,"score_gpt":0.5538640880432741,"score_spread":0.42478652060632266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414698255","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4445944,0.0022978983,0.0034292454,0.0007143877,0.00057793426,0.00024121543,0.5395221,0.001456056,0.0071667163],"genre_scores_gemma":[0.10218585,0.0005736927,0.0050091385,0.00022244237,0.00011928872,0.00033290393,0.8876004,0.00020035141,0.003755844],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99943775,0.00009831744,0.000068812355,0.00017750045,0.00012867566,0.00008891844],"domain_scores_gemma":[0.9980375,0.00041205002,0.00017184205,0.0004949276,0.00048649128,0.00039725978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074762566,0.00093490153,0.0007647095,0.0010968184,0.00067028595,0.0007219586,0.0009386887,0.0013838493,0.00276441],"category_scores_gemma":[0.0028057257,0.0002477995,0.0010759337,0.0011863557,0.00044969528,0.0009375406,0.0013502731,0.0008475383,0.005376152],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002710859,0.001529026,0.23083505,0.0015856139,0.00075489195,0.0032667862,0.002874536,0.0018220653,0.013320439,0.0010760858,0.6170915,0.12313314],"study_design_scores_gemma":[0.00039171253,0.0005129408,0.62260455,0.00043781052,0.00027301422,0.00323538,0.0054909317,0.0043515144,0.004082513,0.0016612312,0.3567496,0.00020876495],"about_ca_topic_score_codex":0.018434621,"about_ca_topic_score_gemma":0.06507302,"teacher_disagreement_score":0.018434621,"about_ca_system_score_codex":0.00044761124,"about_ca_system_score_gemma":0.0008813479,"threshold_uncertainty_score":0.03665465},"labels":[],"label_agreement":null},{"id":"W4414798325","doi":"10.3758/s13428-025-02812-1","title":"A systematic review of latent class analysis in psychology: Examining the gap between guidelines and research practice","year":2025,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Università Cattolica del Sacro Cuore","keywords":"Latent class model; Categorical variable; Class (philosophy); Flexibility (engineering); Systematic review; Quality (philosophy); Population; Inclusion (mineral)","score_opus":0.9062522744482858,"score_gpt":0.804378768394313,"score_spread":0.10187350605397283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414798325","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011195423,0.98119557,0.0050745397,0.0059404066,0.001035716,0.0031800205,0.0012146209,0.00007504927,0.0011645879],"genre_scores_gemma":[0.021576533,0.93384105,0.02543323,0.0052711694,0.0004053711,0.011809241,0.0012502996,0.00007726368,0.0003359524],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.79126614,0.098202534,0.07657637,0.0068606352,0.02559273,0.0015016578],"domain_scores_gemma":[0.44837195,0.44654018,0.044109188,0.012467915,0.046383943,0.002126743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17104919,0.002172243,0.0090129385,0.045849737,0.002943918,0.010199403,0.0053546545,0.0052113873,0.005179273],"category_scores_gemma":[0.50869864,0.0025507824,0.009429237,0.040169347,0.004964586,0.011488887,0.007445979,0.0043135285,0.0010252753],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100549725,0.000017843564,0.00091766036,0.9002878,0.0026124865,0.00012229486,0.0016759479,0.0001700429,0.00014847396,0.0034264345,0.00637397,0.08414658],"study_design_scores_gemma":[0.00005388386,0.000029294079,0.0007680379,0.97550243,0.0043302663,0.00008950841,0.0004243248,0.000083296014,0.000072717856,0.0013788665,0.01724175,0.000025604608],"about_ca_topic_score_codex":0.014982835,"about_ca_topic_score_gemma":0.047650527,"teacher_disagreement_score":0.8289508,"about_ca_system_score_codex":0.01691922,"about_ca_system_score_gemma":0.07969457,"threshold_uncertainty_score":0.9046054},"labels":[],"label_agreement":null},{"id":"W4414872730","doi":"10.3758/s13428-025-02802-3","title":"Can you beat the music? Validation of a gamified rhythmic training in children with ADHD","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Children's Physical and Motor Development","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université de Montréal; Bell (Canada); International Laboratory for Brain, Music and Sound Research; Centre for Research on Brain Language and Music","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Rhythm; Beat (acoustics); Perception; Sensorimotor rhythm; Cognition; Affect (linguistics); Synchronization (alternating current); Metronome; Control (management)","score_opus":0.21568506785745156,"score_gpt":0.5133693839716763,"score_spread":0.29768431611422475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414872730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9975394,0.000060784074,0.00034978602,0.00008574218,0.000035016386,0.0008011818,0.000112039066,0.000014445719,0.0010016431],"genre_scores_gemma":[0.9877374,0.00029301658,0.005112291,0.00013737497,0.000021421947,0.0039993804,0.0005579271,0.00002816748,0.0021129993],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99681216,0.001282315,0.00031124052,0.00050993636,0.00082228443,0.00026212353],"domain_scores_gemma":[0.9946589,0.0025677306,0.0005899447,0.0006522711,0.0010191974,0.00051192025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074510905,0.0009676085,0.0015017077,0.00066118845,0.0013348236,0.00120668,0.001769394,0.0012704688,0.0021116724],"category_scores_gemma":[0.015557962,0.00053166365,0.0013437151,0.00033581868,0.0014046088,0.0010525675,0.001444718,0.0015810783,0.00057946227],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.051954705,0.13475132,0.43695465,0.0024386086,0.0014896035,0.0017574835,0.0329367,0.0058768475,0.02094622,0.0020848075,0.0033826404,0.30542642],"study_design_scores_gemma":[0.009638755,0.091141574,0.8548501,0.0011396814,0.0013638933,0.0010378239,0.011453571,0.0073874923,0.010841584,0.001209484,0.00967959,0.0002564727],"about_ca_topic_score_codex":0.013482215,"about_ca_topic_score_gemma":0.019676404,"teacher_disagreement_score":0.013482215,"about_ca_system_score_codex":0.0013726667,"about_ca_system_score_gemma":0.0022017655,"threshold_uncertainty_score":0.039405584},"labels":[],"label_agreement":null},{"id":"W4415379075","doi":"10.3758/s13428-025-02806-z","title":"LexKO: A quick, reliable lexical test of Korean language proficiency","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Toronto","funders":"Kyung Hee University; University of Manitoba; City University of Hong Kong","keywords":"Language proficiency; Test (biology); Korean language; Multilingualism; Language assessment; Foreign language","score_opus":0.17705806644686634,"score_gpt":0.5632092123204916,"score_spread":0.38615114587362526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415379075","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9330615,0.0009268722,0.024126189,0.00050134887,0.00012473302,0.0026269504,0.014912653,0.0009831417,0.022736711],"genre_scores_gemma":[0.85621446,0.0013857662,0.07935589,0.00064258615,0.00005041014,0.0039334544,0.027421908,0.0003347991,0.030660693],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994049,0.00012261908,0.00019267907,0.00009367789,0.00014292703,0.00004324289],"domain_scores_gemma":[0.9981061,0.00029555112,0.00059216295,0.00018425751,0.00060091104,0.00022098505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010747444,0.0007247505,0.00039099765,0.0013530247,0.00031749276,0.0005020842,0.0005891355,0.00041422804,0.007787994],"category_scores_gemma":[0.0033621725,0.00019430909,0.00033524848,0.0004805544,0.00027761827,0.0013870767,0.00093128945,0.0005145261,0.002242089],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016652794,0.0020510973,0.46011955,0.0012735063,0.00035432487,0.0015386445,0.0033479065,0.0010434578,0.09274741,0.0019674797,0.031294532,0.4025968],"study_design_scores_gemma":[0.00021325784,0.0024160822,0.93910235,0.00022041485,0.00012839164,0.00371698,0.0018478902,0.0018460514,0.018767787,0.0012397857,0.030357987,0.0001430251],"about_ca_topic_score_codex":0.0014397056,"about_ca_topic_score_gemma":0.004493307,"teacher_disagreement_score":0.007787994,"about_ca_system_score_codex":0.00017619257,"about_ca_system_score_gemma":0.00062812783,"threshold_uncertainty_score":0.026053488},"labels":[],"label_agreement":null},{"id":"W4415668209","doi":"10.3758/s13428-025-02783-3","title":"Errors-in-variables regression as a viable approach to mediation analysis with random error-tainted measurements: Estimation, effectiveness, and an easy-to-use implementation","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Regression analysis; Mediation; Observational error; Ordinary least squares; Regression; Regression diagnostic; Errors-in-variables models; Instrumental variable; Standard error; Linear regression","score_opus":0.3125196999863581,"score_gpt":0.6438098672918707,"score_spread":0.33129016730551264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415668209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038636436,0.00020106893,0.99132335,0.00051832164,0.000263274,0.0012123772,0.00024845733,0.0013841036,0.0009854432],"genre_scores_gemma":[0.0819917,0.00027553015,0.91055834,0.00033393566,0.0001615673,0.0042827777,0.00018449489,0.00056130614,0.0016502992],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7770072,0.20597786,0.0040113446,0.005759405,0.006524201,0.0007198985],"domain_scores_gemma":[0.57315475,0.37866625,0.007917024,0.03258855,0.006864226,0.0008092506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19061925,0.003212246,0.0037243618,0.003026275,0.0012876623,0.0036248253,0.0054199495,0.0028392987,0.014784727],"category_scores_gemma":[0.382371,0.0025517375,0.004123348,0.0038468922,0.0019023446,0.005922577,0.004324415,0.0068464135,0.0022309918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003958033,0.0032343552,0.035436906,0.0026057558,0.009086575,0.00034859785,0.0038237472,0.01659547,0.0029108028,0.1099394,0.0148415845,0.79721874],"study_design_scores_gemma":[0.004635824,0.008702651,0.029520288,0.0024607002,0.0056422763,0.0008673837,0.0020090786,0.53234684,0.015070439,0.3538382,0.044120576,0.0007857104],"about_ca_topic_score_codex":0.0036422042,"about_ca_topic_score_gemma":0.0047119358,"teacher_disagreement_score":0.19061925,"about_ca_system_score_codex":0.00083281595,"about_ca_system_score_gemma":0.003685844,"threshold_uncertainty_score":0.9981106},"labels":[],"label_agreement":null},{"id":"W4415812611","doi":"10.3758/s13428-025-02871-4","title":"Publisher Correction: A systematic review of latent class analysis in psychology: Examining the gap between guidelines and research practice","year":2025,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Latent class model; Class (philosophy); Practice research; Systematic review; Research design; Research methodology","score_opus":0.8840180937043264,"score_gpt":0.781607092634572,"score_spread":0.10241100106975443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415812611","genre_codex":"editorial","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026593514,0.07581969,0.0039354917,0.13902064,0.76858747,0.002087534,0.0071748313,0.0008357657,0.0022726364],"genre_scores_gemma":[0.03106182,0.21333817,0.043850645,0.30209914,0.3244496,0.02473248,0.008134052,0.004351943,0.04798219],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.7779227,0.07749659,0.073653564,0.010843417,0.056119036,0.003964621],"domain_scores_gemma":[0.42718253,0.21019514,0.06327244,0.02871697,0.26295167,0.0076812366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13438597,0.004684674,0.013447998,0.024094285,0.0048796874,0.014846036,0.012495617,0.017159104,0.05137341],"category_scores_gemma":[0.65738374,0.0046083974,0.0065784566,0.029836802,0.0077132257,0.009976342,0.0077877,0.01582503,0.019591143],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024893507,0.000014383075,0.00030695758,0.054990217,0.0011796477,0.00022094278,0.00025806844,0.00007265686,0.00006679218,0.0012901854,0.9202172,0.021133946],"study_design_scores_gemma":[0.0024033946,0.00016153435,0.0035085268,0.25225115,0.009853707,0.0008702684,0.0005035397,0.0005622124,0.000502082,0.007564395,0.72142124,0.00039807294],"about_ca_topic_score_codex":0.025539685,"about_ca_topic_score_gemma":0.045550212,"teacher_disagreement_score":0.86561406,"about_ca_system_score_codex":0.01717757,"about_ca_system_score_gemma":0.065893255,"threshold_uncertainty_score":0.71070945},"labels":[],"label_agreement":null},{"id":"W4416118469","doi":"10.3758/s13428-025-02878-x","title":"Quantifying word informativeness and its impact on eye-movement reading behavior: Cross-linguistic variability and individual differences","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation; Hebrew University of Jerusalem","keywords":"Sentence; Reading (process); Meaning (existential); Centrality; Word (group theory); Affect (linguistics); Measure (data warehouse)","score_opus":0.37613696170262745,"score_gpt":0.6139571780082518,"score_spread":0.23782021630562433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416118469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98649514,0.00024019161,0.011147096,0.00004563053,0.000012811606,0.000023498867,0.00048011303,0.00011032689,0.0014452995],"genre_scores_gemma":[0.99548197,0.000057845406,0.00369778,0.000020320758,0.0000075809103,0.000026297666,0.00038033354,0.000050019175,0.00027774984],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989864,0.00033333345,0.00009477046,0.0003859136,0.0001611216,0.00003836895],"domain_scores_gemma":[0.9888498,0.0070888666,0.0018490369,0.0014586276,0.00052310544,0.0002304061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017582614,0.00036076145,0.00036261705,0.0008536648,0.00018882626,0.0009630054,0.0002169909,0.00039584356,0.0013162513],"category_scores_gemma":[0.015527989,0.0001685415,0.00022895854,0.0005829314,0.00050920696,0.00064629415,0.00058663427,0.00041857277,0.00026921567],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012559668,0.00031074526,0.6077496,0.0005078956,0.0013239525,0.00022089487,0.0039918697,0.00486809,0.2501093,0.0014193151,0.0010848527,0.12715754],"study_design_scores_gemma":[0.0000069753632,0.00016586199,0.9819225,0.000015592197,0.00006720951,0.00020289344,0.00023940706,0.0056465273,0.010192627,0.0010818873,0.00042502806,0.00003350746],"about_ca_topic_score_codex":0.0012382045,"about_ca_topic_score_gemma":0.002766939,"teacher_disagreement_score":0.0017582614,"about_ca_system_score_codex":0.00016213019,"about_ca_system_score_gemma":0.00013208832,"threshold_uncertainty_score":0.009298682},"labels":[],"label_agreement":null},{"id":"W4416322110","doi":"10.3758/s13428-025-02787-z","title":"Spower: A general-purpose Monte Carlo simulation power analysis program","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Subroutine; Monte Carlo method; Software; Comparability; Function (biology); Software package; Population; Power (physics)","score_opus":0.6411716053274139,"score_gpt":0.6920635075483204,"score_spread":0.05089190222090645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416322110","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011919336,0.000082052924,0.9134482,0.00015229746,0.00013321656,0.0010464881,0.0033394971,0.058540117,0.011338794],"genre_scores_gemma":[0.10873279,0.00010934548,0.85070854,0.000253193,0.00006549754,0.0069602313,0.0030121426,0.017692935,0.012465372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864906,0.000728104,0.00008766773,0.00019214465,0.0002404311,0.000102564845],"domain_scores_gemma":[0.9904727,0.0074926466,0.00029564183,0.00079720473,0.0007967589,0.00014503833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046109837,0.0014442833,0.0014733417,0.0012618749,0.0009404111,0.001397066,0.0032501102,0.0012624767,0.08011373],"category_scores_gemma":[0.023386447,0.0014015745,0.0012313026,0.0009651998,0.00044750865,0.0011549059,0.0015781884,0.0028081883,0.008452118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032819023,0.00160424,0.009780483,0.0014738479,0.0015920436,0.00042912632,0.0010009266,0.34255004,0.0059558414,0.072716355,0.15740444,0.4022107],"study_design_scores_gemma":[0.00068964536,0.0001650809,0.0009918428,0.00007212346,0.00018106589,0.00009948112,0.00003777606,0.9430567,0.0054237125,0.020763267,0.028458234,0.00006109771],"about_ca_topic_score_codex":0.00599106,"about_ca_topic_score_gemma":0.008911017,"teacher_disagreement_score":0.08011373,"about_ca_system_score_codex":0.00093100325,"about_ca_system_score_gemma":0.0021544297,"threshold_uncertainty_score":0.26800716},"labels":[],"label_agreement":null},{"id":"W4416887635","doi":"10.3758/s13428-025-02872-3","title":"The Subliminal Threshold Estimation Procedure (STEP): A calibration method tailored for estimating subliminal thresholds","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Tel Aviv University","keywords":"Subliminal stimuli; Stimulus (psychology); Calibration; Detection threshold; Psychophysics; Just-noticeable difference","score_opus":0.4554719485315771,"score_gpt":0.6203202001042937,"score_spread":0.1648482515727166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416887635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012736855,0.0001193405,0.9849139,0.000056741224,0.000030886644,0.00011158672,0.00007435703,0.0014236515,0.0005327669],"genre_scores_gemma":[0.1377342,0.00016278408,0.86025745,0.0001554915,0.000026455002,0.00038504176,0.00015170757,0.00038736156,0.00073943945],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985241,0.00043976094,0.00008959849,0.00042026018,0.00043662672,0.000089594985],"domain_scores_gemma":[0.99511045,0.002259187,0.0006748421,0.0010360281,0.0007721623,0.00014729235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028275428,0.00092444144,0.00080348545,0.0010114753,0.0005284348,0.0009977054,0.0019446171,0.001352613,0.002776443],"category_scores_gemma":[0.013897588,0.00053079583,0.00078614254,0.00082192104,0.0007163583,0.0014553802,0.0015229703,0.0021010053,0.001347359],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005916401,0.00025121777,0.0077113444,0.0007351177,0.00031974612,0.00018433199,0.0007071608,0.033570956,0.31208742,0.012767802,0.004379031,0.6266942],"study_design_scores_gemma":[0.00009567189,0.00060267764,0.019484816,0.00010149315,0.00016129173,0.0013470037,0.000147811,0.6733761,0.2791056,0.015677124,0.009556589,0.00034385183],"about_ca_topic_score_codex":0.0010158385,"about_ca_topic_score_gemma":0.0014844573,"teacher_disagreement_score":0.0028275428,"about_ca_system_score_codex":0.0004770058,"about_ca_system_score_gemma":0.001213296,"threshold_uncertainty_score":0.014953613},"labels":[],"label_agreement":null},{"id":"W763189797","doi":"10.3758/s13428-015-0614-z","title":"Performance impact of stop lists and morphological decomposition on word–word corpus-based semantic space models","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Word (group theory); Word lists by frequency; Space (punctuation); Semantics (computer science); Class (philosophy); Text corpus; Linguistics; Sentence","score_opus":0.4101321547628593,"score_gpt":0.5636734972443137,"score_spread":0.1535413424814544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W763189797","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60108954,0.0057634683,0.3480953,0.0025480397,0.00086715963,0.0002774936,0.0044548144,0.031177545,0.0057265516],"genre_scores_gemma":[0.8126616,0.0011241664,0.16803959,0.0003145479,0.00017552817,0.00026706234,0.012253397,0.0014980133,0.0036660694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639565,0.0021271007,0.00034911354,0.0006211416,0.00029075862,0.00021622084],"domain_scores_gemma":[0.9738045,0.022055306,0.00035544424,0.0012355486,0.0018212562,0.00072790764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008810797,0.0020294462,0.0020118982,0.0021421562,0.0010966402,0.0031719427,0.0018044825,0.0020356586,0.0056156255],"category_scores_gemma":[0.025051665,0.0007043006,0.0018081074,0.0020768445,0.00046426835,0.0048781135,0.0020282567,0.0026861108,0.003521552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060602566,0.0011322924,0.014574089,0.0006121611,0.0013755254,0.00012257235,0.00045723844,0.25806105,0.0058210264,0.0032423758,0.01402256,0.6945188],"study_design_scores_gemma":[0.000036563717,0.000075938064,0.00085841573,0.000018094604,0.000091172624,0.000019415473,0.00013108003,0.9958188,0.0014761094,0.0010701332,0.00038714215,0.000017198843],"about_ca_topic_score_codex":0.040212,"about_ca_topic_score_gemma":0.03300215,"teacher_disagreement_score":0.040212,"about_ca_system_score_codex":0.001468977,"about_ca_system_score_gemma":0.0039817803,"threshold_uncertainty_score":0.079955876},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8490125083874293,"score_gpt":0.6913935802776402,"score_spread":0.15761892810978906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W927394476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4849517,0.0067640846,0.4887429,0.0025714366,0.0011849762,0.0025163123,0.0010822535,0.0014943824,0.01069191],"genre_scores_gemma":[0.88242406,0.0004972008,0.11456479,0.00043778511,0.00019418779,0.0010155315,0.00026738716,0.00029212906,0.0003069027],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.5009733,0.44398212,0.014951648,0.017215712,0.021580234,0.0012970107],"domain_scores_gemma":[0.02876417,0.9496429,0.0041998154,0.013014574,0.0040144613,0.0003640606],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39217842,0.0028835877,0.0026233005,0.0033586673,0.0021419912,0.004369305,0.0060164765,0.004625771,0.0033840246],"category_scores_gemma":[0.75159955,0.0011864213,0.0060821236,0.0032775234,0.009734583,0.007974709,0.0036351318,0.0042854114,0.0005402932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03846532,0.0023517485,0.39241204,0.0048039765,0.0287086,0.0018827234,0.0085851,0.050695997,0.014383925,0.06852322,0.0066384776,0.38254887],"study_design_scores_gemma":[0.007972783,0.033414017,0.36410737,0.0028581014,0.03291376,0.0044627073,0.0026270153,0.42309773,0.031223042,0.08183305,0.013856397,0.0016341561],"about_ca_topic_score_codex":0.0017491474,"about_ca_topic_score_gemma":0.002020345,"teacher_disagreement_score":0.6078216,"about_ca_system_score_codex":0.0016202264,"about_ca_system_score_gemma":0.0014598923,"threshold_uncertainty_score":0.74955225},"labels":[],"label_agreement":null}]}