{"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,"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","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01943448,0.0002642205,0.0007037428,0.000428415,0.0003282083,0.00004664897,0.0006661518,0.0002250782,0.0004297216],"category_scores_gemma":[0.001948212,0.0002105314,0.000329744,0.001640383,0.0003396875,0.000152602,0.000489781,0.0007082124,0.00001254091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001286875,"about_ca_system_score_gemma":0.0004944932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009966753,"about_ca_topic_score_gemma":0.00004754074,"domain_scores_codex":[0.9882201,0.007072538,0.001209305,0.0008206454,0.002007906,0.0006695017],"domain_scores_gemma":[0.9943011,0.001385566,0.0004000959,0.001556668,0.002122464,0.0002341265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002937036,0.001408089,0.0003090882,0.00007737612,0.0001732507,0.000003702082,0.007908138,0.007574301,0.9062579,0.002069695,0.00003919955,0.07388556],"study_design_scores_gemma":[0.002726851,0.0007011461,0.007732294,0.000293893,0.001530109,0.00003388306,0.02601898,0.4982706,0.4556222,0.00635901,0.00005060841,0.000660511],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.738034,0.0007039263,0.2588158,0.0001099348,0.0001943839,0.001125914,0.0001421568,0.00002158938,0.0008523779],"genre_scores_gemma":[0.5284936,0.00001962681,0.4696293,0.00006972605,0.00004064641,0.0005104668,0.00003866828,0.00004604587,0.001151894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4906963,"threshold_uncertainty_score":0.8585221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7789337434495036,"score_gpt":0.6764091439089269,"score_spread":0.1025245995405767,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}