{"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,"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","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005174702,0.0001308694,0.0002176143,0.000402747,0.0005776829,0.00006877808,0.000348487,0.0000927456,0.002449022],"category_scores_gemma":[0.007726813,0.0001318227,0.00006743488,0.0009553037,0.001154655,0.00009730305,0.0001387009,0.0005194798,0.00005251564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273371,"about_ca_system_score_gemma":0.0002876642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001388595,"about_ca_topic_score_gemma":0.00004327486,"domain_scores_codex":[0.9940817,0.003738375,0.0003790376,0.0005430035,0.0008497217,0.0004081323],"domain_scores_gemma":[0.9916701,0.005922754,0.0001676564,0.0003895017,0.001703086,0.0001469207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000403581,0.00397931,0.4144021,0.00002629372,0.0001660044,0.0000288687,0.1476055,0.00003589439,0.1413643,0.02318818,0.00365358,0.2651464],"study_design_scores_gemma":[0.0004560951,0.0004295491,0.959783,0.00005089756,0.00004831704,0.000009314466,0.01087386,0.0003484113,0.0197033,0.007963671,0.0002045806,0.000128999],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9365806,0.0001269362,0.01754528,0.0001437177,0.001108623,0.0007314379,0.0001965536,0.00005408558,0.04351277],"genre_scores_gemma":[0.9056915,0.000002537676,0.09184727,0.00004622966,0.0004199071,0.0002915617,0.00004040443,0.00002040803,0.001640166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5453809,"threshold_uncertainty_score":0.9984629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3290861747777553,"score_gpt":0.6516848971259406,"score_spread":0.3225987223481853,"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."}}