{"id":"W1709985024","doi":"","title":"Automatically Assessing Whether a Text Is Cliched, with Applications to Literary Analysis","year":2013,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Style (visual arts); Computer science; Text generation; Natural language processing; Artificial intelligence; Literature; Psychology; Art","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001330207,0.000133851,0.0001778289,0.0002945976,0.00009941638,0.001099385,0.00087439,0.00005661296,0.0002819184],"category_scores_gemma":[0.0000136796,0.00008872693,0.000058279,0.002277626,0.00002709797,0.001127572,0.0002247582,0.0001129265,0.0002534268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003075231,"about_ca_system_score_gemma":0.00004621977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007897155,"about_ca_topic_score_gemma":0.000008870346,"domain_scores_codex":[0.998875,0.00003135033,0.0001981232,0.000409842,0.0002592232,0.0002264713],"domain_scores_gemma":[0.9987512,0.00006995029,0.00006490776,0.0007753425,0.0002023663,0.0001362814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002165538,0.0001869473,0.003912573,0.00005274565,0.0003304849,0.000007265683,0.003362668,0.00001329471,0.007634521,0.09651235,0.007929266,0.8800557],"study_design_scores_gemma":[0.0005172347,0.0003093915,0.02049037,0.0002408689,0.0004610962,0.00006914542,0.0002103355,0.5476257,0.04196955,0.372744,0.01300676,0.002355512],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002073393,0.0001674957,0.9855121,0.005816952,0.000005295054,0.0003454306,5.204429e-7,0.001115508,0.00496331],"genre_scores_gemma":[0.2496645,4.650607e-7,0.7448859,0.004217017,0.00001477769,0.0002065563,0.000001303156,0.000007776453,0.001001726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8777002,"threshold_uncertainty_score":0.9999376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009963230175129095,"score_gpt":0.2962544717027327,"score_spread":0.2862912415276037,"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."}}