{"id":"W4220896903","doi":"10.1145/3507356","title":"Leveraging Narrative to Generate Movie Script","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada); Université de Montréal","funders":"","keywords":"Computer science; Narrative; Scripting language; Context (archaeology); Upload; Unavailability; Task (project management); Construct (python library); Information retrieval; Artificial intelligence; Natural language processing; World Wide Web; Linguistics; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001006298,0.001547464,0.0006471928,0.001417509,0.0004606232,0.001031738,0.001286224,0.001105809,0.003305051],"category_scores_gemma":[0.007260557,0.0003497479,0.0009467202,0.0008347764,0.0003005739,0.002396334,0.000811511,0.001007088,0.004078469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006596388,"about_ca_system_score_gemma":0.0007117531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003101846,"about_ca_topic_score_gemma":0.007379603,"domain_scores_codex":[0.998886,0.000376968,0.0001151612,0.0004112692,0.0001586242,0.00005192119],"domain_scores_gemma":[0.9977105,0.001163285,0.0002159999,0.0004582072,0.0003121934,0.0001398766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001350945,0.0008443535,0.02174144,0.003527634,0.0002601086,0.002078766,0.002096648,0.04065398,0.06060839,0.008855675,0.1330206,0.7249614],"study_design_scores_gemma":[0.0002559425,0.0008183273,0.01114974,0.0002874789,0.0001658627,0.001887493,0.001434327,0.7107973,0.0683767,0.01666888,0.1879784,0.0001796377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1991323,0.005511935,0.6519421,0.002397991,0.0007547352,0.00315166,0.06144606,0.05850615,0.01715713],"genre_scores_gemma":[0.2847327,0.001024344,0.5931274,0.0006304219,0.0001595921,0.0008682896,0.1085972,0.001378167,0.009481948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003305051,"threshold_uncertainty_score":0.01105648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03357747367188199,"score_gpt":0.2455136343496178,"score_spread":0.2119361606777358,"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."}}