{"id":"W4206551931","doi":"10.22215/etd/2021-14648","title":"Augmenting AI Creativity: event segmentation and AI planning for quest generation","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Event (particle physics); Segmentation; Context (archaeology); Artificial intelligence; Representation (politics); Architecture; Natural language generation; Generator (circuit theory); Conceptual architecture; Software engineering; Creativity; Narrative; Natural language processing; Natural 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000302427,0.0002025332,0.0002091998,0.0001264288,0.0002614572,0.0006607235,0.0001942742,0.0001493061,0.00002729409],"category_scores_gemma":[0.0001041774,0.0002107494,0.00006588296,0.0001441187,0.00001229265,0.0006943962,0.00005035113,0.0001439692,0.000005543617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007321684,"about_ca_system_score_gemma":0.0001408658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001458186,"about_ca_topic_score_gemma":0.0007905166,"domain_scores_codex":[0.9985405,0.00006137942,0.0003799993,0.0005533909,0.0002558005,0.0002089243],"domain_scores_gemma":[0.9991179,0.0001191101,0.0002090419,0.000221812,0.0002801798,0.00005201319],"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":[0.00003320327,0.0001753091,0.001992174,0.0004696219,0.0001781435,0.0000218374,0.02523837,0.003488268,0.09020702,0.0701886,0.01053641,0.797471],"study_design_scores_gemma":[0.0001022085,0.0001078176,0.0004222256,0.0002703243,0.00004849444,0.000004961717,0.002677781,0.5058204,0.4849184,0.003588085,0.001588118,0.0004512022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05015101,0.000469593,0.9460278,0.0004612931,0.001181955,0.0004775257,0.000005269372,0.0001027877,0.001122816],"genre_scores_gemma":[0.7686394,0.0001439245,0.187055,0.002289893,0.001343502,0.0007396176,0.004719869,0.00009089935,0.03497782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7970198,"threshold_uncertainty_score":0.8594112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05270487591426373,"score_gpt":0.3807042900370405,"score_spread":0.3279994141227768,"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."}}