{"id":"W4387835509","doi":"10.1145/3586183.3606772","title":"WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AI","year":2023,"lang":"en","type":"article","venue":"","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Autodesk (Canada)","funders":"","keywords":"Computer science; Generative grammar; Leverage (statistics); Formative assessment; Scratch; Human–computer interaction; Process (computing); Artificial intelligence; Programming language; Psychology","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":[0.001466847,0.0009073102,0.0002832834,0.0005235453,0.0006182065,0.001879127,0.00143717,0.001156651,0.0181759],"category_scores_gemma":[0.006615349,0.0004510087,0.0006046379,0.0002225288,0.001518411,0.002776439,0.004173014,0.001057576,0.00248015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002982461,"about_ca_system_score_gemma":0.0003665645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002316798,"about_ca_topic_score_gemma":0.0005327663,"domain_scores_codex":[0.9993213,0.0003061135,0.00002696267,0.0001135529,0.0001768813,0.00005521829],"domain_scores_gemma":[0.9967243,0.00241268,0.00009651235,0.0005029212,0.0001009435,0.0001626668],"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":[0.001284838,0.001015897,0.003557372,0.001833286,0.0001032969,0.003449201,0.04569757,0.0210615,0.2444893,0.1194397,0.02616047,0.5319076],"study_design_scores_gemma":[0.0006605576,0.001590751,0.005285204,0.0004685453,0.0001171129,0.004974813,0.006439885,0.2261583,0.2181269,0.1212822,0.4144678,0.0004278271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05900306,0.0001551873,0.9088525,0.0002585896,0.000100909,0.0003472588,0.0002685191,0.01651971,0.01449429],"genre_scores_gemma":[0.3909546,0.0001874125,0.5911601,0.0001669483,0.0000412734,0.000549344,0.000575939,0.001871104,0.01449306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0181759,"threshold_uncertainty_score":0.06080443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02752014472764055,"score_gpt":0.3065254036185444,"score_spread":0.2790052588909038,"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."}}