{"id":"W4312496759","doi":"10.1609/aiide.v17i1.18915","title":"A Tool for Generating Monster Silhouettes with a Word-Conditioned Variational Autoencoder","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Autoencoder; Character (mathematics); Monster; Task (project management); Game design; Computer science; Creativity; Word (group theory); Human–computer interaction; Process (computing); Artificial intelligence; Engineering design process; Psychology; Aesthetics; Natural language processing; Linguistics; Engineering; Art; Mathematics; Social psychology; Artificial neural network; Literature","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":[0.0001823381,0.0002833761,0.000282626,0.0001012446,0.0002509953,0.001034144,0.00063539,0.00006439181,0.00005791718],"category_scores_gemma":[0.0004585065,0.0002046083,0.0001420699,0.0002958167,0.0002249757,0.001215483,0.0003337498,0.0002013545,0.00001640945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000872005,"about_ca_system_score_gemma":0.0001334971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006414217,"about_ca_topic_score_gemma":0.000006982577,"domain_scores_codex":[0.9979509,0.00001704473,0.0005911588,0.0006460366,0.0004532186,0.0003417075],"domain_scores_gemma":[0.9979101,0.0003184717,0.0003780804,0.0002297553,0.001084721,0.00007888274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000342891,0.0006717513,0.001039311,0.00005909274,0.000185066,0.000003635012,0.005043222,0.001006101,0.02771295,0.8021594,0.0001858816,0.1615907],"study_design_scores_gemma":[0.00008313699,0.0005260815,0.0002652299,0.0004577987,0.00002689534,0.00002993914,0.003298002,0.36757,0.5333583,0.09376686,0.0002238796,0.0003939472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3471753,0.00002375525,0.6415646,0.006088335,0.0003751083,0.0008648611,0.00005687497,0.00007680343,0.003774336],"genre_scores_gemma":[0.9863994,0.000007394853,0.01219676,0.0006913582,0.00007515523,0.000158287,0.000005749705,0.00001597071,0.0004499119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7083926,"threshold_uncertainty_score":0.9972271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03727612705984979,"score_gpt":0.2778835742385605,"score_spread":0.2406074471787107,"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."}}