{"id":"W4307475428","doi":"10.1145/3526113.3545621","title":"Opal: Multimodal Image Generation for News Illustration","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"USable; Computer science; Pipeline (software); Image (mathematics); Tone (literature); Multimedia; Artificial intelligence; Human–computer interaction; 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":[0.0006600939,0.00106615,0.0003401218,0.0009292765,0.0003584223,0.001376897,0.001221315,0.0009303733,0.04092586],"category_scores_gemma":[0.004176745,0.0003087929,0.0007123771,0.0003223766,0.0004706389,0.001940886,0.002664908,0.0008202728,0.007500923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002976388,"about_ca_system_score_gemma":0.0002319209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005509158,"about_ca_topic_score_gemma":0.0008944009,"domain_scores_codex":[0.9996618,0.000104022,0.00001896166,0.00007059431,0.0001125868,0.00003204265],"domain_scores_gemma":[0.9987778,0.0007850826,0.00004848847,0.0001873678,0.0001137277,0.00008757089],"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":[0.001508667,0.0004379209,0.002114498,0.001489434,0.0001412625,0.001638637,0.002189235,0.007448649,0.06867528,0.01598488,0.1730248,0.7253468],"study_design_scores_gemma":[0.000660887,0.0007773051,0.005115304,0.0002971718,0.0001587177,0.003383244,0.001092508,0.3153363,0.1408467,0.03637942,0.4956816,0.0002707756],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04721922,0.001081266,0.6951739,0.0007763701,0.0004274234,0.000802593,0.00440804,0.2056984,0.04441281],"genre_scores_gemma":[0.3175625,0.000881445,0.615178,0.0008096385,0.0001848374,0.001111941,0.009267103,0.01342721,0.04157737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04092586,"threshold_uncertainty_score":0.1369106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03235914812416576,"score_gpt":0.2967623643262253,"score_spread":0.2644032162020595,"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."}}