{"id":"W3192616105","doi":"10.48550/arxiv.2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Computer science; Bridging (networking); Phrase; Artificial intelligence; Modal; Semantics (computer science); Natural language processing; Mobile device; Set (abstract data type); Information retrieval; Human–computer interaction; World Wide Web; 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":[0.0006406558,0.002681204,0.0007747879,0.002564242,0.000451529,0.00104337,0.001771604,0.00124279,0.005375295],"category_scores_gemma":[0.003607229,0.0003350481,0.001170539,0.00121656,0.0003062918,0.001781609,0.001684323,0.001278781,0.005103868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009598411,"about_ca_system_score_gemma":0.0007547289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007319795,"about_ca_topic_score_gemma":0.01644022,"domain_scores_codex":[0.9992719,0.0001566487,0.00005974491,0.0002551978,0.0001795729,0.00007691023],"domain_scores_gemma":[0.9990739,0.0002829619,0.00008467206,0.0002032125,0.0002989957,0.00005628301],"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":[0.0008164626,0.000470802,0.004668708,0.001348273,0.0002744509,0.0003601028,0.0004522442,0.02339044,0.0487365,0.001757035,0.1246521,0.7930729],"study_design_scores_gemma":[0.000211505,0.0008791899,0.009512015,0.0002325883,0.000253968,0.0004425983,0.0008131673,0.80491,0.09026818,0.008581564,0.08372782,0.0001673179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1101961,0.003995143,0.623796,0.0007678505,0.0004622103,0.001256685,0.05507392,0.1944561,0.009995971],"genre_scores_gemma":[0.3044372,0.001048435,0.5119711,0.0006479426,0.0001834805,0.001568216,0.1601854,0.00271896,0.01723927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007319795,"threshold_uncertainty_score":0.01798218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02825793177744283,"score_gpt":0.1912261793573584,"score_spread":0.1629682475799156,"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."}}