{"id":"W4395095858","doi":"10.1007/978-3-031-46549-9_14","title":"Designing and Evaluating Context-Sensitive Visualization Models for Deep Learning Text Classifiers","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Machine learning; Visualization; Salient; Context (archaeology); Quality (philosophy); Natural language processing","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":[0.006171498,0.002011578,0.001474215,0.001756936,0.0006579091,0.003170812,0.002507431,0.002466007,0.002989505],"category_scores_gemma":[0.03025979,0.000955965,0.00111015,0.001477409,0.0007557714,0.006480378,0.002143561,0.003625745,0.00128096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002020882,"about_ca_system_score_gemma":0.001271472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005565107,"about_ca_topic_score_gemma":0.008065531,"domain_scores_codex":[0.9971969,0.001315209,0.0001770819,0.0005523593,0.000579578,0.0001787238],"domain_scores_gemma":[0.9822109,0.01295967,0.0008001913,0.001475427,0.002072434,0.0004813329],"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":[0.001326748,0.0007425225,0.005908011,0.0005363735,0.0003276695,0.0001259278,0.0002723394,0.3365035,0.01538014,0.008771134,0.01761087,0.6124948],"study_design_scores_gemma":[0.00001639574,0.00007414698,0.0001801044,0.0000213735,0.00002060567,0.00001415716,0.00002955042,0.9897459,0.00404923,0.005471271,0.0003698492,0.000007401645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1442871,0.003508792,0.8321437,0.001440045,0.0003751493,0.0004530899,0.001524317,0.01321949,0.003048246],"genre_scores_gemma":[0.5767171,0.0009885934,0.4148735,0.0003524363,0.0001791285,0.0003964215,0.002759566,0.0007614208,0.002971798],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006171498,"threshold_uncertainty_score":0.03263837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2104355097885403,"score_gpt":0.4323086960692927,"score_spread":0.2218731862807524,"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."}}