{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007768664,0.000344314,0.0004382536,0.0004156028,0.0002723009,0.0002373093,0.0002986543,0.0001382662,0.000005143196],"category_scores_gemma":[0.0003838649,0.000358394,0.00008986612,0.0001936281,0.0002720033,0.0003874548,0.0004416699,0.0003071812,0.00002437717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002050302,"about_ca_system_score_gemma":0.0001105465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002984755,"about_ca_topic_score_gemma":0.00001766117,"domain_scores_codex":[0.9977714,0.00005970944,0.0006725639,0.0007887812,0.0004662744,0.0002413048],"domain_scores_gemma":[0.9968021,0.001862932,0.0002928208,0.000146612,0.0008350443,0.00006050632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005186721,0.000005353034,0.00000168555,0.0001246981,0.0001043163,0.00000764488,0.002947007,0.293217,0.000001063899,0.6690573,0.00009324,0.03443558],"study_design_scores_gemma":[0.00005599612,0.00008578604,6.934265e-7,0.0005406886,0.00002860051,0.000007046879,0.001014552,0.6030018,0.0000139194,0.3944411,0.0005881692,0.0002216363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000003683421,0.004252252,0.9856495,0.0001708074,0.0004578752,0.0003914011,0.00001639847,0.0001186467,0.008939383],"genre_scores_gemma":[0.4938296,0.007698574,0.3776888,0.002254393,0.0006657462,0.0002064822,0.0007420679,0.0003007503,0.1166136],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6079608,"threshold_uncertainty_score":0.9998868,"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."}}