{"id":"W4379983287","doi":"10.1109/icit58465.2023.10143149","title":"A Hybrid Continual Learning Approach for Efficient Hierarchical Classification of IT Support Tickets in the Presence of Class Overlap","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); Western University","funders":"","keywords":"Computer science; Class hierarchy; Hierarchy; Task (project management); Inference; Artificial intelligence; Machine learning; Class (philosophy); Ticket; Multiclass classification; Key (lock); Data mining; Support vector machine; Computer security","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":[0.001731245,0.00008973094,0.0001788755,0.0001776078,0.00003791334,0.00003834018,0.001250057,0.00003957939,0.000002866493],"category_scores_gemma":[0.0005266641,0.00006566176,0.00005632647,0.0004959364,0.0001263235,0.0001485006,0.0003050783,0.0001545836,0.000003116991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001534332,"about_ca_system_score_gemma":0.00007697532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001959039,"about_ca_topic_score_gemma":0.000002064495,"domain_scores_codex":[0.9985263,0.0001534276,0.0003698906,0.0003284998,0.0003904424,0.0002314127],"domain_scores_gemma":[0.998408,0.0007497859,0.0001603647,0.0005722704,0.00008253716,0.00002700805],"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":[0.0001416054,0.001296347,0.01025638,0.0004043259,0.00004784966,0.00001843704,0.01469659,0.004006326,0.02399177,0.7811578,0.06247358,0.101509],"study_design_scores_gemma":[0.0002683606,0.0002911809,0.009944979,0.00002677541,0.000004750789,0.000008316596,0.000540485,0.977284,0.008666451,0.0009842047,0.001878372,0.0001021623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1959758,0.000002435514,0.7966697,0.0007988559,0.00003679099,0.0005665299,0.00002039325,0.0001856691,0.00574388],"genre_scores_gemma":[0.934747,0.00000223151,0.06484951,0.00003771273,0.000009823787,0.00009927822,0.00005026258,0.000005842377,0.0001983414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9732776,"threshold_uncertainty_score":0.2677609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04476575027070322,"score_gpt":0.305961615575104,"score_spread":0.2611958653044008,"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."}}