{"id":"W4379382350","doi":"10.1109/tsmc.2023.3275298","title":"Online Semi-Supervised Classification on Multilabel Evolving High-Dimensional Text Streams","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Term (time); Set (abstract data type); Function (biology); Concept drift; Process (computing); Task (project management); Dirichlet distribution; Artificial intelligence; Subspace topology; Data stream mining; Data mining; Pattern recognition (psychology); Machine learning; Mathematics","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":[0.0004949176,0.0003963326,0.0004435078,0.0005426366,0.0003301359,0.000505905,0.0007059502,0.0002413634,0.000006153869],"category_scores_gemma":[0.0000122556,0.0003707242,0.0000867176,0.0007434599,0.00007993342,0.0003311571,0.00001633122,0.0003474308,0.0002630145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001643356,"about_ca_system_score_gemma":0.00006237371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008719913,"about_ca_topic_score_gemma":0.00004631118,"domain_scores_codex":[0.9969229,0.0002609228,0.0006895338,0.0008995004,0.0007604336,0.0004666695],"domain_scores_gemma":[0.9977934,0.000335281,0.0002260069,0.001234434,0.0001833564,0.000227555],"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":[0.0003372853,0.007756063,0.0007302715,0.003408791,0.001608983,0.0005728964,0.008888425,0.2568999,0.07279236,0.08851974,0.1116536,0.4468317],"study_design_scores_gemma":[0.0007186923,0.0004060743,0.001140315,0.0008570981,0.00003315085,0.00006685197,0.0004786561,0.9927266,0.001626281,0.00004692816,0.00140992,0.0004894348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2778005,0.0003420982,0.7080818,0.0005683685,0.005319513,0.001982921,0.0008700595,0.003763645,0.001271059],"genre_scores_gemma":[0.994888,0.00008738312,0.001630182,0.00005759979,0.0001306367,0.000196366,0.00007533874,0.0000540671,0.002880423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7358267,"threshold_uncertainty_score":0.9998745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0348453369964253,"score_gpt":0.2608562871229483,"score_spread":0.226010950126523,"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."}}