{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002504398,0.001732922,0.002320182,0.002466955,0.001199641,0.001690192,0.003217192,0.001609183,0.001422234],"category_scores_gemma":[0.006377621,0.0005015614,0.001593331,0.002441328,0.0007951254,0.00359267,0.001678146,0.002146358,0.001401103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001086198,"about_ca_system_score_gemma":0.001641908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003429408,"about_ca_topic_score_gemma":0.00444381,"domain_scores_codex":[0.9977832,0.0005102371,0.0002036203,0.0008826646,0.0004101919,0.0002099644],"domain_scores_gemma":[0.9938974,0.002966807,0.0007133165,0.0007529994,0.001345645,0.0003239583],"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":[0.0008669242,0.0008791314,0.0062978,0.0003710151,0.0002016639,0.0003299127,0.00058463,0.1681181,0.009537085,0.003810842,0.01119859,0.7978043],"study_design_scores_gemma":[0.0000142081,0.00004052672,0.0004596432,0.000007587691,0.00001091372,0.0000411736,0.00007136401,0.9914718,0.002667093,0.004622029,0.0005812572,0.00001234611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1111174,0.0006727351,0.879694,0.0004613906,0.0002055341,0.0003257731,0.001080701,0.005046531,0.001395963],"genre_scores_gemma":[0.5189027,0.0003161046,0.4684785,0.0003085056,0.0004161977,0.000620249,0.006319488,0.000294288,0.004344043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003429408,"threshold_uncertainty_score":0.01324463,"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."}}