{"id":"W3158310581","doi":"10.1111/rssc.12483","title":"Clustering and Automatic Labelling Within Time Series of Categorical Observations—With an Application to Marine Log Messages","year":2021,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"NRC Steacie Institute for Molecular Sciences","keywords":"Computer science; Cluster analysis; Data mining; Set (abstract data type); A priori and a posteriori; Categorical variable; Inference; Bayesian probability; Series (stratigraphy); State (computer science); Hierarchical clustering; Identification (biology); Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005298618,0.0002187191,0.0005263741,0.00002866442,0.0003434782,0.0002393864,0.0004948976,0.0000720077,0.00005572839],"category_scores_gemma":[0.000178804,0.0001531331,0.00007307424,0.0004851029,0.00021481,0.0003018608,0.0004709903,0.0002818991,0.000002325031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007449463,"about_ca_system_score_gemma":0.0001661245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004117916,"about_ca_topic_score_gemma":0.00008773423,"domain_scores_codex":[0.997932,0.00009777138,0.0008268234,0.0003019011,0.0005673941,0.0002741335],"domain_scores_gemma":[0.9979577,0.0003529156,0.0006191644,0.0003754212,0.0004818226,0.0002129559],"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":[0.0003581477,0.0004179958,0.001783902,0.0006278718,0.0007892336,0.00007959799,0.007108002,0.09332372,0.005363883,0.8019921,0.002019289,0.08613625],"study_design_scores_gemma":[0.0005245389,0.0006473451,0.01666232,0.00006152775,0.000253699,0.0001610022,0.001232137,0.9430572,0.0009839613,0.03561362,0.0004270827,0.0003755127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008917539,0.00002875551,0.9899018,0.0007320861,0.00006940275,0.0001419803,0.00008108384,0.00002535384,0.0001019455],"genre_scores_gemma":[0.1577311,0.00001459141,0.8417276,0.000145731,0.00005770436,0.000007707017,0.00001799058,0.00001942259,0.0002781293],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8497335,"threshold_uncertainty_score":0.6244588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01078433395384456,"score_gpt":0.2181222175034086,"score_spread":0.2073378835495641,"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."}}