{"id":"W4200412035","doi":"10.1186/s40537-021-00547-2","title":"Dynamic order Markov model for categorical sequence clustering","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Hidden Markov model; Cluster analysis; Pattern recognition (psychology); Markov chain; Markov model; Sequence (biology); Categorical variable; Suffix tree; Data mining; Artificial intelligence; Algorithm; Data structure; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004107699,0.00008467925,0.0001700866,0.00005498738,0.00008458018,0.0001744508,0.001914084,0.00004279893,0.000003834075],"category_scores_gemma":[0.0001640897,0.0000668822,0.00004084378,0.0002052561,0.00001499083,0.001134425,0.001681459,0.0001623099,0.000002501674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004265122,"about_ca_system_score_gemma":0.0003947739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005230826,"about_ca_topic_score_gemma":0.0000158753,"domain_scores_codex":[0.9989398,0.00002923724,0.0003196306,0.0002550377,0.0002795002,0.0001768545],"domain_scores_gemma":[0.9983215,0.00007659817,0.0001935053,0.001014515,0.0002919176,0.0001019928],"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":[0.00004458869,0.0001681841,0.00003447989,0.00006609669,0.00005835019,0.0004749766,0.0001898733,0.01045334,0.006274268,0.0008829067,0.02727417,0.9540788],"study_design_scores_gemma":[0.0003053111,0.00002964313,0.00003534748,0.0000340367,0.000009977809,0.0005245124,0.0000096958,0.9903805,0.00007298675,0.001828299,0.006682993,0.00008674018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004565541,0.0003755108,0.9969351,0.001210313,0.0008296912,0.00003603932,0.0001082009,0.00001055797,0.00003807827],"genre_scores_gemma":[0.06092351,0.0002183138,0.9380301,0.0002955986,0.0002009466,0.000001041323,0.00009264482,0.000008896141,0.0002289825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9799271,"threshold_uncertainty_score":0.3556877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1343751196579093,"score_gpt":0.3358048966184071,"score_spread":0.2014297769604978,"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."}}