{"id":"W4282841940","doi":"10.1016/j.patcog.2022.108849","title":"Symbolic sequence representation with Markovian state optimization","year":2022,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"Fujian Provincial Department of Science and Technology; National Natural Science Foundation of China","keywords":"Hidden Markov model; Embedding; Computer science; Sequence (biology); Representation (politics); Cluster analysis; Artificial intelligence; Pattern recognition (psychology); Markov process; Sequence labeling; Set (abstract data type); Markov chain; Theoretical computer science; Algorithm; Machine learning; Task (project management); 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":[],"consensus_categories":[],"category_scores_codex":[0.0001956711,0.00009115355,0.00009875487,0.0001211304,0.0003184622,0.0001440362,0.000232096,0.00001149426,0.0004062567],"category_scores_gemma":[0.000009325632,0.00008888786,0.00003740872,0.0005638567,0.00001588201,0.0005463505,0.0001435017,0.0001078183,0.00002459466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006310455,"about_ca_system_score_gemma":0.00002285292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001929317,"about_ca_topic_score_gemma":0.00002604497,"domain_scores_codex":[0.9988896,0.0001233405,0.0001808251,0.0003312502,0.0002999482,0.0001750285],"domain_scores_gemma":[0.9994415,0.0000276091,0.0001672099,0.0002342002,0.00008483534,0.00004464928],"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":[0.0000173848,0.00004517191,0.004502187,0.00001089011,0.00002968813,0.00003225501,0.0009446211,0.1192614,0.00019657,0.0000195349,0.00008019013,0.8748601],"study_design_scores_gemma":[0.0002983792,0.0001774491,0.001989189,0.00001686154,0.0000181697,0.00008834906,0.0002219919,0.9955703,0.000589193,0.0006287421,0.0001774588,0.0002239162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08835132,0.00001139297,0.9099131,0.0003597872,0.00009429672,0.0001399082,0.00002468959,0.0001177763,0.0009877145],"genre_scores_gemma":[0.977655,0.00001244335,0.02147342,0.0003317368,0.00003440537,0.00008733712,0.0002497018,0.00001257699,0.0001433824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8893037,"threshold_uncertainty_score":0.4448226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03560563657482425,"score_gpt":0.235520869452255,"score_spread":0.1999152328774307,"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."}}