{"id":"W4211010039","doi":"10.1109/isit.2005.1523736","title":"Analyticity of entropy rate in families of hidden markov chains","year":2005,"lang":"en","type":"article","venue":"","topic":"Mathematical Dynamics and Fractals","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov chain; Maximum-entropy Markov model; Markov chain mixing time; Examples of Markov chains; Variable-order Markov model; Markov kernel; Hidden semi-Markov model; Markov property; Entropy (arrow of time); Markov model; Mathematics; Markov process; Hidden Markov model; Binary number; Markov renewal process; Statistical physics; Entropy rate; Additive Markov chain; Binary entropy function; Computer science; Artificial intelligence; Principle of maximum entropy; Statistics; Physics; Thermodynamics; Arithmetic","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":[0.0004562527,0.00009496722,0.0003870152,0.0001128629,0.000007967346,0.000004546138,0.0001332192,0.00005553188,0.0006730478],"category_scores_gemma":[0.000376262,0.00007251676,0.00008555525,0.0001622196,0.00005953433,0.00004974408,0.00005078968,0.00006675687,0.000008126958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002113994,"about_ca_system_score_gemma":0.00001641819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004134567,"about_ca_topic_score_gemma":0.0002082869,"domain_scores_codex":[0.9990116,0.00003929158,0.0005403155,0.0001047843,0.0001544025,0.0001495493],"domain_scores_gemma":[0.9990612,0.0004442906,0.0001621206,0.0002395847,0.00005520918,0.00003759724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001469907,0.000520864,0.002541852,0.0003710231,0.00004088872,0.000001364031,0.0005773786,0.000009008685,0.00404648,0.9878724,0.000315837,0.003688193],"study_design_scores_gemma":[0.001446766,0.0001315659,0.01506587,0.0002316381,0.00008258785,0.000002077327,0.00087159,0.3820896,0.02042709,0.5790341,0.0002428503,0.0003742198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9490901,0.00001310747,0.009524208,0.0002485731,0.0000121626,0.0001682902,0.00001387792,0.00001564228,0.04091404],"genre_scores_gemma":[0.9648686,0.00003164896,0.03293325,0.00003575694,0.00001473644,0.00000337725,0.000001386192,0.000009434178,0.002101799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4088383,"threshold_uncertainty_score":0.7369402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02577996306751417,"score_gpt":0.2987554952966643,"score_spread":0.2729755322291501,"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."}}