{"id":"W2094353923","doi":"10.1890/11-2241.1","title":"Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions","year":2012,"lang":"en","type":"article","venue":"Ecology","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":478,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Center for Northern Studies","funders":"Engineering and Physical Sciences Research Council","keywords":"Hidden Markov model; Computer science; Markov model; Markov chain; Variable-order Bayesian network; Bayesian probability; Machine learning; Variable-order Markov model; Artificial intelligence; Bayesian inference","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":[0.0004255392,0.00006116561,0.0001169033,0.00002285484,0.00009182704,0.000003969571,0.00006313547,0.0001063719,0.0003899228],"category_scores_gemma":[0.0001436989,0.00005819376,0.000007112109,0.00005766574,0.0001671471,0.0006403423,0.0004678013,0.0001018974,0.00002612145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001603955,"about_ca_system_score_gemma":0.00001282919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005582244,"about_ca_topic_score_gemma":0.00008834628,"domain_scores_codex":[0.9993404,0.00006788388,0.0001416202,0.0001908598,0.00005696975,0.000202323],"domain_scores_gemma":[0.9995114,0.0001783177,0.00004835483,0.000182842,0.000005884377,0.00007317522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005679623,0.00009995532,0.9929704,0.000005296527,0.00001258136,0.000002899485,0.000123244,0.000148791,0.0005353194,0.001607707,0.003357484,0.001079506],"study_design_scores_gemma":[0.0001780801,0.00008740831,0.7821202,0.000001499737,0.00002757349,0.00007614492,0.00009974527,0.215319,0.00002304213,0.001799148,0.0001967472,0.00007150393],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947047,0.00007843083,0.001694469,0.001500095,0.00008012541,0.00008813012,0.000005571451,0.0000127441,0.001835778],"genre_scores_gemma":[0.9852545,0.00004664118,0.01405241,0.000514233,0.000035378,0.000005294819,0.000008258658,0.000004966039,0.0000783406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2151702,"threshold_uncertainty_score":0.4269381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07015033126805864,"score_gpt":0.3071856308862854,"score_spread":0.2370352996182267,"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."}}