{"id":"W4379259273","doi":"10.1186/s40462-023-00392-3","title":"Flexible hidden Markov models for behaviour-dependent habitat selection","year":2023,"lang":"en","type":"article","venue":"Movement Ecology","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Hidden Markov model; Animal ecology; Selection (genetic algorithm); Computer science; Model selection; Markov model; Machine learning; Artificial intelligence; Ecology; Markov chain; Biology","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004194535,0.0001099431,0.0001250123,0.00006580154,0.0002483329,0.00001293243,0.0001467522,0.0001365981,0.001735809],"category_scores_gemma":[0.00002602066,0.0001174693,0.00005221491,0.0002103731,0.00005881763,0.0001859321,0.000138989,0.0000790147,0.0009049892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002631164,"about_ca_system_score_gemma":0.0000182741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001005063,"about_ca_topic_score_gemma":0.002835417,"domain_scores_codex":[0.998892,0.00005059515,0.0002128342,0.0003325207,0.0001249085,0.000387115],"domain_scores_gemma":[0.9996332,0.0000983412,0.00007551519,0.0001281388,0.00001234494,0.00005245145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000387995,0.00008652922,0.9334916,0.000004212798,0.00001652247,0.000002637362,0.00006972104,0.004721532,0.0008547857,0.0008549497,0.05762177,0.002236903],"study_design_scores_gemma":[0.0005617087,0.0002768176,0.9518027,0.000001292396,0.00002193221,0.000001495693,0.00005862771,0.01913575,0.00102046,0.02625417,0.0007275087,0.0001374941],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899318,0.000002944499,0.002947154,0.003111441,0.0004940263,0.0006429058,0.00001098218,0.0001871201,0.002671682],"genre_scores_gemma":[0.97565,0.00001165639,0.001345565,0.003630172,0.0000595756,0.0007696793,0.00007155936,0.00001858264,0.01844324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05689427,"threshold_uncertainty_score":0.9998729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01972296123188448,"score_gpt":0.2442464403569913,"score_spread":0.2245234791251069,"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."}}