{"id":"W4404217563","doi":"10.1017/awf.2024.55","title":"How well can you tell? Success of human categorisation of horse behavioural responses depicted in media","year":2024,"lang":"en","type":"article","venue":"Animal Welfare","topic":"Animal and Plant Science Education","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Animal welfare; Animal-assisted therapy; HUBzero; Pet therapy; Horse; Psychology; Applied psychology; Biology; Ecology","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":[0.0002587754,0.0001137213,0.0001763769,0.0002856305,0.00005667415,0.00002992182,0.0001908174,0.0001178913,0.000627442],"category_scores_gemma":[0.00004836683,0.00009915241,0.00005051046,0.0004814502,0.0001118487,0.0001527828,0.000021145,0.0001534707,0.00001784926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003679073,"about_ca_system_score_gemma":0.00005400148,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00797375,"about_ca_topic_score_gemma":0.003412588,"domain_scores_codex":[0.9989353,0.0001224547,0.0002739756,0.0002685826,0.0001937987,0.000205857],"domain_scores_gemma":[0.9995354,0.00009739309,0.00009775469,0.0001487549,0.000066651,0.00005408367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004198812,0.0002227816,0.8737315,0.00009177346,0.00002115946,0.00007491286,0.01604713,5.482339e-7,0.06945274,0.03675557,0.001249191,0.001932814],"study_design_scores_gemma":[0.0001372186,0.0003196454,0.9870221,0.00003372403,0.0000228339,0.0000130478,0.006362218,0.00001637483,0.005041446,0.0001128167,0.0008076356,0.0001109472],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949337,0.0002473257,0.000002298431,0.002777357,0.000477596,0.0001392145,0.0001052511,0.00003468763,0.00128259],"genre_scores_gemma":[0.9987516,0.000007284652,0.00002057437,0.00001067318,0.00008361781,0.00001459225,0.0001294677,0.0000114784,0.00097066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1132906,"threshold_uncertainty_score":0.9986323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04776387623041366,"score_gpt":0.3253842794486139,"score_spread":0.2776204032182003,"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."}}