{"id":"W4417398205","doi":"10.21083/caree.v1i1.8922","title":"Evaluating the Effectiveness of Large Language Models for Livestock and Climate-Related Agricultural Advice in Ontario","year":2025,"lang":"","type":"article","venue":"Canadian Agri-food & Rural Advisory Extension and Education Journal","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Comparability; Context (archaeology); Quality (philosophy); Agriculture; Livestock; Reliability (semiconductor)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005782128,0.0002366109,0.0004292584,0.0004226366,0.001601736,0.0001971751,0.000196314,0.0001590192,0.000106175],"category_scores_gemma":[0.0007111155,0.0001637155,0.0001724882,0.0007287201,0.0001719803,0.0003931919,0.00005071678,0.0005983885,0.000001178462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005719708,"about_ca_system_score_gemma":0.004606138,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1552268,"about_ca_topic_score_gemma":0.6433175,"domain_scores_codex":[0.9962612,0.00197246,0.000672935,0.000317444,0.0002698461,0.0005060835],"domain_scores_gemma":[0.9967685,0.001545333,0.000345516,0.0001212036,0.0007164099,0.0005029966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001674955,0.00124892,0.06282847,0.001325713,0.001300527,0.00001047976,0.2177404,0.02040288,0.006869772,0.2221705,0.001679799,0.4627475],"study_design_scores_gemma":[0.001144044,0.0003489127,0.8836251,0.001353465,0.0002863481,0.00004147,0.07072564,0.01049072,0.00001340386,0.03128691,0.0004115947,0.0002724087],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9878229,0.006409557,0.00009479035,0.002039823,0.001034905,0.0007283246,0.00001828316,0.00000662764,0.001844801],"genre_scores_gemma":[0.9972544,0.0002966818,0.0006770745,0.0004025558,0.00009938911,0.00002903535,0.00003546351,0.000007858646,0.001197491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8207966,"threshold_uncertainty_score":0.999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03074393541240867,"score_gpt":0.3522021382032282,"score_spread":0.3214582027908195,"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."}}