{"id":"W4403243243","doi":"10.34133/plantphenomics.0268","title":"Counting Canola: Toward Generalizable Aerial Plant Detection Models","year":2024,"lang":"en","type":"article","venue":"Plant Phenomics","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Canada First Research Excellence Fund","keywords":"Canola; Field (mathematics); Artificial intelligence; Set (abstract data type); Computer science; Machine learning; Noise (video); Population; Generalizability theory; Statistics; Mathematics; Image (mathematics); Biology; Agronomy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001204689,0.0001429346,0.0001396647,0.00001053664,0.0001606722,0.0002352374,0.0001407395,0.00009573439,0.00007119354],"category_scores_gemma":[0.000005181219,0.00005155859,0.00007085365,0.0001561601,0.00001370315,0.0001953043,0.00004631397,0.00012009,0.00005937021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005343664,"about_ca_system_score_gemma":0.00001128763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009869279,"about_ca_topic_score_gemma":0.001714902,"domain_scores_codex":[0.9991174,0.00001987311,0.0001724164,0.0002777132,0.0001336472,0.0002789109],"domain_scores_gemma":[0.9997805,0.00006862941,0.00003366225,0.00003078119,0.00001928358,0.00006711651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008928079,0.00005555023,0.0003222382,0.00004295726,0.00007537064,0.00005122826,0.0005768387,0.002072877,0.9518014,0.005693925,0.01956211,0.01965629],"study_design_scores_gemma":[0.0002908693,0.0002713497,0.002185444,0.0001434682,0.000113037,0.0002906811,0.0006729958,0.1452876,0.05454518,0.005778807,0.7893385,0.001082048],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946119,0.0006102764,0.0001263288,0.0003787273,0.001476858,0.0001309514,0.0005447076,0.0002211377,0.001899167],"genre_scores_gemma":[0.996296,0.0001952265,0.00007687578,0.0001915663,0.002503343,0.00001305776,0.0004810532,0.000001620767,0.0002412864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8972561,"threshold_uncertainty_score":0.2268399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0293015466956985,"score_gpt":0.1829206317113541,"score_spread":0.1536190850156556,"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."}}