{"id":"W7106287717","doi":"10.5281/zenodo.17675089","title":"Training data and ensemble results of an ensemble of models trained to find flowers on herbarium sheet images","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Biological and pharmacological studies of plants","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Herbarium; Metadata; Phenology; Training (meteorology); Training set; Ensemble learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001791326,0.0002698545,0.0006185849,0.0002288224,0.0009029964,0.0001245314,0.00126001,0.0001748687,0.00163558],"category_scores_gemma":[0.002567983,0.0002258948,0.0000574331,0.0006792168,0.0004434384,0.0001976356,0.002427688,0.0004351112,0.0001579497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005949095,"about_ca_system_score_gemma":0.00001387509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004329264,"about_ca_topic_score_gemma":9.413828e-7,"domain_scores_codex":[0.9968922,0.0005508464,0.0007153502,0.0009033359,0.0004098302,0.0005284921],"domain_scores_gemma":[0.9979028,0.0002413927,0.0001968747,0.0007386918,0.0005425452,0.0003777462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0106687,0.001435275,0.000003033947,0.0006210619,0.0004912635,0.00005806981,0.005123768,0.001036503,0.1786225,0.001368211,0.1493245,0.6512471],"study_design_scores_gemma":[0.01521454,0.0196074,0.007402041,0.001798409,0.0006405066,0.00007685806,0.008660079,0.03679793,0.02860678,0.002197038,0.8779019,0.001096555],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.525638,0.001625989,0.006093245,0.009326727,0.0004798364,0.002910624,0.01478608,0.0004253878,0.4387141],"genre_scores_gemma":[0.9945869,0.0008020519,0.0006391456,0.0006148057,0.000102963,5.532096e-8,0.00173974,0.0002358042,0.001278501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7285774,"threshold_uncertainty_score":0.9992771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1522654449125505,"score_gpt":0.3335928425343037,"score_spread":0.1813273976217532,"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."}}