{"id":"W4315927472","doi":"10.22541/au.167365587.77636790/v1","title":"NAPPN Annual Conference Abstract: Automated root phenotyping via deep learning- based landmark detection using SLEAP","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Rice Cultivation and Yield Improvement","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Biological Sciences","funders":"","keywords":"Artificial intelligence; Landmark; Root (linguistics); Pipeline (software); Python (programming language); Computer science; Biology; Deep learning; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001195207,0.001678352,0.0008913641,0.0009583397,0.0005359077,0.0019123,0.001952705,0.001185816,0.03194222],"category_scores_gemma":[0.001494681,0.0007180828,0.001094588,0.0007231902,0.0004062279,0.001689807,0.002547538,0.00267779,0.02230125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076394,"about_ca_system_score_gemma":0.00155524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005790276,"about_ca_topic_score_gemma":0.01296746,"domain_scores_codex":[0.9993936,0.00005448739,0.00002038757,0.0001856856,0.0002799673,0.00006584913],"domain_scores_gemma":[0.9989638,0.000117549,0.00003430576,0.0002155863,0.0004982325,0.0001705177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000437013,0.0002343441,0.00353291,0.0005881491,0.0001604509,0.0003412989,0.000132498,0.0238586,0.08711264,0.005607298,0.4788327,0.3991621],"study_design_scores_gemma":[0.0001491636,0.0003116418,0.008706727,0.0001858697,0.0000939156,0.0004253889,0.000129308,0.3757734,0.09658917,0.01672221,0.5007042,0.0002090928],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02429179,0.001869045,0.7368019,0.003255258,0.00247124,0.0004213984,0.03114767,0.1562332,0.0435085],"genre_scores_gemma":[0.1282381,0.003370443,0.6280421,0.001613473,0.0006119627,0.0009943745,0.1207818,0.01592415,0.1004236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03194222,"threshold_uncertainty_score":0.1068574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05222068898635517,"score_gpt":0.2672286559714121,"score_spread":0.2150079669850569,"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."}}