{"id":"W4307277822","doi":"10.21203/rs.3.rs-2179960/v1","title":"3D Annotation and deep learning for cotton plant part segmentation and architectural trait extraction","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Leaf Properties and Growth Measurement","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Cotton Incorporated; National Science Foundation","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Inference; Point cloud; Trait; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Point (geometry); Annotation; Machine learning; Mathematics","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":[0.001283623,0.0001390431,0.0001525665,0.00003914812,0.0007984726,0.0002213242,0.00009824022,0.0001050659,0.0002242982],"category_scores_gemma":[0.0001318562,0.00006176371,0.00004999253,0.0001049534,0.00006348408,0.00007925185,0.0002374777,0.000676594,0.000001138499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059009,"about_ca_system_score_gemma":0.00001580919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006631123,"about_ca_topic_score_gemma":0.0006398882,"domain_scores_codex":[0.9980285,0.0004346334,0.0001929803,0.0004494708,0.0005731668,0.0003212522],"domain_scores_gemma":[0.9992769,0.0003555631,0.00008677811,0.00004214281,0.0001429324,0.00009570029],"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":[0.0004030665,0.00006522838,0.004894695,0.0005411291,0.00003348405,0.000003639065,0.00193691,0.0005645898,0.03901187,0.00005215422,0.0002350263,0.9522582],"study_design_scores_gemma":[0.001763423,0.007013166,0.7055063,0.0008059657,0.0001005842,0.00008301651,0.03114777,0.03030846,0.005527336,0.003591694,0.2127483,0.001403921],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954742,0.001468114,0.00004404076,0.001251432,0.0001233949,0.001310033,0.0001708492,0.00004029059,0.0001176625],"genre_scores_gemma":[0.9961867,0.0006122086,0.0002075294,0.00002302,0.0003142854,0.0006106244,0.001735869,0.000002646349,0.0003071048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9508543,"threshold_uncertainty_score":0.6141286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112582683320631,"score_gpt":0.3464831387275977,"score_spread":0.2339004554069666,"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."}}