{"id":"W4321601084","doi":"10.21203/rs.3.rs-2598116/v1","title":"A supervised algorithm entirely trained on a synthetic dataset to segment granular suspension images","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Nautical Research Society","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Suspension (topology); Construct (python library); Segmentation; Generalization; Pattern recognition (psychology); Synthetic data; Market segmentation; Field (mathematics); Image (mathematics); Artificial neural network; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001717383,0.0004347014,0.0004733367,0.00101558,0.000262597,0.0004029854,0.0006881478,0.0002906143,0.0001782472],"category_scores_gemma":[0.0003422602,0.0004120935,0.0001446293,0.0006364668,0.00006197235,0.00006931484,0.0008632948,0.001679239,0.001243063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003821928,"about_ca_system_score_gemma":0.0001040587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002811382,"about_ca_topic_score_gemma":0.00003252839,"domain_scores_codex":[0.9960115,0.0002516013,0.0003873706,0.0008803636,0.00143345,0.001035723],"domain_scores_gemma":[0.9980062,0.000309894,0.00002593796,0.001064369,0.0001810249,0.0004125917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001966152,0.0004175279,0.00009582409,0.01271006,0.0003144555,0.002044652,0.003445114,0.195284,0.02616094,0.00008007647,0.5728894,0.1863613],"study_design_scores_gemma":[0.003393337,0.001742118,0.003832566,0.03111201,0.0001825791,0.00005073413,0.002780088,0.8463882,0.03696977,0.005506411,0.06335907,0.004683172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8677736,0.003937691,0.03175944,0.009604096,0.006170177,0.01305848,0.05693902,0.007747381,0.003010096],"genre_scores_gemma":[0.975657,0.0007189917,0.005065572,0.00007857085,0.0009007154,0.001020852,0.01393425,0.0004816788,0.002142386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6511041,"threshold_uncertainty_score":0.9998331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08680068671941002,"score_gpt":0.3677319451123272,"score_spread":0.2809312583929172,"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."}}