{"id":"W6929423502","doi":"10.48550/arxiv.1704.02744","title":"Finding strong lenses in CFHTLS using convolutional neural networks","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Nausea and vomiting management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Lens (geology); Pattern recognition (psychology); Artificial neural network; Completeness (order theory); Set (abstract data type); Data set; Identification (biology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002541972,0.0002665218,0.0004316011,0.0003339301,0.0002055393,0.00005984802,0.000330486,0.0002657359,0.00006792337],"category_scores_gemma":[0.00006808279,0.0003157743,0.0001914965,0.0001334844,0.0001469526,0.0001339679,0.0007929823,0.000791156,0.00000961272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004675663,"about_ca_system_score_gemma":0.0001406459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004254982,"about_ca_topic_score_gemma":0.00007283153,"domain_scores_codex":[0.9985436,0.00007603841,0.0002077391,0.0006664825,0.0000872292,0.000418951],"domain_scores_gemma":[0.9987985,0.0000718268,0.0002825128,0.0006386283,0.00007933655,0.000129194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000224399,0.0001034865,0.313647,0.0001905783,0.0001786575,0.00155851,0.00003937014,0.6747923,0.00003383918,0.008665267,0.000185545,0.0003809877],"study_design_scores_gemma":[0.001722071,0.00005079833,0.06791715,0.0006298326,0.0003304317,0.00001329807,0.0001122826,0.927779,0.00001215904,0.0009506702,0.0001490776,0.0003332262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97461,0.000145424,0.02136263,0.00008399349,0.0006194348,0.0004217245,0.00001060375,0.00007181704,0.002674407],"genre_scores_gemma":[0.9974325,0.0001053674,0.0001625389,0.00006318533,0.0003172581,5.486899e-7,0.00005073822,0.00002571501,0.001842105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2529867,"threshold_uncertainty_score":0.9999294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2204055381856903,"score_gpt":0.256451019581437,"score_spread":0.03604548139574662,"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."}}