{"id":"W4312339971","doi":"10.1109/cvpr52688.2022.00373","title":"Kubric: A scalable dataset generator","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia; McGill University; University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Scalability; Reuse; Generator (circuit theory); Ground truth; Code generation; Software; Architecture; Source code; Machine learning; Artificial intelligence; Software engineering; Data mining; Distributed computing; Database; Programming language; Computer security","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":[0.002126149,0.001775596,0.0008753784,0.00194234,0.0006926638,0.001619239,0.004099258,0.0008426259,0.02058815],"category_scores_gemma":[0.008919818,0.001117562,0.001998853,0.002489394,0.0006804305,0.002021321,0.004543413,0.002599538,0.01617854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008727916,"about_ca_system_score_gemma":0.001753818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00459851,"about_ca_topic_score_gemma":0.008807066,"domain_scores_codex":[0.9987534,0.0002210603,0.0001164329,0.0003767081,0.0004084533,0.0001239176],"domain_scores_gemma":[0.9975832,0.0005538442,0.00008106379,0.001105714,0.0004904149,0.0001857702],"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":[0.0006872304,0.000268259,0.003928306,0.0008962551,0.000207219,0.0004000049,0.0002541206,0.02590782,0.008093567,0.007562405,0.8250743,0.1267206],"study_design_scores_gemma":[0.001270174,0.0002310563,0.008386162,0.0002086978,0.0001019189,0.000713265,0.0002712583,0.4233863,0.03473168,0.04039609,0.4900487,0.000254776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.01469813,0.0005204171,0.2798215,0.0007681536,0.0007465146,0.00128374,0.2305647,0.4590518,0.01254504],"genre_scores_gemma":[0.06082972,0.0003517448,0.3141715,0.0006710063,0.00009420994,0.002682094,0.5750005,0.04013898,0.006060246],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.02058815,"threshold_uncertainty_score":0.06887424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04847059047974639,"score_gpt":0.2917939615108296,"score_spread":0.2433233710310833,"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."}}