{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004598394,0.0003759387,0.0003868709,0.0003532734,0.0008396394,0.0006786347,0.0009115012,0.00006011362,0.002115227],"category_scores_gemma":[0.00001087137,0.0003620509,0.00009378666,0.0005092711,0.00006679857,0.0008607217,0.001021231,0.0005882758,0.0004782815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000067974,"about_ca_system_score_gemma":0.00008192648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002710529,"about_ca_topic_score_gemma":0.000005993538,"domain_scores_codex":[0.9967597,0.0004003851,0.0004786567,0.001138911,0.0007260109,0.0004963332],"domain_scores_gemma":[0.99843,0.0001374598,0.0002239378,0.0007538812,0.0001459981,0.00030869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002809674,0.0002181888,0.00009647546,0.00001972568,0.00001584042,0.00008741819,0.0001789399,0.00007632775,0.001326746,0.0002644543,0.07273697,0.9249508],"study_design_scores_gemma":[0.001752648,0.001111446,0.0005427974,0.0001247492,0.00001403887,0.0002395366,0.00008821579,0.8805358,0.001462631,0.00258491,0.110679,0.0008641312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02111964,0.0001000489,0.9705487,0.003157824,0.002424007,0.0004463564,0.001038394,0.0003221395,0.000842915],"genre_scores_gemma":[0.8655962,0.0005968045,0.06942122,0.05850293,0.0008711823,0.0003540286,0.003543887,0.0001113744,0.001002318],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9240867,"threshold_uncertainty_score":0.9998832,"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."}}