{"id":"W4312906868","doi":"10.1109/cvpr52688.2022.01147","title":"CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CAD; Computer science; Constructive solid geometry; Artificial neural network; Artificial intelligence; Parametric statistics; Net (polyhedron); Solid modeling; Interpretability; Constructive; Computer Aided Design; Generalizability theory; Ground truth; Topology (electrical circuits); Algorithm; Machine learning; Geometry; Engineering drawing; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002346055,0.0003641569,0.0004406294,0.0002913721,0.0004482765,0.0002023099,0.0001805144,0.00007329455,0.001040186],"category_scores_gemma":[0.000003672058,0.0003336399,0.0001083328,0.0002600814,0.00004393618,0.0001780523,0.00007093856,0.0008086881,0.0001002259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008175056,"about_ca_system_score_gemma":0.00003396794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007854153,"about_ca_topic_score_gemma":0.00004352339,"domain_scores_codex":[0.9980766,0.0002491118,0.0003197557,0.0005308948,0.0004740058,0.0003496217],"domain_scores_gemma":[0.999289,0.0001360085,0.0001139953,0.0001506162,0.000141263,0.0001691356],"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":[0.0002107863,0.0002314903,0.001040737,0.00008913394,0.0003993927,0.0001487303,0.002242282,0.2810478,0.002078415,0.00002942443,0.003053112,0.7094287],"study_design_scores_gemma":[0.000835898,0.001102361,0.001767478,0.0002159481,0.00006631696,0.00004277392,0.0005866195,0.993828,0.0004132789,0.0000786016,0.0005335092,0.0005292136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6895164,0.00008321154,0.3061855,0.0002650152,0.0003163007,0.0002573628,0.0001581962,0.0003985951,0.002819453],"genre_scores_gemma":[0.9983147,0.0001433803,0.0003761367,0.0005525044,0.0001416583,0.00003966086,0.0002070505,0.00005289978,0.0001720008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7127802,"threshold_uncertainty_score":0.9999115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519507238058299,"score_gpt":0.2389541671139973,"score_spread":0.2037590947334144,"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."}}