{"id":"W4285965606","doi":"10.1145/3528233.3530713","title":"Learning Smooth Neural Functions via Lipschitz Regularization","year":2022,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Canada; University of Toronto","funders":"","keywords":"Lipschitz continuity; Extrapolation; Interpolation (computer graphics); Regularization (linguistics); Computer science; Artificial neural network; Hyperparameter; Active shape model; Artificial intelligence; Algorithm; Point cloud; Mathematics; Mathematical analysis; Image (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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006877567,0.00005832891,0.00006284721,0.00008568503,0.0002663443,0.0000200719,0.00005238011,0.00001437206,0.0009748494],"category_scores_gemma":[0.000005604893,0.0000623145,0.00005092786,0.0002656829,0.000003993978,0.00004816796,0.00002743254,0.0001935696,0.00003217712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003003767,"about_ca_system_score_gemma":0.000003451691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001630102,"about_ca_topic_score_gemma":0.000004562563,"domain_scores_codex":[0.9995757,0.00002423273,0.00009339354,0.00009036451,0.0001109036,0.0001054061],"domain_scores_gemma":[0.9998547,0.000009034815,0.000009660434,0.00008795135,0.00001133518,0.00002728494],"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":[7.384611e-7,0.000004966632,0.0003368784,0.000002474432,0.00001507603,7.100772e-7,0.00007115219,0.9885449,0.001061173,0.0000365262,0.0005492839,0.009376164],"study_design_scores_gemma":[0.00005654444,0.00001743791,0.0001089837,5.729476e-7,0.00001863848,0.00000247172,0.000175371,0.9952674,0.00005224869,0.00007208378,0.004149541,0.00007870965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1401586,0.00009302054,0.8451788,0.0001584521,0.0002671483,0.00003378038,0.000001852244,0.0009148637,0.01319344],"genre_scores_gemma":[0.9876789,0.000003032083,0.0002931425,0.00004091542,0.00005270443,0.00001294729,0.00005251886,0.00001861954,0.01184718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8475203,"threshold_uncertainty_score":0.9999384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006660351561520977,"score_gpt":0.1774205666135119,"score_spread":0.1707602150519909,"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."}}