{"id":"W4403321952","doi":"10.1145/3680528.3687566","title":"Neural Product Importance Sampling via Warp Composition","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Discretization; Rendering (computer graphics); Global illumination; Importance sampling; Computer science; Monte Carlo method; Algorithm; Sampling (signal processing); Spline (mechanical); Variance reduction; Artificial intelligence; Computer vision; Mathematics; Statistics; Mathematical analysis; Engineering","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":[0.001505956,0.0008007486,0.0009680797,0.0006435945,0.0004804293,0.0008356324,0.001178897,0.000924908,0.003439967],"category_scores_gemma":[0.005171346,0.0005998976,0.0006775967,0.000588214,0.001123558,0.001288151,0.001661903,0.001677221,0.0008452389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008763883,"about_ca_system_score_gemma":0.0009844543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00379702,"about_ca_topic_score_gemma":0.005580912,"domain_scores_codex":[0.9994356,0.0001539652,0.00002341785,0.0001025138,0.0002308247,0.00005366649],"domain_scores_gemma":[0.9986233,0.0007328936,0.00008111163,0.0002220333,0.0002629473,0.00007778322],"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":[0.0002956092,0.0001302037,0.001361048,0.0001311852,0.00005917572,0.000116516,0.0001638411,0.6176649,0.01704448,0.04693707,0.002720374,0.3133755],"study_design_scores_gemma":[0.000007663088,0.00001191554,0.00004553861,0.000002613637,0.000003150298,0.00001496901,0.000003356092,0.9920961,0.002307088,0.005073092,0.0004309343,0.000003511068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008624676,0.00005501064,0.9898727,0.00004962722,0.00002086462,0.00003428426,0.00001659115,0.0004976696,0.0008285312],"genre_scores_gemma":[0.3384395,0.0001810693,0.6551465,0.0002096452,0.0001029883,0.0002062521,0.000217203,0.0005557517,0.004941132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00379702,"threshold_uncertainty_score":0.01150781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04007821709071144,"score_gpt":0.3285728440270743,"score_spread":0.2884946269363629,"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."}}