{"id":"W2938206986","doi":"10.48550/arxiv.1904.07865","title":"ZoomOut: Spectral Upsampling for Efficient Shape Correspondence","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Upsampling; Computer science; Mathematics; Artificial intelligence","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"],"consensus_categories":[],"category_scores_codex":[0.0001971736,0.0003552687,0.0004314647,0.0003074519,0.0000976701,0.00006687435,0.000590612,0.0002932762,0.0001141665],"category_scores_gemma":[0.00002811916,0.0004314007,0.0004365566,0.0002868037,0.00003771329,0.000050473,0.0002420727,0.0005079096,0.0002005491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002474065,"about_ca_system_score_gemma":0.0000688226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002972419,"about_ca_topic_score_gemma":0.00001205436,"domain_scores_codex":[0.9985113,0.00002308289,0.0002148696,0.000722747,0.00008212212,0.0004459344],"domain_scores_gemma":[0.9989206,0.0001274815,0.00008360587,0.0006386198,0.0001014714,0.0001282617],"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":[0.00003105179,0.00002155005,0.0003274947,0.0001910746,0.0001345774,0.00002178238,0.0001086924,0.9976921,0.00008104919,0.001127856,0.0001451363,0.000117618],"study_design_scores_gemma":[0.0003082667,0.00001869342,0.00007449751,0.0001377492,0.0002235621,0.000001145121,0.00009472445,0.9970233,0.0001161778,0.001375471,0.0001460673,0.0004802755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4667546,0.0001168648,0.5313389,0.000007401961,0.000573785,0.0001913937,0.00005316449,0.0002690891,0.0006947686],"genre_scores_gemma":[0.9966213,0.0001095178,0.0008957615,0.00001880593,0.0001553115,0.000001782012,0.00005832453,0.00006118792,0.002077972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5304432,"threshold_uncertainty_score":0.9998138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06322529920391909,"score_gpt":0.185945960739819,"score_spread":0.1227206615358999,"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."}}