{"id":"W3036014493","doi":"10.48550/arxiv.2006.10187","title":"TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Point cloud; Autoencoder; Topology (electrical circuits); Computer science; Network topology; Cloud computing; Theoretical computer science; Graph; Artificial intelligence; Point (geometry); Deep learning; Mathematics; Geometry; Computer network; Combinatorics","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":[0.0006390224,0.001562075,0.0007667153,0.000652609,0.0002730362,0.0008131259,0.002054549,0.001478201,0.003396275],"category_scores_gemma":[0.002619889,0.0006541936,0.0007173215,0.0007706643,0.0006264461,0.001943006,0.001326624,0.002351033,0.001858747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000782863,"about_ca_system_score_gemma":0.000762275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007603646,"about_ca_topic_score_gemma":0.01002788,"domain_scores_codex":[0.9997271,0.00003788612,0.00001235163,0.00009938246,0.00008252904,0.00004078364],"domain_scores_gemma":[0.9994792,0.0001780769,0.00004406337,0.0001380313,0.0001237964,0.00003681243],"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":[0.0001458573,0.0001205728,0.001398224,0.0001050062,0.0001089834,0.0001272735,0.00005131609,0.7172201,0.009261635,0.006402582,0.01331072,0.2517478],"study_design_scores_gemma":[0.000003882771,0.00001314206,0.00007315144,0.000003778991,0.000002834834,0.00001289772,0.000003879721,0.9962155,0.001561783,0.001644818,0.0004614433,0.000002862048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01817296,0.0002572185,0.9724984,0.0002214285,0.0001018804,0.00005326127,0.0004958655,0.006771799,0.001427144],"genre_scores_gemma":[0.4652616,0.0004948953,0.5175409,0.0005915613,0.0001171952,0.0003096927,0.006348657,0.001011278,0.008324177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007603646,"threshold_uncertainty_score":0.01511878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05728296883477053,"score_gpt":0.2000661662235008,"score_spread":0.1427831973887303,"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."}}