{"id":"W2989871076","doi":"10.48550/arxiv.1911.11098","title":"StructEdit: Learning Structural Shape Variations","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology; Dassault Systèmes La Fondation; National Science Foundation","keywords":"Encoding (memory); ENCODE; Computer science; Autoencoder; Decoding methods; Robustness (evolution); Artificial intelligence; Representation (politics); Pattern recognition (psychology); Shape analysis (program analysis); Feature vector; Active shape model; Space (punctuation); Abstraction; Encoder; Topology (electrical circuits); Theoretical computer science; Algorithm; Mathematics; Deep learning; Combinatorics; Segmentation","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":[0.001185974,0.002013734,0.001340697,0.001835853,0.00054168,0.001503491,0.004168272,0.002507548,0.004136415],"category_scores_gemma":[0.003361271,0.001143822,0.002504005,0.001482024,0.001229892,0.002346568,0.002329168,0.003220186,0.00265696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001567253,"about_ca_system_score_gemma":0.001011765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005876833,"about_ca_topic_score_gemma":0.01425578,"domain_scores_codex":[0.9991918,0.0001343836,0.00002636689,0.0003726099,0.0002095607,0.00006538427],"domain_scores_gemma":[0.9989889,0.0003793623,0.00006278937,0.0003866974,0.0001188741,0.00006344305],"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":[0.0003131489,0.0002397407,0.003056095,0.000311416,0.000298466,0.0002485187,0.0001322008,0.3760591,0.01850961,0.01114279,0.03761588,0.552073],"study_design_scores_gemma":[0.00002496487,0.00005781517,0.0004147211,0.00001426733,0.00001525052,0.0001150245,0.00001762463,0.9836214,0.004688937,0.007815465,0.003196056,0.00001848289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03995496,0.0009931067,0.9250032,0.0004779371,0.0002770692,0.0002125762,0.003746477,0.02630829,0.00302635],"genre_scores_gemma":[0.3517146,0.0007859516,0.6103072,0.0009126628,0.0001622605,0.0004267737,0.0219612,0.003176004,0.0105534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005876833,"threshold_uncertainty_score":0.0138377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03759352578148012,"score_gpt":0.1646498820120665,"score_spread":0.1270563562305864,"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."}}