{"id":"W2770212906","doi":"10.1145/3130800.3130841","title":"Learning to group discrete graphical patterns","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Measure (data warehouse); Computer science; Granularity; Feature (linguistics); Artificial intelligence; Element (criminal law); Convolutional neural network; Pattern recognition (psychology); Noise (video); Encoding (memory); Context (archaeology); Key (lock); Deep learning; Group (periodic table); Theoretical computer science; Machine learning; Data mining; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001254334,0.0001736564,0.000174769,0.0002805541,0.0007397112,0.0001499471,0.0004873576,0.0001099178,0.00004679612],"category_scores_gemma":[0.0000315978,0.0001726522,0.0002285184,0.0001809204,0.00003944229,0.0001376008,0.000007223663,0.0005466517,0.00004435816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001465153,"about_ca_system_score_gemma":0.000002847006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007997057,"about_ca_topic_score_gemma":0.0003300987,"domain_scores_codex":[0.9991103,0.00002048096,0.0001703552,0.0002321804,0.0002020567,0.0002646107],"domain_scores_gemma":[0.9988862,0.0000496076,0.00002398941,0.000853785,0.00002799,0.0001584665],"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":[0.00003837677,0.0001413194,0.01177996,0.0001063229,0.000654514,0.00003308764,0.00114026,0.8438663,0.001362547,0.0005628814,0.0001498076,0.1401646],"study_design_scores_gemma":[0.001683771,0.0007588772,0.07006688,0.0005147414,0.0007664132,0.00002219948,0.0007868212,0.9053931,0.002708768,0.008505217,0.006329777,0.00246342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3100634,0.00001667151,0.6883466,0.0007489357,0.0002120528,0.0000566493,0.00001895201,0.0003229389,0.0002139095],"genre_scores_gemma":[0.9984022,0.0003117005,0.0009505459,0.0001157729,0.00004964272,0.00002725498,0.000007503517,0.00004240018,0.00009300501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6883388,"threshold_uncertainty_score":0.7040552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01649311156644022,"score_gpt":0.2519915800317465,"score_spread":0.2354984684653063,"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."}}