{"id":"W2793173694","doi":"10.48550/arxiv.1803.05827","title":"Local Spectral Graph Convolution for Point Set Feature Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Pooling; Graph; Computer science; Pattern recognition (psychology); Artificial intelligence; Spectral clustering; Point cloud; Feature (linguistics); Segmentation; Convolution (computer science); Cluster analysis; Feature learning; k-nearest neighbors algorithm; Nearest neighbor graph; Point (geometry); Theoretical computer science; Mathematics; Artificial neural network","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":[0.0001592562,0.0003011974,0.0003353705,0.000257459,0.0001472075,0.00004305705,0.0002938863,0.0004085343,0.00004747005],"category_scores_gemma":[0.00001621958,0.0003613492,0.0004071657,0.0002617808,0.00009357437,0.0000859971,0.0001350268,0.0007177422,0.00005174357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002303101,"about_ca_system_score_gemma":0.00003673961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005182211,"about_ca_topic_score_gemma":0.00005654089,"domain_scores_codex":[0.9988717,0.00003903308,0.0001340122,0.000543089,0.00005558056,0.0003566033],"domain_scores_gemma":[0.9993101,0.0000375029,0.00007129459,0.0003444022,0.0001189748,0.0001177575],"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":[0.00002489923,0.000009795311,0.0003366575,0.0001320063,0.000236675,0.00001985831,0.000102726,0.9959797,0.00004002442,0.0007505923,0.00221692,0.0001501228],"study_design_scores_gemma":[0.0003169407,0.00004004495,0.00006360924,0.00008974671,0.0002910651,0.000001962338,0.0002048476,0.9872928,0.0002223268,0.01054453,0.0005348594,0.0003973131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2818622,0.0001126318,0.7164189,0.00002964533,0.0002977987,0.0001272013,0.00003830593,0.0004090909,0.0007042706],"genre_scores_gemma":[0.9974201,0.0002182205,0.0005135424,0.00001409709,0.0002159044,0.00000121122,0.0002112848,0.00004776554,0.001357863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7159053,"threshold_uncertainty_score":0.9998838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03903675356036479,"score_gpt":0.1728643131250985,"score_spread":0.1338275595647337,"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."}}