{"id":"W2947685135","doi":"10.14288/1.0384585","title":"Incidence Networks for Geometric Deep Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Incidence (geometry); Polytope; Equivariant map; Pooling; Node (physics); Invariant (physics); Enhanced Data Rates for GSM Evolution; Mathematics; Decomposition; Tensor decomposition; Variety (cybernetics); Tensor (intrinsic definition); Computer science; Combinatorics; Pure mathematics; Artificial intelligence; Geometry; Physics","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":[0.001113558,0.00150018,0.0006508937,0.00193967,0.0006260134,0.002015851,0.001583528,0.001147471,0.006686159],"category_scores_gemma":[0.005917806,0.0006310422,0.0009365536,0.002180032,0.00140222,0.004251873,0.002283817,0.003250132,0.002230961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002100359,"about_ca_system_score_gemma":0.0009177611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003586285,"about_ca_topic_score_gemma":0.00665211,"domain_scores_codex":[0.9991655,0.0002253301,0.00004447032,0.0002159029,0.0002723989,0.000076371],"domain_scores_gemma":[0.9984882,0.00053899,0.0002132931,0.0004070551,0.0002566084,0.00009576658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001237413,0.0001165071,0.002678342,0.0003077038,0.0001200946,0.000106778,0.000165664,0.2409575,0.00417337,0.4399895,0.0273184,0.2839424],"study_design_scores_gemma":[0.000007196185,0.0000265135,0.0004752674,0.00004441518,0.00001650118,0.00005674128,0.00003462738,0.6015401,0.002016283,0.3833922,0.01237273,0.00001743806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01001669,0.001134997,0.9793099,0.0009912897,0.0001179466,0.00005659686,0.001383294,0.00164347,0.005345776],"genre_scores_gemma":[0.494639,0.005130566,0.4702902,0.0009594391,0.0006017086,0.0005165648,0.01074778,0.0009654653,0.01614941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006686159,"threshold_uncertainty_score":0.02236742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05613920351421213,"score_gpt":0.1918339605509961,"score_spread":0.135694757036784,"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."}}