{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005263865,0.0003118257,0.0005063576,0.001105206,0.0002207621,0.0002188572,0.003179112,0.0004014205,0.00006601913],"category_scores_gemma":[0.0004066034,0.00031429,0.0004203581,0.004488311,0.0000780774,0.0004207328,0.003773577,0.0007842123,0.0001575797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001534374,"about_ca_system_score_gemma":0.00006948941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001438314,"about_ca_topic_score_gemma":0.000018961,"domain_scores_codex":[0.9975294,0.0001295066,0.0002404768,0.001439551,0.0001249077,0.0005360952],"domain_scores_gemma":[0.9972609,0.00072898,0.0003649034,0.001227085,0.0002309962,0.0001871502],"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":[0.00001116384,0.00004162015,0.008933236,0.00003001608,0.00009761701,0.00005261786,0.00001628098,0.9426873,4.61688e-7,0.03825917,0.0002214551,0.009649003],"study_design_scores_gemma":[0.0002612909,0.0001027299,0.003944226,0.00002098853,0.0001049026,0.00000205653,0.00002342498,0.9793802,0.000004234595,0.01272967,0.003005664,0.0004205734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02469463,0.0004656072,0.9729046,0.00006385848,0.0005682174,0.0002864757,0.000009945386,0.0002273989,0.0007792119],"genre_scores_gemma":[0.9914728,0.0006276639,0.003771464,0.0001161657,0.0001056968,0.000001979705,0.00006239368,0.00001161048,0.003830169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9691332,"threshold_uncertainty_score":0.9999309,"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."}}