{"id":"W4389469990","doi":"10.48550/arxiv.2312.02339","title":"Expressive Sign Equivariant Networks for Spectral Geometric Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Multidisciplinary University Research Initiative; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Equivariant map; Sign (mathematics); Sign language; Eigenvalues and eigenvectors; Computer science; Node (physics); Homogeneous space; Code (set theory); Link (geometry); Artificial intelligence; Mathematics; Theoretical computer science; Algebra over a field; Topology (electrical circuits); Pure mathematics; Programming language; Combinatorics; Linguistics; Physics; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003662495,0.0005260726,0.0005566678,0.0008165507,0.0003900252,0.0002310491,0.002833576,0.0004898111,0.00001164551],"category_scores_gemma":[0.0001692973,0.0006204745,0.0004934828,0.002688368,0.0001161065,0.0005364441,0.003286661,0.001501356,0.00004865353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002306518,"about_ca_system_score_gemma":0.0001151941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003599492,"about_ca_topic_score_gemma":0.00001176757,"domain_scores_codex":[0.9963762,0.0001880193,0.0003210897,0.00195431,0.0001451151,0.001015316],"domain_scores_gemma":[0.99674,0.0009671826,0.0005268001,0.001276675,0.0002076676,0.0002816939],"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":[0.00003893684,0.00002929973,0.0004544735,0.00003577369,0.00009027253,0.0004304594,0.0000504101,0.9301659,0.00001881609,0.06670839,0.0008596547,0.001117544],"study_design_scores_gemma":[0.0005246067,0.0001449687,0.0005809828,0.000106044,0.00005970807,0.000005055919,0.00003479725,0.9129854,0.00006602121,0.0844053,0.0004325651,0.0006545898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01012111,0.000162952,0.9855815,0.00009520466,0.001858772,0.0007673549,0.00001152609,0.001072277,0.0003293427],"genre_scores_gemma":[0.9859478,0.000402786,0.009483915,0.00007438846,0.0004383457,0.000009645189,0.00004531853,0.00007141704,0.003526347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9760975,"threshold_uncertainty_score":0.9996247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0976965443162144,"score_gpt":0.2104560134164799,"score_spread":0.1127594691002655,"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."}}