{"id":"W4403929272","doi":"10.48550/arxiv.2410.03989","title":"Symmetry From Scratch: Group Equivariance as a Supervised Learning Task","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Mathematics Education and Teaching Techniques","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Resources Canada; Alliance de recherche numérique du Canada","keywords":"Scratch; Symmetry (geometry); Task (project management); Group (periodic table); Computer science; Mathematics; Artificial intelligence; Physics; Geometry; Engineering; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003617874,0.0007439609,0.0008505272,0.0005499413,0.0007038678,0.001326672,0.00192501,0.001145361,0.003907736],"category_scores_gemma":[0.01300356,0.0004365732,0.001180116,0.0005816219,0.00243124,0.003539206,0.003468643,0.003662149,0.001047209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009980358,"about_ca_system_score_gemma":0.001483424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000863298,"about_ca_topic_score_gemma":0.001373874,"domain_scores_codex":[0.9978957,0.0009690843,0.00009713513,0.0005515674,0.0003599557,0.0001264718],"domain_scores_gemma":[0.993257,0.002537184,0.0005103106,0.003075477,0.0003795231,0.0002404623],"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":[0.0003590036,0.0003762482,0.005856386,0.0003269304,0.0001674529,0.0002927865,0.0007678317,0.1061534,0.01369487,0.5673288,0.01199021,0.2926862],"study_design_scores_gemma":[0.00003986017,0.0001092599,0.0006273632,0.00003309347,0.00002502158,0.00007604659,0.0000732869,0.4064223,0.006584203,0.5809337,0.005054137,0.0000217723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04303003,0.000117767,0.9501625,0.0008979319,0.00006767231,0.00009339784,0.0002188584,0.001041518,0.004370415],"genre_scores_gemma":[0.6626937,0.0002191985,0.3282379,0.0005692808,0.0001449437,0.0003089148,0.00098436,0.0005651941,0.006276408],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003907736,"threshold_uncertainty_score":0.01913333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09563825311457648,"score_gpt":0.2607815936514705,"score_spread":0.165143340536894,"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."}}