{"id":"W4376123182","doi":"10.48550/arxiv.2305.05577","title":"FAENet: Frame Averaging Equivariant GNN for Materials Modeling","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Equivariant map; Scalability; Computer science; Invariant (physics); Homogeneous space; Frame (networking); Theoretical computer science; Representation (politics); Simple (philosophy); Algorithm; Artificial intelligence; Distributed computing; Mathematics; Pure mathematics; Geometry","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":[0.0007386344,0.001489921,0.0008858302,0.0009686513,0.000529297,0.0008889463,0.002813734,0.001847086,0.00540567],"category_scores_gemma":[0.002055467,0.0004482369,0.001521066,0.0007649241,0.0006259176,0.001485995,0.001423698,0.001866949,0.002126995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044764,"about_ca_system_score_gemma":0.0009786162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006765491,"about_ca_topic_score_gemma":0.01125196,"domain_scores_codex":[0.9996697,0.00006976043,0.00001305582,0.0001087296,0.0001097132,0.00002900685],"domain_scores_gemma":[0.9997205,0.00008918328,0.00002659599,0.00009091088,0.00005045478,0.00002235789],"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":[0.0001422499,0.00009518317,0.0009817767,0.0002678191,0.0001362916,0.0001666395,0.00007667075,0.7314866,0.01019512,0.0609941,0.03920982,0.1562477],"study_design_scores_gemma":[0.000007499576,0.000009973352,0.00005602449,0.000006429922,0.000004867703,0.00001789075,0.000004343585,0.976171,0.001222281,0.01799514,0.004497972,0.000006638732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01075892,0.0004498217,0.9665242,0.0003425776,0.0002416945,0.00008015731,0.00229447,0.01506012,0.004248022],"genre_scores_gemma":[0.2284573,0.0005372518,0.7434109,0.0006865437,0.000199636,0.0004583955,0.01162511,0.005227215,0.009397758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006765491,"threshold_uncertainty_score":0.01808375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.153828673311559,"score_gpt":0.2338576904466584,"score_spread":0.08002901713509938,"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."}}