{"id":"W4382317874","doi":"10.1609/aaai.v37i8.26102","title":"GENNAPE: Towards Generalized Neural Architecture Performance Estimators","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Architecture; Network architecture; Estimator; Graph; Machine learning; Time delay neural network; Theoretical computer science; Mathematics","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":[0.0003843954,0.0003530354,0.0003452503,0.0002649367,0.0003308396,0.0002343502,0.003120781,0.0001179446,0.00002927193],"category_scores_gemma":[0.0002340976,0.0002549706,0.0001923709,0.002412268,0.0002881698,0.0005429849,0.0007972809,0.0005414669,0.0001325015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003460979,"about_ca_system_score_gemma":0.00007307958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001319575,"about_ca_topic_score_gemma":0.000003717986,"domain_scores_codex":[0.9973121,0.00002421778,0.000585478,0.0006959443,0.000708391,0.000673921],"domain_scores_gemma":[0.9985013,0.00008499994,0.0003639481,0.0004927299,0.0004090393,0.0001479848],"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":[0.0000909345,0.0000643293,0.0005137582,0.00007135153,0.00002217752,0.000003220709,0.001069726,0.01204266,0.02842407,0.5394973,0.0005073519,0.4176931],"study_design_scores_gemma":[0.0000399216,0.0001877523,0.001172447,0.000125502,0.000008987591,0.0000150943,0.00006671184,0.6548672,0.2248497,0.1181478,0.0001815211,0.0003373616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9557005,0.00003576205,0.03105154,0.007495256,0.001350196,0.0006556734,0.000005963788,0.0007373028,0.002967877],"genre_scores_gemma":[0.9916105,0.00009212564,0.007408011,0.0004033115,0.0001103645,0.00004795566,0.000001093868,0.00002484774,0.0003018361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6428245,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06564785021917369,"score_gpt":0.2948797587371016,"score_spread":0.229231908517928,"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."}}