{"id":"W2897818259","doi":"10.48550/arxiv.1810.05749","title":"Graph HyperNetworks for Neural Architecture Search","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Architecture; Artificial neural network; Graph; Network architecture; Network topology; Artificial intelligence; Task (project management); Random search; Topological graph theory; Machine learning; Theoretical computer science; Algorithm; Computer network; Engineering","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":[0.0001705881,0.0003716961,0.0003229978,0.00023107,0.0003302018,0.0001195484,0.003013172,0.0003138715,0.00001147015],"category_scores_gemma":[0.00001737611,0.0004126143,0.0003136502,0.0008740821,0.000197855,0.0002169904,0.002389902,0.0008170378,0.00004269215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001063402,"about_ca_system_score_gemma":0.0001014224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001448854,"about_ca_topic_score_gemma":0.00002647712,"domain_scores_codex":[0.9974279,0.0001061323,0.0001972046,0.001541005,0.0001045885,0.0006231822],"domain_scores_gemma":[0.9972427,0.0002872209,0.0001773795,0.001814157,0.0002438625,0.0002346692],"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":[0.00003373799,0.00004268741,0.0002761056,0.00003794633,0.00004447347,0.00002764122,0.0000798404,0.868533,0.00001842971,0.1253596,0.001455631,0.004090885],"study_design_scores_gemma":[0.0002829052,0.0000693647,0.0002247975,0.00002985326,0.00003117682,0.000007710993,0.000007013505,0.7889608,0.00006755559,0.207595,0.002325318,0.000398521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0577599,0.00008264127,0.9392424,0.000435661,0.0005544072,0.0008747032,0.00002711008,0.0004278862,0.0005952758],"genre_scores_gemma":[0.9741484,0.00008785768,0.02384712,0.0002682646,0.0004914653,0.00001205711,0.00004139089,0.00003691105,0.001066535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9163885,"threshold_uncertainty_score":0.9998326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0792400169802236,"score_gpt":0.2173487636365504,"score_spread":0.1381087466563268,"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."}}