{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001159833,0.001386881,0.0008363453,0.001854962,0.0007188267,0.001286212,0.001877409,0.001792107,0.00794932],"category_scores_gemma":[0.008595533,0.0008163704,0.001033374,0.00145884,0.001073295,0.003063032,0.001298076,0.002731903,0.00150744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001740566,"about_ca_system_score_gemma":0.001311292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005271148,"about_ca_topic_score_gemma":0.01186994,"domain_scores_codex":[0.9993741,0.0002417709,0.00003474007,0.0001730222,0.0001253149,0.00005104137],"domain_scores_gemma":[0.9977584,0.001445,0.0001816,0.0003055219,0.0002238805,0.00008556453],"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":[0.0001147303,0.00006399723,0.001388373,0.0002316336,0.0001107602,0.00009763317,0.00006975287,0.7854698,0.001407481,0.07155575,0.009558326,0.1299318],"study_design_scores_gemma":[0.00001776376,0.00001984734,0.0001062248,0.00002205419,0.00001141307,0.00002056649,0.00001068176,0.9167305,0.0004392716,0.08059883,0.002014902,0.000008029635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02547021,0.002173442,0.9598275,0.001123584,0.0001652396,0.0001248724,0.0007857897,0.003006153,0.007323231],"genre_scores_gemma":[0.4960549,0.00190956,0.4864444,0.0009131429,0.000243386,0.0007495909,0.00288889,0.0009682534,0.009827944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00794932,"threshold_uncertainty_score":0.02659315,"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."}}