{"id":"W2927780566","doi":"10.48550/arxiv.1904.00438","title":"Understanding Neural Architecture Search Techniques","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Computer science; Controller (irrigation); Architecture; Computation; Graph; Artificial neural network; Artificial intelligence; Similarity (geometry); Machine learning; ENCODE; Theoretical computer science; Algorithm","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004556911,0.0004264007,0.0004190188,0.0005309536,0.0002583978,0.0002542203,0.003224765,0.0004453201,0.00003394737],"category_scores_gemma":[0.00005477352,0.000481328,0.0002601032,0.0007062583,0.000124964,0.0004063957,0.005453492,0.00231251,0.00005922188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006997414,"about_ca_system_score_gemma":0.0002522416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001198188,"about_ca_topic_score_gemma":0.00001354888,"domain_scores_codex":[0.9972098,0.0003789067,0.0002013096,0.001431462,0.0002050517,0.0005734257],"domain_scores_gemma":[0.997616,0.000250292,0.0002168044,0.001659605,0.00009504851,0.0001622748],"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":[0.00001807016,0.00001822533,0.00174234,0.00008373997,0.00004311931,0.0002218114,0.000267348,0.7786193,0.00002392142,0.2182544,0.0001045923,0.0006030382],"study_design_scores_gemma":[0.0002458206,0.00005712083,0.0001863451,0.0001316683,0.00003188549,0.00001332158,0.0001104934,0.9303828,0.0001142891,0.06792083,0.0002438594,0.00056152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01493992,0.00002824138,0.9756473,0.0004132811,0.0008037321,0.0004379595,0.000005558939,0.0008563079,0.006867669],"genre_scores_gemma":[0.9849883,0.00003438904,0.01350179,0.0001199178,0.0001608937,6.667997e-7,0.00001187581,0.00003854029,0.001143664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9700484,"threshold_uncertainty_score":0.9999892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1685196417328178,"score_gpt":0.2283406863077185,"score_spread":0.05982104457490073,"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."}}