{"id":"W4376870215","doi":"10.1016/j.engappai.2023.106413","title":"A hybrid deep learning approach for the design of 2D low porosity auxetic metamaterials","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Cellular and Composite Structures","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Siemens (Canada); McGill University","funders":"","keywords":"Computer science; Generative Design; Inverse; Metamaterial; Set (abstract data type); Optimal design; Surrogate model; Engineering design process; Computer engineering; Machine learning; Mechanical engineering; Materials 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":[],"consensus_categories":[],"category_scores_codex":[0.0003132224,0.0001276616,0.0001935073,0.0001162541,0.00008172305,0.00002333808,0.0003167745,0.00003810782,0.00001129028],"category_scores_gemma":[0.00005243604,0.0001143017,0.00008637627,0.0003745144,0.00004659301,0.00003389004,0.00003368405,0.00009660421,0.000008408125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001453764,"about_ca_system_score_gemma":0.00000781494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001035174,"about_ca_topic_score_gemma":3.114073e-7,"domain_scores_codex":[0.9991855,0.00001342902,0.0003573654,0.000143771,0.0001157564,0.0001841885],"domain_scores_gemma":[0.9992619,0.0003040648,0.00005376459,0.0002836465,0.00006537958,0.00003129926],"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":[0.000005262594,0.000008915756,0.000001241492,0.0001223237,0.00003367264,6.249184e-8,0.0001279683,0.7481364,0.2359875,0.002777872,0.000008239532,0.01279053],"study_design_scores_gemma":[0.000007435151,0.00001049194,0.00002081284,0.00000562288,0.00002210062,8.564915e-7,0.00004353431,0.5622012,0.4368731,0.0006587192,0.00009140269,0.00006474091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02400616,0.0002980135,0.9747133,0.000007056089,0.00009234551,0.0005956664,0.00001383497,0.0002496834,0.00002390723],"genre_scores_gemma":[0.9737374,0.00007209626,0.02567298,0.000001107992,0.00006882675,0.0003788334,0.00002700407,0.00002995959,0.00001181427],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9497312,"threshold_uncertainty_score":0.4661086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163191681289786,"score_gpt":0.238681376567787,"score_spread":0.2170494597548892,"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."}}