{"id":"W7083024938","doi":"10.1016/j.engappai.2025.112273","title":"Structural design through reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Reinforcement learning; Topology optimization; Scratch; Interface (matter); Active learning (machine learning); Baseline (sea); Space (punctuation); Sample (material)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001663589,0.00009169954,0.0001011926,0.00006246356,0.0001033879,0.00003603899,0.0005811546,0.0000445663,0.00001679413],"category_scores_gemma":[0.0001342207,0.00009669411,0.00003673363,0.0005979298,0.00003331252,0.0001159968,0.0001298937,0.0001329056,0.00001504809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002072878,"about_ca_system_score_gemma":0.00003340765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001416019,"about_ca_topic_score_gemma":2.110313e-7,"domain_scores_codex":[0.9992384,0.00001099522,0.0002867781,0.0002109166,0.00009564908,0.0001572179],"domain_scores_gemma":[0.999302,0.0001371828,0.00006482461,0.0003621212,0.0001117151,0.00002213612],"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":[9.335824e-7,0.000004476334,0.000005659708,0.00001820157,0.00000609061,1.437467e-7,0.0001230322,0.6177582,0.004065135,0.3621963,0.00001449893,0.01580733],"study_design_scores_gemma":[0.000006228913,0.00001239155,0.00001340872,0.00001876054,0.000002843324,9.206217e-7,0.00004555915,0.726983,0.2340331,0.03400518,0.004801931,0.00007668339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002299567,0.00007625229,0.9964153,0.0005010194,0.00007391387,0.0001814407,1.548211e-7,0.0001453762,0.002376561],"genre_scores_gemma":[0.8413839,0.000008309737,0.1580741,0.00001836724,0.00001982846,0.00007673494,0.000001642035,0.000001407192,0.0004156764],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8411539,"threshold_uncertainty_score":0.3943071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02820441540823576,"score_gpt":0.2670159940120866,"score_spread":0.2388115786038508,"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."}}