{"id":"W4412754795","doi":"10.11159/iccste25.349","title":"Prediction of Strength and Ductility of Thin-Walled Steel Tubular Columns Using Physics-Informed Reinforcement Learning and Agentic Frameworks","year":2025,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Civil, Structural and Transportation Engineering","topic":"Concrete Corrosion and Durability","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Reinforcement; Ductility (Earth science); Materials science; Reinforcement learning; Composite material; Artificial intelligence; Computer science; Creep","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003828247,0.0005950834,0.0005172912,0.0005748358,0.0001867884,0.0004180721,0.0006472529,0.0008960552,0.0006280784],"category_scores_gemma":[0.001782997,0.0004820224,0.0004369052,0.0002358934,0.0005353155,0.0004730609,0.0003527945,0.0006620201,0.0001165843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005257818,"about_ca_system_score_gemma":0.0005136707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009193485,"about_ca_topic_score_gemma":0.01022757,"domain_scores_codex":[0.9999152,0.00002160271,0.000004023072,0.00002711024,0.00001722702,0.00001473874],"domain_scores_gemma":[0.998764,0.0008262949,0.0001424729,0.00004066935,0.0001480716,0.00007838685],"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":[0.00002089443,0.0000207959,0.0007647825,0.000005678554,0.000006318178,0.00001338794,0.000003826836,0.9968517,0.0004588897,0.000118961,0.00004749537,0.001687232],"study_design_scores_gemma":[9.033552e-7,0.00000230512,0.0001109476,2.248655e-7,4.252113e-7,6.228245e-7,4.410931e-7,0.9997413,0.0000696261,0.00006969673,0.000003076604,5.284095e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.801135,0.0001875532,0.1968059,0.0001761866,0.00002978353,0.00002767378,0.0001567166,0.0004133478,0.001067751],"genre_scores_gemma":[0.9958191,0.00001961725,0.003826361,0.000007548497,0.000004394006,0.000008397107,0.0000549195,0.00001071592,0.0002489632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009193485,"threshold_uncertainty_score":0.01827991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01482928046714469,"score_gpt":0.2285938028658175,"score_spread":0.2137645223986728,"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."}}