{"id":"W4416018545","doi":"10.48550/arxiv.2511.03112","title":"Accelerating inverse materials design using generative diffusion models with reinforcement learning","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Property (philosophy); Computation; Workflow; Reinforcement learning; Inverse; Diffusion","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0007570808,0.0009238841,0.0007490198,0.0004999969,0.0003708173,0.0008526816,0.001097156,0.001193684,0.003326931],"category_scores_gemma":[0.001962357,0.0006737184,0.001023572,0.000347371,0.0008644497,0.000819604,0.001051417,0.00149016,0.0007094611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009087455,"about_ca_system_score_gemma":0.00101645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002343041,"about_ca_topic_score_gemma":0.004661413,"domain_scores_codex":[0.9997568,0.00006739565,0.000009535191,0.00006164505,0.0000755615,0.00002914328],"domain_scores_gemma":[0.9992225,0.0004943128,0.00007365681,0.00009433166,0.00007165953,0.0000435598],"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":[0.00003122411,0.00004409933,0.0004946709,0.00007327036,0.00002522609,0.00004583161,0.00002671757,0.9535583,0.004365803,0.00894171,0.0009927831,0.03140028],"study_design_scores_gemma":[0.000006720099,0.000009297566,0.00001633575,0.00000296786,0.000002502127,0.000006093668,0.00000226411,0.9956449,0.0007348152,0.003188656,0.0003832608,0.000002175204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02393078,0.0003874284,0.9690452,0.0002900808,0.00005652017,0.00005005114,0.00007616073,0.001514416,0.004649329],"genre_scores_gemma":[0.5698746,0.0003016556,0.4243578,0.0002792668,0.00003767309,0.0002104455,0.0002550006,0.0004521958,0.004231236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003326931,"threshold_uncertainty_score":0.01112968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.122121986936091,"score_gpt":0.3095336895479037,"score_spread":0.1874117026118127,"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."}}