{"id":"W4417057229","doi":"10.1016/j.xcrp.2025.103019","title":"Accelerated inorganic materials design with generative AI agents","year":2025,"lang":"en","type":"article","venue":"Cell Reports Physical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"ACT-X; Japan Science and Technology Agency; University of Tokyo; Japan Science and Technology Corporation","keywords":"Generative grammar; Generative Design; Property (philosophy); Generative model; Variety (cybernetics)","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002169342,0.0003525745,0.0004572682,0.0001810922,0.0008732053,0.00115067,0.001068147,0.00006116356,0.0009282836],"category_scores_gemma":[0.0003878413,0.0002498993,0.00003857285,0.001946136,0.001485149,0.000990347,0.0004922818,0.0001824899,0.0002383547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001978287,"about_ca_system_score_gemma":0.001149352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001430437,"about_ca_topic_score_gemma":0.000002320418,"domain_scores_codex":[0.9958493,0.0002647187,0.0005298711,0.00138763,0.001103577,0.0008649598],"domain_scores_gemma":[0.9979067,0.0001144765,0.0004176689,0.0009156753,0.000409796,0.0002356892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003090071,0.0001472024,0.0002737791,0.00002254743,0.000002281805,0.0001023766,0.0003385272,0.004766609,0.9931375,0.0004450712,0.0006331502,0.0001000046],"study_design_scores_gemma":[0.0001692322,0.0001460639,0.00305494,0.0000454396,0.00001592651,0.00003558056,0.00003257921,0.0031017,0.9909109,0.001788956,0.0003799586,0.0003186801],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712262,0.000009515139,0.02169328,0.0002511446,0.001157706,0.0005506552,0.000004118242,0.0002325832,0.004874771],"genre_scores_gemma":[0.9908287,0.000001698062,0.006748867,0.0007609823,0.000124681,0.0000602294,0.000003605076,0.00002020299,0.001451013],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0196025,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01757417288718109,"score_gpt":0.294138645586083,"score_spread":0.2765644726989019,"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."}}