{"id":"W4413820841","doi":"10.1088/2632-2153/ae011a","title":"32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McGill University","funders":"Material Measurement Laboratory; Office of Advanced Cyberinfrastructure","keywords":"Scientific discovery; Automation; Nanotechnology; Data science; Engineering; Computer science; Engineering ethics; Chemistry; Materials science; Mechanical engineering; Psychology; Cognitive science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008264982,0.001275841,0.0006386367,0.003472821,0.001630931,0.003365459,0.00222167,0.002359359,0.01229038],"category_scores_gemma":[0.01607684,0.0008446476,0.002272344,0.005549967,0.001961533,0.005048807,0.00492915,0.002353943,0.005901475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002206634,"about_ca_system_score_gemma":0.002687445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00329861,"about_ca_topic_score_gemma":0.004316448,"domain_scores_codex":[0.9937371,0.002873706,0.0004044415,0.0007250792,0.002021992,0.0002376048],"domain_scores_gemma":[0.990494,0.005821991,0.0005823565,0.001625818,0.001207693,0.0002681903],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002068453,0.0002399247,0.003905564,0.003381975,0.0001349505,0.0008758128,0.002470757,0.01467723,0.006957844,0.2075641,0.08048059,0.6791043],"study_design_scores_gemma":[0.00004503392,0.00009996243,0.00178001,0.0008414154,0.00006185908,0.0008567165,0.0004653143,0.03546378,0.01053113,0.1054492,0.8443016,0.0001039194],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01450052,0.02425348,0.8452422,0.009370496,0.0007831265,0.0008857169,0.003220393,0.01666514,0.08507888],"genre_scores_gemma":[0.07014026,0.01711279,0.8819948,0.001990805,0.0002651593,0.001050256,0.003768379,0.001804589,0.02187291],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.991735,"threshold_uncertainty_score":0.04370993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01150832997095216,"score_gpt":0.2825833235286461,"score_spread":0.2710749935576939,"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."}}