{"id":"W4385671288","doi":"10.1039/d3dd00113j","title":"14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon","year":2023,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":202,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"NCCR Catalysis; Center for Hierarchical Materials Design; Fédération Wallonie-Bruxelles; High Energy Physics; Francis Crick Institute; National Institute of General Medical Sciences; Grantham Foundation for the Protection of the Environment; Engineering and Physical Sciences Research Council; Consejo Superior de Investigaciones Científicas; National Center for Advancing Translational Sciences; Medical Research Council; National Institute of Standards and Technology; Office of Science; H2020 Marie Skłodowska-Curie Actions; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Agencia Estatal de Investigación; Cancer Research UK; Wellcome Trust; U.S. Department of Energy; European Commission; Esperantic Studies Foundation; Horizon 2020 Framework Programme; National Science Foundation; National Institutes of Health; U.S. Department of Commerce","keywords":"Reflection (computer programming); Computer science; Chemistry; Nanotechnology; Materials science; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.00009398487,0.00007747153,0.00008655737,0.00006518375,0.00002422927,0.0001350989,0.00005958938,0.000037109,0.000001990622],"category_scores_gemma":[0.00004778997,0.00006811508,0.00001476828,0.0002915734,0.00005392191,0.0003632127,0.00001383028,0.00003935555,0.000002313772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000043368,"about_ca_system_score_gemma":0.00002750761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000584535,"about_ca_topic_score_gemma":0.000002824921,"domain_scores_codex":[0.9994709,9.770461e-7,0.00007516256,0.0001154129,0.0001694274,0.0001681138],"domain_scores_gemma":[0.999827,0.00001082603,0.000009743181,0.00008965948,0.00001392439,0.00004887217],"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":[0.000007591535,0.00002501729,0.000007913953,0.0005008443,0.000008268491,0.000001377145,0.001056939,0.00110072,0.9915775,0.000240905,0.0006084753,0.004864417],"study_design_scores_gemma":[0.000286873,0.00003674516,0.001331299,0.0001597323,0.000008036016,0.000004744979,0.0006664697,0.03644171,0.9595902,0.0005244892,0.0006969747,0.0002527333],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966155,0.00002408588,0.000929079,0.0001278155,0.0001361117,0.00005032331,0.0003281364,0.0001554179,0.001633472],"genre_scores_gemma":[0.9993005,0.00003092984,0.00002119974,0.000007474869,0.0000375614,0.00001149302,0.00009784222,0.00001322304,0.0004797551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03534099,"threshold_uncertainty_score":0.2777652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01335407115510984,"score_gpt":0.2290966937165547,"score_spread":0.2157426225614449,"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."}}