{"id":"W4402507667","doi":"10.1039/d4fd00153b","title":"Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science","year":2024,"lang":"en","type":"article","venue":"Faraday Discussions","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Structural Genomics Consortium; Vector Institute; University of Toronto","funders":"Canada First Research Excellence Fund; King Abdullah University of Science and Technology; University of Toronto","keywords":"Perspective (graphical); Field (mathematics); Computer science; Diversity (politics); Maturity (psychological); Artificial intelligence; Chemistry; Data science; Sociology; Psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007381599,0.0002621877,0.0003218322,0.0003692283,0.0007342141,0.002798259,0.001032893,0.0001249641,0.0007232362],"category_scores_gemma":[0.002828471,0.000176196,0.00004569883,0.001771977,0.001037623,0.0005551787,0.0005843056,0.0002994704,0.0001361888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002279945,"about_ca_system_score_gemma":0.0005293306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001249099,"about_ca_topic_score_gemma":0.00002721237,"domain_scores_codex":[0.9960502,0.000210815,0.0004409925,0.001218266,0.0009613098,0.00111836],"domain_scores_gemma":[0.9983929,0.0004626181,0.00005835577,0.0005428102,0.0001401434,0.0004031869],"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":[0.00007376686,0.00002778812,0.000009103326,0.0001220983,0.000001403122,0.00001317405,0.001375716,0.0004111797,0.985871,0.006343779,0.0004594021,0.005291552],"study_design_scores_gemma":[0.00006665055,0.0001291327,0.0002510014,0.0003164935,0.000007377639,0.00002495456,0.0006943737,0.002700533,0.9630931,0.02890399,0.003467595,0.0003447734],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9605402,0.0001342872,0.02046387,0.01300427,0.004218405,0.0009765257,0.0002322571,0.0001595898,0.0002705405],"genre_scores_gemma":[0.988026,0.00001022336,0.01066801,0.0000467995,0.0008445074,0.0001860319,0.00000790075,0.00003290328,0.0001775976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02748577,"threshold_uncertainty_score":0.998237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04662916291121966,"score_gpt":0.3886794174781502,"score_spread":0.3420502545669305,"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."}}