{"id":"W4380997161","doi":"10.1039/d2dd00133k","title":"By how much can closed-loop frameworks accelerate computational materials discovery?","year":2023,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency; Advanced Research Projects Agency - Energy; U.S. Department of Energy","keywords":"Workflow; Computer science; Task (project management); Automation; Selection (genetic algorithm); Loop (graph theory); Closed loop; Artificial intelligence; Machine learning; Distributed computing; Control engineering; Engineering; Systems engineering; Database","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005940697,0.000446591,0.000501189,0.0001652478,0.0003533784,0.01083575,0.0009795977,0.0002437841,0.0004759289],"category_scores_gemma":[0.00056518,0.00039048,0.0001153032,0.0006494976,0.0003883384,0.005324862,0.0006097239,0.0002901934,0.001362555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009919023,"about_ca_system_score_gemma":0.0001421365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000101578,"about_ca_topic_score_gemma":0.000008074449,"domain_scores_codex":[0.9964556,0.0001600096,0.0005178272,0.0009595967,0.0009730532,0.0009339085],"domain_scores_gemma":[0.9985148,0.0003435892,0.000312746,0.0005504888,0.00009485622,0.0001834626],"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":[0.00008256736,0.0001174912,0.001390523,0.0001002835,0.00001974515,0.00005890864,0.0002897341,0.006522318,0.950496,0.004367609,0.03599208,0.0005627144],"study_design_scores_gemma":[0.00226651,0.0005711241,0.03100223,0.000611608,0.00006241613,0.00009634983,0.001311265,0.008835679,0.8768595,0.06351721,0.01098099,0.003885112],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838709,0.00002700374,0.005431289,0.002652505,0.00206737,0.0003313708,0.004019696,0.0005615941,0.001038225],"genre_scores_gemma":[0.9872299,0.00001273748,0.0003867933,0.0007035606,0.0002886752,0.00006217252,0.001525541,0.00007398796,0.009716598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07363652,"threshold_uncertainty_score":0.9998547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01167997041459491,"score_gpt":0.2524485562295728,"score_spread":0.2407685858149779,"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."}}