{"id":"W4388088420","doi":"10.1557/s43578-023-01194-4","title":"Accelerating training of MLIPs through small-cell training","year":2023,"lang":"en","type":"article","venue":"Journal of materials research/Pratt's guide to venture capital sources","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"U.S. Naval Research Laboratory","keywords":"Training (meteorology); Materials 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01972268,0.0004565376,0.001245728,0.0007805279,0.0006351217,0.001113893,0.002289457,0.000255843,0.002536556],"category_scores_gemma":[0.004956888,0.0003707213,0.000231898,0.001278289,0.0005009018,0.0009127698,0.0008588341,0.0006939552,0.0004935003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552237,"about_ca_system_score_gemma":0.0006014912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002670485,"about_ca_topic_score_gemma":0.00002306918,"domain_scores_codex":[0.9910403,0.001882433,0.002353779,0.0006825511,0.002499824,0.001541047],"domain_scores_gemma":[0.9952505,0.001133829,0.001487644,0.0005963966,0.001063984,0.0004676584],"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":[0.0002075675,0.0000666059,0.00007358483,0.0002619442,0.00002440473,0.0001665571,0.03148283,0.008707588,0.953496,0.0003418207,0.004653762,0.0005173769],"study_design_scores_gemma":[0.000885047,0.001227809,0.0008718105,0.0006991821,0.0000335,0.0002083688,0.02341626,0.0001205923,0.9567747,0.001513758,0.01376841,0.0004806267],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934341,0.0003601985,0.0004158802,0.001463837,0.002388263,0.0004814787,0.00008708868,0.0001218227,0.001247304],"genre_scores_gemma":[0.9772485,0.00008950341,0.019853,0.0001692272,0.001738016,0.00003025497,0.00001083539,0.00009857371,0.0007621126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01943712,"threshold_uncertainty_score":0.9999231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1323820890533287,"score_gpt":0.3809918597663554,"score_spread":0.2486097707130266,"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."}}