{"id":"W4396706898","doi":"10.1038/s41524-024-01259-w","title":"JARVIS-Leaderboard: a large scale benchmark of materials design methods","year":2024,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"National Institute of Standards and Technology; U.S. Department of Energy; National Science Foundation","keywords":"Benchmarking; Benchmark (surveying); Computer science; NIST; Computer engineering; Set (abstract data type); Theoretical computer science; Data science; Data mining; Computational 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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007888664,0.0004348866,0.0008471722,0.0003321956,0.0002306463,0.0008908673,0.0008133636,0.0001912828,0.01971705],"category_scores_gemma":[0.0004409043,0.0003812993,0.0001052539,0.0004690868,0.0003101804,0.0005823757,0.0003529914,0.0001156139,0.001338749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008979062,"about_ca_system_score_gemma":0.0003103785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008164148,"about_ca_topic_score_gemma":0.00000126606,"domain_scores_codex":[0.9940515,0.00210242,0.001333872,0.000932646,0.0008708477,0.0007087094],"domain_scores_gemma":[0.9975744,0.001150031,0.0003983811,0.0004695174,0.0002549196,0.0001527016],"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":[0.0001019738,0.00007530825,0.0000116708,0.0004840589,0.00002130945,0.00001631137,0.0006923506,0.01399399,0.9751688,0.007970601,0.001182771,0.0002808354],"study_design_scores_gemma":[0.0003259199,0.0001507645,0.0009660095,0.0002961647,0.00004809177,0.00006760409,0.00007085296,0.007494932,0.9660183,0.02269043,0.001448168,0.0004227439],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5722548,0.0002081493,0.4206299,0.0002867607,0.004738196,0.0005116496,0.0005646204,0.0003822966,0.0004236171],"genre_scores_gemma":[0.5574328,0.000005363363,0.4416534,0.0001527554,0.000354612,0.00007456386,0.00009514549,0.00005354279,0.0001778222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02102344,"threshold_uncertainty_score":0.9998639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02412037443777965,"score_gpt":0.3478499076356072,"score_spread":0.3237295331978276,"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."}}