{"id":"W7083179284","doi":"10.18434/mds2-3172","title":"JARVIS-Leaderboard: Large Scale Benchmark of Materials Design Methods","year":2024,"lang":"en","type":"dataset","venue":"National Institute of Standards and Technology (NIST)","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scale (ratio); Benchmark (surveying); Design methods; Stability (learning theory); Context (archaeology)","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"],"consensus_categories":[],"category_scores_codex":[0.002195656,0.0002874682,0.0006382578,0.0005294378,0.0001321556,0.00006329826,0.001010308,0.0008197263,0.0001222118],"category_scores_gemma":[0.0007223142,0.0002607686,0.00007120127,0.0006836888,0.0006486782,0.0001693778,0.0007671952,0.0004084476,0.00000885666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008197816,"about_ca_system_score_gemma":0.00093384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000126471,"about_ca_topic_score_gemma":0.00001045029,"domain_scores_codex":[0.9978096,0.0000703308,0.0006082254,0.0005861063,0.0006521189,0.0002735584],"domain_scores_gemma":[0.99792,0.0001040036,0.0003785992,0.0005069614,0.001043152,0.00004727825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001652607,0.00007730337,0.000002401419,0.0008074963,0.0001319493,0.0000254768,0.00002123498,0.00001950314,0.002318474,0.06371103,0.9311951,0.001673519],"study_design_scores_gemma":[0.000251167,0.0001037839,0.000003686567,0.00025323,0.00004418932,0.00005875334,0.00002054205,0.0001274317,0.03983141,0.06526964,0.8938264,0.0002098152],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.00005256018,0.00127171,0.07600617,0.002363112,0.0009115677,0.0002436004,0.9172089,0.00009862234,0.001843726],"genre_scores_gemma":[0.006847369,0.001373579,0.5451163,0.000251001,0.0003189092,0.0001771747,0.4451243,0.00002012903,0.000771249],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.4720847,"threshold_uncertainty_score":0.9999844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01982016710292146,"score_gpt":0.3245723505298443,"score_spread":0.3047521834269228,"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."}}