{"id":"W4392124033","doi":"10.26434/chemrxiv-2024-m9sk0-v2","title":"Roadmap on Data-Centric Materials Science","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Data science; Transformative learning; Field (mathematics); Computer science; Big data; Nanotechnology; Key (lock); Engineering ethics; Sociology; Engineering; Materials science; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01796053,0.002157744,0.001897418,0.003892981,0.002181058,0.009319042,0.003718814,0.00926994,0.02921773],"category_scores_gemma":[0.02225204,0.000984557,0.002081842,0.003490879,0.004251847,0.02165264,0.009425478,0.01081105,0.01094377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003986123,"about_ca_system_score_gemma":0.01131612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002045253,"about_ca_topic_score_gemma":0.001406403,"domain_scores_codex":[0.9936104,0.002466349,0.0002963482,0.0008658802,0.002130446,0.0006305044],"domain_scores_gemma":[0.965466,0.02350757,0.0005413793,0.002972076,0.005511357,0.002001611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001977589,0.0003266787,0.0004862424,0.004846569,0.00009186677,0.0003177601,0.0003707205,0.007293488,0.001401573,0.6051306,0.1305329,0.2490039],"study_design_scores_gemma":[0.0000301953,0.0001156312,0.00027249,0.001625505,0.00002298463,0.0001633253,0.0002640757,0.004878666,0.00054266,0.386571,0.6054628,0.00005074708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.007415798,0.3942672,0.1809041,0.2905113,0.01895327,0.0005499808,0.003151219,0.003337765,0.1009092],"genre_scores_gemma":[0.0794385,0.4850635,0.351934,0.03980497,0.01156667,0.001330757,0.006773233,0.001193199,0.02289516],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02921773,"threshold_uncertainty_score":0.09774303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04080134894419537,"score_gpt":0.3270762941877631,"score_spread":0.2862749452435677,"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."}}