{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.006763464,0.0007295509,0.0008090707,0.0005785498,0.0004303052,0.002385374,0.008458467,0.0003488857,0.005314405],"category_scores_gemma":[0.00161902,0.0006108973,0.00008773262,0.0008397064,0.00132545,0.000366711,0.01804096,0.000929629,0.01483914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003524744,"about_ca_system_score_gemma":0.001250664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001771622,"about_ca_topic_score_gemma":0.000002959477,"domain_scores_codex":[0.992355,0.0002262757,0.0009243549,0.003478081,0.001818863,0.001197404],"domain_scores_gemma":[0.993739,0.0001511633,0.0005464054,0.005018478,0.000203344,0.0003416039],"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":[0.00002736682,0.00007206939,0.00002686886,0.0005651877,0.000007233295,0.00005999132,0.0001517695,0.0009165943,0.9896354,0.002285014,0.005997486,0.0002549961],"study_design_scores_gemma":[0.0001501541,0.00005355155,0.0004127436,0.0006516831,0.00006538348,0.00002615659,0.00001683604,0.003077373,0.9824354,0.007900157,0.004371114,0.0008394467],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699069,0.0003823398,0.0001098077,0.0009618893,0.01885893,0.0006480162,0.0002657817,0.0009183163,0.007947992],"genre_scores_gemma":[0.9907491,0.00005136212,0.005678467,0.0003901444,0.00156044,0.00008411672,0.0001795239,0.0001086706,0.001198204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02084214,"threshold_uncertainty_score":0.9996343,"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."}}