{"id":"W4293567371","doi":"10.1038/s43246-022-00283-x","title":"Why big data and compute are not necessarily the path to big materials science","year":2022,"lang":"en","type":"article","venue":"Communications Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Big data; Conversation; Computer science; Data science; Creativity; Computational thinking; Artificial intelligence; Visualization; Crowdsourcing; Scale (ratio); Interrogation; Machine learning; Human–computer interaction; Data mining; World Wide Web; Sociology","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","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.01209918,0.0003397341,0.0005370733,0.0002755132,0.004907681,0.002563824,0.01497245,0.00004958519,0.001409094],"category_scores_gemma":[0.001222404,0.0002710373,0.00002350515,0.001089873,0.001823892,0.0005683436,0.02858477,0.0002192471,0.0002107958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001304121,"about_ca_system_score_gemma":0.0002741689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001357377,"about_ca_topic_score_gemma":0.00009397923,"domain_scores_codex":[0.9940753,0.002180816,0.0008807208,0.001106883,0.001034444,0.000721818],"domain_scores_gemma":[0.9897385,0.0005577318,0.0006886174,0.008585951,0.0002165807,0.0002126209],"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":[0.00003936048,0.0000781206,0.00008398044,0.00003354648,0.000004383884,0.000002411111,0.0006448533,0.0001465307,0.9912067,0.001839741,0.005122579,0.0007977724],"study_design_scores_gemma":[0.0006318422,0.0002310978,0.01394246,0.0001304805,0.00007249254,0.0001754281,0.001337128,0.001172242,0.6738731,0.00125875,0.3061115,0.001063469],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655435,0.0001806939,0.001299219,0.02304589,0.005582203,0.0009976685,0.002789251,0.0002753469,0.0002862193],"genre_scores_gemma":[0.9805991,0.0000748014,0.01186546,0.00642573,0.0003641216,0.0003500989,0.0001583902,0.00004767255,0.0001146416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3173336,"threshold_uncertainty_score":0.9999742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09792307150403638,"score_gpt":0.3277328509773155,"score_spread":0.2298097794732791,"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."}}