{"id":"W3115677442","doi":"10.1063/5.0021106","title":"Data-driven materials research enabled by natural language processing and information extraction","year":2020,"lang":"en","type":"article","venue":"Applied Physics Reviews","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":294,"is_retracted":false,"has_abstract":true,"ca_institutions":"Xerox (Canada)","funders":"Lawrence Livermore National Laboratory; Office of Naval Research; ISIS Neutron and Muon Source; Royal Academy of Engineering; Laboratory Directed Research and Development; U.S. Department of Energy; Science and Technology Facilities Council; National Nuclear Security Administration; National Science Foundation","keywords":"Computer science; Data science; Information extraction; Variety (cybernetics); Field (mathematics); Domain (mathematical analysis); Data processing; Natural language; Natural (archaeology); Artificial intelligence; Natural language processing","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01122231,0.001562246,0.001893574,0.0142173,0.001176364,0.006934674,0.002952438,0.001587596,0.005709463],"category_scores_gemma":[0.02792555,0.0007365914,0.002467634,0.01329081,0.002601163,0.01053119,0.003849555,0.003394355,0.005019592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001590702,"about_ca_system_score_gemma":0.004222305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001595033,"about_ca_topic_score_gemma":0.002880869,"domain_scores_codex":[0.9932415,0.002317982,0.0008449954,0.001045057,0.002390424,0.0001598945],"domain_scores_gemma":[0.9685985,0.02296926,0.001400578,0.002766728,0.004053429,0.0002114355],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001057852,0.0001445722,0.002798124,0.01394872,0.0002870721,0.0007213572,0.001670576,0.006001453,0.01428773,0.1494385,0.05087804,0.759718],"study_design_scores_gemma":[0.00003641511,0.0000830942,0.002950592,0.004767287,0.0001978044,0.0006620664,0.001576808,0.02803149,0.02323467,0.474034,0.4642192,0.0002067009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009941602,0.07159603,0.8497222,0.01475387,0.001352217,0.001097137,0.01785804,0.005274223,0.02840462],"genre_scores_gemma":[0.03548084,0.06047124,0.8772228,0.002029854,0.001009996,0.001158592,0.01824586,0.0007890754,0.00359174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9887777,"threshold_uncertainty_score":0.05935001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0655541559999387,"score_gpt":0.374987713412994,"score_spread":0.3094335574130553,"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."}}