{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002287652,0.0001726709,0.0003550581,0.00002805375,0.0002810069,0.0006597,0.0006782403,0.00004919191,0.0002488579],"category_scores_gemma":[0.000345867,0.0001390463,0.00001374555,0.0003429918,0.0001418874,0.00216783,0.0004838873,0.0002329254,0.0008622559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002775145,"about_ca_system_score_gemma":0.00004409745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002638174,"about_ca_topic_score_gemma":9.234334e-7,"domain_scores_codex":[0.9979807,0.0003061378,0.000476073,0.0004403325,0.0004634467,0.0003332935],"domain_scores_gemma":[0.9989555,0.00009341938,0.0003360001,0.0004451273,0.00006740275,0.0001025888],"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":[0.00001865414,0.000009166872,0.000002573007,0.0003358597,0.000001057826,4.047955e-7,0.0009208316,0.00004151963,0.9617804,0.0004403896,0.00462932,0.03181982],"study_design_scores_gemma":[0.00060089,0.00006647823,0.0001186094,0.0002432017,0.00003835321,0.00000748364,0.0004671619,0.02665593,0.657354,0.0003083459,0.3134718,0.0006677529],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651938,0.007186506,0.01535182,0.001385841,0.0007202056,0.003606834,0.0005201843,0.0005023625,0.005532424],"genre_scores_gemma":[0.990885,0.0003896951,0.006776352,0.0008133361,0.0004051494,0.0001007165,0.0005786795,0.00001989622,0.00003118566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3088425,"threshold_uncertainty_score":0.9999157,"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."}}