{"id":"W4390410521","doi":"10.26434/chemrxiv-2023-wd5cr-v3","title":"NLP meets Materials Science: Quantifying the presentation of materials data in scientific literature","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Division of Materials Research; National Science Foundation","keywords":"Computer science; Presentation (obstetrics); Point (geometry); Data science; Information extraction; Natural language processing; Space (punctuation); Artificial intelligence; Information retrieval","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","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01804038,0.0008514848,0.0009263328,0.02575627,0.001408464,0.00719572,0.001183772,0.002298651,0.004628384],"category_scores_gemma":[0.134684,0.0005284554,0.0009216571,0.02493487,0.002473718,0.01296532,0.005052859,0.001737151,0.002937428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001490127,"about_ca_system_score_gemma":0.00145878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001208076,"about_ca_topic_score_gemma":0.001587027,"domain_scores_codex":[0.9841277,0.007989238,0.001841027,0.002089053,0.003536656,0.0004163382],"domain_scores_gemma":[0.8781928,0.09612321,0.009893782,0.008819468,0.005693126,0.001277609],"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":[0.001613037,0.0005100997,0.1526804,0.01034392,0.001412176,0.001135625,0.008380511,0.0245465,0.03099073,0.1003598,0.05791261,0.6101146],"study_design_scores_gemma":[0.0001339233,0.0003920778,0.109086,0.001059983,0.0004819603,0.00228308,0.007120945,0.1808308,0.02825287,0.5530569,0.116843,0.0004585004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4959731,0.03412022,0.3259417,0.01761124,0.00117717,0.0005965223,0.0836609,0.008087901,0.03283127],"genre_scores_gemma":[0.8401966,0.006007925,0.1162872,0.0009426217,0.001224686,0.0006671872,0.03071331,0.0007847634,0.003175782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9819596,"threshold_uncertainty_score":0.09540778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1103278492235733,"score_gpt":0.3833335595120569,"score_spread":0.2730057102884836,"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."}}