{"id":"W4388657357","doi":"10.26434/chemrxiv-2023-wd5cr","title":"Quantifying the distribution of materials data types in scientific literature across text, tables, and figures","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Data science; Computer science; Presentation (obstetrics); Field (mathematics); Data extraction; 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":[0.02755116,0.0009771517,0.0011292,0.05668527,0.00202096,0.008139866,0.001335607,0.001303408,0.007428095],"category_scores_gemma":[0.2001113,0.0006226022,0.001161555,0.0588698,0.002663231,0.006620785,0.004862544,0.001206981,0.003273567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001873082,"about_ca_system_score_gemma":0.003063284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001339038,"about_ca_topic_score_gemma":0.002004577,"domain_scores_codex":[0.9693964,0.009429688,0.007224195,0.004528802,0.008752526,0.0006684554],"domain_scores_gemma":[0.6215088,0.2948389,0.03323074,0.01938739,0.0296164,0.001417903],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001285293,0.0002830654,0.1762094,0.04249933,0.001721951,0.003710021,0.03306703,0.008522602,0.03345394,0.06589172,0.06773423,0.5656214],"study_design_scores_gemma":[0.0002000677,0.000318935,0.2269767,0.01097683,0.001521813,0.003782754,0.02789869,0.01525828,0.02627334,0.1332937,0.5529782,0.0005205465],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4968374,0.04421194,0.1778397,0.009196725,0.001659552,0.002035087,0.2117798,0.005213526,0.05122626],"genre_scores_gemma":[0.6509578,0.01745319,0.2055213,0.001411363,0.001049068,0.003619856,0.1103598,0.002283463,0.00734412],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9724488,"threshold_uncertainty_score":0.1457062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07577923707857756,"score_gpt":0.3529841997853836,"score_spread":0.2772049627068061,"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."}}