{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02294977,0.0005644785,0.0009475834,0.0008162505,0.0006613953,0.005029344,0.00891574,0.0003711896,0.000806268],"category_scores_gemma":[0.003941181,0.0004133513,0.00006826779,0.002097943,0.00282542,0.001178828,0.01008591,0.0005060203,0.0003502854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432824,"about_ca_system_score_gemma":0.0009735968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008369661,"about_ca_topic_score_gemma":0.00008426483,"domain_scores_codex":[0.9918674,0.0008116108,0.001649283,0.002592674,0.002061941,0.001017075],"domain_scores_gemma":[0.992547,0.0003831809,0.00145372,0.004986311,0.0005007267,0.0001290337],"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":[0.00004145579,0.00005190349,0.000419378,0.001038525,0.000005822476,0.00001610316,0.001885022,0.001231879,0.9939418,0.0006355217,0.0007031859,0.00002935732],"study_design_scores_gemma":[0.0002087263,0.00001685925,0.009990066,0.001352981,0.00003063381,0.00001005246,0.0001564472,0.0009123394,0.9845025,0.002178489,0.0002156969,0.000425207],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821009,0.0002776786,0.00007746296,0.001049725,0.01440007,0.001155125,0.0006185818,0.0002274478,0.00009301755],"genre_scores_gemma":[0.9940825,0.00007097545,0.003912505,0.00003688347,0.0004558001,0.0001322213,0.0008226639,0.00007647305,0.000409965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01900859,"threshold_uncertainty_score":0.9998883,"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."}}