{"id":"W4380244113","doi":"10.1038/s41524-023-01040-5","title":"Sizing up feature descriptors for macromolecular machine learning with polymeric biomaterials","year":2023,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Federation of University Women; McLean Foundation","keywords":"Biomaterial; Feature (linguistics); Sizing; Computer science; Representation (politics); Artificial intelligence; Process (computing); Feature engineering; Machine learning; Nanotechnology; Materials science; Chemistry; Deep learning","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0008020924,0.0005541832,0.0007325973,0.001069723,0.0002142037,0.000997311,0.0007195923,0.0007775094,0.001806125],"category_scores_gemma":[0.002541378,0.0002688817,0.0007992553,0.0009963851,0.0004222981,0.001219455,0.0007005465,0.001028948,0.0007300099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005382985,"about_ca_system_score_gemma":0.0006423463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009817624,"about_ca_topic_score_gemma":0.001005452,"domain_scores_codex":[0.999763,0.00006675492,0.00002371056,0.00004814632,0.00006117095,0.00003732956],"domain_scores_gemma":[0.9991565,0.0005173107,0.00007424029,0.0000927052,0.000129239,0.00003013385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002175791,0.0001708981,0.002111833,0.0002476062,0.00008032534,0.000108707,0.00005080459,0.4743108,0.026456,0.0226115,0.003901171,0.4697328],"study_design_scores_gemma":[0.000006637692,0.00003527218,0.0001404265,0.000007783707,0.000006249102,0.00001413552,0.000008913892,0.9852174,0.005139671,0.00846481,0.0009532365,0.000005479636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04589033,0.0004216344,0.9508219,0.0003480337,0.00004949102,0.00008759839,0.0003337483,0.001127036,0.0009203695],"genre_scores_gemma":[0.5179924,0.000454167,0.477858,0.0001571922,0.00007390251,0.0003472014,0.001306024,0.000168345,0.001642661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001806125,"threshold_uncertainty_score":0.006042063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01491550666261397,"score_gpt":0.2617355342669427,"score_spread":0.2468200276043287,"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."}}