{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002010569,0.0004950214,0.0006779819,0.0003483896,0.0007778972,0.0009586273,0.0006588181,0.0001581627,0.001480589],"category_scores_gemma":[0.0004599097,0.0004128808,0.00009010974,0.0007142733,0.0002446655,0.000411269,0.0002532659,0.00008420565,0.000830381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000837982,"about_ca_system_score_gemma":0.0001534407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001506562,"about_ca_topic_score_gemma":0.000004393008,"domain_scores_codex":[0.9961286,0.0005390174,0.0006599772,0.0009395131,0.0008205859,0.0009123313],"domain_scores_gemma":[0.9982553,0.0004348164,0.0005264072,0.0003368301,0.0002640594,0.0001826168],"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":[0.0002913706,0.00002320774,0.0002241304,0.0001712435,0.00002219207,0.00002794439,0.0002744419,0.0340809,0.962907,0.001063742,0.0007574015,0.0001564899],"study_design_scores_gemma":[0.001359123,0.0004264115,0.002631975,0.0001540567,0.0000528823,0.0001339532,0.00009792081,0.01197329,0.9758519,0.002611909,0.00392168,0.0007849301],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.974848,0.00008418544,0.01848171,0.0007861927,0.003286151,0.0008176069,0.0004767542,0.001145781,0.00007364061],"genre_scores_gemma":[0.9502134,0.000007474145,0.04670483,0.0002959495,0.0004318088,0.0002626161,0.0009223742,0.0001309325,0.00103058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02822313,"threshold_uncertainty_score":0.9999476,"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."}}