{"id":"W4385486326","doi":"10.1007/978-3-031-33390-3_13","title":"Feature Engineering","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Artificial intelligence; Logarithm; Data mining; Machine learning; Mathematics; Deep learning","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"],"consensus_categories":[],"category_scores_codex":[0.000216097,0.0004669385,0.0004650192,0.0001030257,0.0002629851,0.0001452376,0.0001665682,0.0004678934,0.000004644479],"category_scores_gemma":[0.0001315577,0.0004696767,0.00006091475,0.00004056761,0.0002188845,0.000001569312,0.0005818211,0.0005075865,0.000006392142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008844573,"about_ca_system_score_gemma":0.00006009693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005166633,"about_ca_topic_score_gemma":0.000006327385,"domain_scores_codex":[0.9983175,0.00001819847,0.0003353862,0.0006863347,0.0002189878,0.0004235847],"domain_scores_gemma":[0.9989843,0.0002372373,0.000242925,0.0002564819,0.00008513236,0.0001939555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004085829,0.00002501139,0.0002598132,0.0007712983,0.000593904,0.000216459,0.0003905509,0.000344927,0.000515927,0.2564201,0.04257757,0.6978436],"study_design_scores_gemma":[0.00200519,0.001754379,0.00318329,0.001622949,0.0004885485,0.0004994876,0.0003159649,0.1838454,0.0001325795,0.03243713,0.7703181,0.003396991],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00993752,0.01303517,0.9416732,0.001165963,0.003455621,0.0008609622,0.001943325,0.0005887027,0.02733949],"genre_scores_gemma":[0.09352043,0.007632566,0.5617148,0.001148705,0.003953899,0.000007426389,0.002685944,0.0007788347,0.3285574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7277405,"threshold_uncertainty_score":0.9997755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01220526921624156,"score_gpt":0.2435632484900194,"score_spread":0.2313579792737778,"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."}}