{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004878564,0.0008728219,0.0005173896,0.00171213,0.0005130153,0.001946758,0.001162142,0.000563671,0.03846046],"category_scores_gemma":[0.003175587,0.000348173,0.001204182,0.001419548,0.0002714927,0.002116424,0.001612593,0.001234479,0.0219074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005879911,"about_ca_system_score_gemma":0.0008642832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002124502,"about_ca_topic_score_gemma":0.002992832,"domain_scores_codex":[0.999337,0.00005189933,0.0000402925,0.0002139409,0.000279332,0.00007743907],"domain_scores_gemma":[0.9992992,0.0001410994,0.00002606337,0.0002632197,0.0002399387,0.00003044503],"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":[0.0001412061,0.0001174076,0.001286268,0.0002158697,0.00005140648,0.0001772334,0.00009234257,0.004338247,0.0124003,0.03112411,0.09539714,0.8546584],"study_design_scores_gemma":[0.00006730815,0.0001782886,0.002803991,0.0001477763,0.0001245715,0.000941119,0.000214573,0.1563562,0.07496801,0.1330849,0.6310409,0.00007248925],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01113337,0.0003789352,0.8955999,0.0005393068,0.0003894677,0.0004962615,0.008065662,0.03637066,0.04702638],"genre_scores_gemma":[0.1768625,0.0008475803,0.6194766,0.0008812847,0.0002113702,0.0008848712,0.04176397,0.008518859,0.1505531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03846046,"threshold_uncertainty_score":0.1286631,"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."}}