{"id":"W4408813631","doi":"10.5731/pdajpst.2024-003020","title":"Phase-Incremental Decision Trees for Multi-Phase Feature Selection and Interaction in Biologics Manufacturing","year":2025,"lang":"en","type":"article","venue":"PDA Journal of Pharmaceutical Science and Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Phase (matter); Feature selection; Selection (genetic algorithm); Decision tree; Computer science; Feature (linguistics); Artificial intelligence; Machine learning; Chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.001010111,0.0000737572,0.0001233769,0.0007470485,0.0001810389,0.0001006239,0.0003366143,0.00007698704,0.000001713449],"category_scores_gemma":[0.0005042769,0.00005528425,0.00001525319,0.0007062221,0.0001712274,0.0005340149,0.0001415915,0.000339484,3.087934e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007757467,"about_ca_system_score_gemma":0.00006355227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002426147,"about_ca_topic_score_gemma":0.00001237221,"domain_scores_codex":[0.9992298,0.00002666997,0.0002094365,0.0002310633,0.0001281716,0.0001748521],"domain_scores_gemma":[0.9995131,0.0001216194,0.000116378,0.00007576332,0.0001170869,0.00005599243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007385486,0.0001833018,0.001158952,0.000006708038,0.000004089044,0.000002375796,0.00002329891,0.000003430518,0.1316611,0.004527354,0.00003960957,0.8623159],"study_design_scores_gemma":[0.007961281,0.001194457,0.003398556,0.0001129564,0.00002442987,0.000276649,0.000242275,0.5135133,0.4354443,0.006392197,0.03128189,0.0001577347],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.601502,0.0002906515,0.3937948,0.004115877,0.0001647076,0.00009340684,9.857766e-7,0.00002236208,0.00001519834],"genre_scores_gemma":[0.9396459,0.0002050149,0.06000781,0.0001156893,0.00001451267,0.000003540896,5.437237e-7,0.000001268,0.000005743853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8621582,"threshold_uncertainty_score":0.2254426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05018730905169769,"score_gpt":0.438773905189776,"score_spread":0.3885865961380783,"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."}}