{"id":"W4389095557","doi":"10.1007/978-3-031-49252-5_6","title":"IDPP: Imbalanced Datasets Pipelines in Pyrus","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Python (programming language); Pipeline transport; Pipeline (software); Preprocessor; Code reuse; Code (set theory); Data mining; Analytics; Machine learning; Programming language; Database; Software engineering; Software","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":[0.001936028,0.002251992,0.001281353,0.002450092,0.001330893,0.002582866,0.002930437,0.0007384025,0.03449459],"category_scores_gemma":[0.004824865,0.001809044,0.002062475,0.002419962,0.0005869175,0.003072649,0.003229525,0.001927518,0.02285137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094504,"about_ca_system_score_gemma":0.001932682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01000912,"about_ca_topic_score_gemma":0.01273749,"domain_scores_codex":[0.9985818,0.0001576311,0.0001044164,0.0005065372,0.000515061,0.0001345994],"domain_scores_gemma":[0.9989449,0.0002259907,0.00004668103,0.0004592222,0.0002024923,0.0001207273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001479198,0.0003448481,0.00225227,0.0005720607,0.0003804215,0.0002264288,0.0003614439,0.01006227,0.01269026,0.006357295,0.716971,0.2483025],"study_design_scores_gemma":[0.001082754,0.0004863236,0.007671988,0.0001945783,0.0001916739,0.0004363578,0.0003170047,0.3548444,0.071088,0.05054777,0.5128279,0.0003112617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.0183473,0.001093877,0.1718298,0.0007061906,0.0009155866,0.0008488434,0.08862152,0.7042615,0.01337526],"genre_scores_gemma":[0.1002541,0.0007660445,0.4946001,0.001179843,0.0002648794,0.001878596,0.2928594,0.07020181,0.03799524],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03449459,"threshold_uncertainty_score":0.115396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09353235581372939,"score_gpt":0.3594079730076309,"score_spread":0.2658756171939016,"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."}}