{"id":"W4405601045","doi":"10.1109/icsme58944.2024.00052","title":"Can We Do Better with What We Have Done? Unveiling the Potential of ML Pipeline in Notebooks","year":2024,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pipeline (software); Computer science; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0004383709,0.0001380701,0.0001594311,0.0001329964,0.00006632021,0.0005296421,0.000441781,0.00004542093,0.00002111999],"category_scores_gemma":[0.00000638661,0.0000774099,0.00006267947,0.000187607,0.00004214697,0.000339947,0.0001424348,0.0002869563,0.00001974287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000385165,"about_ca_system_score_gemma":0.00006535283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004499424,"about_ca_topic_score_gemma":0.0002168129,"domain_scores_codex":[0.9987614,0.00008083326,0.0002738053,0.0003334154,0.0003038424,0.0002467705],"domain_scores_gemma":[0.9994241,0.0001032283,0.00005240196,0.000325174,0.00006046331,0.00003462527],"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":[0.0000433592,0.00008827526,0.001769803,0.0003780869,0.0001600825,0.0006579945,0.03287669,0.02848741,0.01776909,0.4368545,0.0006146151,0.4803],"study_design_scores_gemma":[0.0009109994,0.0004873124,0.0007136898,0.007786005,0.00005226206,0.0002431114,0.01367677,0.7302446,0.07629842,0.008976399,0.1594167,0.001193714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03962464,0.001785851,0.9419907,0.01349685,0.001076391,0.0002427125,8.844177e-7,0.0001291599,0.001652822],"genre_scores_gemma":[0.9831718,0.00006621581,0.003653803,0.0001926744,0.0002339578,0.000007063727,4.113196e-7,0.0000136426,0.01266039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9435472,"threshold_uncertainty_score":0.5107351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01418757948596912,"score_gpt":0.2300523150022752,"score_spread":0.2158647355163061,"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."}}