{"id":"W4382362073","doi":"10.1145/3589806.3600039","title":"Integrated Reproducibility with Self-describing Machine Learning Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Java; Machine learning; Modular design; Process (computing); Artificial intelligence; License; MIT License; Documentation; Software engineering; Human–computer interaction; Data science; Programming language; Operating system","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02264668,0.0001314051,0.0001992198,0.0004091793,0.0003510747,0.0007023059,0.0008563069,0.00002536125,0.0003270599],"category_scores_gemma":[0.004238066,0.00007543091,0.00005392668,0.003978172,0.00005577369,0.000449303,0.0006923953,0.0001908864,0.001139535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003770716,"about_ca_system_score_gemma":0.00004923796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000370132,"about_ca_topic_score_gemma":0.0001449582,"domain_scores_codex":[0.9954536,0.0002582739,0.0004763964,0.002135831,0.001344553,0.0003313718],"domain_scores_gemma":[0.9959757,0.0005953604,0.0001190729,0.002910781,0.0002991255,0.00009991018],"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":[0.0001076535,0.0002300823,0.06176591,0.00001506982,0.00008684049,0.00008532002,0.004122368,0.356023,0.0002568357,0.01056569,0.1729256,0.3938156],"study_design_scores_gemma":[0.0001695187,0.00004451202,0.001820158,0.00001231083,0.000006463087,0.00000333836,0.00169408,0.9612366,0.00009403565,0.007657662,0.02712878,0.000132518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7576121,0.00003063085,0.1769298,0.002056363,0.0007739183,0.0003482613,0.00001286055,0.002982711,0.05925336],"genre_scores_gemma":[0.958967,0.000003093226,0.00962931,0.00008800784,0.00002915448,0.000004629112,0.00003590906,0.00001011653,0.03123281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6052136,"threshold_uncertainty_score":0.9996382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3395261948733915,"score_gpt":0.3580994167655376,"score_spread":0.01857322189214611,"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."}}