{"id":"W3160121929","doi":"10.1109/saner50967.2021.00061","title":"MSR4ML: Reconstructing Artifact Traceability in Machine Learning Repositories","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Traceability; Computer science; Artifact (error); Software engineering; Software versioning; Source code; Commit; Software evolution; Software development; Requirements traceability; Software; Process (computing); Database; Software construction; Programming language; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007004681,0.001223021,0.0008261966,0.009680835,0.0009649437,0.003615419,0.003239738,0.001634137,0.001504453],"category_scores_gemma":[0.03989104,0.000988605,0.001516389,0.00539687,0.001103933,0.005380373,0.004460903,0.00201033,0.001197972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033591,"about_ca_system_score_gemma":0.002517016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005979814,"about_ca_topic_score_gemma":0.008277765,"domain_scores_codex":[0.9938461,0.001525729,0.0007231056,0.001391811,0.002190153,0.0003231425],"domain_scores_gemma":[0.9664835,0.01241207,0.005715454,0.01158113,0.003232179,0.0005756901],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003694671,0.000553561,0.08742762,0.00114697,0.0003712395,0.001260329,0.003088207,0.07459222,0.01651766,0.01707511,0.01397851,0.7836191],"study_design_scores_gemma":[0.00005633442,0.0002752482,0.01544369,0.0002862396,0.0001302847,0.0008549686,0.0007715671,0.8793722,0.04365899,0.0331016,0.02595172,0.00009713768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06803674,0.0006134656,0.8749905,0.0005746336,0.00006469654,0.0002743886,0.003692869,0.05050573,0.001246989],"genre_scores_gemma":[0.2578135,0.0003612414,0.7229639,0.0001123335,0.00004365149,0.0003067178,0.01378621,0.002652833,0.001959588],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9929953,"threshold_uncertainty_score":0.0370447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01758268226082918,"score_gpt":0.2589639617290205,"score_spread":0.2413812794681914,"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."}}