{"id":"W4417339614","doi":"10.1145/3785001","title":"An Empirical Study of Self-Admitted Technical Debt in Machine Learning Software","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Technical debt; Context (archaeology); Empirical research; Code smell; Pipeline (software); Source code; Code (set theory)","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":[0.009979682,0.000291134,0.000253538,0.004381401,0.0009941591,0.001689214,0.0008779667,0.0007960689,0.00129067],"category_scores_gemma":[0.1420031,0.0004264343,0.0002509228,0.004446433,0.001944622,0.004505402,0.00237486,0.001735638,0.0004592429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173374,"about_ca_system_score_gemma":0.0009962147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0029382,"about_ca_topic_score_gemma":0.003680659,"domain_scores_codex":[0.9905129,0.002843995,0.001280141,0.001441281,0.003254713,0.0006670812],"domain_scores_gemma":[0.6949841,0.1497777,0.1034175,0.01381794,0.03128923,0.006713547],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000978913,0.0001040391,0.9733928,0.0001064971,0.00003016661,0.0002860512,0.006301539,0.0004126611,0.0006705216,0.0004902371,0.0007070336,0.01740051],"study_design_scores_gemma":[0.000007431724,0.0002272285,0.9825613,0.0001124432,0.00001539568,0.0006947956,0.007430382,0.005000664,0.0007635559,0.0006499116,0.002503649,0.00003318113],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979715,0.0001299007,0.0007750765,0.0001793237,0.00000386875,0.00002160523,0.0002054827,0.0000323242,0.0006808942],"genre_scores_gemma":[0.9983571,0.00009638168,0.0007360541,0.00004500346,0.000009989183,0.00002461752,0.0003789742,0.00002326492,0.0003285678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9900203,"threshold_uncertainty_score":0.05277824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05521184893937985,"score_gpt":0.3650327064973448,"score_spread":0.309820857557965,"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."}}