{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001402302,0.0002586109,0.0004999787,0.001087745,0.000101004,0.00003434456,0.0008859845,0.0002422938,0.000006681963],"category_scores_gemma":[0.004974175,0.0002658418,0.00006609586,0.001442168,0.00003556886,0.0001825781,0.00007025864,0.001071067,0.000001723187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009447359,"about_ca_system_score_gemma":0.00008820893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001011217,"about_ca_topic_score_gemma":0.00004312321,"domain_scores_codex":[0.9977202,0.000552556,0.0004285766,0.0006349749,0.0002410565,0.0004226653],"domain_scores_gemma":[0.9910572,0.007754007,0.00004131441,0.000924773,0.00008616643,0.000136547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001421015,0.002524345,0.4110655,0.0003383419,0.0002820585,0.0001138523,0.004063891,0.4204838,0.002174651,0.0002849453,0.00001543017,0.1585111],"study_design_scores_gemma":[0.004789618,0.004398636,0.8521167,0.0002704759,0.0001330974,0.0001819405,0.0003550754,0.1296982,0.005116626,0.0007956019,0.0009970212,0.001147013],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3209113,0.0001433967,0.6775222,0.00005966793,0.0001981704,0.000205637,0.000001778288,0.0009569511,8.840943e-7],"genre_scores_gemma":[0.4937674,0.00002491866,0.5060759,0.00002448281,0.000007179229,0.00006487988,0.000001269754,0.00001753077,0.00001642827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4410512,"threshold_uncertainty_score":0.9999794,"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."}}