{"id":"W2579161546","doi":"10.1109/tse.2017.2654244","title":"Using Natural Language Processing to Automatically Detect Self-Admitted Technical Debt","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":220,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Technical debt; Computer science; Debt; Quality (philosophy); Bad debt; Code (set theory); Finance; Software development; Business; Software; Programming language; Set (abstract data type)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003114274,0.0003404778,0.0002975339,0.0004576987,0.0005745204,0.0006731451,0.001655975,0.0001578011,0.00000997057],"category_scores_gemma":[0.0006496295,0.0003543943,0.0001391622,0.0005112952,0.00002971048,0.0007875952,0.00003275219,0.0007480875,0.000063703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003489801,"about_ca_system_score_gemma":0.0001372677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002381793,"about_ca_topic_score_gemma":0.00000720364,"domain_scores_codex":[0.9977618,0.00002291046,0.0003116649,0.0005905143,0.000610117,0.000702936],"domain_scores_gemma":[0.9977298,0.0004289049,0.0000615068,0.001326825,0.0001218495,0.0003311242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004140178,0.0003139926,0.0005875853,0.0006197973,0.0002069263,0.0005160373,0.001917848,0.5819237,0.07366839,0.00009364095,0.00008710389,0.3400235],"study_design_scores_gemma":[0.0004453444,0.0001093991,0.008917673,0.0003811378,0.00002747252,0.0001909835,0.000007772595,0.9474352,0.04165025,0.00000714543,0.0001113591,0.0007162467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08798596,0.00009536758,0.9067763,0.00006335347,0.0007876182,0.0003072217,0.000004036925,0.003971991,0.000008159311],"genre_scores_gemma":[0.5739614,0.000001219974,0.4258483,0.00002890352,0.00004797145,0.00004277143,2.180059e-7,0.00004429615,0.00002491722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4859754,"threshold_uncertainty_score":0.9998908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647430844027475,"score_gpt":0.2907908957815483,"score_spread":0.2743165873412735,"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."}}