{"id":"W2612705982","doi":"10.1007/s10664-017-9522-4","title":"Identifying self-admitted technical debt in open source projects using text mining","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Concordia University","funders":"Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Technical debt; Computer science; Classifier (UML); Source code; Code review; Baseline (sea); Open source; Artificial intelligence; F1 score; Machine learning; Data mining; Natural language processing; Software; Software quality; Software development; Programming language","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001092554,0.0004008083,0.0005087902,0.0004819765,0.0004576864,0.002019179,0.005158322,0.0002621862,0.0000125523],"category_scores_gemma":[0.007963097,0.0004276124,0.0001167774,0.0008401823,0.00004643335,0.001843286,0.004464046,0.0008085683,0.0000406439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005513057,"about_ca_system_score_gemma":0.0002476913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001741777,"about_ca_topic_score_gemma":0.00001583222,"domain_scores_codex":[0.9966274,0.00006131829,0.0005212922,0.0009986634,0.0006878369,0.001103501],"domain_scores_gemma":[0.9963688,0.001237933,0.0001414895,0.001813742,0.00009576895,0.0003422138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001046591,0.0001593137,0.9702091,0.000176375,0.00005006883,0.0004077705,0.001309973,0.01984857,0.001588212,0.0001091726,0.0003957234,0.005735232],"study_design_scores_gemma":[0.001035742,0.0000718739,0.7463515,0.0005730992,0.00001217171,0.0001746964,0.00002599675,0.2472291,0.001214608,0.00007214633,0.002286248,0.0009527431],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4400647,0.00009959622,0.5575956,0.0001305056,0.0003604548,0.0004045475,8.095723e-7,0.00130687,0.00003695014],"genre_scores_gemma":[0.6484872,0.000003676615,0.3511574,0.00004542707,0.0001163442,0.0000661286,0.000001245709,0.00006922843,0.0000533685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2273805,"threshold_uncertainty_score":0.9998176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07815053665037296,"score_gpt":0.3568263279761991,"score_spread":0.2786757913258261,"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."}}