{"id":"W2022675432","doi":"10.1002/smr.539","title":"TIDIER: an identifier splitting approach using speech recognition techniques","year":2011,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Identifier; Computer science; Program comprehension; Source code; Maintainability; Unique identifier; Set (abstract data type); Documentation; Software; Code (set theory); Relation (database); Natural language processing; Comprehension; Information retrieval; Artificial intelligence; Data mining; Software engineering; Programming language; Software system","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":[],"consensus_categories":[],"category_scores_codex":[0.00148663,0.0001236253,0.0001767606,0.0003617349,0.0001385743,0.0001302872,0.0004517363,0.0001003941,0.00001034615],"category_scores_gemma":[0.0007211032,0.0001125283,0.00005029738,0.0004511834,0.0000501149,0.002071427,0.00008331499,0.000322468,0.000002484059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009133742,"about_ca_system_score_gemma":0.0001418023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001837442,"about_ca_topic_score_gemma":5.714024e-7,"domain_scores_codex":[0.9986764,0.0000806731,0.000365412,0.0002224759,0.0004223625,0.0002326331],"domain_scores_gemma":[0.9986019,0.00009954105,0.0002562786,0.0001850787,0.0006928505,0.000164333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001350787,0.0006504228,0.125545,0.0009246089,0.0001203009,0.0001490213,0.007819364,0.00009596482,0.002561297,0.0004869294,0.0003559273,0.8611561],"study_design_scores_gemma":[0.004950937,0.004538727,0.364587,0.004461201,0.0004104495,0.02888704,0.004257093,0.1449466,0.2235423,0.213068,0.001348778,0.005001874],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2672078,0.0003366121,0.7319939,0.000007588846,0.0001842598,0.00007764367,9.900207e-7,0.0001407722,0.00005046338],"genre_scores_gemma":[0.5100473,0.0000214242,0.4897196,0.00001581483,0.0001671729,0.00000269578,8.521958e-7,0.00001178547,0.00001333731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8561543,"threshold_uncertainty_score":0.4588771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06451466082664108,"score_gpt":0.2980101579526624,"score_spread":0.2334954971260213,"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."}}