{"id":"W2040027946","doi":"10.1002/smr.413","title":"Recommending change clusters to support software investigation: an empirical study","year":2009,"lang":"en","type":"article","venue":"Journal of Software Maintenance and Evolution Research and Practice","topic":"Software Engineering Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Software; Empirical research; Software system; Software maintenance; Change impact analysis; Software development; Source code; Software engineering; Source lines of code; Code (set theory); Programming language; Set (abstract data type)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01030649,0.0001680055,0.0002685778,0.0007414058,0.0004224331,0.00049919,0.0006521211,0.00008896552,0.000007777686],"category_scores_gemma":[0.02377321,0.0001429325,0.00003710003,0.001199894,0.0001075511,0.003915481,0.0003088942,0.0009532553,0.00001250724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002688954,"about_ca_system_score_gemma":0.0002781699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005839484,"about_ca_topic_score_gemma":0.00001238477,"domain_scores_codex":[0.9964029,0.0008692393,0.0004523125,0.0004208155,0.001205376,0.0006494015],"domain_scores_gemma":[0.9927639,0.004252162,0.0001782734,0.0003888816,0.001575917,0.0008408632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002231758,0.001560122,0.520278,0.0001311954,0.0001537671,0.001588502,0.02608366,0.0001407153,0.0001948028,0.0008888159,0.07191309,0.3748355],"study_design_scores_gemma":[0.00164141,0.02043731,0.9442145,0.0002620326,0.0000212109,0.002606683,0.004646048,0.0006266615,0.0000232098,0.004641538,0.02046905,0.0004103281],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4416745,0.0007464134,0.5082353,0.04781148,0.0004462603,0.0008691489,0.000004484239,0.0001709575,0.00004143203],"genre_scores_gemma":[0.8861947,0.0002109074,0.1115389,0.001621409,0.0003032568,0.0000202485,0.000001089485,0.00001401607,0.00009548699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4445202,"threshold_uncertainty_score":0.98445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1476434909259721,"score_gpt":0.4217483332518392,"score_spread":0.2741048423258671,"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."}}