{"id":"W2101341488","doi":"10.1109/msr.2009.5069477","title":"MapReduce as a general framework to support research in Mining Software Repositories (MSR)","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Debugging; Software deployment; Eclipse; Reuse; Software; Process (computing); Software engineering; Source code; Operating system; Resource (disambiguation); Database; Distributed computing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005517667,0.0005366594,0.0007381943,0.001746715,0.001068809,0.002669693,0.003218407,0.0008327588,0.001244364],"category_scores_gemma":[0.005472772,0.000692989,0.001203601,0.001981608,0.001051001,0.003274257,0.002865165,0.001440012,0.0009214104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00078292,"about_ca_system_score_gemma":0.002985287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004277142,"about_ca_topic_score_gemma":0.00489764,"domain_scores_codex":[0.9976526,0.0007097949,0.0001797733,0.000350573,0.0009341848,0.000173036],"domain_scores_gemma":[0.9969453,0.0007312106,0.0001838438,0.001213485,0.0005468396,0.000379316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000542657,0.0005013235,0.006799535,0.001658213,0.0004179681,0.001029401,0.002163325,0.07062575,0.02961266,0.1832018,0.07655522,0.6268921],"study_design_scores_gemma":[0.0002935551,0.0003705498,0.005171332,0.0002293761,0.000162986,0.001484943,0.0008430358,0.3088868,0.03352461,0.2356511,0.413157,0.0002247442],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007047004,0.000503108,0.9702244,0.001428053,0.0001419049,0.0003558205,0.000490052,0.016002,0.003807642],"genre_scores_gemma":[0.0876701,0.0008135894,0.9051417,0.0003912908,0.0001258401,0.0004335515,0.001471051,0.000879008,0.003073919],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005517667,"threshold_uncertainty_score":0.02918053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05066098468250915,"score_gpt":0.3755869231365201,"score_spread":0.324925938454011,"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."}}