{"id":"W2117508687","doi":"10.1145/1858996.1859050","title":"An experience report on scaling tools for mining software repositories using MapReduce","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Scalability; Software engineering; Software; Field (mathematics); Search-based software engineering; Data science; Scale (ratio); Heuristic; Software development; Software construction; Database; Operating system; Artificial intelligence","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":[0.0005275336,0.0001535995,0.0001478736,0.0001168748,0.0002759638,0.0008602998,0.0009586852,0.00009525733,0.000007249242],"category_scores_gemma":[0.004667363,0.0001453263,0.00005489173,0.0003018371,0.00005137802,0.001383982,0.0001614636,0.0002032961,0.000002635289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004583075,"about_ca_system_score_gemma":0.0001390941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003872385,"about_ca_topic_score_gemma":0.000002523819,"domain_scores_codex":[0.9981896,0.00001719527,0.0002822315,0.0006477995,0.0004340124,0.0004291612],"domain_scores_gemma":[0.997077,0.001185554,0.00007090691,0.001268302,0.0002207054,0.0001774695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007565741,0.0003974669,0.1214246,0.0001801902,0.00006386772,0.001155971,0.01666513,0.01453321,0.6513872,0.01550548,0.0009853039,0.1776259],"study_design_scores_gemma":[0.0004969803,0.0003999586,0.02213908,0.0001408315,0.00000854101,0.001528869,0.0006675599,0.2406442,0.7285819,0.0005059203,0.00374524,0.001140874],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5144421,0.000004018376,0.4837547,0.00002609578,0.001189007,0.000122139,5.46159e-7,0.0004295649,0.00003179078],"genre_scores_gemma":[0.5278938,1.072787e-7,0.4717013,0.00002417195,0.0002239284,0.00003668444,0.000001622022,0.00001388743,0.0001045131],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.226111,"threshold_uncertainty_score":0.8295891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0511332506367634,"score_gpt":0.3470636156374646,"score_spread":0.2959303650007012,"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."}}