{"id":"W3144106047","doi":"10.1109/msr.2009.5069475","title":"The promises and perils of mining git","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":310,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Commit; Computer science; Decentralization; Semantics (computer science); Confusion; Focus (optics); Data science; Code (set theory); Source code; World Wide Web; Computer security; Database; Political science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1651691,0.001802266,0.002848276,0.02104551,0.005956217,0.01947621,0.007215227,0.006229762,0.001140287],"category_scores_gemma":[0.4530978,0.00203891,0.001902596,0.02234838,0.01528206,0.03594103,0.01268392,0.01294424,0.001335412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004774755,"about_ca_system_score_gemma":0.008772228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005088204,"about_ca_topic_score_gemma":0.008103662,"domain_scores_codex":[0.854779,0.08575933,0.00889255,0.0113123,0.03683215,0.002424774],"domain_scores_gemma":[0.3858554,0.4312324,0.02727302,0.1143469,0.03490128,0.00639111],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001177595,0.0005846863,0.2213413,0.004341671,0.0007659025,0.001697643,0.02163153,0.02796626,0.004444677,0.139976,0.05377226,0.5223005],"study_design_scores_gemma":[0.0001978268,0.0002701869,0.05680725,0.002025568,0.0002075264,0.00218766,0.0208345,0.1303884,0.005486655,0.6357783,0.1452772,0.0005389287],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3025976,0.02548324,0.4628119,0.1761629,0.002008006,0.000865939,0.01112508,0.005158046,0.01378739],"genre_scores_gemma":[0.4266008,0.005447721,0.544447,0.005661374,0.002367391,0.001037268,0.01082483,0.001345489,0.002268219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8348309,"threshold_uncertainty_score":0.8735079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01494064876810455,"score_gpt":0.2601414647745975,"score_spread":0.245200816006493,"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."}}