{"id":"W3161504508","doi":"10.1109/icse43902.2021.00135","title":"CodeShovel: Constructing Method-Level Source Code Histories","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Source code; Correctness; Software engineering; Code review; Field (mathematics); Programming language; Software; Code (set theory); Empirical research; Static program analysis; Software development","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004640053,0.001158662,0.0005383652,0.009494727,0.001060386,0.002545223,0.001529077,0.0009401616,0.003137738],"category_scores_gemma":[0.03713779,0.001393262,0.0009359104,0.003792378,0.0009417713,0.005542779,0.002886627,0.001485151,0.002251295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005108,"about_ca_system_score_gemma":0.004597563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006906363,"about_ca_topic_score_gemma":0.01274313,"domain_scores_codex":[0.9969523,0.000619807,0.0003370787,0.0007458461,0.001189974,0.0001549318],"domain_scores_gemma":[0.9715816,0.01350564,0.003895593,0.005689007,0.004618761,0.0007095133],"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":[0.0005930605,0.0002827375,0.1351321,0.00203197,0.0002189846,0.0009401535,0.01067588,0.01364918,0.01373216,0.01921423,0.04508993,0.7584395],"study_design_scores_gemma":[0.0002343489,0.0006820225,0.0884406,0.001815212,0.0003522412,0.002091208,0.005140378,0.3694184,0.1019281,0.06124775,0.3681449,0.0005049453],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1462016,0.001770919,0.6917556,0.0006877058,0.0001835431,0.001362549,0.03094039,0.119345,0.007752619],"genre_scores_gemma":[0.2987255,0.001081803,0.6338144,0.0001764544,0.00006583735,0.001065316,0.04865299,0.01076974,0.00564804],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009494727,"threshold_uncertainty_score":0.02453929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05602422699197473,"score_gpt":0.3145581738295238,"score_spread":0.2585339468375491,"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."}}