{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004798303,0.0001110819,0.0001564288,0.00007489547,0.00009282018,0.0001815988,0.0006011447,0.00005469968,0.0001022757],"category_scores_gemma":[0.001971678,0.0001122139,0.00005058632,0.000540673,0.00003506076,0.0002411529,0.0004944755,0.0002072874,0.00004709618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001141134,"about_ca_system_score_gemma":0.0002400351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003144195,"about_ca_topic_score_gemma":0.0000210986,"domain_scores_codex":[0.9986393,0.00007761653,0.0001675711,0.0003966435,0.0003834106,0.0003354327],"domain_scores_gemma":[0.9973961,0.001612409,0.00002845779,0.0006084708,0.000235025,0.0001195883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005897382,0.00009707783,0.03005833,0.0001449042,0.0001392962,0.0003998526,0.004660336,0.004335201,0.02601545,0.5070735,0.01488934,0.4121808],"study_design_scores_gemma":[0.001201511,0.00007403655,0.005572692,0.00007452939,0.00001665352,0.001637455,0.001170337,0.2142191,0.3323283,0.004545376,0.4377928,0.001367157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002728837,0.0001543628,0.992586,0.0006779481,0.0005351783,0.00004133001,0.000002589412,0.0006538352,0.002619876],"genre_scores_gemma":[0.07036124,0.000002646013,0.9213282,0.0001551477,0.00005754828,0.000006181375,0.00000134976,0.00001476923,0.008072933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5025281,"threshold_uncertainty_score":0.4575948,"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."}}