{"id":"W4402483878","doi":"10.1145/3696002","title":"A Novel Refactoring and Semantic Aware Abstract Syntax Tree Differencing Tool and a Benchmark for Evaluating the Accuracy of Diff Tools","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Computer science; Benchmark (surveying); Abstract syntax tree; Abstract syntax; Programming language; Syntax; Software engineering; Tree (set theory); Semantics (computer science); Artificial intelligence; Software","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":[0.005836069,0.00250582,0.001161393,0.01116818,0.0007101853,0.001554876,0.002982541,0.002257985,0.001277875],"category_scores_gemma":[0.0378413,0.0006724041,0.001155266,0.005152533,0.0007406771,0.00337561,0.002385216,0.001232289,0.001259685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004019,"about_ca_system_score_gemma":0.002234731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006514304,"about_ca_topic_score_gemma":0.006930084,"domain_scores_codex":[0.9883265,0.00206264,0.002148233,0.002765439,0.004214083,0.0004830065],"domain_scores_gemma":[0.9671292,0.01457764,0.003172623,0.005863199,0.008528554,0.0007288902],"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":[0.00101662,0.0007165404,0.0757986,0.002212005,0.000446893,0.001267506,0.001148724,0.02928804,0.041278,0.00412106,0.05644497,0.786261],"study_design_scores_gemma":[0.0006858154,0.001729846,0.06468144,0.0005445008,0.0003949197,0.004022438,0.001006328,0.6727848,0.1736765,0.007020215,0.07286976,0.0005835004],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3946746,0.005151602,0.369396,0.0004704997,0.0005792083,0.0007837068,0.01576493,0.2078685,0.005311022],"genre_scores_gemma":[0.4341518,0.0006821627,0.5172611,0.0002997798,0.00007769156,0.0005980889,0.04073235,0.003412402,0.002784538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01116818,"threshold_uncertainty_score":0.03086448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1808719798081679,"score_gpt":0.3856275967855456,"score_spread":0.2047556169773777,"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."}}