{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001534964,0.0002377339,0.0003385904,0.0002789102,0.0001669655,0.0001785979,0.0003555741,0.0001285356,0.000003173182],"category_scores_gemma":[0.009136548,0.0001884302,0.00007807666,0.0002977049,0.00005710337,0.0003110816,0.00006131164,0.000445967,3.206568e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004175591,"about_ca_system_score_gemma":0.00005662871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004268463,"about_ca_topic_score_gemma":0.000004698775,"domain_scores_codex":[0.9985498,0.0000725995,0.0003115646,0.0005068163,0.0002041374,0.0003550813],"domain_scores_gemma":[0.9603587,0.03895337,0.00004376394,0.0004957179,0.00006340636,0.00008500915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003760923,0.00003354601,0.0004251386,0.001554529,0.0002376454,0.000007884793,0.00295919,0.0101547,0.0547181,0.0007613643,0.000004038256,0.9291062],"study_design_scores_gemma":[0.002258122,0.001847655,0.2245303,0.002716916,0.0004264256,0.000998624,0.0004370435,0.73067,0.03141313,0.002490623,0.0006435246,0.001567583],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3470789,0.0006883722,0.651319,0.0001341774,0.0003136634,0.000230415,0.00001760538,0.0002175701,3.424239e-7],"genre_scores_gemma":[0.6100448,0.0001163838,0.3896592,0.000009967894,0.00003159721,0.00009772035,0.000001295868,0.00002305511,0.00001592897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9275387,"threshold_uncertainty_score":0.9992099,"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."}}