{"id":"W2102772625","doi":"10.1007/s10664-006-9006-4","title":"Replaying development history to assess the effectiveness of change propagation tools","year":2006,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Victoria","funders":"","keywords":"Computer science; Dependency (UML); Notice; Source code; Software engineering; Code review; Open source; Empirical research; Software development; Software; Dependency graph; Code (set theory); Change impact analysis; Data science; Static program analysis; Database; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00141207,0.0001909323,0.0002218462,0.0001983346,0.00006440722,0.00006176432,0.0007599452,0.00007386487,0.000005140332],"category_scores_gemma":[0.002729007,0.0001563745,0.00006034343,0.000631643,0.00001819857,0.0003738256,0.000326563,0.0002323381,0.00002142925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007377683,"about_ca_system_score_gemma":0.0001238716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003267315,"about_ca_topic_score_gemma":0.000001195395,"domain_scores_codex":[0.9982477,0.0001025343,0.0003010762,0.0003839387,0.0005645792,0.0004001875],"domain_scores_gemma":[0.9957724,0.003416437,0.00004706141,0.0005277815,0.0001373482,0.00009898187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008120212,0.0003658104,0.7329366,0.002101867,0.000140497,0.0001154304,0.003268928,0.1796243,0.02147338,0.004779944,0.003335772,0.05177623],"study_design_scores_gemma":[0.000143859,0.00004429459,0.9647074,0.0001787573,0.000003001797,0.000009139776,0.000001689961,0.00310133,0.01569612,0.00002081297,0.01583883,0.0002547194],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2917388,0.0002067762,0.7067032,0.00005624595,0.0003866018,0.0004128597,6.59915e-7,0.0004785125,0.0000163438],"genre_scores_gemma":[0.9248052,7.067122e-7,0.07457839,0.000049424,0.0001288402,0.0003691843,0.000004961473,0.0000304947,0.00003277297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6330664,"threshold_uncertainty_score":0.6376767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1118926139354591,"score_gpt":0.2994290649800117,"score_spread":0.1875364510445526,"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."}}