{"id":"W2080505681","doi":"10.1016/j.infsof.2004.08.005","title":"Replicating software engineering experiments: a poisoned chalice or the Holy Grail","year":2004,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Holy Grail; Software; Engineering; Computer science; Software engineering; World Wide Web; 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":[0.0002874538,0.0001804573,0.0001609854,0.0004241689,0.0002359474,0.0002120456,0.0009790324,0.000178941,0.000007301988],"category_scores_gemma":[0.003879931,0.000118472,0.0000338385,0.001051041,0.00008635557,0.00117126,0.000497041,0.0003522328,0.00006265857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001051496,"about_ca_system_score_gemma":0.00009287773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003485811,"about_ca_topic_score_gemma":0.000003000965,"domain_scores_codex":[0.9987432,0.000009762777,0.0003481259,0.0002270618,0.000281589,0.0003902127],"domain_scores_gemma":[0.9985381,0.0003178992,0.0001051514,0.0008226476,0.0001378146,0.0000783478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004541605,0.0001142438,0.01394145,0.0003354689,0.0001478633,0.00005529819,0.01502514,0.004772775,0.001117641,0.09927907,0.001066412,0.8640992],"study_design_scores_gemma":[0.02412692,0.004136357,0.1931821,0.002202661,0.0001043889,0.01003778,0.00820107,0.06630492,0.09264892,0.03172178,0.558463,0.008870028],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09315272,0.0002409553,0.899633,0.00291549,0.0001563031,0.0003195895,0.000003689186,0.003568228,0.00001006676],"genre_scores_gemma":[0.620299,0.00006556232,0.3783862,0.0007881389,0.00003367857,0.0003447688,0.000009521793,0.00002237072,0.00005074011],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8552292,"threshold_uncertainty_score":0.4831147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0136977408834442,"score_gpt":0.2550356574540044,"score_spread":0.2413379165705602,"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."}}