{"id":"W4229596932","doi":"10.1109/icse.2003.1201189","title":"Using benchmarking to advance research: a challenge to software engineering","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Software Engineering Research","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Benchmark (surveying); Computer science; Data science; Software engineering; Software; Academic community; Engineering management; Management science; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3067313,0.003312443,0.005469552,0.01250765,0.006122894,0.03085333,0.01107002,0.009709315,0.001905074],"category_scores_gemma":[0.5274109,0.001453562,0.0017279,0.01837414,0.02152988,0.05805392,0.02213132,0.01872171,0.002495675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007025863,"about_ca_system_score_gemma":0.02400173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002756448,"about_ca_topic_score_gemma":0.002514663,"domain_scores_codex":[0.6199469,0.2506683,0.02084692,0.01553928,0.08845881,0.004539864],"domain_scores_gemma":[0.2921697,0.4562198,0.02753133,0.1162977,0.09335408,0.01442746],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001250323,0.0003574165,0.00556878,0.00191922,0.0001852378,0.0001715079,0.004492269,0.009868663,0.001382212,0.4544932,0.03955973,0.4818767],"study_design_scores_gemma":[0.00008790466,0.0003992956,0.001505697,0.002298149,0.00004907482,0.0001694284,0.003333045,0.01498317,0.00163817,0.8636523,0.1116718,0.0002119368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0188834,0.02802297,0.6365957,0.280543,0.004217784,0.0006292321,0.0003318153,0.003720886,0.02705528],"genre_scores_gemma":[0.207364,0.0152135,0.7508223,0.01493976,0.003533965,0.00204169,0.0007791676,0.002474252,0.002831387],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6932687,"threshold_uncertainty_score":0.8549237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1101268605763671,"score_gpt":0.3553565504832152,"score_spread":0.2452296899068481,"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."}}