{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001606062,0.0007129067,0.0005186179,0.00200932,0.0002552777,0.00086891,0.00282113,0.0002609519,0.0001812547],"category_scores_gemma":[0.02405716,0.0008155166,0.0001168275,0.003684172,0.00004172446,0.001062824,0.0008015716,0.001321366,0.000329014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001114423,"about_ca_system_score_gemma":0.0003632354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002198966,"about_ca_topic_score_gemma":0.00000306171,"domain_scores_codex":[0.9935786,0.00003417471,0.0006685107,0.001602658,0.00239492,0.001721186],"domain_scores_gemma":[0.9948,0.00009815988,0.000114142,0.0007420091,0.00324367,0.001001977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002660777,0.0001408052,0.003339393,0.0001527551,0.00009051163,0.00009192485,0.001150655,0.04131754,0.0005259609,0.9495891,0.002829731,0.000744961],"study_design_scores_gemma":[0.0008193678,0.0008566037,0.004067846,0.001747629,0.00001117939,0.0001344538,0.0001256912,0.8810512,0.006227043,0.000123015,0.1028016,0.002034442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03554428,0.0001257,0.9582456,0.00007472648,0.002669547,0.0009707446,0.00002500254,0.001614498,0.0007298615],"genre_scores_gemma":[0.1309175,0.00003994091,0.8674935,0.0002010498,0.0004453416,0.0003523687,0.000007128916,0.0001439733,0.0003992042],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9494662,"threshold_uncertainty_score":0.9994296,"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."}}