{"id":"W2037556552","doi":"10.5555/776816.776826","title":"Using benchmarking to advance research: a challenge to software engineering","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Benchmarking; Benchmark (surveying); Computer science; Data science; Software; Software engineering; Academic community; Management science; Engineering management; 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":[],"consensus_categories":[],"category_scores_codex":[0.001574427,0.0001855728,0.0001784032,0.000770873,0.0001672662,0.0002238184,0.00114399,0.00006469671,0.00004546241],"category_scores_gemma":[0.00657624,0.0001967732,0.00004518996,0.002388001,0.00001308876,0.0003994119,0.0006434722,0.0003861713,0.0002115424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003101651,"about_ca_system_score_gemma":0.0001077279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002942709,"about_ca_topic_score_gemma":0.000007967398,"domain_scores_codex":[0.9970098,0.00008196669,0.0002070441,0.0006905207,0.0009227904,0.001087936],"domain_scores_gemma":[0.9969612,0.001214816,0.00001221281,0.0009823786,0.0002763311,0.0005530898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001930115,0.0002786608,0.01071525,0.0003342186,0.00008029558,0.0004764595,0.007109301,0.65373,0.0169212,0.2121951,0.004859355,0.09328087],"study_design_scores_gemma":[0.001597145,0.002095603,0.02561524,0.001610251,0.00000964691,0.0003157147,0.0003433308,0.35259,0.05547032,0.003241575,0.5524682,0.004642979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03964792,0.0001647837,0.9580805,0.0002710849,0.000423417,0.0003788807,6.509526e-7,0.0005838079,0.0004489836],"genre_scores_gemma":[0.3091921,0.000004509859,0.6903958,0.00008655852,0.00007880252,0.0000501552,1.615773e-7,0.00002920056,0.0001626937],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5476089,"threshold_uncertainty_score":0.8024179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112132774218325,"score_gpt":0.3623551205264038,"score_spread":0.2502223463080788,"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."}}