{"id":"W4406858164","doi":"10.1109/tse.2025.3533972","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Software engineering; Workflow; Programming language; Foundation (evidence); World Wide Web; Database","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":[0.0003359242,0.0001497686,0.0001779509,0.0003155848,0.0001574522,0.00002133335,0.0001222547,0.00007886003,0.0001548502],"category_scores_gemma":[0.00001632409,0.0001316023,0.00003925494,0.0002924243,0.00003797116,0.0001433224,0.000001482101,0.000234819,0.00001115313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003972365,"about_ca_system_score_gemma":0.00004419934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001038281,"about_ca_topic_score_gemma":0.00006030173,"domain_scores_codex":[0.9990457,0.00007285094,0.0003234783,0.0002113586,0.000210232,0.0001364297],"domain_scores_gemma":[0.9993457,0.0001789768,0.00004107976,0.0003228392,0.00008133853,0.00003008538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006874269,0.0003998416,0.0001216221,0.00003192187,0.0001148995,2.905837e-7,0.02696965,0.9606627,0.0004932235,0.0005260315,0.00004346957,0.01056759],"study_design_scores_gemma":[0.003673419,0.001527045,0.01106398,0.000474664,0.0003188994,0.000001863839,0.02696354,0.9429153,0.01209878,0.0001417798,0.0001434702,0.0006773173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5921766,0.00001423296,0.4071506,0.0000236648,0.000242476,0.0002922344,0.00000352993,0.00005074991,0.00004589141],"genre_scores_gemma":[0.9980687,0.000006711699,0.001208142,0.00005121654,0.00001644153,0.0001868326,0.000004167448,0.00001969134,0.0004380319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4059424,"threshold_uncertainty_score":0.5366586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04758252356410681,"score_gpt":0.3070713554868336,"score_spread":0.2594888319227268,"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."}}