{"id":"W4312691443","doi":"10.14778/3554821.3554869","title":"SmartBench","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmark (surveying); Computer science; Question answering; Usability; Cover (algebra); Task (project management); Software deployment; Natural language; Information retrieval; Quality (philosophy); Natural language processing; Artificial intelligence; Software engineering; Human–computer interaction; Systems engineering; 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":[0.0003158916,0.00006761811,0.00008442576,0.00004501127,0.0002024335,0.00003581343,0.001526354,0.000009437035,0.00003639613],"category_scores_gemma":[0.00002051232,0.00005075029,0.0000653261,0.0002716388,0.00001666288,0.0001405936,0.001748927,0.0001261654,0.000003004922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007914117,"about_ca_system_score_gemma":0.00002542472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002764384,"about_ca_topic_score_gemma":3.025146e-7,"domain_scores_codex":[0.9990034,0.000005422598,0.0001646442,0.000211024,0.0004493598,0.0001662043],"domain_scores_gemma":[0.9996046,0.00001246391,0.0001188564,0.0001852888,0.00004962919,0.00002910781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008051571,0.0001871533,0.007434713,0.00005735252,0.00003687705,9.458402e-7,0.003747841,0.00115341,0.04477048,0.9100366,0.009307684,0.02325891],"study_design_scores_gemma":[0.002323903,0.0005978493,0.007704653,0.00008927898,0.00005686779,0.000205834,0.002078534,0.1757082,0.3851894,0.2358406,0.189196,0.001008793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8732742,0.0004516206,0.0161319,0.0190174,0.002649425,0.001127141,0.000006052176,0.0003439264,0.08699835],"genre_scores_gemma":[0.9899225,0.000002821462,0.008913582,0.0003391297,0.00003118925,0.00006525459,8.006887e-8,0.000004368705,0.0007210274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.674196,"threshold_uncertainty_score":0.2836372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01437296138964501,"score_gpt":0.2055985376341623,"score_spread":0.1912255762445173,"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."}}