{"id":"W3164690045","doi":"10.14778/3457390.3457398","title":"CBench","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Question answering; Benchmark (surveying); Benchmarking; Suite; Set (abstract data type); Vocabulary; Information retrieval; Syntax; Graph; Artificial intelligence; Task (project management); Natural language processing; Theoretical computer science; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.005451474,0.002440565,0.001496007,0.00423879,0.001706122,0.004822135,0.005067746,0.002149372,0.05476948],"category_scores_gemma":[0.02197831,0.0009330835,0.001660417,0.004336617,0.001032908,0.005819295,0.005233258,0.003004603,0.04980744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002263814,"about_ca_system_score_gemma":0.003387237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01020541,"about_ca_topic_score_gemma":0.009110434,"domain_scores_codex":[0.9904391,0.00178865,0.0009540799,0.001575753,0.004353908,0.0008884288],"domain_scores_gemma":[0.9841962,0.003254206,0.0005617816,0.004424116,0.006858056,0.0007057588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001689816,0.0007363506,0.004956339,0.002487053,0.0001500611,0.0004098694,0.00101506,0.009941691,0.01033483,0.03232332,0.5929157,0.3430398],"study_design_scores_gemma":[0.0002302654,0.0005296072,0.004220993,0.000356691,0.00008261956,0.0004934697,0.000688325,0.04128337,0.01673515,0.0255317,0.9096842,0.0001635778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.03932189,0.004870806,0.2052555,0.002321876,0.002400007,0.002562144,0.08441047,0.4129123,0.245945],"genre_scores_gemma":[0.1754389,0.002539444,0.2789048,0.002925299,0.0003828545,0.003662153,0.3646212,0.05175762,0.1197677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05476948,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596362296791629,"score_gpt":0.2186539506523365,"score_spread":0.2026903276844202,"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."}}