{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00327499,0.001817317,0.001035483,0.003552251,0.0006837181,0.003465737,0.004507342,0.00159575,0.05794492],"category_scores_gemma":[0.01444713,0.001086044,0.001561992,0.003222921,0.0006370103,0.005446407,0.003845767,0.001806692,0.04109969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146098,"about_ca_system_score_gemma":0.001470749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004169803,"about_ca_topic_score_gemma":0.005275348,"domain_scores_codex":[0.9971499,0.0007481547,0.0003645708,0.0007594156,0.0007755948,0.0002023985],"domain_scores_gemma":[0.993634,0.002954484,0.0002469922,0.00155558,0.001306752,0.0003022793],"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":[0.001241639,0.0003884413,0.002480673,0.002670638,0.0001248469,0.0004665133,0.0008909164,0.005640082,0.008594096,0.03274715,0.6902624,0.2544926],"study_design_scores_gemma":[0.0003850048,0.0003315411,0.001920897,0.0003015352,0.00007524446,0.0004427908,0.0003827529,0.0491253,0.01721393,0.03099647,0.8987173,0.000107189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.0129569,0.002483359,0.213393,0.001392905,0.000843357,0.001489803,0.1222516,0.570156,0.07503302],"genre_scores_gemma":[0.07148253,0.001757595,0.2461993,0.001769576,0.0002430859,0.002089349,0.5752949,0.05870382,0.04245991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05794492,"threshold_uncertainty_score":0,"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."}}