{"id":"W1984067593","doi":"10.1145/2768577.2768578","title":"The SDEval benchmarking toolkit","year":2015,"lang":"en","type":"article","venue":"ACM communications in computer algebra","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Executable; Benchmarking; Computer science; Focus (optics); Field (mathematics); Task (project management); Symbolic computation; Programming language; Software engineering; Software; Code (set theory); Systems engineering; Engineering; Set (abstract data type); Mathematics","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002911709,0.0001594834,0.0001576056,0.0001434883,0.0004664883,0.0004602503,0.01219438,0.00007845067,0.000001924911],"category_scores_gemma":[0.0005332512,0.0001340782,0.00005863285,0.0009381298,0.0002337241,0.000819654,0.006117589,0.0004395798,0.0001012396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839442,"about_ca_system_score_gemma":0.000165156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004809508,"about_ca_topic_score_gemma":0.00005835616,"domain_scores_codex":[0.9976721,0.0007941445,0.0005031042,0.0003292695,0.0003550858,0.0003462715],"domain_scores_gemma":[0.9900909,0.001196783,0.0001692665,0.008224669,0.0002113462,0.0001070497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003789974,0.0000732648,0.001205274,0.000002660395,0.00001254903,0.000001406548,0.001658764,0.0002968569,0.00000809855,0.5270539,0.002651076,0.4670324],"study_design_scores_gemma":[0.0003808603,0.00008501956,0.01049676,0.00003484849,0.000004482355,0.00003460432,0.00005664806,0.797322,0.0000759211,0.102701,0.08853679,0.0002710864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004963717,0.0009426719,0.9809031,0.008093212,0.001243941,0.0003001147,8.476297e-7,0.0002477279,0.003304614],"genre_scores_gemma":[0.1298205,0.0001794742,0.8692609,0.0004961517,0.0001180399,0.0000731274,0.000007080515,0.00001104888,0.00003366864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7970251,"threshold_uncertainty_score":0.9931501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.114504119115066,"score_gpt":0.355765799854737,"score_spread":0.241261680739671,"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."}}