{"id":"W3181957689","doi":"10.1145/3460319.3464837","title":"Empirical evaluation of smart contract testing: what is the best choice?","year":2021,"lang":"en","type":"article","venue":"","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Vulnerability (computing); Empirical research; Computer security; Risk analysis (engineering); Data science","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":[0.0007515386,0.0000598313,0.00008988305,0.00002615308,0.0001120266,0.00008984808,0.000495252,0.00007870406,0.00007107125],"category_scores_gemma":[0.0003105773,0.00004129022,0.00003663003,0.0005692279,0.00007637108,0.0001906322,0.0001670013,0.0001253788,0.00002789802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001721293,"about_ca_system_score_gemma":0.0001643401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004063123,"about_ca_topic_score_gemma":0.0000642891,"domain_scores_codex":[0.9990972,0.00008804145,0.0001693378,0.0002364005,0.0002959954,0.000113067],"domain_scores_gemma":[0.9981029,0.000439047,0.00006770599,0.0007532072,0.0006131014,0.00002402177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001195893,0.0005460623,0.03364038,0.00001077949,0.0000476214,0.000002261268,0.0009523251,0.0000358178,0.002148831,0.1143701,0.002938509,0.8453061],"study_design_scores_gemma":[0.0006674908,0.0001058894,0.04455723,0.0000423388,0.00007278442,0.00005985096,0.0005607143,0.7872536,0.06783003,0.0783315,0.02028991,0.0002286601],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.790145,0.003382725,0.1008048,0.09585902,0.0002745215,0.0005513302,0.000001973239,0.0002424432,0.008738131],"genre_scores_gemma":[0.9902514,0.00003509844,0.007992092,0.00157667,0.00001798532,0.00003964033,7.644124e-7,0.000002336783,0.00008398323],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8450775,"threshold_uncertainty_score":0.1683766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07999998757489113,"score_gpt":0.3409563399381531,"score_spread":0.260956352363262,"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."}}