{"id":"W4393803857","doi":"10.5281/zenodo.8377067","title":"Software performance comparison traces","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Software; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001269581,0.0003290442,0.0004141855,0.0004336238,0.002801371,0.00157184,0.004996765,0.0002684624,0.001035649],"category_scores_gemma":[0.0006485379,0.0003139909,0.0001156708,0.001199752,0.0001757333,0.0006331468,0.00328641,0.0007633772,0.08693967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002127184,"about_ca_system_score_gemma":0.00001496522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000578707,"about_ca_topic_score_gemma":0.000001142458,"domain_scores_codex":[0.9967351,0.0003490779,0.0005634062,0.0009018274,0.0008395055,0.0006110625],"domain_scores_gemma":[0.9970591,0.00007739053,0.0003051757,0.001745525,0.0005945853,0.0002181932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001172413,0.00009041533,0.000004232616,0.0004499563,0.00003315457,0.00001284453,0.0001963687,0.00009099253,0.000003495624,0.00002289109,0.9280105,0.07107342],"study_design_scores_gemma":[0.0002584766,0.0002631814,0.0003670118,0.0001449461,0.00001544902,0.00009026195,0.00004338612,0.001341788,0.00002357634,0.00002630067,0.997063,0.0003625853],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0009116352,0.0002624159,0.01190935,0.0004649061,0.001841706,0.001063406,0.976,0.006028367,0.001518185],"genre_scores_gemma":[0.001049932,0.0004803324,0.0006634655,0.00009675369,0.0003423329,1.98984e-7,0.9959837,0.0009202565,0.0004630925],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08590402,"threshold_uncertainty_score":0.9999312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04082866879981261,"score_gpt":0.2673405081622772,"score_spread":0.2265118393624646,"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."}}