{"id":"W2913028816","doi":"","title":"Proceedings of the third international workshop on Large scale testing","year":2014,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Acceptance testing; Unit testing; Schedule; Software performance testing; Scale (ratio); Integration testing; Software engineering; Software testing; System testing; Software; Software system; Operating system","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":[0.01051777,0.001873963,0.00145932,0.002316363,0.001363124,0.008182506,0.003369992,0.002993159,0.09661298],"category_scores_gemma":[0.01532964,0.0008636297,0.001803853,0.001628756,0.001906961,0.006463076,0.004477895,0.005281199,0.03690586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002263135,"about_ca_system_score_gemma":0.003112991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001982855,"about_ca_topic_score_gemma":0.00232858,"domain_scores_codex":[0.9908735,0.002803798,0.0006746367,0.001314022,0.003491873,0.00084217],"domain_scores_gemma":[0.9865814,0.003989554,0.0003093966,0.002391639,0.005012704,0.001715201],"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":[0.0002266015,0.0001847135,0.0004034849,0.0004283416,0.00005434407,0.0002786494,0.000474466,0.001966629,0.00323492,0.03024396,0.6324925,0.3300114],"study_design_scores_gemma":[0.00002556036,0.0000830549,0.0003389592,0.0003317782,0.00002035367,0.0002578972,0.0001682076,0.001838615,0.001369225,0.01415449,0.9813831,0.00002880397],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.007965323,0.05612106,0.4077241,0.04395731,0.1116116,0.001227632,0.00274964,0.009803102,0.3588403],"genre_scores_gemma":[0.08111969,0.03659369,0.1810789,0.01091961,0.02430252,0.001533311,0.01291066,0.008454876,0.6430868],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.09661298,"threshold_uncertainty_score":0.3232027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01366349227969791,"score_gpt":0.2378753392185736,"score_spread":0.2242118469388757,"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."}}