{"id":"W4231242876","doi":"10.1145/3089649.3089655","title":"4th International Workshop on Conducting Empirical Studies in Industry (CESI 2016)","year":2017,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Empirical research; Software; Field (mathematics); Computer science; Replication (statistics); Software engineering; Engineering management; Engineering; Knowledge management; Management science; 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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007076408,0.0003780602,0.0003884656,0.0004858028,0.0002515088,0.0004880189,0.004014483,0.0003371009,0.00001890352],"category_scores_gemma":[0.5211869,0.0003778868,0.00009753145,0.0003299006,0.0001095781,0.001007352,0.001917457,0.001454369,0.00008263328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002914492,"about_ca_system_score_gemma":0.0001055501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003245354,"about_ca_topic_score_gemma":0.000004692089,"domain_scores_codex":[0.9974512,0.00003479096,0.0003974046,0.0007472496,0.0006668659,0.0007024815],"domain_scores_gemma":[0.921598,0.07553887,0.0001541902,0.002292889,0.0002046309,0.0002114831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001074191,0.00008131489,0.9706451,0.00008012564,0.0001069631,0.0002598874,0.001078168,0.009194403,0.0003114391,0.0002768659,0.001895289,0.01605965],"study_design_scores_gemma":[0.001265283,0.0001173919,0.9821308,0.001836446,0.00001143834,0.00007252798,0.0001030569,0.003498924,0.005685919,0.0001590083,0.003887272,0.001231985],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9704151,0.000749558,0.02006411,0.003074344,0.004013329,0.0002559241,0.000007882329,0.001404887,0.00001484158],"genre_scores_gemma":[0.9566398,0.00005708336,0.0424111,0.0001254611,0.0004305417,0.00006344443,0.000004143879,0.00005587076,0.0002125684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5204793,"threshold_uncertainty_score":0.9998673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.196112487251442,"score_gpt":0.4040139648779832,"score_spread":0.2079014776265412,"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."}}