{"id":"W4401414416","doi":"10.1109/ms.2024.3440190","title":"A State-of-the-Practice Release-Readiness Checklist for Generative AI-Based Software Products: A Gray Literature Survey","year":2024,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bank of Canada; National Bank of Canada; Business Development Bank of Canada; Queen's University","funders":"","keywords":"Software engineering; Checklist; Computer science; Software peer review; Software development; Software; Generative grammar; State (computer science); Software release life cycle; Software quality; Engineering management; Software construction; Engineering; Programming language; Artificial intelligence; Psychology","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":[0.00157253,0.0004319604,0.0004007679,0.0003173527,0.0003461506,0.0006634931,0.001750402,0.000164965,0.000004118946],"category_scores_gemma":[0.02255543,0.0003307698,0.0002327008,0.003475017,0.0001493858,0.00108423,0.0002825828,0.0007462843,0.00002137702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002241972,"about_ca_system_score_gemma":0.001228762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001155768,"about_ca_topic_score_gemma":0.00005387839,"domain_scores_codex":[0.9964437,0.0003913876,0.0004785601,0.001112508,0.0008778072,0.0006960439],"domain_scores_gemma":[0.9896922,0.006283782,0.0001346284,0.001584584,0.002125293,0.0001794858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001528886,0.00224874,0.05172657,0.02219174,0.00213585,0.001547732,0.0284363,0.1125784,0.01003047,0.003059828,0.4621376,0.3023779],"study_design_scores_gemma":[0.005919045,0.002260441,0.05344822,0.009248441,0.000373339,0.0006207786,0.00005998289,0.1916513,0.3808894,0.009725594,0.3395758,0.006227675],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0151157,0.003279404,0.9730742,0.002144747,0.003237605,0.00119057,0.0007814332,0.001173666,0.000002655416],"genre_scores_gemma":[0.5467156,0.00004517123,0.4466026,0.001433065,0.0007332809,0.0009471118,0.0002647725,0.000271029,0.002987453],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5315998,"threshold_uncertainty_score":0.9999144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01837307102445155,"score_gpt":0.2940337656147816,"score_spread":0.27566069459033,"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."}}