{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05121178,0.001179579,0.001506986,0.01863438,0.002225072,0.007846904,0.004282611,0.002523297,0.00253115],"category_scores_gemma":[0.1759272,0.001190864,0.001196628,0.01037175,0.003730793,0.01118076,0.004054109,0.002715519,0.001987969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00412288,"about_ca_system_score_gemma":0.0189489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007031085,"about_ca_topic_score_gemma":0.01048119,"domain_scores_codex":[0.9581364,0.01279819,0.0101522,0.002363499,0.0152297,0.001319977],"domain_scores_gemma":[0.6911216,0.1844923,0.02876047,0.01184197,0.07917626,0.004607349],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001329596,0.0003712685,0.02138189,0.01648476,0.0001025017,0.0002353402,0.00677727,0.002115092,0.002337684,0.01633772,0.01719898,0.9165245],"study_design_scores_gemma":[0.0001201377,0.002755484,0.09847998,0.1617994,0.0009416596,0.003162283,0.04755078,0.02045649,0.01901704,0.04237653,0.6024073,0.0009329029],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1798538,0.3839487,0.2835966,0.05131593,0.001417899,0.00435869,0.003059932,0.00632307,0.08612535],"genre_scores_gemma":[0.4555297,0.2100793,0.3157879,0.004388963,0.0003808406,0.003384261,0.004760479,0.001034198,0.004654411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9487882,"threshold_uncertainty_score":0.270837,"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."}}