{"id":"W4400484650","doi":"10.1145/3663529.3663849","title":"Rethinking Software Engineering in the Era of Foundation Models: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","year":2024,"lang":"en","type":"article","venue":"","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Trustworthiness; Foundation (evidence); Computer science; Software engineering; Software development; Software; Data science; Computer security; History; Programming language; Archaeology","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":[],"consensus_categories":[],"category_scores_codex":[0.00135771,0.00006959253,0.0001103923,0.0001202829,0.00002849994,0.00003436786,0.0006435663,0.0000412407,0.000001446482],"category_scores_gemma":[0.00007430737,0.00004599694,0.00002589828,0.0006616632,0.00001753004,0.000259897,0.0000751733,0.0001892458,5.146793e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002459295,"about_ca_system_score_gemma":0.0001146792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006257118,"about_ca_topic_score_gemma":0.0002066111,"domain_scores_codex":[0.9990124,0.00007912092,0.0004069627,0.0001646294,0.0002411027,0.00009576108],"domain_scores_gemma":[0.9990855,0.0005005392,0.000076687,0.0002690856,0.00006161434,0.000006547892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003575588,0.00008088582,0.0002483605,0.0005454124,0.00001858214,0.000002919727,0.478738,0.04134883,0.00007039758,0.3606243,0.000009400091,0.1183093],"study_design_scores_gemma":[0.0001117137,0.00002180309,0.003914707,0.0005149752,0.000002360918,0.000004994897,0.002070083,0.9837919,0.001177609,0.00819727,0.0001091423,0.00008344432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2973065,0.001183253,0.7002565,0.0007398867,0.0001118562,0.0001908765,8.472776e-7,0.00005501014,0.000155318],"genre_scores_gemma":[0.9553778,0.00005350129,0.0445171,0.0000189349,0.000009105058,0.00001250108,0.00000745524,0.000003111901,5.441437e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9424431,"threshold_uncertainty_score":0.1875701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09938154788201323,"score_gpt":0.2759678766141226,"score_spread":0.1765863287321094,"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."}}