{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04915947,0.0009891796,0.000821157,0.003335233,0.004827689,0.01307873,0.002346434,0.005123787,0.001374419],"category_scores_gemma":[0.07170636,0.001359175,0.001127618,0.002602431,0.01878156,0.03714928,0.009208269,0.01281183,0.0006169698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005549296,"about_ca_system_score_gemma":0.009157106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003437137,"about_ca_topic_score_gemma":0.004959668,"domain_scores_codex":[0.9644681,0.01579294,0.001920047,0.001856597,0.01434677,0.001615499],"domain_scores_gemma":[0.9037346,0.05463267,0.004501927,0.02445681,0.01093732,0.001736692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001012368,0.0001393708,0.007809752,0.001057259,0.00007511445,0.001363791,0.05888037,0.00677599,0.006961025,0.6580594,0.01629446,0.2424822],"study_design_scores_gemma":[0.0000272087,0.0002376664,0.002456101,0.002459452,0.00005507085,0.002465708,0.02474934,0.02056652,0.00869486,0.6207321,0.3172907,0.0002652611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.1437377,0.02941271,0.6156038,0.1572421,0.001570205,0.0002521962,0.0001447793,0.001658082,0.05037848],"genre_scores_gemma":[0.6648684,0.01339199,0.3015198,0.009830563,0.0006887679,0.0002253201,0.0001964664,0.001404681,0.007874068],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.04915947,"threshold_uncertainty_score":0.2599833,"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."}}