{"id":"W7131243771","doi":"10.1109/jproc.2026.3659717","title":"Open-World Verification: A Grand Challenge for Autonomous Systems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the IEEE","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pleiades Robotics (Canada)","funders":"European Commission; Royal Academy of Engineering; Jet Propulsion Laboratory; UK Research and Innovation; California Institute of Technology; National Aeronautics and Space Administration","keywords":"Viewpoints; Automation; Robotics; Process (computing); Key (lock); Autonomy","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":[0.04012845,0.0007481367,0.001538009,0.001261962,0.002849597,0.007526376,0.004518304,0.004319133,0.003469999],"category_scores_gemma":[0.07062711,0.001003603,0.001691653,0.001103855,0.01438457,0.02491659,0.007445113,0.01086806,0.001287553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003178023,"about_ca_system_score_gemma":0.008793524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003246004,"about_ca_topic_score_gemma":0.002151724,"domain_scores_codex":[0.9766611,0.01117545,0.001173853,0.00218957,0.007696043,0.00110393],"domain_scores_gemma":[0.8842223,0.08593781,0.001957937,0.01484391,0.01095822,0.002079929],"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":[0.00005904614,0.00005572321,0.0006518062,0.000362374,0.00004822014,0.0001459128,0.0007697024,0.007341211,0.0007392317,0.8994572,0.01120649,0.07916304],"study_design_scores_gemma":[0.00002391801,0.0000303255,0.0001204084,0.0002121808,0.00001484232,0.0001155683,0.0003379789,0.01691354,0.0007479199,0.9367568,0.04468998,0.00003641511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00819629,0.01103542,0.8683638,0.1009849,0.001276074,0.0001109721,0.000153848,0.001106646,0.008772082],"genre_scores_gemma":[0.3997013,0.0179488,0.558741,0.01003074,0.003157214,0.0005631392,0.00065578,0.001044649,0.008157358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04012845,"threshold_uncertainty_score":0.2122221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04566996870659187,"score_gpt":0.3176068745893962,"score_spread":0.2719369058828044,"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."}}