{"id":"W4403943776","doi":"10.1007/978-3-031-67695-6_1","title":"The ARCH-COMP Friendly Verification Competition for Continuous and Hybrid Systems","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Arch; Engineering; Structural engineering","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002255681,0.0003929137,0.0003863984,0.0003993246,0.0005686177,0.001563432,0.002184173,0.0001688315,8.342234e-7],"category_scores_gemma":[0.00016844,0.000304415,0.00009339274,0.0003170492,0.0009519603,0.0005039105,0.0005889789,0.0005564401,0.00002144913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002574105,"about_ca_system_score_gemma":0.0002253881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001860399,"about_ca_topic_score_gemma":0.00001184143,"domain_scores_codex":[0.9968747,0.00005940634,0.000588257,0.001301766,0.0006659335,0.0005099708],"domain_scores_gemma":[0.9969851,0.0009666457,0.0003232356,0.001282941,0.0003299503,0.0001121141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007034065,0.000006304238,0.000002901783,0.000090897,0.000008458736,0.000005434458,0.0001813958,0.001866723,0.0001115614,0.7424939,0.00002193336,0.2552034],"study_design_scores_gemma":[0.0001389009,0.0002084393,0.00004210291,0.0003509801,0.00001176139,0.0001177223,7.062721e-7,0.7321773,0.0007126367,0.2380742,0.02779419,0.0003710311],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007220416,0.002281174,0.9888474,0.0006704764,0.004953855,0.00107447,0.00001992614,0.000203228,0.001877228],"genre_scores_gemma":[0.1358142,0.0002979,0.8614612,0.0002883041,0.0008770243,0.0001772134,0.00002501547,0.00006472318,0.00099443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7303106,"threshold_uncertainty_score":0.9999408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01732455329492432,"score_gpt":0.2649090069582571,"score_spread":0.2475844536633328,"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."}}