{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005760757,0.0009810219,0.0009364152,0.000920521,0.001671034,0.005909058,0.002245005,0.002481732,0.06099211],"category_scores_gemma":[0.007205335,0.001383971,0.001520306,0.001288062,0.002365236,0.006542679,0.003975207,0.006242442,0.02006918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002745237,"about_ca_system_score_gemma":0.002580027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002925157,"about_ca_topic_score_gemma":0.004912888,"domain_scores_codex":[0.9963933,0.0007990336,0.0001327379,0.0003971615,0.001963001,0.0003148397],"domain_scores_gemma":[0.9940777,0.002627954,0.00009324166,0.001719156,0.001099361,0.0003826212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002953254,0.0000624298,0.0001680696,0.0002005238,0.0000236765,0.0001635286,0.0002190271,0.007253157,0.002774022,0.7030381,0.1335389,0.1522632],"study_design_scores_gemma":[0.00007368328,0.00008848557,0.0002996673,0.0001382819,0.00001813944,0.0003581855,0.00009711716,0.05427005,0.006272242,0.4019119,0.5364149,0.00005738361],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007924654,0.004465508,0.6248156,0.008334802,0.003819814,0.0001151293,0.0006403975,0.007231851,0.3426522],"genre_scores_gemma":[0.2287616,0.003125733,0.2642184,0.003104458,0.002315788,0.0002519613,0.001785535,0.006590496,0.4898461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06099211,"threshold_uncertainty_score":0.2040389,"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."}}