{"id":"W4311273067","doi":"10.29007/fhnk","title":"ARCH-COMP 2022 Category Report: Falsification with Ubounded Resources","year":2022,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"JST-Mirai Program; Core Research for Evolutional Science and Technology; Exploratory Research for Advanced Technology; National Science Foundation; Division of Civil, Mechanical and Manufacturing Innovation; ACT-X; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Division of Industrial Innovation and Partnerships; Defense Advanced Research Projects Agency","keywords":"Comparability; Competition (biology); Arch; Computer science; Work (physics); Data science; Software engineering; Engineering; Civil engineering; Mathematics; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002430517,0.0001554417,0.0002073504,0.0001862652,0.0007432938,0.00013848,0.00119208,0.00003468438,0.0000486499],"category_scores_gemma":[0.0001627642,0.0001672693,0.00003633729,0.0009564,0.0001403815,0.0004395155,0.0007552759,0.000451809,0.000007594408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001991147,"about_ca_system_score_gemma":0.0001042539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002373543,"about_ca_topic_score_gemma":0.00003681194,"domain_scores_codex":[0.9975262,0.000491144,0.0004753012,0.000617688,0.0005363749,0.000353303],"domain_scores_gemma":[0.99832,0.0001715745,0.0003888906,0.001005395,0.00006237109,0.0000517253],"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":[0.0002865499,0.0007185246,0.05085755,0.0001894915,0.00008904227,0.00128755,0.09557209,0.09819148,0.003011927,0.3905536,0.001822792,0.3574194],"study_design_scores_gemma":[0.00151293,0.001085465,0.150528,0.00009058703,0.00001498436,0.00437872,0.009398364,0.7032407,0.002553464,0.03780273,0.08804655,0.001347446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3589231,0.0002556884,0.6338502,0.0008161234,0.00090763,0.0002953535,9.097465e-7,0.0003313181,0.004619597],"genre_scores_gemma":[0.6683764,0.000002682943,0.3311155,0.0001308282,0.00006784115,0.00003011087,0.00001023618,0.00001328205,0.0002530653],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6050493,"threshold_uncertainty_score":0.6821043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02085790349343988,"score_gpt":0.2712023298882709,"score_spread":0.2503444263948311,"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."}}