{"id":"W4402457710","doi":"10.1145/3650212.3680398","title":"Characterizing and Detecting Program Representation Faults of Static Analysis Frameworks","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Representation (politics); Static analysis; Program analysis; Programming language","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":[0.0002603071,0.00006505432,0.0001244065,0.0002556995,0.00003907329,0.0001811043,0.0001440531,0.00005670284,0.000002708498],"category_scores_gemma":[0.0002562669,0.00005505247,0.00004764553,0.001216006,0.00002127904,0.0002558775,0.00009768039,0.0001427265,0.000001011382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008963317,"about_ca_system_score_gemma":0.00001250231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001175519,"about_ca_topic_score_gemma":0.000003306845,"domain_scores_codex":[0.9992903,0.00003226109,0.0001773156,0.0002640299,0.0001278195,0.0001082497],"domain_scores_gemma":[0.9991459,0.0004790064,0.00005001907,0.0002498716,0.00004447202,0.00003073837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001102152,0.00001854412,0.01287051,0.00006861468,0.0001038861,0.000009962853,0.001535366,0.00002180817,0.0005729678,0.001176187,0.00008589205,0.9835352],"study_design_scores_gemma":[0.0000261797,0.00007817435,0.01338658,0.0001247838,0.00006637842,0.000009472014,0.00002136116,0.9648974,0.0052914,0.0159618,0.00003470423,0.0001017459],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.168599,0.00007771219,0.8235719,0.0002087244,0.00004929035,0.00009217564,3.931686e-7,0.007244086,0.000156757],"genre_scores_gemma":[0.6177772,0.000004207605,0.3821462,0.00003516584,0.000007983598,0.0000120567,0.000001021467,0.000002903279,0.00001323608],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9834334,"threshold_uncertainty_score":0.2244974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02245917158366384,"score_gpt":0.333704196811921,"score_spread":0.3112450252282571,"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."}}