{"id":"W2171074827","doi":"10.1145/2687148.2687151","title":"Verifying security patches","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Correctness; Credence; Sketch; Semantics (computer science); Set (abstract data type); Program analysis; Computer security; Nothing; Programming language; Theoretical computer science; Algorithm; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.000277546,0.00005551405,0.00006175611,0.00003098241,0.00006174271,0.00008057846,0.000408248,0.00002727138,0.000005561377],"category_scores_gemma":[0.0002197015,0.00004637591,0.00002262249,0.0001146469,0.00001375521,0.0001390939,0.0001457425,0.0000583726,0.00004272175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009095956,"about_ca_system_score_gemma":0.000009125823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008665673,"about_ca_topic_score_gemma":0.000002144467,"domain_scores_codex":[0.9995103,0.00002859062,0.00006993457,0.0001679503,0.00009653066,0.0001266875],"domain_scores_gemma":[0.9993575,0.0001786688,0.00002062932,0.0003775766,0.00002546075,0.00004016197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001385777,0.00006901194,0.03346958,0.00002913147,0.000007326955,0.000006349398,0.001522065,0.000007055458,0.0001828919,0.2902309,0.1158422,0.5586321],"study_design_scores_gemma":[0.00009348673,0.00007137159,0.002793586,0.00002285012,0.000001421102,0.00001542877,0.000002115846,0.1603732,0.00459576,0.8170413,0.01477205,0.0002174772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005582052,0.00001588388,0.9595575,0.000368996,0.000102954,0.00002421642,5.578503e-8,0.01721693,0.01713141],"genre_scores_gemma":[0.7182918,6.817944e-7,0.2811425,0.0004798285,0.00002763066,0.000002952856,1.39427e-7,0.00000244565,0.0000520579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7127097,"threshold_uncertainty_score":0.1891155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01113564913132811,"score_gpt":0.2292289484173727,"score_spread":0.2180932992860446,"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."}}