{"id":"W2910794638","doi":"10.1145/3287624.3287661","title":"Suspect2vec","year":2019,"lang":"en","type":"article","venue":"","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Suspect; Boolean satisfiability problem; Overhead (engineering); Algorithmic program debugging; Key (lock); Baseline (sea); Prioritization; Solver; Satisfiability; Software deployment; Programming language; Algorithm; Software engineering; Operating system","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001639529,0.00002587041,0.0000307539,0.00002320142,0.00001144032,0.00003367143,0.0003799159,0.00001370055,0.0001707765],"category_scores_gemma":[0.00001379173,0.00002124613,0.00001245844,0.0001280469,0.000004742138,0.0003008983,0.00006878832,0.00002850206,0.002267788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001088672,"about_ca_system_score_gemma":0.000009155695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004104519,"about_ca_topic_score_gemma":3.046619e-7,"domain_scores_codex":[0.9996719,0.00001739053,0.00004963357,0.0001090212,0.00007857577,0.0000734281],"domain_scores_gemma":[0.9995487,0.00001510173,0.00001392449,0.0003875576,0.00001695606,0.00001769839],"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":[2.298355e-7,0.000003569199,0.0005309358,0.000001057677,5.518876e-7,1.518114e-7,0.00003840609,0.000004871144,0.0009961474,0.9841931,0.0002469032,0.0139841],"study_design_scores_gemma":[0.0004462591,0.0001952507,0.05948103,0.000008330403,0.000001526897,0.00003176647,0.00005094156,0.6021128,0.1376138,0.06034437,0.1392865,0.0004274714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01330226,0.000005183275,0.7539688,0.0001543135,0.000323489,0.00004437022,2.151397e-8,0.0001311823,0.2320704],"genre_scores_gemma":[0.2829133,6.583869e-7,0.7126344,0.000172704,0.000009832139,0.000001316994,7.398439e-8,0.000001244034,0.004266492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9238487,"threshold_uncertainty_score":0.998509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00897527818925105,"score_gpt":0.2492333524332143,"score_spread":0.2402580742439633,"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."}}