{"id":"W2798496775","doi":"10.23919/date.2018.8342261","title":"Suspect set prediction in RTL bug hunting","year":2018,"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 Toronto","funders":"","keywords":"Debugging; Computer science; Algorithmic program debugging; Probabilistic logic; Set (abstract data type); Software bug; Representation (politics); Programming language; Graph; Theoretical computer science; Artificial intelligence; Software","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":[0.0003936492,0.00006408888,0.00006687081,0.0001186889,0.0000666954,0.00008247139,0.0003405658,0.00003755333,0.00002635627],"category_scores_gemma":[0.0002297217,0.00005762145,0.00001685766,0.0003832025,0.00003080308,0.0002357369,0.0001497644,0.00007546248,0.00007921396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003152755,"about_ca_system_score_gemma":0.00002357243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003753034,"about_ca_topic_score_gemma":0.00006272759,"domain_scores_codex":[0.9993097,0.00002716375,0.0001317812,0.0002323079,0.0001199476,0.0001790901],"domain_scores_gemma":[0.999455,0.0001060731,0.00003166759,0.0003252667,0.00005317646,0.00002880814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005295872,0.00007913922,0.7109345,0.00001584718,0.000007148633,0.00002484801,0.002071836,0.000009612408,0.0005958337,0.02089517,0.1853839,0.0799769],"study_design_scores_gemma":[0.0005588199,0.0006182967,0.2565306,0.0002238633,0.000004425375,0.0001088494,0.00002642847,0.4786583,0.02010722,0.235895,0.006705118,0.0005629864],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08888572,0.00001481247,0.8545423,0.0004716604,0.0003664499,0.0001031912,6.476663e-7,0.02125661,0.03435868],"genre_scores_gemma":[0.8226154,5.16452e-7,0.1767671,0.0002106391,0.0001135201,0.000005277198,6.07969e-7,0.000004017139,0.0002828474],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7337297,"threshold_uncertainty_score":0.2349734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02626076201855171,"score_gpt":0.2771563603785227,"score_spread":0.250895598359971,"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."}}