{"id":"W1992813097","doi":"10.1109/test.2014.7035339","title":"Clustering-based failure triage for RTL regression debugging","year":2014,"lang":"en","type":"article","venue":"","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Debugging; Triage; Cluster analysis; Robustness (evolution); Data mining; Machine learning; Reliability engineering; Programming language; Engineering","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":[0.0009995521,0.00009594755,0.0001121237,0.00007882906,0.0001283502,0.0001038517,0.0005824862,0.00006145338,0.00001255923],"category_scores_gemma":[0.0003674486,0.00007324103,0.00005737151,0.0001605742,0.0000169971,0.0003355865,0.00009018255,0.00006183854,0.00001723553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002833057,"about_ca_system_score_gemma":0.00002573257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003672593,"about_ca_topic_score_gemma":0.00001213997,"domain_scores_codex":[0.9991013,0.0001038756,0.0001792346,0.0002726227,0.0001454602,0.0001974712],"domain_scores_gemma":[0.9989952,0.0002141475,0.00009238271,0.0005812089,0.00005966704,0.00005733855],"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":[0.00006598559,0.00006699413,0.0001802071,0.0001442058,0.000009282134,7.888374e-7,0.0002885898,0.0027987,0.01061113,0.2189689,0.007767375,0.7590978],"study_design_scores_gemma":[0.0004641362,0.00008046146,0.0001836617,0.00002824671,0.00000235,0.000001514372,0.00000373827,0.9542562,0.02253536,0.001770542,0.0205642,0.0001095406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005035798,0.000007305502,0.9955165,0.001107809,0.0003855168,0.0002301248,4.259343e-7,0.0003579704,0.001890791],"genre_scores_gemma":[0.1937131,2.360182e-7,0.8054914,0.0004581874,0.00004798154,0.00004000212,0.000001918983,0.00000710313,0.0002399916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9514576,"threshold_uncertainty_score":0.2986682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0299304796440166,"score_gpt":0.3068266888396271,"score_spread":0.2768962091956105,"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."}}