{"id":"W4401632577","doi":"10.22215/etd/2024-16009","title":"Multilingual Fault Localization for Deep Learning Compilers","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Compiler; Codebase; Computer science; Deep learning; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001171971,0.001293507,0.0005974991,0.002105591,0.0005264211,0.0009789659,0.001564895,0.0006421632,0.001817927],"category_scores_gemma":[0.00667609,0.0004346931,0.0009196046,0.0009075082,0.0007302455,0.002160854,0.001691792,0.001185064,0.0006510197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001944253,"about_ca_system_score_gemma":0.002127325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006573015,"about_ca_topic_score_gemma":0.008697281,"domain_scores_codex":[0.9986885,0.0002781618,0.0001287265,0.0003354995,0.000419064,0.0001500485],"domain_scores_gemma":[0.9955225,0.001245718,0.0006342252,0.0008231911,0.001612532,0.0001618357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007207002,0.0004377609,0.02121099,0.0004490692,0.0001812916,0.0004849418,0.0004226213,0.3190277,0.04212764,0.01014808,0.009240469,0.5955488],"study_design_scores_gemma":[0.00002415482,0.0001978706,0.002070475,0.00004318641,0.00006003266,0.0001463133,0.0001306993,0.9327369,0.04942057,0.01167891,0.00346075,0.00003008039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2676099,0.0008163922,0.7010395,0.0004984688,0.0000951388,0.000121473,0.0007733974,0.02658988,0.002455961],"genre_scores_gemma":[0.7227369,0.0001699424,0.2725312,0.0001310284,0.00001759644,0.0001076963,0.001580145,0.0007659192,0.001959592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006573015,"threshold_uncertainty_score":0.01410663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01955025092504285,"score_gpt":0.3159425092879183,"score_spread":0.2963922583628755,"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."}}