{"id":"W4282830605","doi":"10.1109/icse-companion55297.2022.9793757","title":"DiffWatch: Watch Out for the Evolving Differential Testing in Deep Learning Libraries","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Python (programming language); Computer science; Differential (mechanical device); Deep learning; Artificial intelligence; Operating system; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001049561,0.0006902372,0.00062372,0.0006028748,0.001044856,0.0012949,0.004616837,0.0001430725,0.0001887587],"category_scores_gemma":[0.005357674,0.0006582238,0.0002207028,0.001155719,0.00008869839,0.0010286,0.001860424,0.001772845,0.00001951527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005421186,"about_ca_system_score_gemma":0.000176242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007640768,"about_ca_topic_score_gemma":0.000003622543,"domain_scores_codex":[0.9953721,0.00007615794,0.0009593977,0.001222957,0.001452339,0.0009170109],"domain_scores_gemma":[0.9951752,0.002566795,0.0005462441,0.0006447714,0.0008602522,0.0002067224],"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":[0.0003675337,0.001801669,0.3607709,0.0006948164,0.0007029518,0.00009450622,0.02461004,0.09401854,0.009380265,0.4203064,0.04242463,0.04482779],"study_design_scores_gemma":[0.000929678,0.0003349578,0.01767826,0.0002756273,0.00002512475,0.00007905126,0.0003478529,0.9633086,0.0006168523,0.01115966,0.004339793,0.0009045032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1019731,0.0001839694,0.8762445,0.002745159,0.006116175,0.001276572,0.00004521902,0.01100362,0.0004116205],"genre_scores_gemma":[0.9072813,0.00001908752,0.09060369,0.0002436931,0.0004525309,0.0008479208,0.00006357917,0.000103686,0.0003844497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8692901,"threshold_uncertainty_score":0.9997419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05555531626052307,"score_gpt":0.2678024017501799,"score_spread":0.2122470854896569,"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."}}