{"id":"W4284693828","doi":"10.1145/3510003.3510106","title":"Nessie","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Callback; Computer science; Asynchronous communication; Unit testing; Test case; Generator (circuit theory); JavaScript; Test (biology); Operating system; Programming language; Software; Machine learning; Computer network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002711871,0.0001240166,0.0001141783,0.000153859,0.0001393715,0.00009453014,0.002244401,0.00002328464,0.00004020818],"category_scores_gemma":[0.0006839926,0.000106105,0.00007518635,0.0003232926,0.00002053543,0.0002143217,0.0009727676,0.0002898964,0.000002630905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009905586,"about_ca_system_score_gemma":0.00004225414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006888553,"about_ca_topic_score_gemma":4.621411e-8,"domain_scores_codex":[0.9988234,0.000004378928,0.0001939404,0.0002442315,0.0005721875,0.0001618409],"domain_scores_gemma":[0.9993235,0.00008121609,0.0001532786,0.0001738229,0.0002317079,0.00003646421],"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":[0.00001972227,0.0001312171,0.02595411,0.00005848585,0.00005977244,0.000003363934,0.0007660842,0.003172541,0.00264806,0.943578,0.01398036,0.009628266],"study_design_scores_gemma":[0.001196696,0.0006936575,0.03647908,0.0009288747,0.00003133746,0.0003582512,0.000146456,0.7370191,0.0391368,0.1598,0.02253695,0.001672765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3173164,0.0001442486,0.6144869,0.01040921,0.009864034,0.001043718,0.00007375061,0.02783776,0.01882404],"genre_scores_gemma":[0.9210782,0.000002053697,0.07837665,0.0001757049,0.00004577408,0.00006732038,8.364511e-7,0.0000124874,0.0002409903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.783778,"threshold_uncertainty_score":0.4326836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02496960565977006,"score_gpt":0.2409004731539503,"score_spread":0.2159308674941803,"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."}}