{"id":"W2485697085","doi":"10.1109/icst.2016.32","title":"Atrina: Inferring Unit Oracles from GUI Test Cases","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Intel Corporation","keywords":"JavaScript; Computer science; Unit testing; Leverage (statistics); Programming language; Assertion; Test suite; Test case; Software testing; Code (set theory); Artificial intelligence; Software; Machine learning","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":[0.0001432031,0.0001149906,0.0001102114,0.00008007242,0.00009154456,0.0001107297,0.00067238,0.00004557075,0.00004846384],"category_scores_gemma":[0.001679904,0.00007183031,0.00003555431,0.0002051274,0.00003843608,0.0003443157,0.0003870887,0.00004931312,0.0001786987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002340214,"about_ca_system_score_gemma":0.00005633161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001224594,"about_ca_topic_score_gemma":0.00005840628,"domain_scores_codex":[0.999163,0.00002507376,0.0001526961,0.0002980652,0.0001500781,0.0002110681],"domain_scores_gemma":[0.9964463,0.00270332,0.00005072287,0.0006461708,0.00007613832,0.00007731503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001885083,0.00006276272,0.6491584,0.000004435282,0.000009410468,0.0001610158,0.00009605585,7.766394e-7,0.001154302,0.01082559,0.02997635,0.3085491],"study_design_scores_gemma":[0.0013267,0.0008123124,0.3126432,0.0009947672,0.00003134312,0.0004376851,0.00002052626,0.005813969,0.08618166,0.53698,0.05279548,0.001962259],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1242079,0.00008893983,0.8437471,0.001286766,0.0001562768,0.00007537694,0.000007034779,0.02678771,0.003642834],"genre_scores_gemma":[0.7643353,0.000007264223,0.2348537,0.0002256681,0.00006339235,0.000004801323,4.760878e-7,0.000007657034,0.0005016997],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6401274,"threshold_uncertainty_score":0.2929155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0483765411939089,"score_gpt":0.2788364857413657,"score_spread":0.2304599445474568,"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."}}