{"id":"W3011348730","doi":"10.1109/ibf50092.2020.9034821","title":"Exploring the Differences between Plausible and Correct Patches at Fine-Grained Level","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Correctness; Abstraction; Invariant (physics); Test case; Programming language; Artificial intelligence; Machine learning; Mathematics","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":[0.0001687887,0.0001186801,0.0001454024,0.00002635778,0.0002153393,0.0001406332,0.000546321,0.00002126077,0.000006812052],"category_scores_gemma":[0.0003183723,0.00007165051,0.00002865342,0.0002351307,0.00004972412,0.0002172168,0.0005633791,0.00009985686,0.00001249903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001088436,"about_ca_system_score_gemma":0.00001905738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001877978,"about_ca_topic_score_gemma":0.00002634547,"domain_scores_codex":[0.9991931,0.00004186763,0.0001296746,0.0002898361,0.0001642124,0.0001813655],"domain_scores_gemma":[0.9987118,0.0009194188,0.00004175569,0.0002122593,0.00002434859,0.00009042597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000594638,0.00001110207,0.8009944,0.00002602715,0.00002286126,0.000007263855,0.005336017,0.000003384586,0.0002094848,0.002182017,0.02739403,0.1638075],"study_design_scores_gemma":[0.0004301315,0.0005456796,0.909102,0.0001158322,0.00002690787,0.00002614982,0.00009701517,0.04735164,0.01635755,0.02299758,0.002190262,0.0007592881],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5847948,0.00004295778,0.4010324,0.007188696,0.00008611943,0.0001081444,0.000003188503,0.006351166,0.0003925428],"genre_scores_gemma":[0.934868,0.00000753106,0.0643864,0.0004823887,0.00008544126,0.00002208182,7.867262e-7,0.000005923702,0.0001414296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3500733,"threshold_uncertainty_score":0.2921823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3754039426601999,"score_gpt":0.2731418934620426,"score_spread":0.1022620491981573,"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."}}