{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003770155,0.0005557916,0.0004629545,0.001038046,0.0003312761,0.001376038,0.001191384,0.0008274643,0.001824004],"category_scores_gemma":[0.03740727,0.0005184539,0.0005507817,0.0005340728,0.001447174,0.002223904,0.000944728,0.001206293,0.0003291483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005300993,"about_ca_system_score_gemma":0.0005611067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001012285,"about_ca_topic_score_gemma":0.001927944,"domain_scores_codex":[0.99613,0.0009076021,0.0002395716,0.0007075703,0.001701275,0.000314033],"domain_scores_gemma":[0.9579926,0.02863689,0.003201532,0.007537012,0.002327181,0.0003047852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001615035,0.0006220036,0.2256907,0.0020452,0.0004109707,0.003073186,0.006679944,0.1748841,0.2158084,0.0265126,0.002782736,0.3398751],"study_design_scores_gemma":[0.0001616172,0.001607967,0.1344825,0.0003496601,0.0004791989,0.002993311,0.002425556,0.6444881,0.1504511,0.04564225,0.01675594,0.0001627655],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7597989,0.0003504389,0.2334078,0.0001845154,0.00002213949,0.0001712257,0.0004009573,0.002715495,0.002948714],"genre_scores_gemma":[0.9358541,0.00007989362,0.06264446,0.00004250279,0.000004734811,0.00005656662,0.0003733351,0.0005773139,0.0003671638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003770155,"threshold_uncertainty_score":0.01993877,"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."}}