{"id":"W3147362533","doi":"10.1007/s10664-021-09944-w","title":"Revisiting the VCCFinder approach for the identification of vulnerability-contributing commits","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds National de la Recherche Luxembourg; European Commission","keywords":"Commit; Computer science; Identification (biology); Vulnerability (computing); Replicate; Artificial intelligence; Machine learning; Replication (statistics); Software; Set (abstract data type); Software deployment; Data science; Software engineering; Computer security; Programming language; Database","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002554971,0.0001725238,0.0002363387,0.00005479828,0.0003298402,0.0002013785,0.001123797,0.00008295929,0.00000379184],"category_scores_gemma":[0.01932131,0.0001174201,0.0001733178,0.0007969289,0.00004426729,0.0001906513,0.0004590539,0.0004402239,0.000002809145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000937538,"about_ca_system_score_gemma":0.00008387148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005078195,"about_ca_topic_score_gemma":1.881656e-7,"domain_scores_codex":[0.99797,0.00009664859,0.0005411925,0.0004192833,0.0004675259,0.0005053122],"domain_scores_gemma":[0.987686,0.01075425,0.0001061075,0.001029121,0.000352231,0.00007231846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001329031,0.0001372309,0.1903456,0.001000226,0.0003346316,0.00001295017,0.002275367,0.7130486,0.004716008,0.004848188,0.001226254,0.08204161],"study_design_scores_gemma":[0.0003915092,0.00001867393,0.2307944,0.00006635732,0.00002566754,0.00003921447,0.00008939335,0.7461123,0.01541568,0.00022062,0.006496404,0.0003297637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0221562,0.001417378,0.9738256,0.001622186,0.000293933,0.0003451027,0.000007873459,0.0003263135,0.000005376879],"genre_scores_gemma":[0.927021,0.000009736954,0.07230441,0.00009087668,0.0003219943,0.0001562254,0.00001159497,0.00002823618,0.00005595777],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9048648,"threshold_uncertainty_score":0.9889393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03679435711364231,"score_gpt":0.3062734892830032,"score_spread":0.2694791321693609,"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."}}