{"id":"W2792451387","doi":"10.1007/s10664-018-9600-2","title":"On the correctness of electronic documents: studying, finding, and localizing inconsistency bugs in PDF readers and files","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Correctness; Computer science; Information retrieval; World Wide Web; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002594352,0.0001414008,0.0001661769,0.0001554853,0.00007786648,0.00004215649,0.0002439828,0.0000587004,0.00001552059],"category_scores_gemma":[0.0007833838,0.0001143079,0.00002221069,0.0004059721,0.00008544721,0.0002108354,0.0001958367,0.0002361247,0.000003906343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008542139,"about_ca_system_score_gemma":0.00002268674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002646801,"about_ca_topic_score_gemma":0.00001969385,"domain_scores_codex":[0.9990344,0.00003441003,0.0002081992,0.0002916858,0.0001572261,0.0002740567],"domain_scores_gemma":[0.99894,0.0006779443,0.00006143233,0.000235125,0.00003803401,0.0000474578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002567774,0.0009554581,0.6598403,0.001264288,0.0004814835,0.000165204,0.03519472,0.01438652,0.005560522,0.05201185,0.01134394,0.2185389],"study_design_scores_gemma":[0.004529833,0.007117333,0.4037745,0.004482636,0.00008939835,0.0004336129,0.001800732,0.3060295,0.1473235,0.08212742,0.03755562,0.004735963],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3614558,0.0001426972,0.6378202,0.0001176324,0.00008357484,0.000138945,5.452549e-7,0.0002098651,0.00003066506],"genre_scores_gemma":[0.9863755,0.00002433019,0.01335935,0.0001498249,0.00002070333,0.00003088606,3.464725e-7,0.00001187658,0.00002723682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6249197,"threshold_uncertainty_score":0.4661342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01594798298001204,"score_gpt":0.2682681163052177,"score_spread":0.2523201333252056,"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."}}