{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008607044,0.0006794533,0.0008949831,0.01232207,0.001418091,0.002757941,0.001706639,0.001569674,0.0006802518],"category_scores_gemma":[0.131563,0.000743259,0.0004958031,0.007535357,0.001867279,0.005455444,0.002093293,0.001124578,0.0004341558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001295771,"about_ca_system_score_gemma":0.001520147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005652518,"about_ca_topic_score_gemma":0.007411249,"domain_scores_codex":[0.9853787,0.003615114,0.002443424,0.002692992,0.005409294,0.0004604697],"domain_scores_gemma":[0.749422,0.1726256,0.03903081,0.01301517,0.02478415,0.001122281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005727429,0.0004871443,0.5883526,0.00227085,0.0002369336,0.00284503,0.01953102,0.006177117,0.02631666,0.002613905,0.004963612,0.3456325],"study_design_scores_gemma":[0.0001547503,0.0009017375,0.6862447,0.001065488,0.0005584673,0.01079359,0.01540701,0.1210099,0.1253408,0.006365136,0.03178252,0.0003759878],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9411913,0.001833777,0.05180269,0.0004553178,0.00005416436,0.0002832739,0.001062377,0.001677618,0.001639572],"genre_scores_gemma":[0.9159771,0.000785875,0.07919738,0.0001631336,0.00005718234,0.0001454093,0.002306357,0.0003667225,0.001000843],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01232207,"threshold_uncertainty_score":0.04551893,"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."}}