{"id":"W2780044948","doi":"10.1109/eisic.2017.19","title":"Text Mining in Unclean, Noisy or Scrambled Datasets for Digital Forensics Analytics","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Punctuation; Preprocessor; String (physics); Digital forensics; Suffix; Mobile device; Data mining; Analytics; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Computer security","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001768902,0.0001231693,0.0001693826,0.00006558045,0.0002804018,0.001227021,0.001504316,0.00005126023,0.00001059948],"category_scores_gemma":[0.0002641997,0.00008658719,0.00003771827,0.0000882915,0.00004617773,0.002133546,0.001123024,0.00006256301,0.00001911117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002101215,"about_ca_system_score_gemma":0.00006865464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004987545,"about_ca_topic_score_gemma":0.0001895868,"domain_scores_codex":[0.998947,0.000006134085,0.0002143512,0.0003714459,0.0001795071,0.0002815646],"domain_scores_gemma":[0.9982354,0.0001415545,0.0001218664,0.00136208,0.00004947097,0.00008962071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007710661,0.0001300513,0.003071642,0.00003304072,0.0000239977,0.00009258384,0.0001711862,0.0001480024,0.00004903927,0.01919325,0.1328228,0.8441873],"study_design_scores_gemma":[0.001211085,0.0001356751,0.003816346,0.00006921955,0.000005752729,0.00001098903,0.00006110901,0.9347559,0.0003076041,0.003418929,0.05592171,0.0002856923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004948186,0.00001038816,0.9912985,0.0005245768,0.0003085054,0.0002133893,0.0003652766,0.00006541701,0.00226579],"genre_scores_gemma":[0.4157477,0.00001033945,0.5813788,0.0004162977,0.0001742572,0.00001599764,0.000464981,0.00001961331,0.001772059],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9346079,"threshold_uncertainty_score":0.9998098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05723131250928121,"score_gpt":0.3220233973309604,"score_spread":0.2647920848216792,"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."}}