{"id":"W2079796778","doi":"10.1016/j.datak.2013.03.005","title":"Subject-based semantic document clustering for digital forensic investigations","year":2013,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Subject (documents); Computer science; Cluster analysis; Information retrieval; Document clustering; Natural language processing; Artificial intelligence; Data science; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.0001087038,0.0002007569,0.0001691635,0.0001127163,0.00007871657,0.0009008776,0.001226964,0.00004159949,0.00000529313],"category_scores_gemma":[0.0001291887,0.0001941127,0.00005082151,0.0003017659,0.00003451807,0.002693376,0.0007711345,0.00008624576,0.000223727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004424399,"about_ca_system_score_gemma":0.00006853037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001155468,"about_ca_topic_score_gemma":0.0000175279,"domain_scores_codex":[0.9987897,0.000004813422,0.0002486324,0.0004413346,0.0001318579,0.0003836167],"domain_scores_gemma":[0.9985476,0.0001581365,0.00004112622,0.001001645,0.00008454589,0.000166949],"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":[0.000003283369,0.0001658308,0.0003896834,0.0005495517,0.0001173596,0.000008035715,0.0005870084,0.002697739,0.0009105752,0.053773,0.0364923,0.9043056],"study_design_scores_gemma":[0.0002446545,0.00003419963,0.0002466253,0.00007350635,0.000007649985,0.000005516285,0.000008895027,0.9771532,0.0007371469,0.001418581,0.01980945,0.0002605248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006381615,0.0001223755,0.9907607,0.0002174032,0.000640729,0.0003830612,0.000111874,0.0003797278,0.001002522],"genre_scores_gemma":[0.8234453,0.000001876692,0.1745082,0.0001030608,0.0002473028,0.0001738758,0.001072483,0.00004979402,0.0003980605],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9744555,"threshold_uncertainty_score":0.8687183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02300508494314149,"score_gpt":0.2321864369908625,"score_spread":0.209181352047721,"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."}}