{"id":"W4402979770","doi":"10.1109/otcon60325.2024.10687910","title":"Efficient Data Sampling and Reduction Methods in Large-Scale Forensic Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Scale (ratio); Reduction (mathematics); Sampling (signal processing); Data reduction; Data mining; Data science; Mathematics; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006429354,0.001112904,0.001231191,0.004133183,0.001494595,0.001551541,0.002112699,0.0007779697,0.002522744],"category_scores_gemma":[0.01502849,0.0006780683,0.001368049,0.003986357,0.001281053,0.002881281,0.0026385,0.001453314,0.001612578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007133856,"about_ca_system_score_gemma":0.001928391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002672701,"about_ca_topic_score_gemma":0.00311689,"domain_scores_codex":[0.9936167,0.002417541,0.0004155175,0.0008271318,0.002438113,0.0002849803],"domain_scores_gemma":[0.9910664,0.00375538,0.0007286571,0.002348297,0.001880445,0.0002206519],"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":[0.0004363283,0.0002615889,0.007463461,0.0005278829,0.0001840684,0.0003008861,0.0006672598,0.05178097,0.02462917,0.02383522,0.008017616,0.8818955],"study_design_scores_gemma":[0.0001074708,0.0002620232,0.008371035,0.0001570971,0.0001239203,0.0009649866,0.0007659678,0.8384922,0.04783604,0.07720236,0.02558471,0.000132317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006793991,0.0004951294,0.990985,0.0001635518,0.00003761347,0.0001211504,0.000112985,0.0008380575,0.00045252],"genre_scores_gemma":[0.1000487,0.0004616607,0.8976963,0.00009372455,0.00007175167,0.0003022674,0.0004995611,0.0001838296,0.0006423617],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006429354,"threshold_uncertainty_score":0.03400213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05488089126165763,"score_gpt":0.3940329991446129,"score_spread":0.3391521078829553,"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."}}