{"id":"W2105974344","doi":"10.1109/ainaw.2007.184","title":"Filtering Spam Using Kolmogorov Complexity Estimates","year":2007,"lang":"en","type":"article","venue":"","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina; University of Ottawa","funders":"","keywords":"Kolmogorov complexity; Security token; Filter (signal processing); Computer science; Bag-of-words model; String (physics); Representation (politics); Bayesian probability; Computational complexity theory; Artificial intelligence; Pattern recognition (psychology); Algorithm; 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":[0.002390358,0.0008537117,0.001344275,0.003948191,0.0007344528,0.002423584,0.0008821145,0.001237486,0.002153291],"category_scores_gemma":[0.02663564,0.0005868862,0.0009696582,0.001227386,0.00125145,0.004874104,0.001382012,0.001560944,0.0009964391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001456963,"about_ca_system_score_gemma":0.001206965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002268653,"about_ca_topic_score_gemma":0.001880638,"domain_scores_codex":[0.9975151,0.0004854876,0.0001701078,0.0003206259,0.001347078,0.0001616502],"domain_scores_gemma":[0.9841471,0.01033475,0.001743465,0.001420527,0.002065101,0.0002890837],"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":[0.0005919502,0.0002395957,0.01311826,0.0003105953,0.0002970954,0.0004538063,0.0005403241,0.2609636,0.0288844,0.116469,0.006044412,0.572087],"study_design_scores_gemma":[0.00002062529,0.0000935723,0.003035541,0.00002720703,0.00003890984,0.0002000667,0.00003508292,0.9388499,0.007689546,0.04703203,0.002908411,0.00006916916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02921196,0.0002982907,0.9667242,0.0002284138,0.0000544555,0.00004407763,0.00005162178,0.0009845305,0.002402459],"genre_scores_gemma":[0.7216015,0.0007445703,0.2722485,0.0002761576,0.0004241453,0.0001553693,0.0003456078,0.0001883131,0.004015714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003948191,"threshold_uncertainty_score":0.01264155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09628748373229344,"score_gpt":0.320777332876426,"score_spread":0.2244898491441326,"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."}}