{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008422009,0.0002123858,0.000244548,0.0001293511,0.0002077487,0.0002468749,0.001061407,0.00006303634,0.0001196645],"category_scores_gemma":[0.00007811098,0.0001957007,0.00008897699,0.0004782672,0.0001059644,0.0004982688,0.00106389,0.0001496089,0.00006501038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000134971,"about_ca_system_score_gemma":0.00004339684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003903439,"about_ca_topic_score_gemma":0.00009549382,"domain_scores_codex":[0.9981018,0.00003211662,0.0003675795,0.000567804,0.0003364798,0.0005941943],"domain_scores_gemma":[0.9985451,0.0002911787,0.00008083139,0.000796211,0.0001075082,0.0001791866],"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":[0.00004391906,0.001218677,0.07867467,0.00023129,0.0001360844,0.0005737875,0.002734522,0.01691697,0.04378317,0.3899777,0.00116044,0.4645488],"study_design_scores_gemma":[0.0001862238,0.00005221558,0.02644075,0.00001197824,0.000003857534,0.0001104724,0.00002070194,0.9334173,0.01052971,0.02842188,0.0005005591,0.0003043272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1157208,0.00003720111,0.877735,0.0002004184,0.0005834216,0.0001452889,9.126533e-7,0.0006168356,0.004960197],"genre_scores_gemma":[0.4032024,4.35084e-7,0.5965079,0.0001610803,0.00008472328,8.284123e-7,8.107746e-7,0.000007411906,0.00003441218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9165003,"threshold_uncertainty_score":0.7980442,"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."}}