{"id":"W2014016891","doi":"10.1007/s007990100043","title":"A fast method for determining the origins of documents based on LZW compression","year":2002,"lang":"en","type":"article","venue":"International Journal on Digital Libraries","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Copying; Computer science; Publication; Revenue; Information retrieval; World Wide Web; Database; Data mining; Advertising","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":[0.001047761,0.00176645,0.00165122,0.007139651,0.00172961,0.002416742,0.001964354,0.001694421,0.007696098],"category_scores_gemma":[0.005058318,0.0008026196,0.0007919612,0.004291499,0.001213389,0.003590774,0.002485089,0.002239023,0.009007812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008682499,"about_ca_system_score_gemma":0.002197223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002345294,"about_ca_topic_score_gemma":0.003136308,"domain_scores_codex":[0.9983425,0.0001826229,0.0001348196,0.0002080379,0.001004478,0.0001275127],"domain_scores_gemma":[0.9973911,0.0008167463,0.0002297157,0.000492349,0.0009538674,0.0001161302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007979483,0.00009273508,0.00107365,0.0005374314,0.00006532498,0.000296059,0.000361882,0.003484308,0.136451,0.01275754,0.007184614,0.8368974],"study_design_scores_gemma":[0.0005476119,0.0006023067,0.004521634,0.0002367804,0.0002550996,0.002920003,0.0005487261,0.3291558,0.5574166,0.0323099,0.07114298,0.000342456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009773999,0.001303897,0.9789028,0.0001675599,0.0002523279,0.0002570642,0.0005381505,0.006942479,0.001861619],"genre_scores_gemma":[0.02655024,0.0006347993,0.9685242,0.00005850483,0.0001237049,0.0002013146,0.001181022,0.000389515,0.002336744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007696098,"threshold_uncertainty_score":0.02574599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02826485079003627,"score_gpt":0.2944132124102884,"score_spread":0.2661483616202521,"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."}}