{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001175155,0.0001286215,0.0001310918,0.0001461221,0.0001597595,0.001518878,0.00145497,0.00003344387,0.00004319664],"category_scores_gemma":[0.0001238408,0.0000768583,0.0001216357,0.00008824513,0.00004296291,0.002380647,0.000231125,0.0001580674,0.00001276609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004880636,"about_ca_system_score_gemma":0.00003275527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001275379,"about_ca_topic_score_gemma":7.640048e-8,"domain_scores_codex":[0.998674,0.00003895342,0.0003014235,0.0001858218,0.0006534206,0.000146428],"domain_scores_gemma":[0.9985855,0.0006827439,0.0002678015,0.0002350163,0.0001570003,0.00007197692],"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":[0.0002379316,0.0006361495,0.001393974,0.000007973117,0.00009509313,0.00003341714,0.0004329003,0.004762416,0.00007640733,0.1623317,0.01216707,0.817825],"study_design_scores_gemma":[0.00146234,0.0005478435,0.001644735,0.0002817679,0.000004970177,0.00003229581,0.00001874148,0.7738176,0.002102931,0.01012544,0.2097846,0.000176681],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003920864,0.00003241906,0.9871644,0.002947726,0.001287188,0.0001287198,0.0001464169,0.00004126539,0.004330977],"genre_scores_gemma":[0.8948642,0.000009056806,0.1029063,0.001509431,0.0003537242,0.0000102928,0.00002687206,0.00001486563,0.000305256],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8909433,"threshold_uncertainty_score":0.9995176,"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."}}