{"id":"W2776578796","doi":"10.1109/eisic.2017.28","title":"Catchem: A Browser Plugin for the Panama Papers Using Approximate String Matching","year":2017,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Plug-in; Levenshtein distance; Computer science; Panama; Matching (statistics); Information retrieval; Index (typography); String searching algorithm; World Wide Web; Government (linguistics); Sample (material); String (physics); Artificial intelligence; Computer security; Pattern matching; Mathematics; Programming language; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004588555,0.0001086492,0.0001329367,0.00003576986,0.001180422,0.001121776,0.001734926,0.00003114191,0.000009977251],"category_scores_gemma":[0.00006705192,0.00006949288,0.00009837679,0.00007081647,0.00004163534,0.0005627915,0.0004749641,0.00007846262,0.000004923928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002141412,"about_ca_system_score_gemma":0.00003900161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001132167,"about_ca_topic_score_gemma":0.0001067676,"domain_scores_codex":[0.9991084,0.00001421159,0.0001396753,0.0003095797,0.0001533796,0.0002747877],"domain_scores_gemma":[0.9984096,0.0001272382,0.0001290189,0.001251657,0.00003133007,0.00005115634],"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":[0.00003184605,0.0001719304,0.01177449,0.0001961502,0.001099295,0.00004114003,0.009933327,0.01325508,0.06270094,0.2364819,0.00370784,0.660606],"study_design_scores_gemma":[0.00030139,0.00001042359,0.001097213,0.00003767213,0.0000592631,0.000007698108,0.0004916312,0.9907325,0.002979611,0.001380384,0.002666972,0.0002352377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05449139,0.00003300718,0.9417815,0.001774902,0.0001477167,0.0001038426,0.000005179197,0.00009288345,0.001569627],"genre_scores_gemma":[0.8941268,0.000005720561,0.1047895,0.0001759826,0.00009053541,0.00001065091,0.000001815069,0.000008633123,0.0007903346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9774774,"threshold_uncertainty_score":0.9999152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05775512202307357,"score_gpt":0.3006049023985867,"score_spread":0.2428497803755131,"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."}}