{"id":"W3005998127","doi":"10.22148/16.034","title":"A BLAST-based, Language-agnostic Text Reuse Algorithm with a MARKUS Implementation and Sequence Alignment Optimized for Large Chinese Corpora","year":2019,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Reuse; Natural language processing; Phrase; Sequence (biology); Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004421076,0.0001831802,0.0003053477,0.0001225645,0.00007245774,0.0002323124,0.0005808324,0.00004945395,0.00001524381],"category_scores_gemma":[0.0001222139,0.000104539,0.00009059459,0.000302438,0.00002799344,0.0007186912,0.0001198862,0.0001695337,0.000001564879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012225,"about_ca_system_score_gemma":0.0001105271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001620211,"about_ca_topic_score_gemma":0.00001028883,"domain_scores_codex":[0.9987382,0.00004417521,0.0003807585,0.0002004407,0.0004008738,0.0002356053],"domain_scores_gemma":[0.998405,0.0001505976,0.000610895,0.0002643191,0.0004601569,0.0001089997],"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":[0.005115679,0.002779701,0.04659068,0.003265742,0.003814781,0.00489786,0.05369989,0.01604754,0.1889545,0.02903188,0.03569426,0.6101075],"study_design_scores_gemma":[0.01769361,0.005526351,0.001163092,0.001093711,0.0005699162,0.002721467,0.004679005,0.9208737,0.03315221,0.009682055,0.001294888,0.001549991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1864178,0.0009082883,0.8104522,0.001605819,0.0001023621,0.0004088714,0.00003107634,0.00006110004,0.00001244069],"genre_scores_gemma":[0.4133109,0.00002206607,0.5862447,0.0002777987,0.00004669969,0.000004354605,0.000008425473,0.000007299993,0.00007770504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9048262,"threshold_uncertainty_score":0.4262978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01158736095800556,"score_gpt":0.3090124364441694,"score_spread":0.2974250754861639,"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."}}