{"id":"W3208600296","doi":"10.1109/dcc52660.2022.00015","title":"Computing Matching Statistics on Repetitive Texts","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Matching (statistics); String (physics); String searching algorithm; Attractor; Measure (data warehouse); Pattern matching; Computer science; Sequence (biology); Space (punctuation); Theoretical computer science; Algorithm; Mathematics; Statistics; Data mining; Artificial intelligence","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003784733,0.0002557111,0.000270825,0.0001245652,0.0003526694,0.0004076656,0.001732199,0.00008914487,0.000401738],"category_scores_gemma":[0.0000339472,0.0002316561,0.00006559158,0.0001149288,0.00002091455,0.0001243328,0.01075251,0.0009985301,0.00006986078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001229218,"about_ca_system_score_gemma":0.0001481144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002417067,"about_ca_topic_score_gemma":0.000004431771,"domain_scores_codex":[0.9977559,0.0001435727,0.0003235364,0.0009068876,0.0005900819,0.0002799858],"domain_scores_gemma":[0.9980416,0.0002673929,0.0002507025,0.001282505,0.00006644823,0.00009134419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009299558,0.0001847458,0.0001010683,0.0001081537,0.00005045756,0.0003108809,0.001652933,0.03970249,0.00001299399,0.7066623,0.02677436,0.2244303],"study_design_scores_gemma":[0.0002178966,0.0001314142,0.001642365,0.0002656301,0.00000934706,0.0000160602,0.0001100483,0.8641078,0.0000699813,0.1152854,0.01745382,0.0006901128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009402742,0.00004732203,0.9775656,0.0001969756,0.001906773,0.0002026694,0.0001961753,0.0003439865,0.01860024],"genre_scores_gemma":[0.03835465,0.00003422003,0.9580331,0.0009578437,0.000263544,0.0000172649,0.0003599203,0.00002910858,0.001950362],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8244054,"threshold_uncertainty_score":0.9972484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02070156763076163,"score_gpt":0.2928627847955807,"score_spread":0.2721612171648191,"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."}}