{"id":"W2081335906","doi":"10.1145/1620432.1620457","title":"Mining very long sequences in large databases with PLWAPLong","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Computer science; Suffix tree; Data mining; Tree (set theory); Event (particle physics); Set (abstract data type); Database; Node (physics); Trie; Algorithm; Theoretical computer science; Data structure; Mathematics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001431788,0.0007025418,0.0008070277,0.004336982,0.001019251,0.001720543,0.001545193,0.0009300285,0.001784668],"category_scores_gemma":[0.01072908,0.0006279519,0.0007002578,0.006051215,0.0005577035,0.003371949,0.001498318,0.000962471,0.001528386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004318906,"about_ca_system_score_gemma":0.00164059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002663897,"about_ca_topic_score_gemma":0.004399716,"domain_scores_codex":[0.9983792,0.0002471853,0.0002513915,0.0003619638,0.0006518167,0.0001084303],"domain_scores_gemma":[0.9945542,0.002686888,0.0007114026,0.00106316,0.000804566,0.0001799227],"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":[0.0008440993,0.0004159658,0.02334924,0.0004198627,0.0001627706,0.001477986,0.000573454,0.04417831,0.02003461,0.008215665,0.009904385,0.8904237],"study_design_scores_gemma":[0.0001026931,0.0002980071,0.004422361,0.00005561034,0.00006526704,0.001355728,0.000451649,0.9233909,0.02283901,0.03680242,0.01016772,0.0000485911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1203219,0.0006464161,0.8598489,0.0004902526,0.000056845,0.0003931263,0.00255737,0.01413223,0.001553011],"genre_scores_gemma":[0.278281,0.0002726301,0.7132434,0.0001757583,0.00006780244,0.0004096327,0.005492121,0.0002406349,0.001817012],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004336982,"threshold_uncertainty_score":0.007572114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02782060083375523,"score_gpt":0.2812846828287234,"score_spread":0.2534640819949682,"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."}}