{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001746973,0.00008081074,0.00008852613,0.00007556835,0.00007783312,0.0001230451,0.0005086253,0.0000133468,0.0000134166],"category_scores_gemma":[0.00001167736,0.00006136629,0.00001070691,0.0004609176,0.00001818645,0.0009137742,0.0000895733,0.00006141319,0.0000200795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001323866,"about_ca_system_score_gemma":0.00004858653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008610705,"about_ca_topic_score_gemma":0.0003279303,"domain_scores_codex":[0.9991887,0.00001271891,0.0001207938,0.0003043283,0.0001432568,0.0002301695],"domain_scores_gemma":[0.9994118,0.00005029322,0.00003310246,0.0004364808,0.00001841224,0.00004996287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000104224,0.0006620589,0.08354156,0.00001636192,0.00002084399,0.0004000805,0.001998334,0.0002482338,0.000467263,0.3341617,0.006730007,0.5717432],"study_design_scores_gemma":[0.001974687,0.0005895117,0.5047813,0.0004500837,0.00001713179,0.0002297679,0.001419671,0.4571238,0.00601455,0.001456769,0.02452713,0.001415624],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.14588,0.00007600533,0.8481065,0.001224313,0.00004604033,0.00009189809,0.0000122348,0.0001798295,0.004383209],"genre_scores_gemma":[0.6248273,0.000009238709,0.3742894,0.0005267981,0.00002577732,0.000009521375,0.00002447293,0.000002844035,0.0002846598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5703275,"threshold_uncertainty_score":0.2502444,"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."}}