{"id":"W1573155476","doi":"10.1007/978-3-642-15105-7_22","title":"An Occurrence Based Approach to Mine Emerging Sequences","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Discriminative model; Constraint (computer-aided design); Computer science; Sequence (biology); Uniqueness; Contrast (vision); Selection (genetic algorithm); Data mining; Artificial intelligence; Pattern recognition (psychology); Mathematics","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001066582,0.0006447805,0.0005471208,0.001016882,0.0004547009,0.001001389,0.00733385,0.0003666453,0.00002612186],"category_scores_gemma":[0.00007747288,0.0005479941,0.0001049893,0.000921888,0.0005674799,0.001284016,0.001520788,0.001175195,0.00004259085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001295211,"about_ca_system_score_gemma":0.0007223747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006472383,"about_ca_topic_score_gemma":0.00004817803,"domain_scores_codex":[0.9947619,0.00004462792,0.0005270281,0.002470134,0.001369315,0.0008269971],"domain_scores_gemma":[0.9960431,0.0002373115,0.0002608055,0.002678464,0.0002940999,0.0004862375],"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":[0.000007101067,0.0001147504,0.00005596465,0.00004626502,0.000004870387,0.00005852845,0.0007286706,0.09696613,0.002002838,0.00685625,0.00005868803,0.8931],"study_design_scores_gemma":[0.0001699424,0.0002173075,0.00006358914,0.0002447431,0.000004925093,0.0000410838,2.069835e-7,0.9742683,0.0024635,0.0165999,0.005046302,0.0008802193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001243812,0.0001332188,0.9947017,0.0004456071,0.00214786,0.0004272815,0.00003902338,0.0002388539,0.001742079],"genre_scores_gemma":[0.03912647,0.000006708518,0.9583722,0.001856051,0.0005017556,0.00001779438,0.00004442517,0.0000232159,0.00005139815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8922197,"threshold_uncertainty_score":0.9996971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02222072025130022,"score_gpt":0.2690253506071146,"score_spread":0.2468046303558144,"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."}}