{"id":"W1765826407","doi":"10.1007/11780441_13","title":"Common Substrings in Random Strings","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Substring; Bernoulli's principle; Computer science; Word (group theory); Set (abstract data type); Algorithm; Bernoulli distribution; Markov chain; Theoretical computer science; Discrete mathematics; Random variable; Mathematics; Machine learning; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.000983109,0.0005874311,0.0007517259,0.001142245,0.0002050761,0.0006599508,0.004324599,0.00037196,0.00001528175],"category_scores_gemma":[0.00003900538,0.0005291375,0.000132585,0.000809194,0.0004430964,0.001010991,0.002309168,0.0008842919,0.00003614629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003431729,"about_ca_system_score_gemma":0.0003975129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004014858,"about_ca_topic_score_gemma":0.0002449603,"domain_scores_codex":[0.9956115,0.00003986604,0.0007469656,0.001689896,0.001106309,0.0008054007],"domain_scores_gemma":[0.9972686,0.0005069607,0.0003260974,0.00161896,0.0001209822,0.000158362],"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":[0.00002422721,0.00007991765,0.0007093139,0.0000484521,0.000006615874,0.0004531353,0.0003707472,0.05401851,0.0001150824,0.01359915,0.0002465538,0.9303283],"study_design_scores_gemma":[0.002093859,0.0001669807,0.001957364,0.00112658,0.00000729321,0.00009994329,1.21357e-7,0.8494489,0.001668335,0.1330425,0.009006953,0.001381219],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005322342,0.0006245543,0.9919131,0.0003108832,0.001182685,0.000405831,0.000009404655,0.0001622615,0.004859013],"genre_scores_gemma":[0.4712368,0.0001530176,0.5246095,0.001660514,0.001071931,0.00002884459,0.0000616606,0.0001020656,0.001075662],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9289471,"threshold_uncertainty_score":0.999716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01159371641536783,"score_gpt":0.2318120370378794,"score_spread":0.2202183206225115,"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."}}