{"id":"W7008917920","doi":"","title":"Computing probabilities for common substrings in random strings","year":2006,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Substring; Set (abstract data type); Feature (linguistics); Term (time)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001501197,0.0008520958,0.001157896,0.0006073705,0.001071389,0.0004094843,0.002293233,0.0007085333,0.00001122166],"category_scores_gemma":[0.0003479884,0.0008803645,0.0004039944,0.0007637307,0.0000530611,0.001707743,0.0005241666,0.00105682,0.00002745899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006096762,"about_ca_system_score_gemma":0.0001084015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001559872,"about_ca_topic_score_gemma":0.001758039,"domain_scores_codex":[0.9947495,0.0002692427,0.001434722,0.001650711,0.0008438015,0.001052062],"domain_scores_gemma":[0.9964794,0.0008746766,0.0008288317,0.001218756,0.0003794957,0.0002188228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005974827,0.0006642283,0.0002722114,0.001629411,0.0001163714,0.00009512152,0.00007863567,0.001135155,0.004961386,0.3507118,0.00007722174,0.639661],"study_design_scores_gemma":[0.03072819,0.001377882,0.01751041,0.009292544,0.0003743769,0.0001283289,0.0009198359,0.05807582,0.1791226,0.4616594,0.2304877,0.01032287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777866,0.0004906262,0.0003668508,0.0000218689,0.002023683,0.002427286,0.0008290148,0.0006387664,0.01541531],"genre_scores_gemma":[0.9638098,0.00005334738,0.03006965,0.0001247294,0.000121717,0.0003065538,0.002456746,0.0001695295,0.002887972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6293381,"threshold_uncertainty_score":0.9993647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01440460458459204,"score_gpt":0.2451875548206702,"score_spread":0.2307829502360782,"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."}}