{"id":"W2137042120","doi":"10.1007/s11390-008-9152-9","title":"New Information Distance Measure and Its Application in Question Answering System","year":2008,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Question answering; Measure (data warehouse); Construct (python library); Ranking (information retrieval); Theory of computation; Information retrieval; Theoretical computer science; Algorithm; Data mining; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001030219,0.00009491944,0.0001944962,0.00078153,0.0001493444,0.0001009904,0.0007327016,0.00007672588,8.489349e-8],"category_scores_gemma":[0.00006609865,0.00008258653,0.00001441408,0.001646225,0.0001642094,0.002357366,0.0003007428,0.0002024238,0.000001456797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001434165,"about_ca_system_score_gemma":0.000262352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009939788,"about_ca_topic_score_gemma":0.000004948796,"domain_scores_codex":[0.9987609,0.00002481366,0.000401896,0.0002056649,0.0004144927,0.0001922471],"domain_scores_gemma":[0.9988419,0.00003100692,0.0002759423,0.0002183545,0.0005400529,0.00009273126],"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":[0.000006612237,0.00002814732,0.009243601,0.00004165222,0.000003948479,0.00002828509,0.0007181729,0.0005294476,0.001097604,0.1517832,0.00003289868,0.8364864],"study_design_scores_gemma":[0.0006967325,0.0003873292,0.04921521,0.0001527218,0.000003531117,0.003308285,0.00005025147,0.9344131,0.001727646,0.008767443,0.001062003,0.0002158083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1831612,0.0003629887,0.8146088,0.001437557,0.0002324668,0.0001078036,1.298597e-7,0.00006597146,0.00002317019],"genre_scores_gemma":[0.8986428,0.00005514123,0.1012177,0.00003478732,0.00004546217,0.0000018054,5.64264e-8,0.000001467612,7.240462e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9338836,"threshold_uncertainty_score":0.3367781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007605724138654834,"score_gpt":0.2149095306185003,"score_spread":0.2073038064798454,"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."}}