{"id":"W2397694745","doi":"10.63317/5agbhnncc4sh","title":"Experiments in Topic Detection","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"WordNet; Computer science; Thesaurus; Information retrieval; Natural language processing; Precision and recall; Implementation; Artificial intelligence; Recall; Domain (mathematical analysis); Linguistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.00002239505,0.00002864577,0.00002775889,0.00007378581,0.00001834965,0.00003750393,0.0002299404,0.00002314423,0.000124227],"category_scores_gemma":[0.000007721216,0.00002483405,0.000008648297,0.0001830945,0.000007717242,0.000245979,0.00005018218,0.00002908217,0.0001688262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002073782,"about_ca_system_score_gemma":8.368305e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008626967,"about_ca_topic_score_gemma":0.000007032916,"domain_scores_codex":[0.9996991,0.000005867747,0.00006415413,0.0001058678,0.00005489112,0.00007009158],"domain_scores_gemma":[0.999771,0.00000645918,0.00001224556,0.0001964766,0.00000479971,0.00000902076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[2.59271e-7,0.00006282261,0.002032557,0.000001091839,0.00000119214,0.000002617728,0.0003203364,0.000001739921,0.008656616,0.1195531,0.000704258,0.8686634],"study_design_scores_gemma":[0.0006893719,0.0001075549,0.02654756,0.000006150429,6.15495e-7,0.000006664553,0.0002831216,0.09305122,0.8122793,0.02097264,0.04576622,0.0002895118],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1840687,0.0002407649,0.7285524,0.003814298,0.000359233,0.000147097,3.946917e-8,0.001270887,0.08154654],"genre_scores_gemma":[0.9926299,0.00001122155,0.004707476,0.00007954527,0.000003952642,0.00001390413,2.915417e-8,8.093001e-7,0.002553176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8683739,"threshold_uncertainty_score":0.2169975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04286456784919886,"score_gpt":0.2522528984422731,"score_spread":0.2093883305930742,"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."}}