{"id":"W2186705392","doi":"","title":"Na¨ ive but effective NIL clustering baselines - CMCRC at TAC 2011","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00799585,0.003175976,0.002801124,0.00573066,0.004371399,0.004268469,0.005471493,0.00449413,0.007864811],"category_scores_gemma":[0.01589905,0.0007849382,0.001433862,0.004253959,0.001384759,0.006392547,0.00482809,0.00297664,0.01186791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002941228,"about_ca_system_score_gemma":0.002537909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02928196,"about_ca_topic_score_gemma":0.04484574,"domain_scores_codex":[0.9869941,0.003783193,0.0008237741,0.003559638,0.003527737,0.001311625],"domain_scores_gemma":[0.9882693,0.002254244,0.0003475448,0.003822211,0.004715643,0.0005910732],"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":[0.00352661,0.001608058,0.008076557,0.001332675,0.0007636983,0.0006539357,0.000704605,0.04435478,0.03094577,0.005894432,0.3096562,0.5924826],"study_design_scores_gemma":[0.001032663,0.001873424,0.01043011,0.0001956971,0.0005393244,0.00156656,0.002371035,0.7424647,0.0941103,0.01763808,0.1273781,0.0003999851],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4045491,0.01529273,0.273369,0.005494719,0.004819176,0.002041715,0.03561018,0.1908994,0.06792405],"genre_scores_gemma":[0.5532016,0.0008911623,0.307013,0.002190095,0.0007723386,0.0005491863,0.1005799,0.004769241,0.03003351],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02928196,"threshold_uncertainty_score":0.05822307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009456469064637365,"score_gpt":0.245669984167565,"score_spread":0.2362135151029276,"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."}}