{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000451679,0.0001150053,0.0001395729,0.00007500235,0.0001819709,0.00002701023,0.000483653,0.00005639726,0.00002651876],"category_scores_gemma":[0.00003712863,0.00008549165,0.00002906746,0.0001477475,0.0002453366,0.0003094431,0.0003593398,0.00007957024,0.000012995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001479574,"about_ca_system_score_gemma":0.00001792294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005242018,"about_ca_topic_score_gemma":0.000006298518,"domain_scores_codex":[0.9993223,0.00007969259,0.0001533942,0.0002374373,0.00008339122,0.0001238158],"domain_scores_gemma":[0.9990956,0.0002172801,0.000114989,0.0004021785,0.0001275736,0.00004235613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000457188,0.00003128355,0.0001058928,0.00006051415,0.00001376883,9.587743e-7,0.002030267,4.700744e-7,0.005671534,0.8973006,0.00006007342,0.09467889],"study_design_scores_gemma":[0.00007993297,0.00004852871,0.0001884676,0.00001346681,0.00001400414,0.00001587691,0.0001509436,0.0001603877,0.3249283,0.6737281,0.0005368789,0.0001350581],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008364452,0.002336338,0.9870566,0.00005530629,0.00003477125,0.000326278,0.000007468268,0.0002743868,0.001544398],"genre_scores_gemma":[0.9129028,0.00004721166,0.08605491,0.0000635461,0.00004154793,0.000262939,0.000004299458,0.000008239189,0.0006145017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9045383,"threshold_uncertainty_score":0.3486248,"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."}}