{"id":"W1988996388","doi":"10.5555/777092.777258","title":"Generalized features: their application to classification","year":2002,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; sort; Focus (optics); Set (abstract data type); Feature (linguistics); Process (computing); Artificial intelligence; Machine learning; Information retrieval; Data mining","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003304261,0.0001992613,0.0001525543,0.0003664396,0.0002436276,0.0003669927,0.001331654,0.0001338477,0.0002285433],"category_scores_gemma":[0.0003141016,0.0001801076,0.00006347066,0.0009658728,0.00008379327,0.0004070952,0.0001113449,0.0002071023,0.002503874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001498503,"about_ca_system_score_gemma":0.00006252169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001018626,"about_ca_topic_score_gemma":0.00002177779,"domain_scores_codex":[0.9979612,0.00006811323,0.0004081682,0.0006404406,0.00065927,0.0002627585],"domain_scores_gemma":[0.9984269,0.0001217674,0.0001581446,0.000596325,0.0005865328,0.0001103906],"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":[0.000005203208,0.00008194943,0.000004978016,0.000001246679,0.000003551326,2.018209e-7,0.000235945,0.0001745904,0.007004846,0.6995606,0.00167587,0.291251],"study_design_scores_gemma":[0.00003801417,0.0001209799,0.001126619,0.00001576629,0.000002199992,0.000003351266,0.0002495755,0.4287553,0.0798503,0.4782806,0.0111947,0.0003626455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001782086,0.00003560359,0.9482105,0.03091697,0.0002289924,0.0004487195,0.00001117666,0.0006274742,0.01773851],"genre_scores_gemma":[0.9834061,0.00004962458,0.01401543,0.001440947,0.00008652132,0.0002456519,0.00001414842,0.000009118272,0.0007324096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9816241,"threshold_uncertainty_score":0.9982728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1686584931109399,"score_gpt":0.3426979531147663,"score_spread":0.1740394600038264,"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."}}