{"id":"W4386544688","doi":"10.1007/s11042-023-16615-z","title":"The hypergeometric test performs comparably to TF-IDF on standard text analysis tasks","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Computer science; Test (biology); Natural language processing; Information retrieval; Artificial intelligence","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":[0.0003471323,0.000128617,0.0001716225,0.0004154341,0.0005858252,0.0004808616,0.0007942502,0.00004856654,0.000006822889],"category_scores_gemma":[0.0002560026,0.00008220053,0.00005972548,0.005611986,0.00005911438,0.0001628978,0.0002346876,0.0001596682,0.0001903639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000376316,"about_ca_system_score_gemma":0.00002942684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002142341,"about_ca_topic_score_gemma":0.00001873705,"domain_scores_codex":[0.9988402,0.0000154608,0.0001982285,0.0003783689,0.0002973473,0.0002704372],"domain_scores_gemma":[0.9980937,0.0009663324,0.00006265569,0.0006302624,0.0001115989,0.0001354803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004339667,0.00003750229,0.002144485,0.000006538226,0.00004028995,0.000001425095,0.0002207994,0.0001153664,0.0007602022,0.007766651,0.004500255,0.9844021],"study_design_scores_gemma":[0.0008363039,0.0005268635,0.1160126,0.00005770766,0.0002487168,0.00001019121,0.0003210771,0.3607212,0.01693252,0.01800537,0.4849979,0.001329514],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0239672,0.001525457,0.956895,0.01191154,0.0001118877,0.001713355,0.0003051215,0.002063696,0.001506751],"genre_scores_gemma":[0.8505944,0.0001956833,0.1468412,0.0004508776,0.0001057813,0.0009161403,0.0000590877,0.00001409265,0.0008227725],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9830726,"threshold_uncertainty_score":0.463696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02123914253418305,"score_gpt":0.2965767467581373,"score_spread":0.2753376042239543,"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."}}