{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01241579,0.002104816,0.00279337,0.01062867,0.001330651,0.003612095,0.001407776,0.002385593,0.01046769],"category_scores_gemma":[0.07745351,0.0002988863,0.001345214,0.005937131,0.0008735848,0.00555961,0.001821642,0.001260392,0.0125089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000723468,"about_ca_system_score_gemma":0.002128956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004852616,"about_ca_topic_score_gemma":0.005257702,"domain_scores_codex":[0.9899401,0.004749954,0.0009435359,0.001194294,0.002729881,0.0004421865],"domain_scores_gemma":[0.9344703,0.05425738,0.001362532,0.003945194,0.004973044,0.0009916008],"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":[0.002616851,0.0006958192,0.018128,0.001196204,0.0008549035,0.0002271707,0.0002275206,0.01383956,0.01384609,0.002096115,0.03514475,0.911127],"study_design_scores_gemma":[0.001101104,0.003665754,0.08214404,0.0004340429,0.001020659,0.002003189,0.001964289,0.7341434,0.03680155,0.06398706,0.07220417,0.0005306851],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3990391,0.01805347,0.4956121,0.003617172,0.004943206,0.001171775,0.01274158,0.0291961,0.0356254],"genre_scores_gemma":[0.7732812,0.003762833,0.1710037,0.0007900385,0.002245876,0.0006536726,0.0296942,0.002621412,0.01594718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01241579,"threshold_uncertainty_score":0.06566173,"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."}}