{"id":"W4412709116","doi":"10.1080/00031305.2025.2539241","title":"A Fisher’s Exact Test Justification of the TF–IDF Term-Weighting Scheme","year":2025,"lang":"en","type":"article","venue":"The American Statistician","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Weighting; Statistics; Mathematics; Test (biology); Physics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00421148,0.0001723609,0.0003989124,0.0001800044,0.0004139657,0.0001387739,0.001745126,0.00002618737,0.0001471373],"category_scores_gemma":[0.04418897,0.00009172234,0.0001117202,0.002682966,0.001123542,0.00007549428,0.000321376,0.0002437572,0.00003791252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000679752,"about_ca_system_score_gemma":0.0001996409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004167809,"about_ca_topic_score_gemma":0.00009681709,"domain_scores_codex":[0.9965428,0.001033039,0.000779644,0.0004223765,0.0009112916,0.000310897],"domain_scores_gemma":[0.9767629,0.02023924,0.001166265,0.001433696,0.00034478,0.0000531124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004830358,0.00005711124,0.08662386,0.0000118504,0.00003065791,0.000001537489,0.0007132344,0.00002332559,0.008158942,0.006201546,0.02437134,0.8737583],"study_design_scores_gemma":[0.0001556199,0.00008457971,0.9542444,0.00007993625,0.00006562736,0.000004819077,0.00181503,0.01130055,0.001461286,0.02459729,0.006035996,0.000154807],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.690428,0.00009295605,0.2243945,0.00674784,0.0009569836,0.000780937,0.000221836,0.0001003653,0.07627667],"genre_scores_gemma":[0.9556899,0.00000371839,0.03948314,0.0008420637,0.00007315548,0.00002680278,0.000001903019,0.00001568974,0.003863642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8736035,"threshold_uncertainty_score":0.9638622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07572393262271854,"score_gpt":0.4222604066798787,"score_spread":0.3465364740571601,"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."}}