{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02903159,0.0008864073,0.00133465,0.004157785,0.001893208,0.003024009,0.002404513,0.003696932,0.006447265],"category_scores_gemma":[0.1611485,0.0003787009,0.001066982,0.004555748,0.007506636,0.006308067,0.002574774,0.004404859,0.002601314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00190665,"about_ca_system_score_gemma":0.00344221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002759357,"about_ca_topic_score_gemma":0.00114658,"domain_scores_codex":[0.9850972,0.006157602,0.001058935,0.002484915,0.004731856,0.0004695959],"domain_scores_gemma":[0.9363114,0.04798051,0.002472267,0.005173155,0.007646332,0.0004162433],"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":[0.0001231614,0.00003164403,0.00257015,0.0002014372,0.0000483716,0.0002423285,0.0004295312,0.00543457,0.001312867,0.8067622,0.01077577,0.1720679],"study_design_scores_gemma":[0.00004693677,0.000118046,0.001614409,0.0002346187,0.00003163136,0.0006198292,0.0001409713,0.04917616,0.002833602,0.9212458,0.02387494,0.00006306529],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004660773,0.001351231,0.9813312,0.004664502,0.0005614488,0.00007955827,0.0003710109,0.0001879408,0.00679246],"genre_scores_gemma":[0.2840706,0.002237994,0.6994736,0.002818017,0.00236347,0.0007996134,0.0007659287,0.0002465816,0.007224205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02903159,"threshold_uncertainty_score":0.1535355,"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."}}