{"id":"W2798963609","doi":"10.1145/3209978.3210147","title":"A New Term Frequency Normalization Model for Probabilistic Information Retrieval","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Ontario Research Foundation","keywords":"Normalization (sociology); Computer science; Probabilistic logic; Divergence-from-randomness model; Term (time); Intuition; Term Discrimination; Information retrieval; Artificial intelligence; Algorithm; Data mining; Search engine","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":[],"consensus_categories":[],"category_scores_codex":[0.0001242239,0.0000749008,0.00006440247,0.00005933901,0.0001291527,0.0001903075,0.0004120192,0.00004597668,0.00002365446],"category_scores_gemma":[0.00007214948,0.00005920591,0.00002372923,0.0001855408,0.00001549974,0.002915937,0.0001327648,0.00002848131,0.0000507751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002918906,"about_ca_system_score_gemma":0.000147865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002870086,"about_ca_topic_score_gemma":0.000007906128,"domain_scores_codex":[0.9993353,0.000006924936,0.0001978023,0.000143974,0.0001663495,0.0001496864],"domain_scores_gemma":[0.9992806,0.00001858282,0.00007234345,0.000342117,0.000213493,0.00007290192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004683801,0.00004334363,0.0001257176,0.000062133,0.000008943213,2.8239e-7,0.002520732,0.001593603,0.0008247741,0.7932512,0.03879292,0.1627296],"study_design_scores_gemma":[0.0002575477,0.00009182008,0.0001717663,0.000009920125,0.000002396924,0.00000214235,0.000002217128,0.958465,0.0004819925,0.03932615,0.001098777,0.00009026366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004259289,0.000004853192,0.9962669,0.0001633019,0.0002240495,0.0002924255,0.000007770044,0.0001518435,0.002462945],"genre_scores_gemma":[0.06410737,0.00000216155,0.9345745,0.0003961662,0.0001740626,0.000009297923,0.00006534098,0.000004178857,0.0006668767],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9568714,"threshold_uncertainty_score":0.2414347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01929637560278458,"score_gpt":0.2568031716177747,"score_spread":0.2375067960149901,"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."}}