{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004191403,0.001788383,0.001953502,0.003555954,0.001150446,0.00239531,0.003704691,0.002366708,0.004449038],"category_scores_gemma":[0.01098011,0.0006819827,0.002108066,0.006035229,0.001540907,0.006103646,0.001783747,0.003161449,0.005211405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002295858,"about_ca_system_score_gemma":0.002306818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00843573,"about_ca_topic_score_gemma":0.008012066,"domain_scores_codex":[0.9964834,0.0008310128,0.0003006735,0.0008804658,0.001287028,0.0002174822],"domain_scores_gemma":[0.9979464,0.0007479767,0.0001769147,0.0004355031,0.0006207221,0.00007246164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006322138,0.0003203996,0.001770324,0.0006522913,0.0003265532,0.0001878323,0.0002314702,0.1310225,0.02617104,0.05218026,0.03236992,0.7541352],"study_design_scores_gemma":[0.00006119593,0.000184576,0.001425997,0.00005462253,0.0001249594,0.0003378437,0.00004491833,0.9337355,0.007638461,0.04161458,0.01466201,0.0001151939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00495359,0.002164628,0.9875694,0.0005705034,0.0002050395,0.0002063121,0.0006313508,0.001963025,0.001736123],"genre_scores_gemma":[0.22244,0.003789566,0.7500831,0.001547052,0.001263612,0.001838081,0.004757959,0.0006892979,0.01359127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00843573,"threshold_uncertainty_score":0.02216649,"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."}}