{"id":"W3177795256","doi":"10.52547/jipm.36.4.1081","title":"Extraction of Effective Textual and Semantic Features in Learning to Rank for Web Document Retrieval","year":2021,"lang":"en","type":"article","venue":"Iranian Journal of Information Processing and Management","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; Toronto Metropolitan University","funders":"","keywords":"Information retrieval; Computer science; Rank (graph theory); Learning to rank; Document clustering; Document retrieval; World Wide Web; Semantic Web; Natural language processing; Artificial intelligence; Ranking (information retrieval); Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008566696,0.00006921705,0.0001384982,0.0003549312,0.00009378765,0.0002513544,0.00009302234,0.00002790424,0.000001518824],"category_scores_gemma":[0.0000967966,0.00005883113,0.00002866773,0.0003303768,0.00001479727,0.00200597,0.00006077174,0.0001157145,7.60334e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003701205,"about_ca_system_score_gemma":0.0000512184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001020764,"about_ca_topic_score_gemma":9.181209e-7,"domain_scores_codex":[0.9990813,0.00003575811,0.0004383424,0.00005997681,0.0002725644,0.0001120574],"domain_scores_gemma":[0.9992186,0.00004502109,0.0002898697,0.00004816216,0.0003386965,0.00005960415],"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":[0.0002993475,0.00003550886,0.0003484642,0.001229658,0.00002774853,0.00001274363,0.01284812,0.001069795,0.001353627,0.003946557,0.000110909,0.9787175],"study_design_scores_gemma":[0.03261443,0.006413713,0.569042,0.008152259,0.0003830628,0.002234011,0.07240385,0.1253306,0.08061276,0.004941836,0.09603131,0.001840127],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.495388,0.0002969208,0.501425,0.001251229,0.0001566873,0.0005698105,0.000001536105,0.00001709132,0.0008938277],"genre_scores_gemma":[0.9817268,0.0001155295,0.01791882,0.0001397752,0.00001267314,0.000004841836,0.000001648687,0.000001932661,0.00007800983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9768774,"threshold_uncertainty_score":0.2423816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007069426982035435,"score_gpt":0.273988742919462,"score_spread":0.2669193159374265,"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."}}