{"id":"W4246750514","doi":"10.1109/wi.2004.10071","title":"A Weighted Freshness Metric for Maintaining Search Engine Local Repository","year":2005,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Web Intelligence (WI'04)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Web crawler; Computer science; Web search engine; Web page; Metric (unit); World Wide Web; Information retrieval; Search engine; Database; Web search query; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001214847,0.0005137954,0.0005269601,0.001246496,0.0003658395,0.000815321,0.005279783,0.0002334688,0.0003818259],"category_scores_gemma":[0.0005183367,0.0004906706,0.000326202,0.00130385,0.0002610837,0.001033996,0.0005784412,0.0006749854,0.0005251212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004737252,"about_ca_system_score_gemma":0.0006057601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002063221,"about_ca_topic_score_gemma":0.0001016768,"domain_scores_codex":[0.995207,0.0001919059,0.0009735932,0.001384617,0.001403711,0.000839248],"domain_scores_gemma":[0.9957059,0.0008918211,0.0003232704,0.001514489,0.001211796,0.0003527076],"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":[0.0002474744,0.000769423,0.0008092897,0.00005174497,0.0006875711,0.0001635426,0.001671148,0.02089477,0.005742841,0.3882038,0.006749879,0.5740085],"study_design_scores_gemma":[0.0003484586,0.000308875,0.00009658552,0.0002438158,0.00003771049,0.00006212218,0.0005792361,0.9223943,0.06037011,0.003401697,0.01153102,0.0006260333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02266066,0.0001233642,0.9636284,0.004590457,0.001764773,0.000320529,0.0001458745,0.0003309054,0.006435032],"genre_scores_gemma":[0.9471025,0.0001656464,0.04818005,0.0006002148,0.0008307269,0.0001134059,0.0001165075,0.00003866268,0.002852307],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9244418,"threshold_uncertainty_score":0.9997545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06173562002561792,"score_gpt":0.3275296771444546,"score_spread":0.2657940571188366,"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."}}