{"id":"W166693255","doi":"10.4018/978-1-60566-172-8.ch009","title":"A Model for Estimating the Savings from Dimensional vs. Keyword Search","year":2009,"lang":"en","type":"book-chapter","venue":"Advances in database research (ADR) book series/Advances in database research series","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Zipf's law; Computer science; Metadata; Keyword search; Process (computing); Information retrieval; Search cost; Search engine; Keyword density; Data mining; Data science; World Wide Web; Economics; Statistics; Mathematics; Microeconomics","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":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"category_scores_codex":[0.02733623,0.00208941,0.003023044,0.004386418,0.002658646,0.001393295,0.01340431,0.0007535286,0.0003664021],"category_scores_gemma":[0.009146239,0.001769613,0.0006414619,0.003180877,0.006147305,0.04484639,0.01375012,0.01003334,0.0001770096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002437383,"about_ca_system_score_gemma":0.00298479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004737211,"about_ca_topic_score_gemma":0.01134853,"domain_scores_codex":[0.971175,0.002694081,0.003951885,0.006130604,0.01076118,0.005287209],"domain_scores_gemma":[0.9702609,0.01305061,0.001040326,0.01096675,0.003716971,0.0009644102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00396221,0.0006779551,0.00008463355,0.001751276,0.0002168408,0.002153064,0.001401979,0.02803856,0.001530289,0.7382082,0.0155786,0.2063964],"study_design_scores_gemma":[0.0009715652,0.0006826376,0.000006020965,0.003678928,0.00002305958,0.00005976857,0.0002167041,0.1629167,0.001669502,0.2646286,0.5636482,0.001498231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001690082,0.2197338,0.6466018,0.01455561,0.001171337,0.0184072,0.02380327,0.00141482,0.07414317],"genre_scores_gemma":[0.0003652359,0.190748,0.7422893,0.0005240283,0.0009533747,0.002904857,0.006759138,0.0004219816,0.05503401],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5480696,"threshold_uncertainty_score":0.9996433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08805243973955451,"score_gpt":0.41779534693456,"score_spread":0.3297429071950055,"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."}}