{"id":"W1996246161","doi":"10.1145/1277741.1277895","title":"Improving retrieval accuracy by weighting document types with clickthrough data","year":2007,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Weighting; Computer science; Task (project management); Relevance (law); Information retrieval; Document retrieval; Function (biology); Term (time); Vector space model; Relevance feedback; tf–idf; Artificial intelligence; Data mining; Image retrieval","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":[0.001218675,0.000121589,0.0001079812,0.00006502135,0.000202735,0.0003772141,0.001426659,0.00004772409,0.00008527099],"category_scores_gemma":[0.0001224703,0.00008207729,0.0000187563,0.0004835734,0.00003848965,0.003153649,0.0007533614,0.0001744102,0.0001258752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005218031,"about_ca_system_score_gemma":0.00009893106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000140729,"about_ca_topic_score_gemma":0.00001427649,"domain_scores_codex":[0.9983433,0.00001904076,0.000311027,0.0003225887,0.0005861244,0.0004178524],"domain_scores_gemma":[0.9985573,0.0001684481,0.0001247823,0.0008898858,0.000131265,0.0001283311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002706519,0.000203929,0.002931065,0.00008246771,0.00006228132,0.00009066052,0.00215443,0.000007851025,0.01248731,0.08886651,0.01896101,0.8738818],"study_design_scores_gemma":[0.004808679,0.001650688,0.006324494,0.0001200785,0.0000711144,0.0002550033,0.001228917,0.1124011,0.4454848,0.001065256,0.4241329,0.002456896],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03595001,0.00004920409,0.9547822,0.0006561885,0.0001583786,0.0002192634,0.000006642683,0.0002257545,0.007952292],"genre_scores_gemma":[0.7202758,0.00002433048,0.273553,0.00155996,0.0001633982,0.000002402178,0.000103877,0.00001766005,0.004299492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8714249,"threshold_uncertainty_score":0.3637485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02680500078858922,"score_gpt":0.3022873821396024,"score_spread":0.2754823813510132,"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."}}