{"id":"W1991678929","doi":"10.1177/0165551506065787","title":"A study of the effect of term proximity on query expansion","year":2006,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Query expansion; Computer science; Term (time); Information retrieval; Query optimization; Web query classification; Mutual information; Sargable; Web search query; Measure (data warehouse); Query language; Data mining; Search engine; Artificial intelligence","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":[0.002726625,0.0000651695,0.0001474147,0.0004129865,0.0001617023,0.0001024553,0.001132893,0.00002104309,0.000002223519],"category_scores_gemma":[0.0002761797,0.00003318952,0.0000723329,0.001255234,0.0001441926,0.006324191,0.0001482422,0.000144376,0.000003965046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005697185,"about_ca_system_score_gemma":0.0002280916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000140655,"about_ca_topic_score_gemma":7.209104e-7,"domain_scores_codex":[0.9973434,0.00007182809,0.0007716775,0.00004418324,0.001648515,0.000120372],"domain_scores_gemma":[0.9978105,0.00008901306,0.001072411,0.0002792479,0.0007074693,0.00004128879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00104603,0.002207256,0.4318886,0.0005411202,0.00004313604,0.00001441536,0.06586263,0.02771747,0.08485121,0.0372624,0.001566764,0.346999],"study_design_scores_gemma":[0.001321127,0.003168749,0.767946,0.000101976,0.000007716056,0.00004861103,0.000425708,0.004326132,0.2224205,0.00008229868,0.00006932757,0.00008177988],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915966,0.000001600804,0.006796835,0.00007257122,0.0002686228,0.0002679055,7.976279e-7,0.000005409905,0.0009896737],"genre_scores_gemma":[0.9994965,7.197254e-7,0.0004465972,0.00003351617,0.00001135054,0.000001533731,8.740068e-8,6.444731e-7,0.00000906662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3469172,"threshold_uncertainty_score":0.4584886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01217584193266941,"score_gpt":0.2799131262771092,"score_spread":0.2677372843444398,"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."}}