{"id":"W1503824486","doi":"10.1023/a:1023936321956","title":"Query Expansion with Long-Span Collocates","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Microsoft Research","keywords":"Collocation (remote sensing); Computer science; Window (computing); Information retrieval; Mathematics; Machine learning","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":[0.0005693992,0.0001714368,0.0001539137,0.0002843468,0.0002626609,0.0004917196,0.0004483455,0.00009944453,0.0001007315],"category_scores_gemma":[0.0001565168,0.000131152,0.00005450564,0.001132674,0.00006208379,0.006169804,0.00006504168,0.0001985593,0.0007388521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000921547,"about_ca_system_score_gemma":0.0003377448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009464384,"about_ca_topic_score_gemma":0.000001859468,"domain_scores_codex":[0.9981608,0.00006013302,0.0004603011,0.0001324086,0.0008290841,0.0003572848],"domain_scores_gemma":[0.9986442,0.00006251842,0.0001920389,0.0004332163,0.0004934813,0.0001745135],"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":[0.001185887,0.0005615865,0.02854419,0.0005410814,0.0001848769,0.0001046682,0.03103234,0.007450412,0.001013661,0.6845196,0.01275044,0.2321112],"study_design_scores_gemma":[0.01129591,0.003960942,0.07571846,0.0003009606,0.00007388744,0.001205494,0.003431266,0.1154809,0.2728475,0.002278146,0.5098674,0.003539114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1789887,0.00002441738,0.80165,0.0003841164,0.000410167,0.0005313431,0.000007018786,0.0003995154,0.01760468],"genre_scores_gemma":[0.9913939,0.00001206317,0.00714157,0.0008805265,0.00001788861,0.00001198678,0.00003398614,0.000006365418,0.0005017775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8124051,"threshold_uncertainty_score":0.9496695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009880289279499396,"score_gpt":0.2239308871336277,"score_spread":0.2140505978541283,"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."}}