{"id":"W2117543632","doi":"10.1145/1367497.1367739","title":"Reasoning about similarity queries in text retrieval tasks","year":2008,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Similarity (geometry); Information retrieval; Sampling (signal processing); Data mining; Calibration; Document retrieval; Query expansion; Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008626205,0.001388286,0.002670268,0.003666923,0.001664264,0.003531452,0.003708377,0.003484712,0.001443653],"category_scores_gemma":[0.0492609,0.001006097,0.001837614,0.004018917,0.001182724,0.01134416,0.002676302,0.002417237,0.0007262339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001742246,"about_ca_system_score_gemma":0.00123439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00595079,"about_ca_topic_score_gemma":0.005102928,"domain_scores_codex":[0.990267,0.004514581,0.001112503,0.001590285,0.0020695,0.0004461344],"domain_scores_gemma":[0.9745063,0.02076044,0.001431539,0.001404632,0.00141879,0.0004782559],"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":[0.00280958,0.001451673,0.0160992,0.001852012,0.0006116037,0.001504241,0.004773039,0.4048863,0.02594133,0.0674697,0.01582963,0.4567716],"study_design_scores_gemma":[0.00008446869,0.0001095058,0.00117122,0.00002702489,0.0000524592,0.0002049941,0.000364717,0.9308471,0.004236829,0.06166523,0.001197725,0.00003863082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08035501,0.001009242,0.9139839,0.0008508218,0.00003583535,0.000364605,0.000612727,0.001785888,0.001001997],"genre_scores_gemma":[0.6589761,0.0007925232,0.3336954,0.0004933688,0.0002952782,0.000538143,0.003893192,0.0001878249,0.001128211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008626205,"threshold_uncertainty_score":0.04562026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02953565206192772,"score_gpt":0.2551199435787342,"score_spread":0.2255842915168065,"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."}}