{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002579044,0.00008849877,0.0001260399,0.00007073988,0.0001033241,0.00005031104,0.0004783199,0.00006408904,0.00004386405],"category_scores_gemma":[0.0001365478,0.00008254009,0.00003137089,0.0002968471,0.0000411432,0.0004360997,0.0002187317,0.0001755634,0.00002970918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004598097,"about_ca_system_score_gemma":0.00008808255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003023556,"about_ca_topic_score_gemma":0.0001000331,"domain_scores_codex":[0.9989848,0.00004058539,0.0001974305,0.0003122103,0.0002170054,0.0002479776],"domain_scores_gemma":[0.9993603,0.00005182686,0.00003373218,0.0004591708,0.00003644835,0.00005850147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000480812,0.0002129954,0.2181438,0.0000443551,0.00002275445,0.0006837164,0.01504861,0.004368002,0.001532721,0.7134135,0.004541811,0.04193972],"study_design_scores_gemma":[0.0008926783,0.00007611173,0.1527629,0.00008145931,0.000002571054,0.000187264,0.000139962,0.8195827,0.006386988,0.008059273,0.01117185,0.0006562307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3868224,0.000152672,0.5855475,0.0009808722,0.0002158804,0.00008248736,3.747806e-7,0.000222596,0.02597524],"genre_scores_gemma":[0.8909823,0.00002587829,0.1073264,0.0004351752,0.00004507408,0.000001565671,3.952076e-7,0.000004228948,0.001178978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8152147,"threshold_uncertainty_score":0.3365887,"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."}}