{"id":"W1984070542","doi":"10.1145/2505515.2505526","title":"Effective measures for inter-document similarity","year":2013,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cosine similarity; Computer science; Cluster analysis; Similarity (geometry); Document clustering; Artificial intelligence; Rank (graph theory); Randomness; Divergence (linguistics); Language model; Document retrieval; Data mining; Natural language processing; Machine learning; Information retrieval; Mathematics; Statistics","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":[0.01181776,0.001520508,0.00201595,0.01514918,0.001302612,0.004550758,0.002516186,0.002275821,0.00181802],"category_scores_gemma":[0.06204601,0.0004110615,0.001251028,0.01121291,0.001977267,0.009582537,0.002328455,0.002248283,0.001106559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002340693,"about_ca_system_score_gemma":0.001413115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001551425,"about_ca_topic_score_gemma":0.002108336,"domain_scores_codex":[0.9782748,0.006054016,0.002687359,0.002535837,0.009924557,0.000523404],"domain_scores_gemma":[0.9585243,0.02087866,0.004863075,0.008155928,0.006811406,0.0007665309],"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":[0.0008887691,0.000731484,0.03118486,0.001679177,0.001325903,0.0002292856,0.0009878119,0.09447375,0.01835704,0.1237637,0.01205871,0.7143195],"study_design_scores_gemma":[0.0001573523,0.001618555,0.03797292,0.0004156984,0.0004311977,0.00170804,0.0009006496,0.6835573,0.03227807,0.2217016,0.0187167,0.0005419613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0619015,0.006917102,0.9221278,0.0004672009,0.0002646778,0.0005218129,0.001470148,0.001085258,0.005244419],"genre_scores_gemma":[0.5487729,0.001307346,0.4449064,0.0002251896,0.0003109952,0.0006463759,0.002092561,0.000237357,0.001500812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01514918,"threshold_uncertainty_score":0.06249911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01948026662985459,"score_gpt":0.2824767624413327,"score_spread":0.2629964958114781,"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."}}