{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002549531,0.00006200956,0.00006963671,0.00004624907,0.00008148774,0.0002298624,0.0003427567,0.00002677561,0.0001213537],"category_scores_gemma":[0.00005596432,0.00004323698,0.00005448198,0.00009557336,0.00001633189,0.0008919853,0.0001166672,0.00005442177,0.0002951525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003704543,"about_ca_system_score_gemma":0.00001978247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006927198,"about_ca_topic_score_gemma":0.000004317937,"domain_scores_codex":[0.9993942,0.00002440557,0.0001189357,0.0001126532,0.0001767702,0.0001730467],"domain_scores_gemma":[0.9993944,0.00008905102,0.00002396386,0.0001834988,0.0002383143,0.0000708408],"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":[0.000009611641,0.00006718978,0.0006413017,0.00002596769,0.00001886852,5.81083e-7,0.001033752,0.00001261156,0.001014611,0.1040989,0.02052226,0.8725543],"study_design_scores_gemma":[0.003929612,0.002380384,0.1042845,0.0000538416,0.00002466211,0.00002018169,0.0004278643,0.3093754,0.2934055,0.08861033,0.1961556,0.001332182],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0160094,0.000004528418,0.9765486,0.001534173,0.0001749458,0.0009691737,9.570191e-7,0.0001141691,0.004644125],"genre_scores_gemma":[0.9677365,0.000001094218,0.02921752,0.0009842913,0.00002562782,0.0003627199,0.000001737381,0.000002589975,0.001667948],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9517271,"threshold_uncertainty_score":0.3793687,"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."}}