{"id":"W2033681837","doi":"10.1007/s10791-011-9163-y","title":"Improving document clustering using Okapi BM25 feature weighting","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Weighting; Cluster analysis; Computer science; Artificial intelligence; Data mining; Feature (linguistics); Document clustering; Pattern recognition (psychology); Term (time)","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":[0.0005130527,0.0001611199,0.0001367132,0.0002224043,0.000243293,0.0003748015,0.00061486,0.0001224578,0.00004676209],"category_scores_gemma":[0.0001045715,0.0001461635,0.00007572631,0.0005935211,0.00003402359,0.004979827,0.0003002153,0.0002161064,0.00008917789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528695,"about_ca_system_score_gemma":0.0000953784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002720457,"about_ca_topic_score_gemma":4.717999e-7,"domain_scores_codex":[0.9986537,0.00003613325,0.00042941,0.0001772465,0.0004096886,0.0002937875],"domain_scores_gemma":[0.9988438,0.00002455741,0.0003633167,0.0004275315,0.0002471335,0.00009369713],"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":[0.0002738333,0.00011825,0.0008292533,0.0005347833,0.00009868265,0.00002612919,0.02204791,0.00005721625,0.05010868,0.06460754,0.001022965,0.8602747],"study_design_scores_gemma":[0.0007008398,0.0002074788,0.001522326,0.0001040015,0.00002065786,0.0001254055,0.0004016093,0.5432329,0.437895,0.002118879,0.0129606,0.0007104031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004745881,0.00003619622,0.9876043,0.0001378365,0.0003831296,0.0002364359,0.000001983369,0.0005358714,0.006318327],"genre_scores_gemma":[0.6141777,0.00001445694,0.3847898,0.0006124816,0.0001029586,0.000006494244,0.00001039994,0.00001218457,0.0002735689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8595644,"threshold_uncertainty_score":0.5960376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02482047029488173,"score_gpt":0.2420373186875677,"score_spread":0.2172168483926859,"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."}}