{"id":"W2016325519","doi":"10.1016/j.ipl.2003.09.002","title":"A new differential LSI space-based probabilistic document classifier","year":2003,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Classifier (UML); Probabilistic logic; Probabilistic classification; Computer science; Search engine indexing; Artificial intelligence; Pattern recognition (psychology); Data mining; A priori and a posteriori; Document classification; Adaptability; Machine learning; Support vector machine; Naive Bayes classifier","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001512553,0.0001770006,0.0001288748,0.000267087,0.000199742,0.00106636,0.0005662534,0.00007780603,0.00006707586],"category_scores_gemma":[0.0001256397,0.0001550285,0.00005405561,0.0004903569,0.00006064076,0.00330794,0.00005213387,0.0001526844,0.0001581677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001342837,"about_ca_system_score_gemma":0.0002551068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005293341,"about_ca_topic_score_gemma":6.533801e-7,"domain_scores_codex":[0.9986607,0.00003371789,0.0003980983,0.0002036081,0.0004106517,0.0002932558],"domain_scores_gemma":[0.9990957,0.00003317816,0.0002827913,0.0004200621,0.00008020216,0.00008807869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001879472,0.00006738297,0.0005672735,0.0002394376,0.00002151548,0.000002680753,0.002033707,0.001478795,0.003833164,0.4534614,0.03481549,0.5034604],"study_design_scores_gemma":[0.006608456,0.0002735509,0.006397063,0.0004001215,0.00007084514,0.00004452365,0.0006231376,0.1148789,0.08724255,0.06269126,0.7182018,0.00256783],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006092139,0.00001977597,0.9752547,0.01517612,0.0002799119,0.000237093,5.334801e-7,0.000770431,0.002169275],"genre_scores_gemma":[0.9063312,0.000001403762,0.09048315,0.002885533,0.00002182932,0.00005814388,0.00001008499,0.000006764216,0.0002018772],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9002391,"threshold_uncertainty_score":0.9999706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01159156178863901,"score_gpt":0.2222046444828678,"score_spread":0.2106130826942288,"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."}}