{"id":"W4237049540","doi":"10.1353/ils.2011.0020","title":"Text mining and information retrieval","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Information and Library Science","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Information retrieval; Computer science; Natural language processing; Data science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003672871,0.00004909624,0.00006670499,0.0006200398,0.0002011015,0.000674348,0.0004585159,0.0000255113,0.00002246011],"category_scores_gemma":[0.0001666701,0.00003900315,0.00001163701,0.0004957223,0.0002335164,0.04754684,0.00004919992,0.00005770156,0.00000563892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000109443,"about_ca_system_score_gemma":0.001041567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009442369,"about_ca_topic_score_gemma":0.00002137946,"domain_scores_codex":[0.9993879,0.000008899346,0.000269482,0.00003677003,0.0001440413,0.0001528738],"domain_scores_gemma":[0.9992629,0.0000204459,0.0001865544,0.00008613438,0.00008603073,0.0003579639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002663435,0.000004132513,0.05797442,0.00004501829,0.000009263497,0.00002241248,0.07552475,0.0000087183,0.00003184065,0.3476879,0.004908011,0.5137569],"study_design_scores_gemma":[0.0006908032,0.0003992055,0.8648993,0.0001077197,0.0000060881,0.001233975,0.007116514,0.01576314,0.002229681,0.004071533,0.103154,0.0003280468],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9074484,0.0003201308,0.03133707,0.002411286,0.0008473886,0.00009451303,0.00000363314,0.00003621857,0.05750143],"genre_scores_gemma":[0.9674401,0.00004322911,0.03084895,0.001641204,0.00001148653,1.075682e-7,4.070296e-7,6.465139e-7,0.00001390691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8069248,"threshold_uncertainty_score":0.9657747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01346260354532961,"score_gpt":0.179926310541338,"score_spread":0.1664637069960084,"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."}}