{"id":"W2154923335","doi":"10.1109/compsac.2005.128","title":"Recovering \"Lack of Words\" in Text Categorization for Item Banks","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Phrase; Text categorization; Feature selection; Artificial intelligence; Classifier (UML); Natural language processing; Support vector machine; Selection (genetic algorithm); Sample (material); Machine learning","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":[0.0000960304,0.00004803992,0.00007333843,0.0001305388,0.00001827234,0.00003811709,0.0002944671,0.000044687,0.00001107552],"category_scores_gemma":[0.00003712583,0.00004354795,0.00002150769,0.0003458953,0.00001519302,0.0003101871,0.00005272016,0.00002680713,0.000005804116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002959412,"about_ca_system_score_gemma":0.0000164027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007607132,"about_ca_topic_score_gemma":0.00005642982,"domain_scores_codex":[0.9994805,0.000005896658,0.0001937736,0.0001500874,0.00006973689,0.000100033],"domain_scores_gemma":[0.9996038,0.00006875443,0.0000701594,0.0002189025,0.00003175243,0.000006617404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002089476,0.00003669606,0.007748601,0.00001383758,0.000001242628,1.464785e-7,0.00005567602,0.0003361315,0.004065971,0.8953811,0.00119025,0.09116829],"study_design_scores_gemma":[0.001143662,0.0001297092,0.09910183,0.00003547552,0.000003717125,0.000001411388,0.0002072499,0.2853529,0.2711086,0.3223027,0.02020762,0.000405091],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03235085,0.00003183208,0.9595033,0.0009263486,0.0000876885,0.0001603395,6.11886e-7,0.000203367,0.006735653],"genre_scores_gemma":[0.9625087,0.000005707281,0.03572882,0.00002362048,0.000009407147,0.00002434526,0.000003619488,0.000002758436,0.001693068],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9301578,"threshold_uncertainty_score":0.1775834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03400157365506067,"score_gpt":0.277484185770742,"score_spread":0.2434826121156813,"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."}}