{"id":"W1888496803","doi":"10.1007/978-3-642-02976-9_46","title":"Automatic Detecting Documents Containing Personal Health Information","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Decision tree; Support vector machine; Natural language processing; Categorization; Information retrieval; Lexical analysis; Text categorization; Naive Bayes classifier; The Internet; Task (project management); Supervised learning; Machine learning; World Wide Web","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001023762,0.0004019271,0.000437945,0.00113935,0.0004435219,0.00109075,0.00236476,0.0002371478,0.00002268904],"category_scores_gemma":[0.0001482919,0.0003774033,0.00009348299,0.0005946736,0.0002881413,0.002388464,0.0006855178,0.0007015741,0.00007613502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006962026,"about_ca_system_score_gemma":0.0006738192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002308288,"about_ca_topic_score_gemma":0.00001942988,"domain_scores_codex":[0.9968918,0.00002814707,0.0007181122,0.0007504657,0.0009799814,0.0006315233],"domain_scores_gemma":[0.9979736,0.0002230749,0.0006898054,0.000828648,0.0001567226,0.0001281836],"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":[0.000001234172,0.000006579868,0.00002350853,0.00002348933,0.000003979188,0.000003798178,0.001306961,0.0003971295,0.000006875664,0.01244202,0.00001828224,0.9857661],"study_design_scores_gemma":[0.0004345794,0.0005221139,0.0004939598,0.0006048508,0.00000401291,0.00006266958,0.000003904412,0.8331494,0.0004007722,0.1596134,0.003988742,0.0007215929],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001686694,0.0002586485,0.9924082,0.003156587,0.0006846512,0.0004049685,0.000001671705,0.0007806205,0.002136052],"genre_scores_gemma":[0.5670185,0.00005480012,0.4282236,0.004347459,0.0001330385,0.00001563513,0.000009676352,0.0000169107,0.0001804444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9850445,"threshold_uncertainty_score":0.9999462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01851048022841444,"score_gpt":0.268608716320946,"score_spread":0.2500982360925316,"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."}}