{"id":"W2128133607","doi":"","title":"Semi-supervised Document Classification with a Mislabeling Error Model","year":2009,"lang":"en","type":"article","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Probabilistic latent semantic analysis; Computer science; Artificial intelligence; Extension (predicate logic); Probabilistic logic; Machine learning; Set (abstract data type); Multiclass classification; Topic model; Document classification; Pattern recognition (psychology); Supervised learning; Data mining; Support vector machine; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0001434853,0.000141652,0.0001239575,0.0001211975,0.0001316604,0.0001894685,0.0008156389,0.00007303207,0.00002546753],"category_scores_gemma":[0.00001987928,0.0001127731,0.00003479109,0.0003825561,0.00004043073,0.0006209149,0.00005957187,0.0001275392,0.00005488212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006858379,"about_ca_system_score_gemma":0.00006709302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.651825e-7,"about_ca_topic_score_gemma":0.000001051838,"domain_scores_codex":[0.9987949,0.00001908474,0.0002060306,0.0004053881,0.0003194051,0.0002552127],"domain_scores_gemma":[0.998974,0.00002110308,0.00009304108,0.0007660967,0.00008378756,0.00006191727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001621713,0.0001109271,0.0001148621,0.000006831265,0.00001101813,0.000003168575,0.000621794,0.0007671,0.1245615,0.6583852,0.003313052,0.2120883],"study_design_scores_gemma":[0.0005143036,0.0001574207,0.0009086665,0.00002470313,0.00000789215,0.000005575266,0.0001321762,0.810419,0.01437385,0.171875,0.00132522,0.0002561859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03591598,0.00004267698,0.9143257,0.02716772,0.00004570707,0.0002478048,8.661902e-7,0.001140599,0.02111292],"genre_scores_gemma":[0.79636,0.00001742939,0.202298,0.0004936191,0.00001139775,0.00002969076,0.000003030223,0.000005026233,0.0007818037],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8096519,"threshold_uncertainty_score":0.4598755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03335914134963362,"score_gpt":0.2681762081773369,"score_spread":0.2348170668277033,"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."}}