{"id":"W7132542374","doi":"","title":"Fast & confident probabilistic categorisation","year":2007,"lang":"en","type":"article","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Probabilistic logic; Labelling; Set (abstract data type); Anomaly detection; Test (biology); Measure (data warehouse); Test set; Layer (electronics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002686637,0.00005937285,0.00005625703,0.00008145082,0.0000628079,0.00008816094,0.0004534073,0.00004278379,0.000059084],"category_scores_gemma":[0.0000630424,0.00005267537,0.00002027293,0.0002205118,0.00004717448,0.0002233402,0.00008312134,0.0000639335,0.0001653057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005182521,"about_ca_system_score_gemma":0.00002451686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005459523,"about_ca_topic_score_gemma":0.000007602366,"domain_scores_codex":[0.9993203,0.000009021841,0.0001497026,0.0001872339,0.0001719823,0.0001617185],"domain_scores_gemma":[0.9994369,0.00005024302,0.00005894485,0.000365777,0.00005300691,0.00003516589],"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":[0.000001158914,0.00002078029,0.0003380326,0.000003049487,0.000001805878,0.000001839194,0.000197313,0.00000324721,0.009512566,0.8297563,0.001393336,0.1587705],"study_design_scores_gemma":[0.0003625186,0.0001061247,0.0332018,0.000008863866,0.000005320553,0.00001236422,0.000387716,0.006792029,0.07575212,0.8518924,0.03117995,0.0002988544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01989255,0.00001425392,0.9333445,0.0025222,0.0002302166,0.0001409008,2.684959e-7,0.0006410502,0.04321404],"genre_scores_gemma":[0.9788626,0.000003545134,0.02028094,0.00008961772,0.00002362624,0.00001091652,0.000001506854,0.000002676187,0.0007245179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9589701,"threshold_uncertainty_score":0.2148039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793904926341709,"score_gpt":0.2566820421824322,"score_spread":0.2387429929190151,"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."}}