{"id":"W2914990229","doi":"","title":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Listing (finance); Analytics; Key (lock); Data science; Library science; World Wide Web; Information retrieval","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01648703,0.001774031,0.002869508,0.004031296,0.00129476,0.011675,0.003391217,0.002408459,0.01900221],"category_scores_gemma":[0.03337491,0.00122195,0.002291783,0.004481761,0.00206227,0.009469463,0.004168551,0.005716007,0.01051062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00164477,"about_ca_system_score_gemma":0.003477793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004252696,"about_ca_topic_score_gemma":0.006308832,"domain_scores_codex":[0.9896492,0.003800069,0.0009080088,0.00158414,0.003566792,0.0004917575],"domain_scores_gemma":[0.9720282,0.01382268,0.000855536,0.004856392,0.006386313,0.002050918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004684456,0.0002912295,0.002083709,0.0008059537,0.0003309164,0.0005421496,0.001075704,0.005064132,0.003697072,0.009620165,0.6282569,0.3477636],"study_design_scores_gemma":[0.000119427,0.0002422253,0.006888452,0.001082272,0.0002005913,0.001061867,0.001940631,0.05323349,0.006874395,0.07139579,0.8567244,0.0002363872],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01572799,0.03915793,0.8226706,0.04796619,0.0265269,0.001288602,0.01292436,0.009514093,0.02422329],"genre_scores_gemma":[0.08447105,0.02933947,0.674687,0.01004924,0.01400412,0.001736301,0.06238323,0.005514374,0.1178153],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01900221,"threshold_uncertainty_score":0.08719277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04627194771488053,"score_gpt":0.289453829297437,"score_spread":0.2431818815825564,"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."}}