{"id":"W2154096410","doi":"","title":"Modeling annotator expertise: Learning when everybody knows a bit of something","year":2010,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Probabilistic logic; Artificial intelligence; Machine learning; Domain (mathematical analysis); Task (project management); Space (punctuation); Agreement; Natural language processing; Training set; Variable (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03110217,0.001563541,0.00274553,0.002858032,0.002513954,0.0038219,0.004286889,0.00508608,0.002260016],"category_scores_gemma":[0.1210571,0.001635869,0.00138883,0.003107981,0.004258732,0.01128816,0.006570463,0.004384953,0.0009073901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002413639,"about_ca_system_score_gemma":0.001743096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005640475,"about_ca_topic_score_gemma":0.006482527,"domain_scores_codex":[0.9759762,0.01204554,0.001012689,0.007377029,0.002653203,0.0009353411],"domain_scores_gemma":[0.8608054,0.1093532,0.01083879,0.01057128,0.006495407,0.00193594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003068018,0.0006519858,0.134864,0.001600233,0.001460881,0.002829668,0.01701951,0.3396285,0.01134928,0.1585079,0.01903733,0.3099828],"study_design_scores_gemma":[0.0001001419,0.0001480382,0.01061812,0.0002021603,0.0002001796,0.0007695259,0.0009835392,0.7049601,0.003464642,0.2714421,0.006966034,0.0001454224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07460673,0.0008307214,0.9165198,0.00315087,0.0001161045,0.0001575959,0.000445831,0.0003362242,0.003836037],"genre_scores_gemma":[0.8376469,0.000548395,0.1545103,0.0009221679,0.0004826018,0.0005160993,0.0009730749,0.0002558932,0.004144591],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03110217,"threshold_uncertainty_score":0.164486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0815228368451885,"score_gpt":0.3287389152244423,"score_spread":0.2472160783792537,"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."}}