{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004900097,0.0001677726,0.0001960172,0.0002057759,0.0001742336,0.0003599813,0.0005176828,0.00008827969,0.0001218592],"category_scores_gemma":[0.000783988,0.0001655716,0.00004011333,0.0001146142,0.000136202,0.0002738724,0.0001465208,0.0004674572,0.00003174567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002026652,"about_ca_system_score_gemma":0.0001052884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001803377,"about_ca_topic_score_gemma":0.0001057335,"domain_scores_codex":[0.9984047,0.00007189756,0.0004866121,0.0003886673,0.000419896,0.0002282707],"domain_scores_gemma":[0.9986982,0.0002899808,0.0001451863,0.0002471116,0.0005123075,0.0001072129],"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":[0.00002322304,0.0000483832,0.00005049237,0.000008000456,0.00001530806,0.00001120271,0.002524544,0.005302793,0.02497779,0.7165547,0.00002183716,0.2504617],"study_design_scores_gemma":[0.00002619096,0.00009163652,0.00001506873,0.00006272485,0.000004340907,0.00001380318,0.0005440806,0.8817701,0.01006932,0.1071056,0.0001333605,0.0001637884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06714629,0.00001676763,0.929545,0.000477826,0.0007904036,0.00007441006,0.00001737918,0.00006014245,0.001871805],"genre_scores_gemma":[0.9049788,0.00003858923,0.09464713,0.0000950042,0.00010064,0.000006277339,0.00000753983,0.000009971207,0.0001160502],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8764672,"threshold_uncertainty_score":0.6751815,"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."}}