{"id":"W2090601220","doi":"10.1145/2660168.2660186","title":"Correcting Large-Scale OMR Data with Crowdsourcing","year":2014,"lang":"en","type":"article","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Crowdsourcing; Computer science; Variety (cybernetics); Scale (ratio); Data science; Process (computing); Globe; Ground truth; Reliability (semiconductor); World Wide Web; Human–computer interaction; Artificial intelligence","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":[0.001188893,0.0001888084,0.0002143214,0.00008360556,0.0004149122,0.0004758848,0.001526348,0.00005788135,0.00002469063],"category_scores_gemma":[0.0001212022,0.0001469244,0.00003098796,0.0003984905,0.00003927864,0.0006641263,0.0008865908,0.0002192454,0.00008806195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002066954,"about_ca_system_score_gemma":0.00004551381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009246084,"about_ca_topic_score_gemma":0.0002204006,"domain_scores_codex":[0.9980434,0.00009605764,0.0002223094,0.0007824493,0.0003186608,0.0005371331],"domain_scores_gemma":[0.9971002,0.0002281927,0.0001013539,0.00234314,0.00007808241,0.0001489959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004242839,0.0003862302,0.04391123,0.0001361994,0.0001162053,0.00007900355,0.009737916,0.007732345,0.003743804,0.02608571,0.02551877,0.8825102],"study_design_scores_gemma":[0.0005381323,0.00009344463,0.001019887,0.000094621,0.00001294539,0.0002976966,0.0005099753,0.9665441,0.003607013,0.0001780422,0.02669924,0.00040493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07020363,0.00002331047,0.9087488,0.000363561,0.0003225197,0.00007999313,0.000001218347,0.0005824463,0.01967453],"genre_scores_gemma":[0.8664985,5.69241e-7,0.131517,0.0006386527,0.0001811599,0.000002498509,0.00000726195,0.00002026117,0.001134118],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9588117,"threshold_uncertainty_score":0.5991402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01433183667179794,"score_gpt":0.2316893982502087,"score_spread":0.2173575615784107,"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."}}