{"id":"W2794325666","doi":"10.1609/hcomp.v5i1.13307","title":"Deja Vu: Characterizing Worker Reliability Using Task Consistency","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Consistency (knowledge bases); Task (project management); Reliability (semiconductor); Metric (unit); Computer science; Context (archaeology); Consistency model; Measure (data warehouse); Reliability engineering; Data mining; Artificial intelligence; Data consistency; Engineering; Geography; Operations management; Database","routes":{"ca_aff":true,"ca_fund":true,"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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008305492,0.0002926506,0.0003927334,0.0001287865,0.002518673,0.001629381,0.001184175,0.0001132082,0.000007448294],"category_scores_gemma":[0.0002876768,0.0002411671,0.0001339439,0.0001489951,0.0004462282,0.0008293572,0.0007230587,0.0003449574,0.000003984014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006278772,"about_ca_system_score_gemma":0.00007633049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007851683,"about_ca_topic_score_gemma":0.000003157505,"domain_scores_codex":[0.9979851,0.00003611805,0.0005246113,0.0006606278,0.0004150496,0.000378512],"domain_scores_gemma":[0.997699,0.00007984375,0.0009906967,0.0005658284,0.0005364556,0.0001282342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009133115,0.0003345876,0.08661412,0.0006413728,0.0001360961,0.000007795934,0.01217517,0.001060286,0.5687669,0.2520036,0.0004277135,0.07774106],"study_design_scores_gemma":[0.00237339,0.0003557845,0.271281,0.004209427,0.0001509469,0.0001597395,0.001410174,0.6205763,0.0525928,0.04481362,0.000458779,0.001617949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813384,0.00002573892,0.009604414,0.001258225,0.0002887009,0.0002772287,0.000001540363,0.0001203029,0.00708545],"genre_scores_gemma":[0.9935684,0.000005053028,0.005924912,0.0002129295,0.0000830273,0.00000604766,5.868292e-7,0.00002042218,0.0001786765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6195161,"threshold_uncertainty_score":0.9994071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06568918211076574,"score_gpt":0.3058742671703849,"score_spread":0.2401850850596192,"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."}}