{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01816675,0.001331362,0.001265428,0.002913164,0.001400664,0.003067796,0.002640934,0.001570054,0.001309621],"category_scores_gemma":[0.1581714,0.0008792727,0.0009301109,0.002124333,0.001941698,0.004787448,0.004089996,0.001940113,0.0005855765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001380721,"about_ca_system_score_gemma":0.002126821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003528017,"about_ca_topic_score_gemma":0.002074333,"domain_scores_codex":[0.9813104,0.007092563,0.001878346,0.003536752,0.005277734,0.0009042301],"domain_scores_gemma":[0.859104,0.07534956,0.01985242,0.02804342,0.01520465,0.002446028],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002845871,0.001053393,0.2738426,0.001482548,0.00075294,0.0004937788,0.009629657,0.1947154,0.0479531,0.04782259,0.0112336,0.4081745],"study_design_scores_gemma":[0.0002600916,0.002020061,0.1031327,0.0002830276,0.0002817565,0.0008477825,0.002160174,0.7385901,0.04159852,0.09697043,0.0133722,0.0004832637],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2668017,0.0008505498,0.7207717,0.0005402839,0.0001862732,0.000716035,0.0009426808,0.003086894,0.006103843],"genre_scores_gemma":[0.8826841,0.0001139636,0.1143242,0.0001419201,0.0000716978,0.0006580505,0.0005861067,0.0003310711,0.001088945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818332,"threshold_uncertainty_score":0.09607613,"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."}}