{"id":"W2802838214","doi":"10.1016/j.infsof.2019.03.003","title":"Images don’t lie: Duplicate crowdtesting reports detection with screenshot information","year":2019,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Context (archaeology); Feature (linguistics); Word embedding; Computer science; Precision and recall; Similarity (geometry); Artificial intelligence; Image (mathematics); Variety (cybernetics); Word (group theory); F1 score; Recall; Information retrieval; Natural language processing; Embedding; Data mining; Pattern recognition (psychology); Mathematics; Geography; Linguistics","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":[0.000270412,0.0001474677,0.0001555779,0.0004806181,0.0002133991,0.0003479203,0.0001879421,0.0001693391,0.000005765297],"category_scores_gemma":[0.0001942896,0.0001279227,0.00002187299,0.0005781014,0.00007596697,0.003648196,0.0001562527,0.0002294826,0.00007056016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003805192,"about_ca_system_score_gemma":0.00004606395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003557204,"about_ca_topic_score_gemma":0.000005309702,"domain_scores_codex":[0.9989743,0.0000114255,0.0004166572,0.0001622056,0.0001899459,0.0002454878],"domain_scores_gemma":[0.9987891,0.00004547433,0.0003554131,0.0005174769,0.0002397436,0.00005279727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001238761,0.000007897119,0.02329192,0.0001077594,0.00001352444,0.000007009367,0.0005901376,0.0004458273,0.0006208584,0.002382121,0.0001535759,0.972367],"study_design_scores_gemma":[0.007236585,0.003491639,0.149499,0.001393427,0.0001143674,0.02428741,0.005600041,0.2084253,0.2004569,0.02191865,0.3726048,0.004971806],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3392174,0.00002910012,0.6575494,0.00036631,0.0001217292,0.0002509576,8.760844e-7,0.001443815,0.001020453],"genre_scores_gemma":[0.9659033,0.000008288274,0.03365774,0.0003469514,0.000008680591,0.00002234954,0.00001140058,0.000004906142,0.0000363639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9673952,"threshold_uncertainty_score":0.5216538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003162984024258265,"score_gpt":0.1814050668166534,"score_spread":0.1782420827923951,"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."}}