{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001699822,0.0009358418,0.001074081,0.003208703,0.000732915,0.001365439,0.001366042,0.001829585,0.001234668],"category_scores_gemma":[0.01217566,0.0004497071,0.0004484045,0.001566989,0.0006375901,0.001155459,0.001553765,0.0006528604,0.001577205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005435722,"about_ca_system_score_gemma":0.00064486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005057563,"about_ca_topic_score_gemma":0.004616965,"domain_scores_codex":[0.996893,0.0005092279,0.0001221545,0.0007022748,0.001492266,0.0002809811],"domain_scores_gemma":[0.989942,0.004733344,0.001420643,0.001389176,0.001924278,0.000590616],"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":[0.007924539,0.001342322,0.136769,0.0009068652,0.0005816937,0.008468709,0.002538271,0.0264015,0.09740275,0.004283771,0.06313199,0.6502486],"study_design_scores_gemma":[0.000150582,0.001010799,0.09143021,0.0001267405,0.0002957025,0.005403623,0.001842584,0.7965984,0.07950948,0.006511847,0.01693229,0.0001876128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8823231,0.001900452,0.09659782,0.0007921196,0.0008224621,0.0002571016,0.002339041,0.006104112,0.008863856],"genre_scores_gemma":[0.9608379,0.000233755,0.03169948,0.0002116743,0.0002745567,0.00006020469,0.001683173,0.000172649,0.004826554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005057563,"threshold_uncertainty_score":0.01005626,"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."}}