{"id":"W2144560128","doi":"10.1061/(asce)co.1943-7862.0000974","title":"Hardhat-Wearing Detection for Enhancing On-Site Safety of Construction Workers","year":2015,"lang":"en","type":"article","venue":"Journal of Construction Engineering and Management","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":221,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Matching (statistics); Construction site safety; Recall; Work (physics); Safety monitoring; Computer science; Occupational safety and health; Precision and recall; Computer security; Risk analysis (engineering); Engineering; Business; Artificial intelligence; Medicine; Psychology","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":[0.001306073,0.00009323498,0.0002230724,0.0003760427,0.0001810503,0.000007516869,0.0000480932,0.00007801299,0.00001076401],"category_scores_gemma":[0.000190895,0.00008640202,0.00005978381,0.0001717559,0.00003559942,0.000145183,0.00002723148,0.0002978258,0.000003490362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002109594,"about_ca_system_score_gemma":0.000111381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001428052,"about_ca_topic_score_gemma":0.000008916903,"domain_scores_codex":[0.9986441,0.00006447772,0.0006663348,0.0001049271,0.0002980677,0.0002220997],"domain_scores_gemma":[0.9987388,0.0002612508,0.0003599903,0.00008553557,0.0003767681,0.0001776804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007713845,0.0001061125,0.05200011,0.006363018,0.0006719693,0.00001479442,0.001817407,0.08280166,0.002743766,0.03521872,0.001077022,0.8094715],"study_design_scores_gemma":[0.04080714,0.005743593,0.4569525,0.01274692,0.0007777721,0.0006844288,0.04505122,0.083294,0.007285674,0.004301799,0.340691,0.001663942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4245383,0.000218574,0.5660327,0.0005078044,0.005073699,0.001087156,0.00001151952,0.00004555138,0.002484703],"genre_scores_gemma":[0.9684669,0.0003516211,0.03052225,0.00003490979,0.0004257739,0.0000328462,0.000002888472,0.00001591395,0.0001468461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8078076,"threshold_uncertainty_score":0.3523372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03699682308425144,"score_gpt":0.3618167803672243,"score_spread":0.3248199572829729,"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."}}