{"id":"W4402314895","doi":"10.21203/rs.3.rs-4934969/v1","title":"Advancing Fire and Smoke Detection Reliability: Integrating Generalized ELAN and Programmable Gradient Information within YOLOv9 to Discriminate Against False Positives","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"False positive paradox; Computer science; Smoke; Reliability (semiconductor); Inference; Object detection; Fire detection; Artificial intelligence; True positive rate; False positives and false negatives; Precision and recall; Data mining; Machine learning; Pattern recognition (psychology); Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001838278,0.0003285558,0.0003679521,0.0005641418,0.0002934258,0.0006822264,0.0001262742,0.0002862178,0.00000256173],"category_scores_gemma":[0.0004763079,0.0002944065,0.00008157312,0.0004558617,0.00007778187,0.0002918836,0.0005680449,0.001541413,0.00001636299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005279645,"about_ca_system_score_gemma":0.00005813677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001291775,"about_ca_topic_score_gemma":0.0009261478,"domain_scores_codex":[0.9976284,0.0002732371,0.0005761504,0.000468698,0.000517771,0.0005357348],"domain_scores_gemma":[0.9988902,0.0001106296,0.00005894225,0.0003627564,0.0002927812,0.0002846977],"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":[0.0003054069,0.00006516682,0.001120565,0.03192049,0.0002671369,0.00005276319,0.05307772,0.05411934,0.00968176,0.0006043796,0.0003572608,0.848428],"study_design_scores_gemma":[0.000467292,0.0005548234,0.003233981,0.005239304,0.00003369597,0.00004118928,0.01186777,0.9645372,0.006370944,0.001785131,0.005134176,0.0007344723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926801,0.001268345,0.001665251,0.0003284083,0.0007864595,0.002029964,0.00007871887,0.0005740202,0.0005887395],"genre_scores_gemma":[0.9974944,0.0004318738,0.001064737,0.00001596615,0.0001135854,0.0006455224,0.00008934226,0.00005445928,0.00009011612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9104179,"threshold_uncertainty_score":0.9999508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806385770021964,"score_gpt":0.3045765931961823,"score_spread":0.2865127354959627,"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."}}