{"id":"W4296021843","doi":"10.3390/urbansci6030062","title":"Rapid Damage Estimation of Texas Winter Storm Uri from Social Media Using Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"Urban Science","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Software deployment; Disadvantaged; Social media; Storm; Estimation; Computer science; Geolocation; Geography; Business; Meteorology; Engineering; Political science; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001586002,0.00006092636,0.00009998982,0.0001422619,0.002004407,0.0001297122,0.0009490254,0.00003449013,0.000575194],"category_scores_gemma":[0.0003051806,0.00006473106,0.00004652648,0.001251855,0.000917264,0.0008021068,0.0002898781,0.0001854939,0.000002425779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002651469,"about_ca_system_score_gemma":0.0002016899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001012951,"about_ca_topic_score_gemma":0.0003857632,"domain_scores_codex":[0.9983425,0.0002692285,0.0002162669,0.0001927065,0.0007470362,0.0002322806],"domain_scores_gemma":[0.9991485,0.000208988,0.0002001635,0.0002608283,0.0001137162,0.00006780736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005544481,0.000444165,0.06343578,0.000005645378,0.00003678655,0.000003411273,0.3318567,0.2017459,0.001634525,0.1171484,0.005925814,0.2777074],"study_design_scores_gemma":[0.0001351837,0.00001564478,0.05311606,0.000002366317,0.00001345124,3.070793e-7,0.008969652,0.9326074,0.00001815556,0.001719386,0.003286562,0.0001158931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9797398,0.0002951462,0.01149416,0.0009476924,0.0006494288,0.0001402244,0.000009446294,0.00004266653,0.006681445],"genre_scores_gemma":[0.9984146,0.000006098691,0.001303693,0.00007545714,0.0001395457,0.00000547599,0.00001583335,0.000004519313,0.00003471945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7308614,"threshold_uncertainty_score":0.9992949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04186394166965906,"score_gpt":0.3100172771061516,"score_spread":0.2681533354364926,"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."}}