{"id":"W2901569361","doi":"10.1111/tgis.12495","title":"Street‐segment‐based salt and abrasive prediction for winter maintenance using machine learning and GIS","year":2018,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Smart Materials for Construction","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Truck; Exploit; Computer science; Salting; Geographic information system; Machine learning; Data mining; Environmental science; Transport engineering; Automotive engineering; Engineering; Remote sensing; Geography; Computer security","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":[0.0001328306,0.0001004606,0.00009944141,0.00006275836,0.000207323,0.00002677253,0.00003619871,0.00005528901,0.0005736651],"category_scores_gemma":[0.00001307504,0.00010122,0.00002248682,0.0001069824,0.0002915484,0.0002277889,0.000008277714,0.00007939971,0.000005825364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001250188,"about_ca_system_score_gemma":0.000006324959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001044345,"about_ca_topic_score_gemma":0.003636124,"domain_scores_codex":[0.9993001,0.00003437426,0.0001626164,0.0002493359,0.0000845278,0.0001690277],"domain_scores_gemma":[0.9997908,0.00003079447,0.00004955378,0.00007672435,0.000009221581,0.00004290474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002769509,0.00007764025,0.7988495,0.00005002048,0.00002958135,0.000002147533,0.0009688197,0.002333803,0.1754951,0.00001408698,0.00004634125,0.02185599],"study_design_scores_gemma":[0.005997669,0.001217191,0.4839035,0.000293809,0.0002234297,0.0001484267,0.001213278,0.3739704,0.1188311,0.0007112421,0.01268025,0.0008096329],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8722712,0.00001101316,0.1269457,0.00009277758,0.0002641364,0.0002385649,0.00004639274,0.00003661806,0.00009357565],"genre_scores_gemma":[0.9888153,0.00001649091,0.01098409,0.00003131998,0.00003945658,0.00002561552,0.000006412831,0.00001423229,0.00006709905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3716366,"threshold_uncertainty_score":0.628123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01183937332943968,"score_gpt":0.2410282286428097,"score_spread":0.22918885531337,"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."}}