{"id":"W2898929540","doi":"10.1016/j.trpro.2018.10.009","title":"Workshop Synthesis: Validation under \"ground truth\" in surveys","year":2018,"lang":"en","type":"article","venue":"Transportation research procedia","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministère des Transports","funders":"","keywords":"Quality (philosophy); Data collection; Order (exchange); Data quality; Point (geometry); Computer science; Ground truth; Transport engineering; Operations research; Survey data collection; Risk analysis (engineering); Data science; Business; Engineering; Operations management; Mathematics; Statistics","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3007323,0.002524884,0.002403285,0.003113263,0.002489607,0.007591174,0.00474104,0.004055788,0.02055782],"category_scores_gemma":[0.555828,0.00147466,0.005006271,0.002652614,0.004532018,0.005575582,0.01075186,0.00452026,0.003724031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007444108,"about_ca_system_score_gemma":0.01290348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003811161,"about_ca_topic_score_gemma":0.002654016,"domain_scores_codex":[0.6092017,0.3439129,0.01341547,0.01473381,0.016343,0.00239311],"domain_scores_gemma":[0.4340899,0.3808967,0.01312245,0.07524459,0.09514456,0.001501815],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.002340514,0.0005590139,0.006653187,0.0234322,0.002623561,0.0004727195,0.01313469,0.04329842,0.004619258,0.3302951,0.1019131,0.4706582],"study_design_scores_gemma":[0.001447539,0.002820645,0.009277787,0.02663561,0.001750575,0.0002727154,0.01199589,0.06002475,0.01748664,0.4963893,0.3715438,0.0003546414],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01625217,0.004327478,0.8914478,0.01689831,0.006719884,0.01883988,0.006384185,0.001042895,0.03808738],"genre_scores_gemma":[0.2281534,0.002831399,0.6838444,0.009472776,0.001824863,0.0550231,0.006645775,0.0009328498,0.0112713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6992677,"threshold_uncertainty_score":0.8623216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1425053003700412,"score_gpt":0.4283320677163855,"score_spread":0.2858267673463443,"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."}}