{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005805681,0.0001139853,0.0001460767,0.0004648037,0.0005817306,0.0001271868,0.0002354108,0.000192193,0.0005710292],"category_scores_gemma":[0.0007759535,0.0001244588,0.00003886402,0.001814322,0.0004756872,0.0006217998,0.000001660052,0.0002939285,0.0001474946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001232728,"about_ca_system_score_gemma":0.0004663163,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002820392,"about_ca_topic_score_gemma":0.04271569,"domain_scores_codex":[0.9968811,0.0007705558,0.0003877669,0.0003729743,0.001050366,0.0005372815],"domain_scores_gemma":[0.9979258,0.0009178656,0.00007683496,0.0001427528,0.0007769004,0.0001598066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003919925,0.0007865507,0.4023741,0.0002503242,0.00008435648,0.00004738244,0.2058808,0.01039488,0.0006102649,0.3542427,0.004233137,0.02070349],"study_design_scores_gemma":[0.0004376521,0.00004521992,0.9757638,0.0001241482,0.00001216026,9.559966e-8,0.01646075,0.000277551,0.0006437429,0.003660158,0.002350957,0.0002237854],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708912,0.00004651799,0.01753816,0.001918585,0.0003303851,0.0007090547,0.00003361582,0.0003478258,0.008184695],"genre_scores_gemma":[0.997511,0.0001251205,0.0008404471,0.00003603037,0.000251664,0.00015579,0.0001537273,0.00002866823,0.0008975319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5733897,"threshold_uncertainty_score":0.9747522,"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."}}