{"id":"W6925200658","doi":"10.17605/osf.io/3zn5d","title":"Validating the Guessing in the Weapons Task","year":2019,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Asphalt Pavement Performance Evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"","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":[],"consensus_categories":[],"category_scores_codex":[0.00520791,0.002077694,0.001127385,0.001080052,0.0009137157,0.002737386,0.002574779,0.004867355,0.01539482],"category_scores_gemma":[0.06219553,0.0007300291,0.001138425,0.0004873568,0.00124812,0.004873264,0.003918602,0.002936426,0.009107206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008849074,"about_ca_system_score_gemma":0.002833835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006154867,"about_ca_topic_score_gemma":0.00438554,"domain_scores_codex":[0.9926455,0.002564939,0.0007174594,0.001853432,0.001694959,0.0005237003],"domain_scores_gemma":[0.9615477,0.02719773,0.001789097,0.005764306,0.002805538,0.000895609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01733865,0.003727397,0.1083118,0.002430934,0.001024573,0.00160262,0.0039708,0.1206894,0.05688038,0.02171498,0.07799903,0.5843093],"study_design_scores_gemma":[0.001058037,0.004063564,0.03327411,0.0007576281,0.0004867778,0.00135877,0.00246995,0.7963,0.08504944,0.02638659,0.048484,0.0003111566],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8452684,0.001043413,0.1094724,0.002025197,0.001372288,0.0009902806,0.006980307,0.008968292,0.02387941],"genre_scores_gemma":[0.9150606,0.0002346226,0.06302489,0.0004770287,0.00008908055,0.0003375992,0.008957157,0.000661756,0.01115718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01539482,"threshold_uncertainty_score":0.05150086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167315272087293,"score_gpt":0.2591218183181582,"score_spread":0.2423902911094289,"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."}}