{"id":"W2742582834","doi":"","title":"POSTER: Overclaiming as Convenient Proxy for Confidence and Overconfidence","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overconfidence effect; Confidence interval; Proxy (statistics); Vocabulary; Respondent; Psychology; Test (biology); Self-confidence; Social psychology; Statistics; Mathematics; Linguistics","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":[0.0005936853,0.0001785532,0.0002627191,0.00005984185,0.0001016125,0.00007590805,0.0002142736,0.00008792287,0.0005013402],"category_scores_gemma":[0.007017757,0.0001203963,0.00004063058,0.00004113657,0.000239556,0.0001642171,0.00007981591,0.00006337132,0.00009387419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000037665,"about_ca_system_score_gemma":0.0003265364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004945373,"about_ca_topic_score_gemma":0.00001165069,"domain_scores_codex":[0.9987344,0.00009924672,0.0003068177,0.0003792525,0.0001778422,0.0003024535],"domain_scores_gemma":[0.994265,0.004705028,0.0001937584,0.0003450154,0.0003626542,0.0001285915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005752261,0.00003587683,0.001193573,0.0001351571,0.00002229326,0.000002748455,0.0007744235,1.074048e-8,0.02048679,0.9458541,0.011532,0.01990554],"study_design_scores_gemma":[0.001021807,0.0002304786,0.001873931,0.0006837817,0.00005215221,0.00005789109,0.0006448554,0.00004556016,0.03775568,0.9380193,0.01927137,0.0003432303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1777897,0.0003191368,0.8040012,0.005255875,0.001875113,0.001716317,0.000296512,0.0002537873,0.008492418],"genre_scores_gemma":[0.9290361,0.0003596054,0.05299064,0.0004686157,0.00009709322,0.0001802558,0.000002852889,0.00002612201,0.0168387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7512465,"threshold_uncertainty_score":0.8401418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2111857715889395,"score_gpt":0.4281265707237906,"score_spread":0.2169407991348511,"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."}}