{"id":"W4255105370","doi":"10.32920/ryerson.14665737.v1","title":"Believe me, believe me not : investigating the possibility of a dual standard in the evaluation of alibi and eyewitness evidence","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Alibi; Excuse; Psychology; Credibility; Honesty; Social psychology; Scapegoat; Law; Political science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01141462,0.0002827312,0.0006073273,0.000160855,0.00008383208,0.000052849,0.000437464,0.000442841,0.001506914],"category_scores_gemma":[0.002147624,0.0001802403,0.0001452806,0.0005438377,0.0009812181,0.0000941436,0.0003930039,0.0009060287,0.000005994435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008583533,"about_ca_system_score_gemma":0.000389941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009470273,"about_ca_topic_score_gemma":0.001911173,"domain_scores_codex":[0.9931313,0.003511457,0.001184925,0.0008222442,0.00108821,0.0002618916],"domain_scores_gemma":[0.9955749,0.001084288,0.0007848131,0.001393005,0.001104676,0.0000583119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.003154925,0.001686396,0.1296435,0.001571908,0.002035131,0.00003710881,0.4840656,0.001459227,0.02237115,0.02662522,0.01425824,0.3130917],"study_design_scores_gemma":[0.002444071,0.0004579345,0.9279245,0.0008606626,0.0004444066,0.0001241872,0.03941064,0.001606524,0.00301136,0.02308735,0.0001559309,0.0004724796],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854783,0.001274652,0.0008337158,0.003408956,0.001376154,0.001195132,0.00005440329,0.00002628322,0.006352433],"genre_scores_gemma":[0.9980414,0.00007996457,0.0003716269,0.0009319824,0.00008379767,0.0001873402,0.00002017118,0.00001737445,0.0002663251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.798281,"threshold_uncertainty_score":0.9994059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1900734664353183,"score_gpt":0.4390192016251682,"score_spread":0.2489457351898499,"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."}}