{"id":"W3180000962","doi":"10.1108/jfp-02-2021-0004","title":"“That’s the way my Wednesdays always go”: reverse-order instructions insufficient to mitigate schema-consistent errors in alibi generation","year":2021,"lang":"en","type":"article","venue":"Journal of Forensic Practice","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bishop's University; Ontario Tech University","funders":"","keywords":"Alibi; Schema (genetic algorithms); Recall; Psychology; Mnemonic; Originality; Social psychology; Computer science; Cognitive psychology; Information retrieval","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":[0.02719872,0.0008047846,0.0003841359,0.0006446661,0.0006214583,0.001503628,0.001606812,0.001111099,0.003565467],"category_scores_gemma":[0.1760819,0.0006886636,0.0003951291,0.0004528165,0.001065131,0.002384861,0.001455952,0.001416577,0.001552274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006668218,"about_ca_system_score_gemma":0.001949995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001250091,"about_ca_topic_score_gemma":0.001569935,"domain_scores_codex":[0.9810075,0.01464781,0.001136195,0.0009627502,0.001870333,0.00037544],"domain_scores_gemma":[0.8417317,0.1176849,0.01316004,0.01948817,0.006854692,0.001080512],"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":[0.002744749,0.002052034,0.09016047,0.003333179,0.0001605872,0.001283678,0.1346764,0.00270689,0.04982479,0.007667093,0.01052107,0.6948691],"study_design_scores_gemma":[0.002213904,0.01768236,0.2365939,0.009834495,0.001439916,0.009904603,0.1402268,0.06915485,0.1752078,0.03071835,0.3060102,0.001012899],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8452323,0.000600784,0.1379787,0.001755817,0.0001885264,0.002431888,0.0002593986,0.002184073,0.009368563],"genre_scores_gemma":[0.7802798,0.0006593717,0.2121861,0.001349267,0.00005270189,0.002251103,0.000367447,0.0002540728,0.002600098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02719872,"threshold_uncertainty_score":0.1438423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0572796402303015,"score_gpt":0.3396740422042591,"score_spread":0.2823944019739575,"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."}}