{"id":"W4400508625","doi":"10.1002/wfs2.1528","title":"Forensic intelligence: Expanding the potential of forensic document examination","year":2024,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Forensic Science","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Handwriting; Forensic science; Forensic examination; Forensic identification; Identification (biology); Crime scene; Criminal investigation; Intelligence analysis; Computer science; Field (mathematics); Data science; Psychology; Artificial intelligence; Criminology; Computer security; Forensic engineering; Engineering; History; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003366751,0.0004629231,0.0005894823,0.0004954478,0.0006195664,0.001034551,0.003095994,0.00008139887,0.00003758577],"category_scores_gemma":[0.0001441049,0.0002829196,0.0004774698,0.003450105,0.002437068,0.00322061,0.003486187,0.0003645253,0.000235011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002409128,"about_ca_system_score_gemma":0.000244048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009280581,"about_ca_topic_score_gemma":0.00001730989,"domain_scores_codex":[0.9953816,0.0001404277,0.001201919,0.00117808,0.001284005,0.0008140007],"domain_scores_gemma":[0.9974127,0.0002015522,0.0003485973,0.001500623,0.0003187345,0.0002178201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005248837,0.00003199008,0.00001229884,0.0001344741,0.00001908894,0.00003111729,0.002791447,0.0000723877,0.0009958644,0.09201974,0.002693264,0.9011931],"study_design_scores_gemma":[0.0003772002,0.001729588,0.002065536,0.008937215,0.0002416385,0.001835625,0.003045391,0.1306261,0.08016656,0.7547645,0.01428743,0.001923284],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1457974,0.029914,0.7814181,0.004656419,0.01470172,0.002771952,0.00002657824,0.0006751115,0.0200387],"genre_scores_gemma":[0.9879306,0.00091195,0.01004795,0.0001885401,0.0002591915,0.00009403127,0.00001062934,0.00002547548,0.0005316366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8992698,"threshold_uncertainty_score":0.9999623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02332187561720813,"score_gpt":0.3100304591510706,"score_spread":0.2867085835338625,"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."}}