{"id":"W3165202216","doi":"10.1002/ffo2.98","title":"Tracking accuracy of strategic intelligence forecasts: Findings from a long‐term Canadian study","year":2021,"lang":"en","type":"article","venue":"Futures & Foresight Science","topic":"Intelligence, Security, War Strategy","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Department of National Defence; Defence Research and Development Canada","funders":"","keywords":"Intelligence analysis; Futures studies; Strategic intelligence; Government (linguistics); Tracking (education); Comprehension; Term (time); Computer science; Knowledge management; Psychology; Artificial intelligence; Computer security","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","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001718376,0.0003110664,0.0003946521,0.0004731896,0.002049068,0.0008157193,0.002322306,0.0001874937,0.001536757],"category_scores_gemma":[0.00118789,0.0002978232,0.0001502096,0.003068277,0.001793581,0.001274524,0.0001862941,0.0004403452,0.00006256708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004999294,"about_ca_system_score_gemma":0.005437152,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2640133,"about_ca_topic_score_gemma":0.8931197,"domain_scores_codex":[0.9951455,0.0002678574,0.0006455689,0.0009886271,0.001663962,0.001288497],"domain_scores_gemma":[0.9969606,0.0004454256,0.00024241,0.0007024598,0.0009497437,0.0006993003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008038644,0.00085369,0.2180205,0.00006212787,0.0001154916,0.001201666,0.2700775,0.0001996129,0.005634302,0.4746901,0.0004089685,0.02865566],"study_design_scores_gemma":[0.0005032404,0.0007227488,0.471427,0.0004319704,0.0001588294,0.00003629625,0.2868199,0.000604943,0.1153195,0.1199888,0.002134318,0.001852523],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786265,0.0007515912,0.0003107814,0.0003298787,0.001243952,0.0006407083,0.0000569662,0.00006086912,0.01797869],"genre_scores_gemma":[0.998625,0.000125995,0.0004158375,0.0001369029,0.0004084618,0.00002121316,0.00001336796,0.00002012186,0.0002331259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6291064,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08554409472267903,"score_gpt":0.3598641847133296,"score_spread":0.2743200899906506,"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."}}