{"id":"W4383500585","doi":"10.1002/9781119863663.ch7","title":"Human–Machine Social Systems: Test and Validation via Military Use Cases","year":2023,"lang":"en","type":"other","venue":"","topic":"Innovation, Sustainability, Human-Machine Systems","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Canada; Defence Research and Development Canada","funders":"","keywords":"Immediacy; Social intelligence; Artificial intelligence; Human resources; Computer science; Test (biology); Knowledge management; Engineering; Operations research; Management; Psychology; Social psychology; Economics","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":[0.02532423,0.0008961406,0.0003951943,0.003043698,0.002032849,0.002480951,0.002072078,0.001583957,0.005858397],"category_scores_gemma":[0.07485883,0.0004138657,0.000840303,0.002278335,0.003011761,0.004790318,0.002860735,0.001874999,0.001985047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00288267,"about_ca_system_score_gemma":0.001587388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006907789,"about_ca_topic_score_gemma":0.01037246,"domain_scores_codex":[0.9774551,0.01659081,0.0008166918,0.001274216,0.003321734,0.0005414396],"domain_scores_gemma":[0.889908,0.08106376,0.003130507,0.01233653,0.01265769,0.0009036309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001795788,0.01442415,0.2541813,0.003505316,0.0006823624,0.00242065,0.06797682,0.07150804,0.007385161,0.08784672,0.04425801,0.4440156],"study_design_scores_gemma":[0.001306017,0.006599149,0.2047479,0.00282297,0.0005132398,0.001486123,0.08423076,0.3921355,0.02837699,0.0868085,0.1905541,0.0004187212],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.9276663,0.0004319497,0.03266728,0.001423473,0.0001420882,0.003170965,0.002470189,0.000382954,0.0316448],"genre_scores_gemma":[0.9278502,0.0004419611,0.05842418,0.0003622602,0.00006505432,0.004145475,0.003942951,0.0001383505,0.004629518],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02532423,"threshold_uncertainty_score":0.1339289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04260603465360654,"score_gpt":0.3478639022685132,"score_spread":0.3052578676149067,"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."}}