{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001724463,0.0003615586,0.00052583,0.00052347,0.001225221,0.0002211905,0.0002651694,0.0005325649,0.0007412686],"category_scores_gemma":[0.00191527,0.0003522288,0.0000912629,0.0006498309,0.0004985747,0.00032415,0.0001036957,0.0002569391,0.00008174323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005111473,"about_ca_system_score_gemma":0.0002080984,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5071307,"about_ca_topic_score_gemma":0.2524575,"domain_scores_codex":[0.9969918,0.0006360026,0.0005952582,0.0005966777,0.0007188288,0.0004614077],"domain_scores_gemma":[0.9982187,0.0006838382,0.000316623,0.0003387071,0.0003519773,0.00009017614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004973274,0.0001731684,0.06074286,0.001182703,0.0001559407,0.00006440748,0.009690138,0.000005952481,0.00001271176,0.08750568,0.8399358,0.0005256107],"study_design_scores_gemma":[0.0007041486,0.0001497841,0.01652256,0.0003428693,0.0001593995,0.00001343921,0.02109831,0.0001131894,0.000002037208,0.001282893,0.9581542,0.00145719],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0183028,0.002142701,0.0003976299,0.001697612,0.005160654,0.007719071,0.0008908176,0.008036537,0.9556522],"genre_scores_gemma":[0.3231146,0.00003375484,0.00002742419,0.00004033148,0.002396598,0.00009779484,0.00017342,0.0004915741,0.6736245],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3048118,"threshold_uncertainty_score":0.999893,"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."}}