{"id":"W54448200","doi":"10.1007/978-3-642-21538-4_31","title":"Towards Unified Performance Metrics for Multi-robot Human Interaction Systems","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Robot; Human–computer interaction; Human–robot interaction; Artificial intelligence","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":[0.0007766099,0.0004078968,0.0004693144,0.001336362,0.0003408679,0.0002043941,0.000855104,0.0004169437,0.0006960324],"category_scores_gemma":[0.00007050348,0.0003785151,0.0001528532,0.0003173543,0.0002852621,0.0003294178,0.0001543259,0.0007440972,0.0002477519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004095554,"about_ca_system_score_gemma":0.0001256047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001265226,"about_ca_topic_score_gemma":0.00007386487,"domain_scores_codex":[0.9974737,0.00004848652,0.0007172162,0.0009118163,0.000408952,0.0004398473],"domain_scores_gemma":[0.9979813,0.0002428452,0.0005075462,0.0007133492,0.0004383265,0.0001166115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001633901,0.0002694045,0.0002288972,0.0003409428,0.000152694,0.00002726852,0.009194663,0.01514538,0.0002234167,0.09485798,0.0006452848,0.8787507],"study_design_scores_gemma":[0.003460532,0.001723143,0.007356802,0.001638572,0.0001220867,0.000340366,0.00002048906,0.8540383,0.001384827,0.009063412,0.1180777,0.002773727],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004141456,0.0001260892,0.9537629,0.00006161052,0.01189619,0.0007228444,0.00001465204,0.0001665945,0.03283492],"genre_scores_gemma":[0.952937,0.00002327361,0.03121679,0.000611392,0.00101763,0.000102242,0.00005114593,0.00007827573,0.01396222],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9525229,"threshold_uncertainty_score":0.9998667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1233720465269389,"score_gpt":0.3787713365868886,"score_spread":0.2553992900599496,"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."}}