{"id":"W213419448","doi":"10.1007/978-3-319-00065-7_65","title":"The UBC Visual Robot Survey: A Benchmark for Robot Category Recognition","year":2013,"lang":"en","type":"book-chapter","venue":"Springer tracts in advanced robotics","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Benchmark (surveying); Robot; Computer vision; Human–computer interaction; Geography; Cartography","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":[0.0005126667,0.0007360198,0.0006873783,0.0002652383,0.0002283795,0.0001808099,0.0003539545,0.0006862024,0.00005975391],"category_scores_gemma":[0.0002298067,0.0006889487,0.0002168326,0.0001213225,0.0001148311,0.00024453,0.00005382917,0.0009217504,0.0001336416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000387542,"about_ca_system_score_gemma":0.00008531613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003456305,"about_ca_topic_score_gemma":0.0007858816,"domain_scores_codex":[0.9971966,0.00004666092,0.001017856,0.000585545,0.0003895217,0.0007638121],"domain_scores_gemma":[0.997709,0.0009195648,0.0002826017,0.0005662963,0.000345844,0.0001766981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000457738,0.00003538398,0.00002209212,0.0001922951,0.00008422568,0.00000875001,0.00003420769,0.9495455,0.0002156807,0.004030913,0.0004015554,0.04538364],"study_design_scores_gemma":[0.002823246,0.0004608254,0.003184431,0.001417526,0.0003080844,0.00001702821,0.00005907003,0.8991534,0.001133812,0.03707759,0.05058042,0.003784575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005665222,0.004852669,0.915099,0.00026997,0.007997137,0.00470941,0.0002071054,0.0007832792,0.06551497],"genre_scores_gemma":[0.3897821,0.03751978,0.3198173,0.0008593906,0.004484863,0.001294753,0.01187114,0.004792302,0.2295783],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5952816,"threshold_uncertainty_score":0.9995562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02482919679582818,"score_gpt":0.2414331348163523,"score_spread":0.2166039380205241,"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."}}