{"id":"W3111882491","doi":"","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Oracle; Mobile robot navigation; Computer vision; Observability; Turn-by-turn navigation; Feature (linguistics); Set (abstract data type); Navigation system; Human–computer interaction; Mobile robot; Robot","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":[0.0002806265,0.0004070369,0.0003758182,0.0002554755,0.0004076368,0.0002128543,0.001825934,0.0003101691,0.00002526906],"category_scores_gemma":[0.00004981037,0.0005234115,0.0002491947,0.0007595571,0.00009589125,0.0004130065,0.002361363,0.001126493,0.0002063051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003735211,"about_ca_system_score_gemma":0.0002312146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00183221,"about_ca_topic_score_gemma":0.00002937691,"domain_scores_codex":[0.9972653,0.0002767499,0.0003077442,0.001614371,0.000160194,0.0003756584],"domain_scores_gemma":[0.9976169,0.0001373696,0.0004752933,0.001360664,0.0001878436,0.0002218616],"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":[0.00001047142,0.0001087524,0.006497432,0.0002470177,0.00009353643,0.0001950565,0.0008146361,0.9761765,0.001113154,0.01283912,0.00003232554,0.001872016],"study_design_scores_gemma":[0.0004527808,0.00002017841,0.008418474,0.000203816,0.00007849128,0.000008574722,0.00004340856,0.9865894,0.0001713075,0.003431226,0.00007383983,0.0005085075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2889696,0.00003201023,0.7091298,0.0002636016,0.0005217132,0.0004321309,0.000007976294,0.0004813626,0.0001618552],"genre_scores_gemma":[0.9141681,0.00001174325,0.08528218,0.0001019719,0.0002092324,0.0000027697,0.00006893482,0.00003231361,0.0001227501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6251985,"threshold_uncertainty_score":0.9997218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059553040641273,"score_gpt":0.2374448356301037,"score_spread":0.1314895315659764,"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."}}