{"id":"W4385430633","doi":"10.15607/rss.2023.xix.041","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","year":2023,"lang":"en","type":"article","venue":"","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Benchmark (surveying); Computer science; Horizon; Artificial intelligence; Mathematics; Geology; Geodesy","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":[],"consensus_categories":[],"category_scores_codex":[0.000964246,0.000188404,0.0002265925,0.0003808939,0.0002469471,0.000185054,0.0007779968,0.00006637305,0.00004607517],"category_scores_gemma":[0.0001266598,0.0001764158,0.00008896021,0.001576051,0.0000263068,0.0004287451,0.0002330412,0.000113722,0.000315185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007007566,"about_ca_system_score_gemma":0.00005802352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001249427,"about_ca_topic_score_gemma":0.00004672469,"domain_scores_codex":[0.9977948,0.00005457822,0.0003597524,0.0009044058,0.0003755893,0.000510891],"domain_scores_gemma":[0.998137,0.0002558331,0.0001241774,0.001231728,0.0001348208,0.0001164383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003609647,0.0001945425,0.03279891,0.0002216298,0.0001182798,0.000165753,0.00130213,0.06939451,0.002808191,0.2060786,0.5628552,0.1240261],"study_design_scores_gemma":[0.0003505522,0.0001662116,0.2196525,0.00002749177,0.000009639445,0.00001141938,0.00001880129,0.763045,0.0007518645,0.01071388,0.004928118,0.0003245991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003743661,0.00001550259,0.9618205,0.002720051,0.001453055,0.0006569455,0.000005919811,0.001767117,0.02781718],"genre_scores_gemma":[0.193602,0.00001953494,0.7697917,0.0003124446,0.0008328219,0.0001399666,0.000396541,0.00004910308,0.03485585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6936504,"threshold_uncertainty_score":0.7194028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1058822593118378,"score_gpt":0.3353532847107676,"score_spread":0.2294710253989298,"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."}}