{"id":"W4404624946","doi":"10.1007/978-3-031-73411-3_12","title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-Fine Pose-Reversible Guidance","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Benchmarking; Computer science; Refining (metallurgy); Artificial intelligence; Computer vision; Chemistry; Management","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":[0.0003593182,0.000353775,0.0002899643,0.0006079206,0.0002531884,0.0003587629,0.0003021058,0.0001668529,0.00005296797],"category_scores_gemma":[0.00001106055,0.000331405,0.00003391054,0.0003102725,0.0001313171,0.0002360803,0.0001877988,0.000671022,0.00002258432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001668822,"about_ca_system_score_gemma":0.00004329514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001864535,"about_ca_topic_score_gemma":0.0004185546,"domain_scores_codex":[0.998284,0.000009293397,0.0003086854,0.0006678808,0.0003847443,0.0003454175],"domain_scores_gemma":[0.9993889,0.00005574201,0.00006489109,0.0003215859,0.00006861959,0.0001002518],"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":[0.000002015649,0.00000169855,0.0001135334,0.00006504887,0.00001028049,0.00003327607,0.0004675522,0.9407752,0.001908363,0.00324952,0.00006701918,0.05330654],"study_design_scores_gemma":[0.0001647908,0.0001472244,0.000354765,0.0007992804,0.00001662629,0.00004168844,3.099065e-7,0.9928576,0.0004354985,0.0008832752,0.00374751,0.0005514001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004500641,0.0007691684,0.9796854,0.0001297572,0.001169048,0.0001713693,0.000001386906,0.0002945961,0.01327867],"genre_scores_gemma":[0.8560154,0.00001456672,0.1397948,0.000376795,0.001776836,0.000008142571,0.00003318114,0.0001028241,0.001877413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8515148,"threshold_uncertainty_score":0.9999138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02346539595968715,"score_gpt":0.2388674453845703,"score_spread":0.2154020494248832,"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."}}