{"id":"W6891717660","doi":"10.48448/3nrj-te42","title":"Improving Open Set Recognition via Visual Prompts Distilled from Common-Sense Knowledge","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Set (abstract data type); Cognitive neuroscience of visual object recognition; Feature (linguistics); Pattern recognition (psychology); Visualization; Open set; Visual perception; Class (philosophy)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002316988,0.001240471,0.0008649543,0.001122579,0.0005070831,0.00192613,0.001619462,0.001261503,0.005099615],"category_scores_gemma":[0.01907912,0.0003375541,0.0009426474,0.0006833894,0.001138875,0.005554785,0.003483328,0.002323925,0.002319294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006881403,"about_ca_system_score_gemma":0.001311474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001320968,"about_ca_topic_score_gemma":0.001781558,"domain_scores_codex":[0.9976484,0.0006969156,0.0001532315,0.0009194373,0.0004452771,0.0001367204],"domain_scores_gemma":[0.9919955,0.004026189,0.0008341031,0.00186848,0.0008570479,0.0004188614],"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":[0.0007027988,0.0006896674,0.007515859,0.0004789621,0.00006806494,0.0002190194,0.00109157,0.03304201,0.02974876,0.01351966,0.007692541,0.9052312],"study_design_scores_gemma":[0.00007156183,0.0007724374,0.005218629,0.0001480231,0.00005430422,0.000330395,0.001029319,0.8587921,0.03270943,0.09069204,0.01006601,0.0001157345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09024607,0.0004678764,0.8918669,0.0008685466,0.0002707427,0.0002746019,0.0006354898,0.01040186,0.004967959],"genre_scores_gemma":[0.6839015,0.0002283394,0.309898,0.0003834018,0.00011264,0.0002998409,0.001674087,0.0002991335,0.003202984],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005099615,"threshold_uncertainty_score":0.01705992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05688192136346401,"score_gpt":0.3723261220682377,"score_spread":0.3154442007047736,"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."}}