{"id":"W4413147242","doi":"10.1109/cvpr52734.2025.02061","title":"HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories","year":2025,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ground truth; Artificial intelligence; Computer science; Training (meteorology); Machine learning; Geography; Meteorology","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":[0.0002070774,0.0001567793,0.0001850004,0.0001135428,0.0002858254,0.0003189477,0.000358896,0.0001075035,0.0001941889],"category_scores_gemma":[0.00003587949,0.000139752,0.00007150045,0.0003198836,0.00003964445,0.0003992144,0.00007283501,0.0003076631,0.00006945265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003160927,"about_ca_system_score_gemma":0.00005399419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000293113,"about_ca_topic_score_gemma":0.00001494279,"domain_scores_codex":[0.9988102,0.00007867566,0.0002264974,0.0003921398,0.0001876899,0.0003048351],"domain_scores_gemma":[0.9994231,0.0001977322,0.00006049578,0.0002004132,0.0000530313,0.00006518001],"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":[0.00005735585,0.0003976863,0.004605525,0.00008702294,0.0002664492,0.00002635272,0.01255157,0.00203926,0.001675935,0.210504,0.03834031,0.7294485],"study_design_scores_gemma":[0.004441681,0.0007227326,0.004733847,0.0004250223,0.0001419651,0.00008283729,0.006421238,0.4825312,0.01494054,0.02028824,0.4630951,0.002175576],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1823138,0.0002286355,0.7149845,0.0003775502,0.00113052,0.0001172866,9.530513e-7,0.0005035501,0.1003432],"genre_scores_gemma":[0.9802053,0.00002765423,0.002117496,0.0005910149,0.0001323199,0.00001483662,0.00001264835,0.0000078549,0.01689087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7978915,"threshold_uncertainty_score":0.569892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01342131982563633,"score_gpt":0.2360095127113873,"score_spread":0.222588192885751,"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."}}