{"id":"W7160033404","doi":"10.1109/iccv51701.2025.02687","title":"ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction","year":2025,"lang":"","type":"article","venue":"","topic":"Random lasers and scattering media","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Noise (video); Gaussian; Pattern recognition (psychology); Focus (optics); Representation (politics)","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":[0.0005263783,0.000380445,0.000626345,0.0001631528,0.0006406095,0.0003102007,0.0001327404,0.0001358301,0.0004630232],"category_scores_gemma":[0.000025673,0.0003594657,0.0002396814,0.0001423018,0.0002342774,0.0001080479,0.00005118846,0.000238555,0.000009823824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005290679,"about_ca_system_score_gemma":0.0002142563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001300516,"about_ca_topic_score_gemma":0.00001581807,"domain_scores_codex":[0.9978665,0.00006719317,0.0006502976,0.0006380956,0.0001237523,0.0006541979],"domain_scores_gemma":[0.998827,0.0003682828,0.0002008716,0.0002843814,0.0001233444,0.0001960863],"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":[0.0009932549,0.0003025371,0.001303392,0.0007127002,0.0008481736,0.0000057787,0.00264087,0.001437909,0.01001133,0.05066637,0.002602638,0.928475],"study_design_scores_gemma":[0.07627482,0.0008542075,0.003088197,0.003460726,0.002138017,0.00005981514,0.06202003,0.6667575,0.1242045,0.0259928,0.03179647,0.003352841],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.68782,0.0004537504,0.2276302,0.00219761,0.002401597,0.002480228,0.0001373417,0.00006521484,0.07681401],"genre_scores_gemma":[0.9772004,0.00001088646,0.001739477,0.0002190676,0.0003453454,0.0001342595,0.00002147385,0.00002690963,0.02030217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9251222,"threshold_uncertainty_score":0.9998857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006558445930852787,"score_gpt":0.2309454969627036,"score_spread":0.2243870510318508,"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."}}