{"id":"W4402475889","doi":"10.1109/hcs61935.2024.10664910","title":"Picasso: An Area/Energy-Efficient End-to-End Diffusion Accelerator with Hyper-Precision Data Type","year":2024,"lang":"en","type":"article","venue":"","topic":"Particle Detector Development and Performance","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"PICASSO; Computer science; Diffusion; End-to-end principle; Energy (signal processing); Type (biology); Artificial intelligence; Physics; Art; Art history; Geology; Statistics; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001416142,0.0001709662,0.0001356381,0.00007940499,0.0001275407,0.0002240523,0.0003757031,0.00002762479,0.002777972],"category_scores_gemma":[0.00000259383,0.0001151109,0.00002039258,0.0004254171,0.00001916939,0.0003076608,0.0002514368,0.0001044332,0.0003069272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002119359,"about_ca_system_score_gemma":0.00009696678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001124176,"about_ca_topic_score_gemma":0.00003516809,"domain_scores_codex":[0.9987922,0.00001988428,0.0001693929,0.0004690875,0.0002698046,0.0002796458],"domain_scores_gemma":[0.9991085,0.0000415291,0.00002164497,0.0005992314,0.00005018083,0.0001789336],"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":[0.0003438529,0.0005434873,0.06057248,0.00002371755,0.0001527697,0.00002116545,0.00100638,0.0008951342,0.08787726,0.007338205,0.01014676,0.8310788],"study_design_scores_gemma":[0.0009199967,0.0004733994,0.03656109,0.0002084608,0.0000777135,0.000006755397,0.0004018123,0.5432177,0.09039726,0.0002515002,0.3263834,0.001100876],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862948,0.00004528711,0.006786062,0.0001073369,0.0003240104,0.0001024989,0.00005037035,0.0001059628,0.006183662],"genre_scores_gemma":[0.9971188,0.000003684885,0.00115136,0.00006170314,0.0002367283,0.00001216549,0.0002493113,0.00002295097,0.001143253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8299779,"threshold_uncertainty_score":0.9981336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04277062954618508,"score_gpt":0.2817623939137339,"score_spread":0.2389917643675488,"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."}}