{"data":[{"project":"default","id":"app.email_spam-harness-kai-1.0834a74f-kai","benchmark":"app.email_spam","split":"harness","system":"kai","version":"kai-1@0834a74f2d140642a453373da09e5a128e3d2c8d9e8bb1dcaf86d7210a4ecdfc","baseline":false,"study":"","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"dde140a63fc527cbeb8f7ada29088bf17064d4bcf30c9680d6423696f0378673","store_digest":"","facts_digest":"","commit":"2c74e2d61addc885e847358975fb866b03cf17dc","questions":400,"answered":400,"when":"","ended":"2026-10-03T00:06:45Z","by":"","completion":"complete","measures":[{"category":"all","metric":"accuracy","value":0.9975,"lo":null,"hi":null,"n":400,"of":400},{"category":"all","metric":"brier","value":0.0047,"lo":null,"hi":null,"n":400,"of":400},{"category":"all","metric":"ece","value":0.003,"lo":null,"hi":null,"n":400,"of":400},{"category":"all","metric":"aurc","value":0,"lo":null,"hi":null,"n":400,"of":400},{"category":"all","metric":"zero_prob","value":0,"lo":null,"hi":null,"n":400,"of":400}],"notes":"device cuda; dtype bf16; preds sha256:9fe4a808809d63c37446a87aed506ba891ceb148c5c8d7c9947e17e3d27bf54e; scores sha256:1ec811cfb085ac209c7b094b408b00ef95d3d3c73b7ae7bdf6c52fc314d112e0","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":false}],"total":1,"completion":{"complete":1,"partial":0,"inconsistent":0,"unknown":0},"gaps":[{"field":"by","runs":1},{"field":"embedder","runs":1},{"field":"facts_digest","runs":1},{"field":"k","runs":1},{"field":"max_tokens","runs":1},{"field":"prompt","runs":1},{"field":"prompt_digest","runs":1},{"field":"reader","runs":1},{"field":"store_digest","runs":1},{"field":"temperature","runs":1},{"field":"when","runs":1}]}