From 7ea36581a0469532630e891a032622c1f21a914b Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Thu, 6 Aug 2026 17:18:33 -0500 Subject: results: reject unmatched random-beta screen --- results/ep_bias/s2_summary.json | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 results/ep_bias/s2_summary.json (limited to 'results/ep_bias/s2_summary.json') diff --git a/results/ep_bias/s2_summary.json b/results/ep_bias/s2_summary.json new file mode 100644 index 0000000..036f353 --- /dev/null +++ b/results/ep_bias/s2_summary.json @@ -0,0 +1,23 @@ +{ + "stage": "rain_ep_random_beta_s2", + "status": "invalid_unmatched_corruption_development", + "rows": [ + { + "seed": 1989, + "random_beta_validation_accuracy": 0.4815, + "positive_beta_steps": 115, + "negative_beta_steps": 122, + "final_bias_state_difference_rms": 0.00019334602670050772 + }, + { + "seed": 1990, + "random_beta_validation_accuracy": 0.739, + "positive_beta_steps": 115, + "negative_beta_steps": 122, + "final_bias_state_difference_rms": 0.00017428155723407375 + } + ], + "reason_not_comparable": "The development injector normalized its fixed field from the first realized clean beta-state difference. A random-sign run initialized from a different beta sign than the fixed-positive runs and realized roughly 2.5 times their bias RMS. The results validate execution and sign accounting but do not compare methods at matched corruption.", + "next_protocol": "Normalize hardware readout bias from the free-state activity only, independently of beta sign and task difference, before comparing fixed-positive EP, random-sign beta, constant calibration and innovation.", + "test_policy": "development holdout observed; no performance claim" +} -- cgit v1.2.3