{"config": {"n_seq": 100, "n_steps": 100, "keep_k": 4, "dict_size": 40, "model": "Qwen/Qwen2.5-7B-Instruct", "seed": 20260728}, "per_condition": {"full": {"mean_step_acc": 0.0204, "ci95": [0.0149, 0.0264], "first20": 0.1005, "last20": 0.0, "drop": 0.1005, "curve": [0.61, 0.36, 0.26, 0.21, 0.16, 0.09, 0.07, 0.03, 0.03, 0.03, 0.03, 0.03, 0.03, 0.02, 0.02, 0.01, 0.01, 0.0, 0.01, 0.0, 0.01, 0.01, 0.01, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0], "mean_first_error_step": 1.93}, "oracle": {"mean_step_acc": 0.5801999999999999, "ci95": [0.5711999999999999, 0.5892000000000001], "first20": 0.747, "last20": 0.461, "drop": 0.286, "curve": [0.6, 0.57, 0.72, 0.83, 0.84, 0.79, 0.79, 0.79, 0.87, 0.78, 0.73, 0.73, 0.82, 0.71, 0.7, 0.63, 0.83, 0.78, 0.72, 0.71, 0.65, 0.62, 0.69, 0.72, 0.57, 0.61, 0.56, 0.65, 0.54, 0.66, 0.62, 0.63, 0.5, 0.62, 0.51, 0.58, 0.56, 0.62, 0.56, 0.65, 0.66, 0.65, 0.59, 0.57, 0.64, 0.57, 0.73, 0.57, 0.62, 0.53, 0.53, 0.61, 0.55, 0.56, 0.53, 0.62, 0.63, 0.6, 0.53, 0.59, 0.57, 0.54, 0.46, 0.5, 0.47, 0.47, 0.51, 0.45, 0.51, 0.52, 0.54, 0.56, 0.52, 0.52, 0.41, 0.5, 0.43, 0.53, 0.44, 0.41, 0.55, 0.44, 0.41, 0.48, 0.45, 0.35, 0.43, 0.33, 0.33, 0.47, 0.43, 0.5, 0.55, 0.55, 0.57, 0.5, 0.52, 0.5, 0.41, 0.45], "mean_first_error_step": 1.86}, "hygiene": {"mean_step_acc": 0.018500000000000003, "ci95": [0.014499999999999999, 0.022600000000000002], "first20": 0.0925, "last20": 0.0, "drop": 0.0925, "curve": [0.6, 0.48, 0.31, 0.2, 0.12, 0.07, 0.04, 0.02, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.01, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0], "mean_first_error_step": 1.8}, "both": {"mean_step_acc": 0.5953, "ci95": [0.5848, 0.6057], "first20": 0.6215, "last20": 0.585, "drop": 0.03650000000000009, "curve": [0.6, 0.82, 0.64, 0.79, 0.72, 0.68, 0.64, 0.63, 0.63, 0.52, 0.57, 0.52, 0.64, 0.59, 0.63, 0.49, 0.62, 0.66, 0.51, 0.53, 0.59, 0.57, 0.59, 0.66, 0.55, 0.46, 0.49, 0.63, 0.69, 0.44, 0.38, 0.45, 0.57, 0.59, 0.48, 0.44, 0.46, 0.6, 0.6, 0.57, 0.69, 0.62, 0.62, 0.65, 0.65, 0.72, 0.62, 0.77, 0.63, 0.58, 0.63, 0.63, 0.59, 0.67, 0.65, 0.67, 0.55, 0.67, 0.64, 0.67, 0.6, 0.58, 0.57, 0.59, 0.53, 0.62, 0.65, 0.56, 0.6, 0.53, 0.64, 0.57, 0.56, 0.67, 0.56, 0.55, 0.55, 0.56, 0.55, 0.63, 0.61, 0.54, 0.53, 0.63, 0.6, 0.56, 0.5, 0.51, 0.63, 0.6, 0.58, 0.61, 0.61, 0.55, 0.64, 0.61, 0.6, 0.53, 0.65, 0.61], "mean_first_error_step": 1.8}}, "verdicts": {"H1_baseline_degrades": {"first20": 0.1005, "last20": 0.0, "drop": 0.1005, "holds": true}, "H2_decoupling": {"oracle_drop": 0.286, "hygiene_drop": 0.0925, "both_drop": 0.03650000000000009, "error_presence_share": -1.8457711442786067, "length_share": 0.07960199004975131}, "H3_deployable_recovery": {"recovered_by_hygiene_over_oracle": -0.04312668463611864, "threshold": 0.5, "holds": false}}}