Upload reports/debate_extended_baselines_2seed.json

reports/debate_extended_baselines_2seed.json

@@ -0,0 +1,45 @@
+{
+  "platform": "H200",
+  "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+  "pytorch": "2.11.0+cu130",
+  "n_topics": 30,
+  "n_agents": 4,
+  "agent_mix": "3 honest + 1 adversarial",
+  "seeds_completed": [42, 123],
+  "seeds_running": [456],
+  "date": "2026-05-08",
+  "per_seed": {
+    "42": {
+      "equal_1round": {"accuracy": 0.867, "correct": 26, "tokens": 41812},
+      "equal_3round": {"accuracy": 0.567, "correct": 17, "tokens": 150099},
+      "random_drop": {"accuracy": 0.833, "correct": 25, "tokens": 34181, "denied": 33},
+      "occ_240_5": {"accuracy": 0.800, "correct": 24, "tokens": 40780, "denied": 6},
+      "occ_180_3": {"accuracy": 0.867, "correct": 26, "tokens": 39952, "denied": 0},
+      "occ_120_3": {"accuracy": 0.833, "correct": 25, "tokens": 42423, "denied": 0}
+    },
+    "123": {
+      "equal_1round": {"accuracy": 0.900, "correct": 27, "tokens": 41875},
+      "equal_3round": {"accuracy": 0.567, "correct": 17, "tokens": 149544},
+      "random_drop": {"accuracy": 0.867, "correct": 26, "tokens": 27200, "denied": 35},
+      "occ_240_5": {"accuracy": 0.767, "correct": 23, "tokens": 32071, "denied": 15},
+      "occ_180_3": {"accuracy": 0.800, "correct": 24, "tokens": 42086, "denied": 0},
+      "occ_120_3": {"accuracy": 0.867, "correct": 26, "tokens": 42902, "denied": 0}
+    }
+  },
+  "aggregate_seeds_42_123": {
+    "equal_1round": {"mean_accuracy": 0.883, "mean_tokens": 41844},
+    "equal_3round": {"mean_accuracy": 0.567, "mean_tokens": 149822},
+    "random_drop": {"mean_accuracy": 0.850, "mean_tokens": 30691},
+    "occ_240_5": {"mean_accuracy": 0.783, "mean_tokens": 36426},
+    "occ_180_3": {"mean_accuracy": 0.833, "mean_tokens": 41019},
+    "occ_120_3": {"mean_accuracy": 0.850, "mean_tokens": 42663}
+  },
+  "key_findings": [
+    "Equal 3-round collapses to 56.7% on BOTH seeds — 32pp below 1-round baseline (88.3%)",
+    "Adversarial agent given 3x speaking time floods the vote pool",
+    "Random 25% drop achieves 85.0% with 26.5% token savings — effective but undiscriminating",
+    "OCC 180/3 achieves 83.3% at iso-compute (41k vs 42k baseline tokens)",
+    "OCC 240/5 is too aggressive (78.3%), OCC 120/3 = random drop (85.0%)",
+    "OCC credit allocation prevents catastrophic failure but doesn't beat random gating at moderate budgets"
+  ]
+}