analysis: diagnose Oral-A calibration failure

1 files changed, 90 insertions, 0 deletions

diff --git a/results/oral_a_failure_diagnosis.json b/results/oral_a_failure_diagnosis.json
new file mode 100644
index 0000000..7c6b31b
--- /dev/null
+++ b/results/oral_a_failure_diagnosis.json
@@ -0,0 +1,90 @@
+{
+  "calibration_precursor": {
+    "checkpoints": [
+      {
+        "epoch": 1,
+        "mse_to_target_power": 1.0000000242141691,
+        "prediction_target_cosine": -5.120151685872971e-06,
+        "target_power": 142.2609250246797
+      },
+      {
+        "epoch": 20,
+        "mse_to_target_power": 1.0000000055445346,
+        "prediction_target_cosine": -9.188050003749003e-06,
+        "target_power": 492.22621874637883
+      },
+      {
+        "epoch": 40,
+        "mse_to_target_power": 1.0000000207505706,
+        "prediction_target_cosine": -1.6028913891638828e-05,
+        "target_power": 3347.859035403952
+      },
+      {
+        "epoch": 60,
+        "mse_to_target_power": 0.9999999997640454,
+        "prediction_target_cosine": 4.038185739212611e-05,
+        "target_power": 12104.714606234214
+      },
+      {
+        "epoch": 80,
+        "mse_to_target_power": 0.9999999967773018,
+        "prediction_target_cosine": 6.468792391264821e-05,
+        "target_power": 364280.45838307025
+      },
+      {
+        "epoch": 87,
+        "mse_to_target_power": 1.0000000346545865,
+        "prediction_target_cosine": 1.4983485078330897e-05,
+        "target_power": 302564383414.18854
+      }
+    ],
+    "max_abs_mse_to_target_power_minus_one": 6.963728138575931e-08,
+    "max_abs_prediction_target_cosine_before_nonfinite": 8.508675264290486e-05,
+    "target_power_growth_epoch1_to_80": 2560.650145638194,
+    "target_power_growth_epoch1_to_87": 2126827049.3932126
+  },
+  "diagnosis": {
+    "classification": "causal_target_not_captured_before_runaway",
+    "evidence": [
+      "prediction-target cosine remains effectively zero",
+      "calibration MSE remains indistinguishable from target power",
+      "target power grows by orders of magnitude before nonfiniteness",
+      "short-run teaching alignment therefore cannot be attributed to learned A"
+    ],
+    "next_test": "reduce estimator variance by perturbing the representable channel-gated feedback subspace, not every spatial unit"
+  },
+  "frozen_outcome": {
+    "confirmation_test_seeds_touched": false,
+    "final_accuracy": 0.1,
+    "final_finite": false,
+    "first_nonfinite_epoch": 89,
+    "last_finite_validation": {
+      "accuracy": 0.2282,
+      "epoch": 80,
+      "finite": true,
+      "loss": 1080.0792
+    },
+    "last_reported_validation": {
+      "accuracy": 0.1,
+      "epoch": 200,
+      "finite": false,
+      "loss": null
+    }
+  },
+  "protocol": "oral_a_A3_failure_diagnosis_v1",
+  "short_screen_contrast": {
+    "accuracy": 0.4198,
+    "early_third_alignment": 0.08889565182228883,
+    "warmup_mse_to_target_power": 1.0000000128001325,
+    "warmup_prediction_target_cosine": 0.00016553175127441687
+  },
+  "source_commits": {
+    "full": "a1d060e6d96d4ab973d16cd75149dd61899c7c95",
+    "short": "a1d060e6d96d4ab973d16cd75149dd61899c7c95"
+  },
+  "source_paths": {
+    "full": "results/oral_a_dev/sdil_full_r20_s0.json",
+    "gate": "results/oral_a_full_gate.json",
+    "short": "results/oral_a_short/sdil_channel_gated_lr0.03.json"
+  }
+}