1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
|
{
"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": "early_credit_limited_by_estimator_efficiency_and_feedback_capacity",
"evidence": [
"instantaneous prediction-target cosine remains effectively zero",
"calibration MSE remains indistinguishable from stochastic target power",
"target power grows by orders of magnitude before nonfiniteness",
"matched frozen-forward unit targets later yield only 0.0011 early-layer alignment",
"structured learning reaches 0.0072 versus a 0.0240 cross-validated family oracle",
"unconstrained coefficients raise the same spatial basis oracle only to 0.0549",
"direct A/G estimation leaves early alignment unchanged at 0.0071",
"held-out gated 3x3 maps from exact child errors reach 0.9998"
],
"interpretation_limit": "instantaneous target metrics alone do not prove zero conditional learning; structured v2 has low instantaneous cosine yet positive exact-gradient alignment",
"next_design_constraint": "do not add the tested activation contexts or repeat the closed A/G rate grid; learn spatial hierarchical feedback without weight copying and audit against hierarchical FA/BurstCCN",
"next_test_outcome": "representable-subspace perturbation improved alignment but failed; direct vectorizer-space estimation then improved only middle/late layers and also failed the frozen early-layer gate"
},
"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
}
},
"post_failure_hierarchical_refinement": {
"direct_output_channel_gated": 0.031122580851844408,
"downstream_activation_context": 0.032068526988258954,
"hierarchical_1x1_gated": 0.50521034930192,
"hierarchical_3x3_gated": 0.9997667354251036
},
"post_failure_representation_refinement": {
"channel_gated_cv_oracle_early_third_alignment": 0.02396580002561188,
"naive_local_context_cv_early_third_alignment": 0.022457713873793972,
"per_example_spatial_oracle_early_third_alignment": 0.05494018487684554,
"trained_structured_early_third_alignment": 0.007209055746595065
},
"post_failure_v2_refinement": {
"structured_all_layer_alignment": 0.05273995646520665,
"structured_early_third_alignment": 0.007209055746595065,
"structured_gate_status": "failed",
"unit_target_all_layer_alignment": 0.011664319529173602,
"unit_target_early_third_alignment": 0.0011051012067279469
},
"post_failure_v3_refinement": {
"matched_v2_all_layer_alignment": 0.052739956808325494,
"matched_v2_early_third_alignment": 0.007209058462952574,
"vectorizer_subspace_all_layer_alignment": 0.0625791079364717,
"vectorizer_subspace_early_third_alignment": 0.007139206010227402,
"vectorizer_subspace_gate_status": "failed"
},
"protocol": "oral_a_A3_failure_diagnosis_v3",
"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",
"hierarchical_oracle": "results/oral_a_hierarchical_oracle.json",
"representation": "results/oral_a_representation_diagnosis.json",
"short": "results/oral_a_short/sdil_channel_gated_lr0.03.json",
"v2_gate": "results/oral_a_v2_calibration_gate.json",
"v3_gate": "results/oral_a_v3_calibration_gate.json"
}
}
|
