Files

66 lines
1.6 KiB
JSON

{
"classification": "post-screen exploratory metric audit; not a primary-protocol positive",
"candidate": {
"id": "conditional_qk_head_3_23_7_6",
"kind": "qk_head",
"i": 3,
"j": 23,
"a": 7,
"b": 6,
"perm": null
},
"conditioning_input_layer": 23,
"donor_projection_layer": 3,
"target_head": 6,
"donor_head": 7,
"selection_basis": "one minimum worst-text JS among the already measured source-conditioned pairs; no raw readout/fresh data used",
"js_max": 0.01,
"js_row_p95_max": 0.05,
"mean_total_variation_max": 0.1,
"row_total_variation_p95_max": 0.2,
"target_head_output_relative_l2_max": 0.2,
"target_head_output_cosine_min": 0.98,
"primary_query_positions": [
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
],
"top5_is_diagnostic_only": true,
"active_head_required": true,
"no_candidate_fallback": true,
"fresh_text_file": "crossqkv/fresh_samples.json",
"same_input_network_direction": "layer23 head6 uses QK probability of layer3 head7 recomputed on H23",
"actual_cache_separate": "layer3 probability on H3 reused at23; different-input diagnostic, not function-equivalence evidence",
"quality_gate": {
"mean_nll_delta_max": 0.01,
"per_text_p95_nll_delta_max": 0.05
},
"training": false,
"R_fitting": false,
"cost_required": false,
"registered_unix": 1794209105.213457,
"fresh_text_sha256": "d3f53fc98fa9d061a3df42f24fe307b693b41a9ddf74c8377dd52096663c40a9"
}