docs/benchmarks/context-activation-product-2026-10-v5.json
Rama main · réplica de lectura del repositorio original.
{
"amended": {
"amendments": [
"unit_parent_recall",
"hedged_poison"
],
"audit_passed": false,
"c9_padding_robustness": {
"base_case_id": "C2",
"padded_case_id": "C9",
"passed": false,
"precision_delta": null,
"precision_padded": null,
"reasons": [
"padded-tree precision below the 0.8 floor"
],
"recall_base": 0.0,
"recall_padded": 0.0
},
"hedged_twins": {
"count": 0,
"total": 4
},
"per_case": [
{
"case_id": "C1",
"failure_reasons": [
"gold recall 0.67 below the 0.9 floor",
"precision 0.67 below the 0.8 floor",
"missing required fact(s): ['capacity ceiling']"
],
"gold": {
"hit": 2,
"total": 3
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": 0.6666666666666666
},
{
"case_id": "T1",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 3
},
"precision": null
},
{
"case_id": "C2",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T2",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C3",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.50 below the 0.9 floor",
"missing required fact(s): ['extending the reporting module']"
],
"gold": {
"hit": 1,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T3",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C4",
"failure_reasons": [
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "T4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C5",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T5",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "C6",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": null
},
{
"case_id": "T6",
"failure_reasons": [
"1 poison anchor(s) surfaced"
],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": false,
"poison": {
"hit": 1,
"total": 1
},
"precision": null
},
{
"case_id": "C7",
"failure_reasons": [],
"gold": {
"hit": 3,
"total": 3
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": 1.0
},
{
"case_id": "T7",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C8",
"failure_reasons": [
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "T8",
"failure_reasons": [
"twin surfaced a ref outside its own gold",
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "C9",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T9",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
}
]
},
"amended_a7": {
"amendments": [
"ambiguity_precision"
],
"audit_passed": false,
"c9_padding_robustness": {
"base_case_id": "C2",
"padded_case_id": "C9",
"passed": false,
"precision_delta": null,
"precision_padded": null,
"reasons": [
"padded-tree precision below the 0.8 floor"
],
"recall_base": 0.0,
"recall_padded": 0.0
},
"hedged_twins": {
"count": 0,
"total": 4
},
"per_case": [
{
"case_id": "C1",
"failure_reasons": [
"gold recall 0.67 below the 0.9 floor",
"precision 0.67 below the 0.8 floor",
"missing required fact(s): ['capacity ceiling']"
],
"gold": {
"hit": 2,
"total": 3
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": 0.6666666666666666
},
{
"case_id": "T1",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 3
},
"precision": null
},
{
"case_id": "C2",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T2",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C3",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.50 below the 0.9 floor",
"missing required fact(s): ['extending the reporting module']"
],
"gold": {
"hit": 1,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T3",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C4",
"failure_reasons": [
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "T4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C5",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T5",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "C6",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": null
},
{
"case_id": "T6",
"failure_reasons": [
"1 poison anchor(s) surfaced"
],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": false,
"poison": {
"hit": 1,
"total": 1
},
"precision": null
},
{
"case_id": "C7",
"failure_reasons": [],
"gold": {
"hit": 3,
"total": 3
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": 1.0
},
{
"case_id": "T7",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C8",
"failure_reasons": [
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "T8",
"failure_reasons": [
"twin surfaced a ref outside its own gold",
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "C9",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T9",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
}
]
},
"amended_a8": {
"amendments": [
"carried_gold"
],
"audit_passed": false,
"c9_padding_robustness": {
"base_case_id": "C2",
"padded_case_id": "C9",
"passed": false,
"precision_delta": null,
"precision_padded": null,
"reasons": [
"padded-tree precision below the 0.8 floor"
],
"recall_base": 0.0,
"recall_padded": 0.0
},
"hedged_twins": {
"count": 0,
"total": 4
},
"per_case": [
{
"case_id": "C1",
"failure_reasons": [
"gold recall 0.67 below the 0.9 floor",
"missing required fact(s): ['capacity ceiling']"
],
"gold": {
"hit": 2,
"total": 3
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T1",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 3
},
"precision": null
},
{
"case_id": "C2",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T2",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C3",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.50 below the 0.9 floor",
"missing required fact(s): ['extending the reporting module']"
],
"gold": {
"hit": 1,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T3",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "T4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C5",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T5",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "C6",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": null
},
{
"case_id": "T6",
"failure_reasons": [
"1 poison anchor(s) surfaced"
],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": false,
"poison": {
"hit": 1,
"total": 1
},
"precision": null
},
{
"case_id": "C7",
"failure_reasons": [],
"gold": {
"hit": 3,
"total": 3
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": 1.0
},
{
"case_id": "T7",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C8",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "T8",
"failure_reasons": [
"twin surfaced a ref outside its own gold",
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "C9",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T9",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
}
]
},
"amended_a9": {
"agent_choice_digest": "bfedee2fce49dd23d2cae7e2756c7a9f8d747dc5e72c4ef7152ea5a35c064a2f",
"amendments": [
"agent_choice"
],
"audit_passed": false,
"c9_padding_robustness": {
"base_case_id": "C2",
"padded_case_id": "C9",
"passed": false,
"precision_delta": null,
"precision_padded": null,
"reasons": [
"padded-tree precision below the 0.8 floor"
],
"recall_base": 0.0,
"recall_padded": 0.0
},
"hedged_twins": {
"count": 0,
"total": 4
},
"per_case": [
{
"case_id": "C1",
"failure_reasons": [
"A9: 1 gold page(s) not served under an honest label",
"A9: gold fact(s) missing from served material: ['capacity ceiling']"
],
"gold": {
"hit": 2,
"total": 3
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": 0.6666666666666666
},
{
"case_id": "T1",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 3
},
"precision": null
},
{
"case_id": "C2",
"failure_reasons": [
"A9: 2 gold page(s) not served under an honest label",
"A9: gold fact(s) missing from served material: ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T2",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C3",
"failure_reasons": [
"A9: 2 gold page(s) not served under an honest label",
"A9: gold fact(s) missing from served material: ['extending the reporting module']"
],
"gold": {
"hit": 1,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T3",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "T4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C5",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T5",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "C6",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": null
},
{
"case_id": "T6",
"failure_reasons": [
"1 poison anchor(s) surfaced"
],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": false,
"poison": {
"hit": 1,
"total": 1
},
"precision": null
},
{
"case_id": "C7",
"failure_reasons": [],
"gold": {
"hit": 3,
"total": 3
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": 1.0
},
{
"case_id": "T7",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C8",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "T8",
"failure_reasons": [
"twin surfaced a ref outside its own gold",
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5
},
{
"case_id": "C9",
"failure_reasons": [
"A9: 2 gold page(s) not served under an honest label",
"A9: gold fact(s) missing from served material: ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T9",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
}
]
},
"amended_v5": {
"amendments": [
"unit_page",
"partial_abstain_hedge"
],
"audit_passed": false,
"c9_padding_robustness": {
"base_case_id": "C2",
"padded_case_id": "C9",
"passed": false,
"precision_delta": null,
"precision_padded": null,
"reasons": [
"padded-tree precision below the 0.8 floor"
],
"recall_base": 0.0,
"recall_padded": 0.0
},
"hedged_twins": {
"count": 1,
"total": 4
},
"per_case": [
{
"case_id": "C1",
"failure_reasons": [
"gold recall 0.67 below the 0.9 floor",
"missing required fact(s): ['capacity ceiling']"
],
"gold": {
"hit": 2,
"total": 3
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T1",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 3
},
"precision": null
},
{
"case_id": "C2",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T2",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C3",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.50 below the 0.9 floor",
"missing required fact(s): ['extending the reporting module']"
],
"gold": {
"hit": 1,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T3",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "T4",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
},
{
"case_id": "C5",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "T5",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0
},
{
"case_id": "C6",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": null
},
{
"case_id": "T6",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": true,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "C7",
"failure_reasons": [],
"gold": {
"hit": 3,
"total": 3
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": 1.0
},
{
"case_id": "T7",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C8",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "T8",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0
},
{
"case_id": "C9",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null
},
{
"case_id": "T9",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null
}
]
},
"audit_passed": false,
"blocked": {
"count": 0,
"total": 18
},
"c9_padding_robustness": {
"base_case_id": "C2",
"padded_case_id": "C9",
"passed": false,
"precision_delta": null,
"precision_padded": null,
"reasons": [
"padded-tree precision below the 0.8 floor"
],
"recall_base": 0.0,
"recall_padded": 0.0
},
"corpus_id": "context-activation-corpus-v5",
"fixture_mechanisms": {
"C1": "resolver",
"C2": "resolver",
"C3": "resolver",
"C4": "resolver",
"C5": "records_state",
"C6": "naming_gate",
"C7": "competing_senses",
"C8": "naming_gate",
"C9": "resolver",
"T1": "naming_gate",
"T2": "naming_gate",
"T3": "resolver",
"T4": "competing_senses",
"T5": "resolver",
"T6": "soundness",
"T7": "competing_senses",
"T8": "naming_gate",
"T9": "naming_gate"
},
"fixture_set_digest": "9d15d155bd61096ba0ff2613d6752a35e03d3fb4078fa189e42b4c1ce2a3bdaa",
"hedged_twins": {
"count": 0,
"total": 4
},
"instrument": "context-activation deterministic audit, real compiler",
"mechanism": "product_activate_context",
"mechanism_removal": {
"competing_senses": {
"audit_passed": false,
"passing_cases": [
"T1",
"T2",
"T3",
"C5",
"T5",
"C6",
"T9"
],
"removes": "competing-sense handling: disconnected same-kind anchors never abstain, whether resolved or reached by one bare shared name, and a qualifier never narrows two senses"
},
"naming_gate": {
"audit_passed": false,
"passing_cases": [
"T3",
"T4",
"C5",
"T5",
"C7",
"T7"
],
"removes": "the retrieval carry's naming gate: the top lexical hit for the turn's words is carried, with no corpus-rare phrase, corpus-size floor or single-page rule"
},
"records_state": {
"audit_passed": false,
"passing_cases": [
"T1",
"T2",
"T3",
"T4",
"T5",
"C6",
"C7",
"T7",
"T9"
],
"removes": "governed current state: no Records or profile state reaches the packet"
},
"resolver": {
"audit_passed": false,
"passing_cases": [
"T1",
"T2",
"C6",
"T6",
"T9"
],
"removes": "anchor resolution: no candidate resolves, so no anchor, lane or current state is served"
},
"soundness": {
"audit_passed": false,
"passing_cases": [
"T1",
"T2",
"T3",
"T4",
"C5",
"T5",
"C6",
"T9"
],
"removes": "the soundness rule: any one contact kind (a rare term or retrieval alone) resolves"
},
"working_set": {
"audit_passed": false,
"passing_cases": [
"T1",
"T2",
"C6",
"T6",
"T9"
],
"removes": "the whole compiler: the documented EXOMEM_DISABLE_WORKING_SET kill switch"
}
},
"per_case": [
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 2
},
"kind": "note",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "records_collection",
"poison": {
"hit": 0,
"total": 0
}
}
],
"case_id": "C1",
"expected_status": "resolved",
"failure_reasons": [
"gold recall 0.67 below the 0.9 floor",
"precision 0.67 below the 0.8 floor",
"missing required fact(s): ['capacity ceiling']"
],
"gold": {
"hit": 2,
"total": 3
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [
"capacity ceiling"
],
"observed_status": "resolved",
"packet_chars": 452,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": 0.6666666666666666,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "note",
"poison": {
"hit": 0,
"total": 2
}
},
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "records_collection",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "T1",
"expected_status": "unresolved",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "unresolved",
"packet_chars": 0,
"passed": true,
"poison": {
"hit": 0,
"total": 3
},
"precision": null,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 1
},
"kind": "equipment",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 0,
"total": 1
},
"kind": "note",
"poison": {
"hit": 0,
"total": 0
}
}
],
"case_id": "C2",
"expected_status": "resolved",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [
"grill",
"cooking method"
],
"observed_status": "unresolved",
"packet_chars": 0,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null,
"status_match": false,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "equipment",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "note",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "T2",
"expected_status": "unresolved",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "unresolved",
"packet_chars": 0,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "note",
"poison": {
"hit": 0,
"total": 0
}
},
{
"gold": {
"hit": 0,
"total": 1
},
"kind": "planning_item",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "C3",
"expected_status": "resolved",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.50 below the 0.9 floor",
"missing required fact(s): ['extending the reporting module']"
],
"gold": {
"hit": 1,
"total": 2
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [
"extending the reporting module"
],
"observed_status": "unresolved",
"packet_chars": 54,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null,
"status_match": false,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "note",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "planning_item",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "T3",
"expected_status": "resolved",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 154,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "entity",
"poison": {
"hit": 0,
"total": 2
}
},
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "note",
"poison": {
"hit": 0,
"total": 0
}
}
],
"case_id": "C4",
"expected_status": "resolved",
"failure_reasons": [
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 202,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 2,
"total": 2
},
"kind": "entity",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "note",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "T4",
"expected_status": "ambiguous",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "ambiguous",
"packet_chars": 299,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "records_collection",
"poison": {
"hit": 0,
"total": 0
}
},
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "resource",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "C5",
"expected_status": "resolved",
"failure_reasons": [],
"gold": {
"hit": 2,
"total": 2
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 481,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "records_collection",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "resource",
"poison": {
"hit": 0,
"total": 0
}
}
],
"case_id": "T5",
"expected_status": "resolved",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 277,
"passed": true,
"poison": {
"hit": 0,
"total": 1
},
"precision": 1.0,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [],
"case_id": "C6",
"expected_status": "unresolved",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "unresolved",
"packet_chars": 0,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": null,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "equipment",
"poison": {
"hit": 1,
"total": 1
}
}
],
"case_id": "T6",
"expected_status": "unresolved",
"failure_reasons": [
"1 poison anchor(s) surfaced"
],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "unresolved",
"packet_chars": 235,
"passed": false,
"poison": {
"hit": 1,
"total": 1
},
"precision": null,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 3,
"total": 3
},
"kind": "hub",
"poison": {
"hit": 0,
"total": 0
}
}
],
"case_id": "C7",
"expected_status": "ambiguous",
"failure_reasons": [],
"gold": {
"hit": 3,
"total": 3
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "ambiguous",
"packet_chars": 366,
"passed": true,
"poison": {
"hit": 0,
"total": 0
},
"precision": 1.0,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "hub",
"poison": {
"hit": 0,
"total": 2
}
}
],
"case_id": "T7",
"expected_status": "resolved",
"failure_reasons": [],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 332,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": 1.0,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "note",
"poison": {
"hit": 0,
"total": 2
}
}
],
"case_id": "C8",
"expected_status": "resolved",
"failure_reasons": [
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 111,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5,
"status_match": true,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 1,
"total": 1
},
"kind": "note",
"poison": {
"hit": 0,
"total": 2
}
}
],
"case_id": "T8",
"expected_status": "resolved",
"failure_reasons": [
"twin surfaced a ref outside its own gold",
"precision 0.50 below the 0.8 floor"
],
"gold": {
"hit": 1,
"total": 1
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "resolved",
"packet_chars": 112,
"passed": false,
"poison": {
"hit": 0,
"total": 2
},
"precision": 0.5,
"status_match": true,
"twin_false_activation": true
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 1
},
"kind": "equipment",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 0,
"total": 1
},
"kind": "note",
"poison": {
"hit": 0,
"total": 0
}
}
],
"case_id": "C9",
"expected_status": "resolved",
"failure_reasons": [
"expected status 'resolved', observed 'unresolved'",
"gold recall 0.00 below the 0.9 floor",
"missing required fact(s): ['grill', 'cooking method']"
],
"gold": {
"hit": 0,
"total": 2
},
"hedged": false,
"is_twin": false,
"must_exclude_present": [],
"must_include_missing": [
"grill",
"cooking method"
],
"observed_status": "unresolved",
"packet_chars": 0,
"passed": false,
"poison": {
"hit": 0,
"total": 1
},
"precision": null,
"status_match": false,
"twin_false_activation": false
},
{
"blocked": false,
"by_anchor_kind": [
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "equipment",
"poison": {
"hit": 0,
"total": 1
}
},
{
"gold": {
"hit": 0,
"total": 0
},
"kind": "note",
"poison": {
"hit": 0,
"total": 1
}
}
],
"case_id": "T9",
"expected_status": "unresolved",
"failure_reasons": [],
"gold": {
"hit": 0,
"total": 0
},
"hedged": false,
"is_twin": true,
"must_exclude_present": [],
"must_include_missing": [],
"observed_status": "unresolved",
"packet_chars": 0,
"passed": true,
"poison": {
"hit": 0,
"total": 2
},
"precision": null,
"status_match": true,
"twin_false_activation": false
}
],
"threshold_digest": "7b2785cf81437ad98eeede3fb9bb046baa80fdcddf883d33c293cae91fbf867a",
"thresholds": {
"end_to_end_p50_ms_ceiling": 10744.641,
"end_to_end_p95_ms_ceiling": 16488.201,
"gold_recall_floor": 0.9,
"hedged_twins_ceiling": 1,
"padding_precision_floor": 0.8,
"precision_floor": 0.8,
"statement_max_chars": 200,
"token_hard_cap": 2000,
"token_p50_ceiling": 900,
"token_p95_ceiling": 1500,
"working_set_p50_ms_ceiling": 800,
"working_set_p95_ms_ceiling": 2500
},
"trees": [
{
"distractor_count": 0,
"fixtures": [
"C1",
"T1",
"C2",
"T2",
"C3",
"T3",
"C4",
"T4",
"C5",
"T5",
"C6",
"T6",
"C7",
"T7",
"C8",
"T8"
],
"graph": {
"edges": 458,
"indexed_files": 148,
"nodes": 588
},
"indexed_pages": 147,
"logical_corpus_digest": "dc2792a1551aaafdb46289376ac21c0a23aeb9fbc7d7c4ca38e28c28620c40b1",
"published_anchors": 18,
"topology_findings": [
{
"case_id": "C1",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c1_weekly_limit_insight",
"key_kind": "note"
},
{
"case_id": "C1",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c1_capacity_ceilings_pattern",
"key_kind": "note"
},
{
"case_id": "C2",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c2_cooking_method_insight",
"key_kind": "note"
},
{
"case_id": "C3",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c3_design_pointer",
"key_kind": "note"
},
{
"case_id": "C4",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c4_failure_note",
"key_kind": "note"
},
{
"case_id": "C8",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c8_active_head",
"key_kind": "note"
},
{
"case_id": "T8",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "t8_unchained_active_note",
"key_kind": "note"
}
]
},
{
"distractor_count": 200,
"fixtures": [
"C9",
"T9"
],
"graph": {
"edges": 458,
"indexed_files": 348,
"nodes": 788
},
"indexed_pages": 147,
"logical_corpus_digest": "76eb939a34717807addf25eb9c8378dd7a3ab4119f892fbe9a3bee7c31ba0e84",
"published_anchors": 18,
"topology_findings": [
{
"case_id": "C9",
"finding": "no anchor; reachable only through the retrieval carry or a resolved anchor's lanes",
"key": "c2_cooking_method_insight",
"key_kind": "note"
}
]
}
],
"verdict": "reviewed"
}