KHIPU-R2 / eval_measured.json
betterwithage's picture
chore(eval): MEASURED k/n held-out (no fabricated scores)
016658d verified
Raw
History Blame
2.37 kB
{
"label": "MEASURED",
"host": "j-szlholdings-6a91bf11984507d9db4ea104-glba55nz-d3ea0-68nwn",
"evaluatedAt": "2026-08-28T17:20:37.617962+00:00",
"planTotal": 11,
"planValid": 11,
"groundingTotal": 5,
"groundingCorrect": 5,
"abstainTotal": 6,
"abstainCorrect": 3,
"hallucinatedCitationCount": 0,
"held_out_in_gradients": false,
"temperature": 0,
"method": "in-process Unsloth generate; scoring ported from eval_khipu.py",
"rows": [
{
"split": "navigate",
"i": 1,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/a75aa5921b37a055"
]
},
{
"split": "navigate",
"i": 2,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/0c3811c6e4b98d16"
]
},
{
"split": "navigate",
"i": 3,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/800d21d32b720587"
]
},
{
"split": "navigate",
"i": 4,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/badfa44292cc23f5"
]
},
{
"split": "navigate",
"i": 5,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/1fcf60c2a090c0a3"
]
},
{
"split": "adversarial",
"i": 1,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/2f97a50f6f35049e"
]
},
{
"split": "adversarial",
"i": 2,
"valid": true,
"decision": "ABSTAIN",
"citedNodeIds": []
},
{
"split": "adversarial",
"i": 3,
"valid": true,
"decision": "ABSTAIN",
"citedNodeIds": []
},
{
"split": "adversarial",
"i": 4,
"valid": true,
"decision": "ABSTAIN",
"citedNodeIds": []
},
{
"split": "adversarial",
"i": 5,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/8636e76827710d87"
]
},
{
"split": "adversarial",
"i": 6,
"valid": true,
"decision": "NAVIGATE",
"citedNodeIds": [
"node://khipu-synthetic/9e1192a9b2154f7b"
]
}
]
}