206 lines
5.8 KiB
JSON
206 lines
5.8 KiB
JSON
{
|
|
"scope": "Synthetic DEV judge calibration, not TEST results",
|
|
"evaluator_sha256": "c32c53db3addbd068e6f40ec7312b8c2eaeebbd481bb6d191e002a65203f0c98",
|
|
"script_sha256": "fd1e1cf5d8a54ab65398f0e345bbbbd8e33f4ad9fcd2e268a1e7ced3fe9e2507",
|
|
"passed": 8,
|
|
"total": 8,
|
|
"results": [
|
|
{
|
|
"id": "planned_supported",
|
|
"expected_accepted": true,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": true,
|
|
"coverage": true,
|
|
"citations": true,
|
|
"appropriate_response": true,
|
|
"clarity": 3,
|
|
"critical_errors": [],
|
|
"reasons": [],
|
|
"proofs": []
|
|
}
|
|
},
|
|
{
|
|
"id": "phase_mutation",
|
|
"expected_accepted": false,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": false,
|
|
"coverage": false,
|
|
"citations": false,
|
|
"appropriate_response": false,
|
|
"clarity": 3,
|
|
"critical_errors": [
|
|
"wrong_work",
|
|
"invented_fact",
|
|
"unsupported_time"
|
|
],
|
|
"reasons": [
|
|
"wrong_work",
|
|
"invented_fact",
|
|
"unsupported_time"
|
|
],
|
|
"proofs": [
|
|
{
|
|
"code": "wrong_work",
|
|
"answer_quote": "Eva už úspešne vyhodnotila model BERT.",
|
|
"source_path": "pages/students/2020/eva/README.md",
|
|
"source_quote": "## Bakalárska práca 2024\nStretnutie 5.5.2026\nStav:\n- Implementovaný model BERT."
|
|
},
|
|
{
|
|
"code": "invented_fact",
|
|
"answer_quote": "Eva už úspešne vyhodnotila model BERT.",
|
|
"source_path": "pages/students/2020/eva/README.md",
|
|
"source_quote": "# Diplomová práca 2027\nCiele:\n- Vyhodnoťte model BERT."
|
|
},
|
|
{
|
|
"code": "unsupported_time",
|
|
"answer_quote": "Eva už úspešne vyhodnotila model BERT.",
|
|
"source_path": "pages/students/2020/eva/README.md",
|
|
"source_quote": "# Diplomová práca 2027\nCiele:\n- Vyhodnoťte model BERT."
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "nested_work_supported",
|
|
"expected_accepted": true,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": true,
|
|
"coverage": true,
|
|
"citations": true,
|
|
"appropriate_response": true,
|
|
"clarity": 3,
|
|
"critical_errors": [],
|
|
"reasons": [],
|
|
"proofs": []
|
|
}
|
|
},
|
|
{
|
|
"id": "work_mutation",
|
|
"expected_accepted": false,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": false,
|
|
"coverage": false,
|
|
"citations": false,
|
|
"appropriate_response": false,
|
|
"clarity": 3,
|
|
"critical_errors": [
|
|
"wrong_work",
|
|
"unsupported_time"
|
|
],
|
|
"reasons": [
|
|
"wrong_work",
|
|
"unsupported_time"
|
|
],
|
|
"proofs": [
|
|
{
|
|
"code": "wrong_work",
|
|
"answer_quote": "Pri diplomovej práci 2027 je zaznamenaná implementácia BERT.",
|
|
"source_path": "pages/students/2020/eva/README.md",
|
|
"source_quote": "## Bakalárska práca 2024\nStretnutie 5.5.2026\nStav:\n- Implementovaný model BERT."
|
|
},
|
|
{
|
|
"code": "unsupported_time",
|
|
"answer_quote": "Pri diplomovej práci 2027 je zaznamenaná implementácia BERT.",
|
|
"source_path": "pages/students/2020/eva/README.md",
|
|
"source_quote": "Stretnutie 15.5.\nStav:"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "actor_mutation",
|
|
"expected_accepted": false,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": false,
|
|
"coverage": true,
|
|
"citations": false,
|
|
"appropriate_response": true,
|
|
"clarity": 3,
|
|
"critical_errors": [
|
|
"wrong_person",
|
|
"unsupported_time"
|
|
],
|
|
"reasons": [
|
|
"wrong_person",
|
|
"unsupported_time"
|
|
],
|
|
"proofs": [
|
|
{
|
|
"code": "wrong_person",
|
|
"answer_quote": "Alena Nová úspešne obhájila diplomovú prácu v roku 2024.",
|
|
"source_path": "pages/students/2020/alena/README.md",
|
|
"source_quote": "Peter Nový úspešne obhájil diplomovú prácu v roku 2024."
|
|
},
|
|
{
|
|
"code": "unsupported_time",
|
|
"answer_quote": "Alena Nová úspešne obhájila diplomovú prácu v roku 2024.",
|
|
"source_path": "pages/students/2020/alena/README.md",
|
|
"source_quote": "Peter Nový úspešne obhájil diplomovú prácu v roku 2024."
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "actor_abstention_supported",
|
|
"expected_accepted": true,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": true,
|
|
"coverage": true,
|
|
"citations": true,
|
|
"appropriate_response": true,
|
|
"clarity": 4,
|
|
"critical_errors": [],
|
|
"reasons": [],
|
|
"proofs": []
|
|
}
|
|
},
|
|
{
|
|
"id": "partial_year_supported",
|
|
"expected_accepted": true,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": true,
|
|
"coverage": true,
|
|
"citations": true,
|
|
"appropriate_response": true,
|
|
"clarity": 4,
|
|
"critical_errors": [],
|
|
"reasons": [],
|
|
"proofs": []
|
|
}
|
|
},
|
|
{
|
|
"id": "partial_year_inference",
|
|
"expected_accepted": false,
|
|
"passed": true,
|
|
"grade": {
|
|
"correct": false,
|
|
"coverage": true,
|
|
"citations": false,
|
|
"appropriate_response": true,
|
|
"clarity": 3,
|
|
"critical_errors": [
|
|
"unsupported_time"
|
|
],
|
|
"reasons": [
|
|
"unsupported_time"
|
|
],
|
|
"proofs": [
|
|
{
|
|
"code": "unsupported_time",
|
|
"answer_quote": "Rozhranie funguje podľa záznamu z 15.5.2024.",
|
|
"source_path": "pages/students/2020/eva/README.md",
|
|
"source_quote": "Stretnutie 15.5."
|
|
}
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|