mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
2af9dae193
- data/splits (d1-v1): dev 1183, calibração 1127, teste 1744 exemplos, 43 rótulos, partição por lote de geração, SHA-256 em MANIFEST.json; cópias em dmb-entrada e dmb-logs-imutaveis. - reports/datagen: relatórios de preparação e de anotação (3 LLMs em rodízio; kappa 0,98–0,99). - reports/sanity/oci: sanidade dos 4 candidatos em CPU (us-chicago-1, sub-rede privada) e GPU A10 (sa-saopaulo-1). - Plano: 47 de 78 tarefas concluídas; docs/02 com o resumo do conjunto. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
223 lines
5.2 KiB
JSON
223 lines
5.2 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "laya",
|
|
"model_id": "laya@1720e3e3357c",
|
|
"revision": "1720e3e3357cfe1e281542e223f8273b0890ca34",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cpu",
|
|
"context_limit": 1024,
|
|
"probabilities_source": "native"
|
|
},
|
|
"device": "cpu",
|
|
"load_seconds": 12.29,
|
|
"conformance": [
|
|
{
|
|
"name": "valid_choice_noul",
|
|
"expected": "ok",
|
|
"got": "ok"
|
|
},
|
|
{
|
|
"name": "valid_score",
|
|
"expected": "ok",
|
|
"got": "ok"
|
|
},
|
|
{
|
|
"name": "valid_state_object",
|
|
"expected": "ok",
|
|
"got": "ok"
|
|
},
|
|
{
|
|
"name": "invalid_17_options",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_single_option",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_noul_missing_false",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_unknown_type",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_empty_state",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_no_questions",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_extra_field",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
}
|
|
],
|
|
"sanity": [
|
|
{
|
|
"name": "choice:pagamento",
|
|
"gold": "pagamento",
|
|
"pred": "pagamento",
|
|
"latency_ms": 140.1,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "pagamento",
|
|
"confidence": 0.9977,
|
|
"probabilities": {
|
|
"pagamento": 0.9997979802020598,
|
|
"cancelamento": 1.0000980096049412e-06,
|
|
"suporte_tecnico": 1.0000980096049412e-06,
|
|
"sem_correspondencia": 0.00020001960192098824
|
|
}
|
|
},
|
|
"pred_permuted": "pagamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:cancelamento",
|
|
"gold": "cancelamento",
|
|
"pred": "cancelamento",
|
|
"latency_ms": 124.9,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "cancelamento",
|
|
"confidence": 1.0,
|
|
"probabilities": {
|
|
"pagamento": 9.999970000090002e-07,
|
|
"cancelamento": 0.9999970000090003,
|
|
"suporte_tecnico": 9.999970000090002e-07,
|
|
"sem_correspondencia": 9.999970000090002e-07
|
|
}
|
|
},
|
|
"pred_permuted": "cancelamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:suporte_tecnico",
|
|
"gold": "suporte_tecnico",
|
|
"pred": "suporte_tecnico",
|
|
"latency_ms": 142.7,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "suporte_tecnico",
|
|
"confidence": 0.2935,
|
|
"probabilities": {
|
|
"pagamento": 0.0496049604960496,
|
|
"cancelamento": 0.047204720472047206,
|
|
"suporte_tecnico": 0.5706570657065706,
|
|
"sem_correspondencia": 0.33253325332533257
|
|
}
|
|
},
|
|
"pred_permuted": "suporte_tecnico",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:sem_correspondencia",
|
|
"gold": "sem_correspondencia",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 137.6,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.7909,
|
|
"probabilities": {
|
|
"pagamento": 0.0034996500349965005,
|
|
"cancelamento": 0.0044995500449955,
|
|
"suporte_tecnico": 0.0642935706429357,
|
|
"sem_correspondencia": 0.9277072292770723
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:clara",
|
|
"gold": "true",
|
|
"pred": "true",
|
|
"latency_ms": 107.2,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.9982
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:vaga",
|
|
"gold": "false",
|
|
"pred": "false",
|
|
"latency_ms": 106.4,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.1563
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:alta",
|
|
"gold": "2",
|
|
"pred": "2",
|
|
"latency_ms": 113.8,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 1.1202,
|
|
"confidence": 0.01,
|
|
"probabilities": {
|
|
"0": 0.2718,
|
|
"1": 0.3362,
|
|
"2": 0.392
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:baixa",
|
|
"gold": "0",
|
|
"pred": "1",
|
|
"latency_ms": 116.9,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 1.0998999999999999,
|
|
"confidence": 0.1514,
|
|
"probabilities": {
|
|
"0": 0.1477,
|
|
"1": 0.6047,
|
|
"2": 0.2476
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": false
|
|
}
|
|
],
|
|
"summary": {
|
|
"contract_violations": [],
|
|
"sanity_correct": "7/8",
|
|
"permutation_invariant": "4/4"
|
|
},
|
|
"oci": {
|
|
"region": "us-chicago-1",
|
|
"run_id": "20261007T154451Z-laya-sanity"
|
|
}
|
|
}
|