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
5.4 KiB
JSON
223 lines
5.4 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "rizzo_flow",
|
|
"model_id": "rizzo_flow@55633c8cbd2b",
|
|
"revision": "55633c8cbd2b826bd3eefdeb05310450996649df",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cpu",
|
|
"context_limit": 2048,
|
|
"probabilities_source": "native"
|
|
},
|
|
"device": "cpu",
|
|
"load_seconds": 4.32,
|
|
"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": 7381.4,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "pagamento",
|
|
"confidence": 0.9939581449644033,
|
|
"probabilities": {
|
|
"pagamento": 0.9954686087233022,
|
|
"cancelamento": 0.0014294878384867884,
|
|
"suporte_tecnico": 0.0006663578744809516,
|
|
"sem_correspondencia": 0.002435545563729951
|
|
}
|
|
},
|
|
"pred_permuted": "pagamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:cancelamento",
|
|
"gold": "cancelamento",
|
|
"pred": "cancelamento",
|
|
"latency_ms": 7903.2,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "cancelamento",
|
|
"confidence": 0.9959894668208951,
|
|
"probabilities": {
|
|
"pagamento": 0.0006611097629735292,
|
|
"cancelamento": 0.9969921001156713,
|
|
"suporte_tecnico": 0.0005694308917635679,
|
|
"sem_correspondencia": 0.0017773592295916517
|
|
}
|
|
},
|
|
"pred_permuted": "cancelamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:suporte_tecnico",
|
|
"gold": "suporte_tecnico",
|
|
"pred": "suporte_tecnico",
|
|
"latency_ms": 7312.8,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "suporte_tecnico",
|
|
"confidence": 0.9550325369120003,
|
|
"probabilities": {
|
|
"pagamento": 0.0009793333603067293,
|
|
"cancelamento": 0.002014121845135763,
|
|
"suporte_tecnico": 0.9662744026840004,
|
|
"sem_correspondencia": 0.030732142110557085
|
|
}
|
|
},
|
|
"pred_permuted": "suporte_tecnico",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:sem_correspondencia",
|
|
"gold": "sem_correspondencia",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 7599.3,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.9885549303273677,
|
|
"probabilities": {
|
|
"pagamento": 0.0036670988032871665,
|
|
"cancelamento": 0.0022098453219148453,
|
|
"suporte_tecnico": 0.002706858129272241,
|
|
"sem_correspondencia": 0.9914161977455258
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:clara",
|
|
"gold": "true",
|
|
"pred": "true",
|
|
"latency_ms": 6481.8,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.9479776743420092
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:vaga",
|
|
"gold": "false",
|
|
"pred": "true",
|
|
"latency_ms": 6144.2,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.5076455176696537
|
|
},
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "score:alta",
|
|
"gold": "2",
|
|
"pred": "2",
|
|
"latency_ms": 5982.9,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 1.9453121647986211,
|
|
"confidence": 0.9510302861376827,
|
|
"probabilities": {
|
|
"0": 0.02204135929316713,
|
|
"1": 0.01060511661504444,
|
|
"2": 0.9673535240917883
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:baixa",
|
|
"gold": "0",
|
|
"pred": "0",
|
|
"latency_ms": 6279.1,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 0.26957479262097783,
|
|
"confidence": 0.6046525975421342,
|
|
"probabilities": {
|
|
"0": 0.7364350650280896,
|
|
"1": 0.2575550773228431,
|
|
"2": 0.0060098576490673645
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
}
|
|
],
|
|
"summary": {
|
|
"contract_violations": [],
|
|
"sanity_correct": "7/8",
|
|
"permutation_invariant": "4/4"
|
|
},
|
|
"oci": {
|
|
"region": "us-chicago-1",
|
|
"run_id": "20261007T152414Z-rizzo_flow-sanity"
|
|
}
|
|
}
|