mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-06 06:14:11 +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>
224 lines
5.4 KiB
JSON
224 lines
5.4 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "rizzo_flow",
|
|
"model_id": "rizzo_flow@55633c8cbd2b",
|
|
"revision": "55633c8cbd2b826bd3eefdeb05310450996649df",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cuda",
|
|
"context_limit": 2048,
|
|
"probabilities_source": "native"
|
|
},
|
|
"device": "cuda",
|
|
"load_seconds": 5.3,
|
|
"process_guard": "ok",
|
|
"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": 62.3,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "pagamento",
|
|
"confidence": 0.9937313892294425,
|
|
"probabilities": {
|
|
"pagamento": 0.9952985419220819,
|
|
"cancelamento": 0.0014555718031770129,
|
|
"suporte_tecnico": 0.0007138147545963065,
|
|
"sem_correspondencia": 0.0025320715201448793
|
|
}
|
|
},
|
|
"pred_permuted": "pagamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:cancelamento",
|
|
"gold": "cancelamento",
|
|
"pred": "cancelamento",
|
|
"latency_ms": 66.4,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "cancelamento",
|
|
"confidence": 0.9958236126678967,
|
|
"probabilities": {
|
|
"pagamento": 0.000736589116875824,
|
|
"cancelamento": 0.9968677095009225,
|
|
"suporte_tecnico": 0.000579527206419017,
|
|
"sem_correspondencia": 0.0018161741757827666
|
|
}
|
|
},
|
|
"pred_permuted": "cancelamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:suporte_tecnico",
|
|
"gold": "suporte_tecnico",
|
|
"pred": "suporte_tecnico",
|
|
"latency_ms": 64.4,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "suporte_tecnico",
|
|
"confidence": 0.9535000077378192,
|
|
"probabilities": {
|
|
"pagamento": 0.001133195848223361,
|
|
"cancelamento": 0.0021639955558770034,
|
|
"suporte_tecnico": 0.9651250058033644,
|
|
"sem_correspondencia": 0.031577802792535394
|
|
}
|
|
},
|
|
"pred_permuted": "suporte_tecnico",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:sem_correspondencia",
|
|
"gold": "sem_correspondencia",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 66.7,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.9874519299503838,
|
|
"probabilities": {
|
|
"pagamento": 0.004033476792992324,
|
|
"cancelamento": 0.0025021007457173418,
|
|
"suporte_tecnico": 0.0028754749985024732,
|
|
"sem_correspondencia": 0.9905889474627878
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:clara",
|
|
"gold": "true",
|
|
"pred": "true",
|
|
"latency_ms": 61.8,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.947542960858974
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:vaga",
|
|
"gold": "false",
|
|
"pred": "false",
|
|
"latency_ms": 55.3,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.4973615950856545
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:alta",
|
|
"gold": "2",
|
|
"pred": "2",
|
|
"latency_ms": 55.9,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 1.9423142016746011,
|
|
"confidence": 0.9482293944199722,
|
|
"probabilities": {
|
|
"0": 0.023172061272047177,
|
|
"1": 0.011341675781304721,
|
|
"2": 0.9654862629466482
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:baixa",
|
|
"gold": "0",
|
|
"pred": "0",
|
|
"latency_ms": 55.1,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 0.2562808099480609,
|
|
"confidence": 0.624089907903691,
|
|
"probabilities": {
|
|
"0": 0.7493932719357941,
|
|
"1": 0.244932646180351,
|
|
"2": 0.005674081883854951
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
}
|
|
],
|
|
"summary": {
|
|
"contract_violations": [],
|
|
"sanity_correct": "8/8",
|
|
"permutation_invariant": "4/4"
|
|
},
|
|
"oci": {
|
|
"region": "sa-saopaulo-1",
|
|
"run_id": "20261007T171106Z-rizzo_flow-sanity"
|
|
}
|
|
}
|