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>
223 lines
5.4 KiB
JSON
223 lines
5.4 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "gliner",
|
|
"model_id": "gliner@a35a0cd3b7a0",
|
|
"revision": "a35a0cd3b7a0f00f2effc576f454cd48fa98aa5f",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cpu",
|
|
"context_limit": 4096,
|
|
"probabilities_source": "native"
|
|
},
|
|
"device": "cpu",
|
|
"load_seconds": 19.49,
|
|
"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": 207.2,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "pagamento",
|
|
"confidence": 0.6344144486132514,
|
|
"probabilities": {
|
|
"pagamento": 0.6344144486132514,
|
|
"cancelamento": 0.016834581647096163,
|
|
"suporte_tecnico": 0.022163255635572723,
|
|
"sem_correspondencia": 0.3265877141040798
|
|
}
|
|
},
|
|
"pred_permuted": "pagamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:cancelamento",
|
|
"gold": "cancelamento",
|
|
"pred": "cancelamento",
|
|
"latency_ms": 206.5,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "cancelamento",
|
|
"confidence": 0.8718590947504495,
|
|
"probabilities": {
|
|
"pagamento": 0.010419044895931304,
|
|
"cancelamento": 0.8718590947504495,
|
|
"suporte_tecnico": 0.012619423054256475,
|
|
"sem_correspondencia": 0.10510243729936272
|
|
}
|
|
},
|
|
"pred_permuted": "cancelamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:suporte_tecnico",
|
|
"gold": "suporte_tecnico",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 204.3,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.634299124256301,
|
|
"probabilities": {
|
|
"pagamento": 0.02020097044151347,
|
|
"cancelamento": 0.04278694633119902,
|
|
"suporte_tecnico": 0.30271295897098655,
|
|
"sem_correspondencia": 0.634299124256301
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "choice:sem_correspondencia",
|
|
"gold": "sem_correspondencia",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 194.3,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.8604282044571466,
|
|
"probabilities": {
|
|
"pagamento": 0.02875952763006619,
|
|
"cancelamento": 0.0316480618158572,
|
|
"suporte_tecnico": 0.07916420609692999,
|
|
"sem_correspondencia": 0.8604282044571466
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:clara",
|
|
"gold": "true",
|
|
"pred": "false",
|
|
"latency_ms": 173.0,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.2368284577603868
|
|
},
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "noul:vaga",
|
|
"gold": "false",
|
|
"pred": "false",
|
|
"latency_ms": 166.4,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.20341389158881357
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:alta",
|
|
"gold": "2",
|
|
"pred": "0",
|
|
"latency_ms": 163.5,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 0.9812680775305056,
|
|
"confidence": 0.3614072907390383,
|
|
"probabilities": {
|
|
"0": 0.3614072907390383,
|
|
"1": 0.2959173409914178,
|
|
"2": 0.34267536826954387
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "score:baixa",
|
|
"gold": "0",
|
|
"pred": "0",
|
|
"latency_ms": 155.1,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 0.4816716677697748,
|
|
"confidence": 0.6750852767416213,
|
|
"probabilities": {
|
|
"0": 0.6750852767416213,
|
|
"1": 0.16815777874698246,
|
|
"2": 0.15675694451139618
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
}
|
|
],
|
|
"summary": {
|
|
"contract_violations": [],
|
|
"sanity_correct": "5/8",
|
|
"permutation_invariant": "4/4"
|
|
},
|
|
"oci": {
|
|
"region": "us-chicago-1",
|
|
"run_id": "20261007T153410Z-gliner-sanity"
|
|
}
|
|
}
|