mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
- Caminho do compartimento pai e CIDR do SSH saem do código para .secrets/oci-settings.json (fora do Git), com override por DMB_*. - Relatórios de sanidade deixam de gravar o hostname local. - tests/test_sensitive.py falha se OCIDs, chaves, IPs públicos ou valores de .secrets aparecerem em arquivos versionados. - tools/plan_progress.py gera o bloco de andamento por fase no plano. - Plano: status reais das tarefas de F0, F3 e F6; README e docs/05 com GPU em sa-saopaulo-1, runtime CUDA do Rizzo e pipeline sintético. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
219 lines
5.3 KiB
JSON
219 lines
5.3 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": 15.93,
|
|
"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": 303.8,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "pagamento",
|
|
"confidence": 0.6344146988487307,
|
|
"probabilities": {
|
|
"pagamento": 0.6344146988487307,
|
|
"cancelamento": 0.016834578235374244,
|
|
"suporte_tecnico": 0.022163211344910134,
|
|
"sem_correspondencia": 0.326587511570985
|
|
}
|
|
},
|
|
"pred_permuted": "pagamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:cancelamento",
|
|
"gold": "cancelamento",
|
|
"pred": "cancelamento",
|
|
"latency_ms": 297.9,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "cancelamento",
|
|
"confidence": 0.8718586499105494,
|
|
"probabilities": {
|
|
"pagamento": 0.010419030596174071,
|
|
"cancelamento": 0.8718586499105494,
|
|
"suporte_tecnico": 0.012619386333082717,
|
|
"sem_correspondencia": 0.10510293316019376
|
|
}
|
|
},
|
|
"pred_permuted": "cancelamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:suporte_tecnico",
|
|
"gold": "suporte_tecnico",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 218.5,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.6342991318760811,
|
|
"probabilities": {
|
|
"pagamento": 0.020201073094038888,
|
|
"cancelamento": 0.04278706948440038,
|
|
"suporte_tecnico": 0.30271272554547957,
|
|
"sem_correspondencia": 0.6342991318760811
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "choice:sem_correspondencia",
|
|
"gold": "sem_correspondencia",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 226.3,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.860428139738716,
|
|
"probabilities": {
|
|
"pagamento": 0.028759410242109536,
|
|
"cancelamento": 0.03164806754541749,
|
|
"suporte_tecnico": 0.07916438247375696,
|
|
"sem_correspondencia": 0.860428139738716
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:clara",
|
|
"gold": "true",
|
|
"pred": "false",
|
|
"latency_ms": 184.3,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.2368283016907438
|
|
},
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "noul:vaga",
|
|
"gold": "false",
|
|
"pred": "false",
|
|
"latency_ms": 227.3,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.20341360543566903
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:alta",
|
|
"gold": "2",
|
|
"pred": "0",
|
|
"latency_ms": 189.4,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 0.9812671227395942,
|
|
"confidence": 0.36140790832709446,
|
|
"probabilities": {
|
|
"0": 0.36140790832709446,
|
|
"1": 0.29591706060621686,
|
|
"2": 0.3426750310666887
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": false
|
|
},
|
|
{
|
|
"name": "score:baixa",
|
|
"gold": "0",
|
|
"pred": "0",
|
|
"latency_ms": 158.1,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 0.4816726286216157,
|
|
"confidence": 0.6750846907546932,
|
|
"probabilities": {
|
|
"0": 0.6750846907546932,
|
|
"1": 0.16815798986899794,
|
|
"2": 0.15675731937630888
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
}
|
|
],
|
|
"summary": {
|
|
"contract_violations": [],
|
|
"sanity_correct": "5/8",
|
|
"permutation_invariant": "4/4"
|
|
}
|
|
}
|