Files
decision-models-benchmark/reports/sanity/semif-cpu.json
Marcos Lohmann 171595f4c9 Proteger dados sensíveis e atualizar andamento do plano
- 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>
2026-10-07 14:08:44 -03:00

219 lines
5.3 KiB
JSON

{
"candidate": {
"name": "semif",
"model_id": "semif@851bf6e806ef",
"revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
"adapter_version": "0.1.0",
"device": "cpu",
"context_limit": 8192,
"probabilities_source": "native"
},
"device": "cpu",
"load_seconds": 6.55,
"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": 15726.0,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.9999576137177726,
"probabilities": {
"pagamento": 0.9999576137177726,
"cancelamento": 2.753528218203348e-05,
"suporte_tecnico": 6.962009617274983e-06,
"sem_correspondencia": 7.888990428051513e-06
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 16084.8,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 0.9982468109808258,
"probabilities": {
"pagamento": 0.001700633028283725,
"cancelamento": 0.9982468109808258,
"suporte_tecnico": 3.114818042829917e-05,
"sem_correspondencia": 2.1407810462216812e-05
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "suporte_tecnico",
"latency_ms": 15810.0,
"answer": {
"type": "choice",
"choice": "suporte_tecnico",
"confidence": 0.9985997601915109,
"probabilities": {
"pagamento": 0.0013249226202503434,
"cancelamento": 3.5307991870190554e-05,
"suporte_tecnico": 0.9985997601915109,
"sem_correspondencia": 4.0009196368602506e-05
}
},
"pred_permuted": "suporte_tecnico",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 15911.3,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.9868525351071245,
"probabilities": {
"pagamento": 0.0096747618254165,
"cancelamento": 0.0027718656714616763,
"suporte_tecnico": 0.0007008373959974223,
"sem_correspondencia": 0.9868525351071245
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "true",
"latency_ms": 13647.4,
"answer": {
"type": "noul",
"noul": 0.9465966702001758
},
"correct": true
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 13233.5,
"answer": {
"type": "noul",
"noul": 0.014063627043245475
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "2",
"latency_ms": 13650.8,
"answer": {
"type": "score",
"score": 1.992728895910905,
"confidence": 0.9963221948103022,
"probabilities": {
"0": 0.003593298899397119,
"1": 8.450629030069868e-05,
"2": 0.9963221948103022
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
},
{
"name": "score:baixa",
"gold": "0",
"pred": "0",
"latency_ms": 13731.5,
"answer": {
"type": "score",
"score": 0.6879537693865432,
"confidence": 0.4373487435378189,
"probabilities": {
"0": 0.4373487435378189,
"1": 0.4373487435378189,
"2": 0.12530251292436217
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "8/8",
"permutation_invariant": "4/4"
}
}