Conjunto D1 sintético congelado e sanidade em CPU e GPU na OCI

- 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>
This commit is contained in:
Marcos Lohmann
2026-10-07 14:16:18 -03:00
parent 171595f4c9
commit 2af9dae193
17 changed files with 5978 additions and 12 deletions

View File

@@ -0,0 +1,223 @@
{
"candidate": {
"name": "semif",
"model_id": "semif@851bf6e806ef",
"revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
"adapter_version": "0.1.0",
"device": "cuda",
"context_limit": 8192,
"probabilities_source": "native"
},
"device": "cuda",
"load_seconds": 6.47,
"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": 66.5,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.9999580355069111,
"probabilities": {
"pagamento": 0.9999580355069111,
"cancelamento": 2.7535293796608728e-05,
"suporte_tecnico": 6.540205536604591e-06,
"sem_correspondencia": 7.888993755683035e-06
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 65.9,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 0.9984434836109674,
"probabilities": {
"pagamento": 0.0015010990652337887,
"cancelamento": 0.9984434836109674,
"suporte_tecnico": 3.11543171817569e-05,
"sem_correspondencia": 2.4263006617207197e-05
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "suporte_tecnico",
"latency_ms": 64.8,
"answer": {
"type": "choice",
"choice": "suporte_tecnico",
"confidence": 0.9987677467505007,
"probabilities": {
"pagamento": 0.001169436800573682,
"cancelamento": 2.7502517470556258e-05,
"suporte_tecnico": 0.9987677467505007,
"sem_correspondencia": 3.531393145509289e-05
}
},
"pred_permuted": "suporte_tecnico",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 65.7,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.9850240302415921,
"probabilities": {
"pagamento": 0.010942628542039331,
"cancelamento": 0.0031351155675534968,
"suporte_tecnico": 0.0008982256488151342,
"sem_correspondencia": 0.9850240302415921
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "true",
"latency_ms": 68.7,
"answer": {
"type": "noul",
"noul": 0.9465966702001758
},
"correct": true
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 65.0,
"answer": {
"type": "noul",
"noul": 0.01590639171181471
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "2",
"latency_ms": 63.8,
"answer": {
"type": "score",
"score": 1.991764792381704,
"confidence": 0.9958345405394164,
"probabilities": {
"0": 0.004069748157712474,
"1": 9.571130287104325e-05,
"2": 0.9958345405394164
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
},
{
"name": "score:baixa",
"gold": "0",
"pred": "0",
"latency_ms": 64.7,
"answer": {
"type": "score",
"score": 0.6683472691146671,
"confidence": 0.44388424362844425,
"probabilities": {
"0": 0.44388424362844425,
"1": 0.44388424362844425,
"2": 0.11223151274311144
},
"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": "20261007T163132Z-semif-sanity"
}
}