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 +1,222 @@
{
"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"
}
}

View File

@@ -0,0 +1,223 @@
{
"candidate": {
"name": "gliner",
"model_id": "gliner@a35a0cd3b7a0",
"revision": "a35a0cd3b7a0f00f2effc576f454cd48fa98aa5f",
"adapter_version": "0.1.0",
"device": "cuda",
"context_limit": 4096,
"probabilities_source": "native"
},
"device": "cuda",
"load_seconds": 21.32,
"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": 16.4,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.6344155822832185,
"probabilities": {
"pagamento": 0.6344155822832185,
"cancelamento": 0.016834572365227046,
"suporte_tecnico": 0.022163173720466455,
"sem_correspondencia": 0.32658667163108795
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 16.1,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 0.8718585964717693,
"probabilities": {
"pagamento": 0.010419094712095255,
"cancelamento": 0.8718585964717693,
"suporte_tecnico": 0.012619434782507587,
"sem_correspondencia": 0.10510287403362785
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "sem_correspondencia",
"latency_ms": 16.9,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.6342994187351121,
"probabilities": {
"pagamento": 0.02020120315928321,
"cancelamento": 0.04278698707030298,
"suporte_tecnico": 0.3027123910353017,
"sem_correspondencia": 0.6342994187351121
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": false
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 15.5,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.8604289616881081,
"probabilities": {
"pagamento": 0.028759510277003655,
"cancelamento": 0.0316479121558098,
"suporte_tecnico": 0.07916361587907846,
"sem_correspondencia": 0.8604289616881081
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "false",
"latency_ms": 16.1,
"answer": {
"type": "noul",
"noul": 0.2368276601557085
},
"correct": false
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 16.4,
"answer": {
"type": "noul",
"noul": 0.20341337939580556
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "0",
"latency_ms": 16.5,
"answer": {
"type": "score",
"score": 0.9812681382516582,
"confidence": 0.3614074480114148,
"probabilities": {
"0": 0.3614074480114148,
"1": 0.29591696572551235,
"2": 0.3426755862630729
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": false
},
{
"name": "score:baixa",
"gold": "0",
"pred": "0",
"latency_ms": 15.9,
"answer": {
"type": "score",
"score": 0.48167205020737197,
"confidence": 0.6750848881824415,
"probabilities": {
"0": 0.6750848881824415,
"1": 0.16815817342774508,
"2": 0.15675693838981344
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "5/8",
"permutation_invariant": "4/4"
},
"oci": {
"region": "sa-saopaulo-1",
"run_id": "20261007T162549Z-gliner-sanity"
}
}

View File

@@ -0,0 +1,222 @@
{
"candidate": {
"name": "laya",
"model_id": "laya@1720e3e3357c",
"revision": "1720e3e3357cfe1e281542e223f8273b0890ca34",
"adapter_version": "0.1.0",
"device": "cpu",
"context_limit": 1024,
"probabilities_source": "native"
},
"device": "cpu",
"load_seconds": 12.29,
"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": 140.1,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.9977,
"probabilities": {
"pagamento": 0.9997979802020598,
"cancelamento": 1.0000980096049412e-06,
"suporte_tecnico": 1.0000980096049412e-06,
"sem_correspondencia": 0.00020001960192098824
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 124.9,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 1.0,
"probabilities": {
"pagamento": 9.999970000090002e-07,
"cancelamento": 0.9999970000090003,
"suporte_tecnico": 9.999970000090002e-07,
"sem_correspondencia": 9.999970000090002e-07
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "suporte_tecnico",
"latency_ms": 142.7,
"answer": {
"type": "choice",
"choice": "suporte_tecnico",
"confidence": 0.2935,
"probabilities": {
"pagamento": 0.0496049604960496,
"cancelamento": 0.047204720472047206,
"suporte_tecnico": 0.5706570657065706,
"sem_correspondencia": 0.33253325332533257
}
},
"pred_permuted": "suporte_tecnico",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 137.6,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.7909,
"probabilities": {
"pagamento": 0.0034996500349965005,
"cancelamento": 0.0044995500449955,
"suporte_tecnico": 0.0642935706429357,
"sem_correspondencia": 0.9277072292770723
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "true",
"latency_ms": 107.2,
"answer": {
"type": "noul",
"noul": 0.9982
},
"correct": true
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 106.4,
"answer": {
"type": "noul",
"noul": 0.1563
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "2",
"latency_ms": 113.8,
"answer": {
"type": "score",
"score": 1.1202,
"confidence": 0.01,
"probabilities": {
"0": 0.2718,
"1": 0.3362,
"2": 0.392
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
},
{
"name": "score:baixa",
"gold": "0",
"pred": "1",
"latency_ms": 116.9,
"answer": {
"type": "score",
"score": 1.0998999999999999,
"confidence": 0.1514,
"probabilities": {
"0": 0.1477,
"1": 0.6047,
"2": 0.2476
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": false
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "7/8",
"permutation_invariant": "4/4"
},
"oci": {
"region": "us-chicago-1",
"run_id": "20261007T154451Z-laya-sanity"
}
}

View File

@@ -0,0 +1,223 @@
{
"candidate": {
"name": "laya",
"model_id": "laya@1720e3e3357c",
"revision": "1720e3e3357cfe1e281542e223f8273b0890ca34",
"adapter_version": "0.1.0",
"device": "cuda",
"context_limit": 1024,
"probabilities_source": "native"
},
"device": "cuda",
"load_seconds": 8.01,
"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": 20.8,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.9977,
"probabilities": {
"pagamento": 0.9997979802020598,
"cancelamento": 1.0000980096049412e-06,
"suporte_tecnico": 1.0000980096049412e-06,
"sem_correspondencia": 0.00020001960192098824
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 20.1,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 1.0,
"probabilities": {
"pagamento": 9.999970000090002e-07,
"cancelamento": 0.9999970000090003,
"suporte_tecnico": 9.999970000090002e-07,
"sem_correspondencia": 9.999970000090002e-07
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "suporte_tecnico",
"latency_ms": 21.0,
"answer": {
"type": "choice",
"choice": "suporte_tecnico",
"confidence": 0.292,
"probabilities": {
"pagamento": 0.0487,
"cancelamento": 0.0457,
"suporte_tecnico": 0.557,
"sem_correspondencia": 0.3486
}
},
"pred_permuted": "suporte_tecnico",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 20.5,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.7962,
"probabilities": {
"pagamento": 0.0032,
"cancelamento": 0.0044,
"suporte_tecnico": 0.0623,
"sem_correspondencia": 0.9301
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "true",
"latency_ms": 20.8,
"answer": {
"type": "noul",
"noul": 0.9981
},
"correct": true
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 20.1,
"answer": {
"type": "noul",
"noul": 0.1546
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "2",
"latency_ms": 20.9,
"answer": {
"type": "score",
"score": 1.123,
"confidence": 0.0105,
"probabilities": {
"0": 0.2703,
"1": 0.3364,
"2": 0.3933
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
},
{
"name": "score:baixa",
"gold": "0",
"pred": "1",
"latency_ms": 21.0,
"answer": {
"type": "score",
"score": 1.1033,
"confidence": 0.1552,
"probabilities": {
"0": 0.1446,
"1": 0.6075,
"2": 0.2479
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": false
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "7/8",
"permutation_invariant": "4/4"
},
"oci": {
"region": "sa-saopaulo-1",
"run_id": "20261007T162118Z-laya-sanity"
}
}

View File

@@ -0,0 +1,222 @@
{
"candidate": {
"name": "rizzo_flow",
"model_id": "rizzo_flow@55633c8cbd2b",
"revision": "55633c8cbd2b826bd3eefdeb05310450996649df",
"adapter_version": "0.1.0",
"device": "cpu",
"context_limit": 2048,
"probabilities_source": "native"
},
"device": "cpu",
"load_seconds": 4.32,
"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": 7381.4,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.9939581449644033,
"probabilities": {
"pagamento": 0.9954686087233022,
"cancelamento": 0.0014294878384867884,
"suporte_tecnico": 0.0006663578744809516,
"sem_correspondencia": 0.002435545563729951
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 7903.2,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 0.9959894668208951,
"probabilities": {
"pagamento": 0.0006611097629735292,
"cancelamento": 0.9969921001156713,
"suporte_tecnico": 0.0005694308917635679,
"sem_correspondencia": 0.0017773592295916517
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "suporte_tecnico",
"latency_ms": 7312.8,
"answer": {
"type": "choice",
"choice": "suporte_tecnico",
"confidence": 0.9550325369120003,
"probabilities": {
"pagamento": 0.0009793333603067293,
"cancelamento": 0.002014121845135763,
"suporte_tecnico": 0.9662744026840004,
"sem_correspondencia": 0.030732142110557085
}
},
"pred_permuted": "suporte_tecnico",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 7599.3,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.9885549303273677,
"probabilities": {
"pagamento": 0.0036670988032871665,
"cancelamento": 0.0022098453219148453,
"suporte_tecnico": 0.002706858129272241,
"sem_correspondencia": 0.9914161977455258
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "true",
"latency_ms": 6481.8,
"answer": {
"type": "noul",
"noul": 0.9479776743420092
},
"correct": true
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "true",
"latency_ms": 6144.2,
"answer": {
"type": "noul",
"noul": 0.5076455176696537
},
"correct": false
},
{
"name": "score:alta",
"gold": "2",
"pred": "2",
"latency_ms": 5982.9,
"answer": {
"type": "score",
"score": 1.9453121647986211,
"confidence": 0.9510302861376827,
"probabilities": {
"0": 0.02204135929316713,
"1": 0.01060511661504444,
"2": 0.9673535240917883
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
},
{
"name": "score:baixa",
"gold": "0",
"pred": "0",
"latency_ms": 6279.1,
"answer": {
"type": "score",
"score": 0.26957479262097783,
"confidence": 0.6046525975421342,
"probabilities": {
"0": 0.7364350650280896,
"1": 0.2575550773228431,
"2": 0.0060098576490673645
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "7/8",
"permutation_invariant": "4/4"
},
"oci": {
"region": "us-chicago-1",
"run_id": "20261007T152414Z-rizzo_flow-sanity"
}
}

View File

@@ -0,0 +1,223 @@
{
"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"
}
}

View File

@@ -0,0 +1,222 @@
{
"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": 6.05,
"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": 16411.3,
"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": 17233.2,
"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": 16699.8,
"answer": {
"type": "choice",
"choice": "suporte_tecnico",
"confidence": 0.9987593932138263,
"probabilities": {
"pagamento": 0.0011694270195878285,
"cancelamento": 3.1164174472760134e-05,
"suporte_tecnico": 0.9987593932138263,
"sem_correspondencia": 4.001559211311531e-05
}
},
"pred_permuted": "suporte_tecnico",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 16903.6,
"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": 13812.9,
"answer": {
"type": "noul",
"noul": 0.9465966702001758
},
"correct": true
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 13046.2,
"answer": {
"type": "noul",
"noul": 0.014063627043245475
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "2",
"latency_ms": 13712.6,
"answer": {
"type": "score",
"score": 1.9927177259683637,
"confidence": 0.9963109844368413,
"probabilities": {
"0": 0.0035932584684774537,
"1": 9.575709468113931e-05,
"2": 0.9963109844368413
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
},
{
"name": "score:baixa",
"gold": "0",
"pred": "1",
"latency_ms": 15147.9,
"answer": {
"type": "score",
"score": 0.7051250202229055,
"confidence": 0.46831026433271183,
"probabilities": {
"0": 0.41328235772219135,
"1": 0.46831026433271183,
"2": 0.11840737794509683
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": false
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "7/8",
"permutation_invariant": "4/4"
},
"oci": {
"region": "us-chicago-1",
"run_id": "20261007T153216Z-semif-sanity"
}
}

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"
}
}