mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +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": "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"
|
|
}
|
|
}
|