Ctrl K
ComunidadGuías…

evals/recall-baseline.json

Rama main · réplica de lectura del repositorio original.

Archivo original ↗Preguntar a KiBot
{
  "ok": false,
  "cases": 24,
  "passed": 20,
  "mean_recall_at_k": 1.0,
  "mean_precision_at_k": 0.9074074074074074,
  "no_answer_passed": 5,
  "no_answer_cases": 6,
  "latency_ms": {
    "p50": 200.0,
    "p95": 212
  },
  "retrieval_modes": {
    "keyword_fallback": 23,
    "skipped": 1
  },
  "judge_statuses": {
    "unavailable": 18,
    "no_records": 5,
    "not_attempted": 1
  },
  "results": [
    {
      "id": "conflicting-deployment",
      "ok": true,
      "errors": [],
      "record_ids": [
        "aurora-blue",
        "aurora-canary"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 227
    },
    {
      "id": "contrarian-evidence",
      "ok": true,
      "errors": [],
      "record_ids": [
        "aurora-canary",
        "aurora-blue"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 208
    },
    {
      "id": "carbon-cjk",
      "ok": true,
      "errors": [],
      "record_ids": [
        "carbon-factor"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 197
    },
    {
      "id": "carbon-activity",
      "ok": true,
      "errors": [],
      "record_ids": [
        "carbon-factor"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 202
    },
    {
      "id": "expo-cjk",
      "ok": true,
      "errors": [],
      "record_ids": [
        "expo-leads"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 199
    },
    {
      "id": "expo-followup",
      "ok": true,
      "errors": [],
      "record_ids": [
        "expo-leads"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 200
    },
    {
      "id": "cards-and-wiki",
      "ok": true,
      "errors": [],
      "record_ids": [
        "provenance-guide",
        "memory-evidence"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 197
    },
    {
      "id": "wiki-source",
      "ok": true,
      "errors": [],
      "record_ids": [
        "provenance-guide"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 201
    },
    {
      "id": "private-cache",
      "ok": true,
      "errors": [],
      "record_ids": [
        "cache-ttl"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 196
    },
    {
      "id": "other-cache",
      "ok": true,
      "errors": [],
      "record_ids": [
        "orchid-other"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 200
    },
    {
      "id": "public-cross-namespace",
      "ok": false,
      "errors": [
        "unexpected: aurora-blue, aurora-canary"
      ],
      "record_ids": [
        "public-release",
        "aurora-blue",
        "aurora-canary"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 0.3333333333333333,
      "no_answer": false,
      "false_positive_count": 2,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 200
    },
    {
      "id": "public-other-namespace",
      "ok": false,
      "errors": [
        "unexpected: other-handbook"
      ],
      "record_ids": [
        "other-handbook",
        "public-release"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 0.5,
      "no_answer": false,
      "false_positive_count": 1,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 212
    },
    {
      "id": "private-budget",
      "ok": true,
      "errors": [],
      "record_ids": [
        "private-budget"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 200
    },
    {
      "id": "budget-denied",
      "ok": true,
      "errors": [],
      "record_ids": [],
      "recall_at_k": null,
      "precision_at_k": null,
      "no_answer": true,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "no_records",
      "elapsed_ms": 212
    },
    {
      "id": "transaction",
      "ok": true,
      "errors": [],
      "record_ids": [
        "rollback"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 198
    },
    {
      "id": "camera",
      "ok": true,
      "errors": [],
      "record_ids": [
        "camera"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 199
    },
    {
      "id": "recycling-cjk",
      "ok": true,
      "errors": [],
      "record_ids": [
        "recycling"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 196
    },
    {
      "id": "backup-wiki",
      "ok": true,
      "errors": [],
      "record_ids": [
        "backup-guide"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 1.0,
      "no_answer": false,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 198
    },
    {
      "id": "other-wiki-denied",
      "ok": true,
      "errors": [],
      "record_ids": [],
      "recall_at_k": null,
      "precision_at_k": null,
      "no_answer": true,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "no_records",
      "elapsed_ms": 201
    },
    {
      "id": "other-wiki-allowed",
      "ok": false,
      "errors": [
        "unexpected: orchid-other"
      ],
      "record_ids": [
        "other-handbook",
        "orchid-other"
      ],
      "recall_at_k": 1.0,
      "precision_at_k": 0.5,
      "no_answer": false,
      "false_positive_count": 1,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "unavailable",
      "elapsed_ms": 197
    },
    {
      "id": "unknown-english",
      "ok": true,
      "errors": [],
      "record_ids": [],
      "recall_at_k": null,
      "precision_at_k": null,
      "no_answer": true,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "no_records",
      "elapsed_ms": 201
    },
    {
      "id": "unknown-cjk",
      "ok": true,
      "errors": [],
      "record_ids": [],
      "recall_at_k": null,
      "precision_at_k": null,
      "no_answer": true,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "no_records",
      "elapsed_ms": 197
    },
    {
      "id": "greeting",
      "ok": true,
      "errors": [],
      "record_ids": [],
      "recall_at_k": null,
      "precision_at_k": null,
      "no_answer": true,
      "false_positive_count": 0,
      "retrieval_mode": "skipped",
      "judge_status": "not_attempted",
      "elapsed_ms": 194
    },
    {
      "id": "acknowledgement",
      "ok": false,
      "errors": [
        "wrong retrieval mode"
      ],
      "record_ids": [],
      "recall_at_k": null,
      "precision_at_k": null,
      "no_answer": true,
      "false_positive_count": 0,
      "retrieval_mode": "keyword_fallback",
      "judge_status": "no_records",
      "elapsed_ms": 209
    }
  ],
  "scope": "synthetic offline keyword/ACL/transport regression; not a semantic quality benchmark"
}