# Sibyl 365d 500c Category Benchmark

Run: `run-2026-06-06-sibyl-365d-500c-50q-category-sonnet46`

## Scope

- System: Sibyl local memory, sync tier.
- Corpus: 500 companies, 1500 stakeholders, 365 simulated days.
- Stored records: 191000 final records.
- Write calls: None.
- Questions: 350, 50 per category.
- Categories: status, milestone, context_stat, role, marker, temporal_topic, negative_trap.
- Retrieval strategy: app-side hybrid exact fallback by question intent.
- Answer mode: `sonnet`.

## Summary

| Metric | Value |
| --- | ---: |
| Retrieval passed | 350 / 350 |
| Avg context rows | 2.10 |
| Avg context tokens | 227.76 |
| DB size bytes | 287391744 |
| Ingest elapsed seconds | 0 |
| Sonnet answers passed | 344 / 350 |
| Sonnet estimated cost USD | 0.639780 |

## Retrieval By Category

| Category | Retrieval passed |
| --- | ---: |
| status | 50 / 50 |
| milestone | 50 / 50 |
| context_stat | 50 / 50 |
| role | 50 / 50 |
| marker | 50 / 50 |
| temporal_topic | 50 / 50 |
| negative_trap | 50 / 50 |

## Answer By Category

344 / 350

| Category | Sonnet answer passed |
| --- | ---: |
| status | 50 / 50 |
| milestone | 50 / 50 |
| context_stat | 50 / 50 |
| role | 50 / 50 |
| marker | 50 / 50 |
| temporal_topic | 44 / 50 |
| negative_trap | 50 / 50 |


## Failures

```json
[
  {
    "answer_score": {
      "contains_ok": false,
      "forbidden_ok": true,
      "passed": false,
      "retrieval_has_expected": true,
      "unknown_ok": true
    },
    "category": "temporal_topic",
    "context_sample": [
      {
        "body": {
          "acted": {
            "body": {
              "company": "Scale365 Company 048",
              "company_slug": "scale365-company-048",
              "date": "2026-01-22",
              "day_index": 18,
              "marker": "scale365scale365company048day018",
              "summary": "Scale365 Company 048 day 018: risk review update recorded.",
              "topic": "risk review"
            },
            "kind": "scale365_chronology_daily_update"
          },
          "evaluated": null,
          "extra": {
            "category": "chronology",
            "company": "run365-scale365-company-048",
            "marker": "scale365scale365company048day018",
            "name": "run365-scale365-company-048-day-018"
          },
          "forward": null
        },
        "category": null,
        "key": "a01ec501-c71b-4faf-9d42-eddea4c27d78",
        "snippet": "...22\",\"topic\":\"risk review\",\"marker\":\"[scale365scale365company048day018]\",\"summary\":\"Scale365 Company 048 day 018...",
        "tier": "journal"
      },
      {
        "body": {
          "context_stats": {
            "milestone_count": 9,
            "simulated_days": 365,
            "topic_cycle_size": 10
          },
          "display_name": "Scale365 Company 048",
          "region": "APAC",
          "segment": "energy",
          "stakeholder_count": 3,
          "timeline_days": 365,
          "timeline_start": "2026-01-05"
        },
        "category": "company",
        "key": "run365-scale365-company-048",
        "snippet": null,
        "tier": "entity"
      }
    ],
    "expected_contains": [
      "Scale365 Company 048",
      "18",
      "2026-01-22",
      "risk review"
    ],
    "id": "topic_company_048_day_018",
    "query": "What topic was recorded for Scale365 Company 048 on day 18?",
    "retrieval_score": {
      "contains_ok": true,
      "forbidden_ok": true,
      "passed": true
    }
  },
  {
    "answer_score": {
      "contains_ok": false,
      "forbidden_ok": true,
      "passed": false,
      "retrieval_has_expected": true,
      "unknown_ok": true
    },
    "category": "temporal_topic",
    "context_sample": [
      {
        "body": {
          "acted": {
            "body": {
              "company": "Scale365 Company 079",
              "company_slug": "scale365-company-079",
              "date": "2026-03-14",
              "day_index": 69,
              "marker": "scale365scale365company079day069",
              "summary": "Scale365 Company 079 day 069: security approval update recorded.",
              "topic": "security approval"
            },
            "kind": "scale365_chronology_daily_update"
          },
          "evaluated": null,
          "extra": {
            "category": "chronology",
            "company": "run365-scale365-company-079",
            "marker": "scale365scale365company079day069",
            "name": "run365-scale365-company-079-day-069"
          },
          "forward": null
        },
        "category": null,
        "key": "cdbbd9b7-bfdc-453a-a75a-c03afe8aee71",
        "snippet": "...14\",\"topic\":\"security approval\",\"marker\":\"[scale365scale365company079day069]\",\"summary\":\"Scale365 Company 079 day 069...",
        "tier": "journal"
      },
      {
        "body": {
          "context_stats": {
            "milestone_count": 9,
            "simulated_days": 365,
            "topic_cycle_size": 10
          },
          "display_name": "Scale365 Company 079",
          "region": "LATAM",
          "segment": "education",
          "stakeholder_count": 3,
          "timeline_days": 365,
          "timeline_start": "2026-01-05"
        },
        "category": "company",
        "key": "run365-scale365-company-079",
        "snippet": null,
        "tier": "entity"
      }
    ],
    "expected_contains": [
      "Scale365 Company 079",
      "69",
      "2026-03-14",
      "security approval"
    ],
    "id": "topic_company_079_day_069",
    "query": "What topic was recorded for Scale365 Company 079 on day 69?",
    "retrieval_score": {
      "contains_ok": true,
      "forbidden_ok": true,
      "passed": true
    }
  },
  {
    "answer_score": {
      "contains_ok": false,
      "forbidden_ok": true,
      "passed": false,
      "retrieval_has_expected": true,
      "unknown_ok": true
    },
    "category": "temporal_topic",
    "context_sample": [
      {
        "body": {
          "acted": {
            "body": {
              "company": "Scale365 Company 099",
              "company_slug": "scale365-company-099",
              "date": "2026-04-17",
              "day_index": 103,
              "marker": "scale365scale365company099day103",
              "summary": "Scale365 Company 099 day 103: billing reconciliation update recorded.",
              "topic": "billing reconciliation"
            },
            "kind": "scale365_chronology_daily_update"
          },
          "evaluated": null,
          "extra": {
            "category": "chronology",
            "company": "run365-scale365-company-099",
            "marker": "scale365scale365company099day103",
            "name": "run365-scale365-company-099-day-103"
          },
          "forward": null
        },
        "category": null,
        "key": "8cee068f-d342-4015-a46b-37ae3eb28302",
        "snippet": "...17\",\"topic\":\"billing reconciliation\",\"marker\":\"[scale365scale365company099day103]\",\"summary\":\"Scale365 Company 099 day 103...",
        "tier": "journal"
      },
      {
        "body": {
          "context_stats": {
            "milestone_count": 9,
            "simulated_days": 365,
            "topic_cycle_size": 10
          },
          "display_name": "Scale365 Company 099",
          "region": "LATAM",
          "segment": "education",
          "stakeholder_count": 3,
          "timeline_days": 365,
          "timeline_start": "2026-01-05"
        },
        "category": "company",
        "key": "run365-scale365-company-099",
        "snippet": null,
        "tier": "entity"
      }
    ],
    "expected_contains": [
      "Scale365 Company 099",
      "103",
      "2026-04-17",
      "billing reconciliation"
    ],
    "id": "topic_company_099_day_103",
    "query": "What topic was recorded for Scale365 Company 099 on day 103?",
    "retrieval_score": {
      "contains_ok": true,
      "forbidden_ok": true,
      "passed": true
    }
  },
  {
    "answer_score": {
      "contains_ok": false,
      "forbidden_ok": true,
      "passed": false,
      "retrieval_has_expected": true,
      "unknown_ok": true
    },
    "category": "temporal_topic",
    "context_sample": [
      {
        "body": {
          "acted": {
            "body": {
              "company": "Scale365 Company 262",
              "company_slug": "scale365-company-262",
              "date": "2026-01-14",
              "day_index": 10,
              "marker": "scale365scale365company262day010",
              "summary": "Scale365 Company 262 day 010: implementation note update recorded.",
              "topic": "implementation note"
            },
            "kind": "scale365_chronology_daily_update"
          },
          "evaluated": null,
          "extra": {
            "category": "chronology",
            "company": "run365-scale365-company-262",
            "marker": "scale365scale365company262day010",
            "name": "run365-scale365-company-262-day-010"
          },
          "forward": null
        },
        "category": null,
        "key": "bd87258c-6015-42ff-b863-93d5dbdd9e09",
        "snippet": "...14\",\"topic\":\"implementation note\",\"marker\":\"[scale365scale365company262day010]\",\"summary\":\"Scale365 Company 262 day 010...",
        "tier": "journal"
      },
      {
        "body": {
          "context_stats": {
            "milestone_count": 9,
            "simulated_days": 365,
            "topic_cycle_size": 10
          },
          "display_name": "Scale365 Company 262",
          "region": "Western Europe",
          "segment": "healthcare",
          "stakeholder_count": 3,
          "timeline_days": 365,
          "timeline_start": "2026-01-05"
        },
        "category": "company",
        "key": "run365-scale365-company-262",
        "snippet": null,
        "tier": "entity"
      }
    ],
    "expected_contains": [
      "Scale365 Company 262",
      "10",
      "2026-01-14",
      "implementation note"
    ],
    "id": "topic_company_262_day_010",
    "query": "What topic was recorded for Scale365 Company 262 on day 10?",
    "retrieval_score": {
      "contains_ok": true,
      "forbidden_ok": true,
      "passed": true
    }
  },
  {
    "answer_score": {
      "contains_ok": false,
      "forbidden_ok": true,
      "passed": false,
      "retrieval_has_expected": true,
      "unknown_ok": true
    },
    "category": "temporal_topic",
    "context_sample": [
      {
        "body": {
          "acted": {
            "body": {
              "company": "Scale365 Company 272",
              "company_slug": "scale365-company-272",
              "date": "2026-01-31",
              "day_index": 27,
              "marker": "scale365scale365company272day027",
              "summary": "Scale365 Company 272 day 027: renewal planning update recorded.",
              "topic": "renewal planning"
            },
            "kind": "scale365_chronology_daily_update"
          },
          "evaluated": null,
          "extra": {
            "category": "chronology",
            "company": "run365-scale365-company-272",
            "marker": "scale365scale365company272day027",
            "name": "run365-scale365-company-272-day-027"
          },
          "forward": null
        },
        "category": null,
        "key": "cafd177f-0583-4fa4-8c0f-571becfb6573",
        "snippet": "...31\",\"topic\":\"renewal planning\",\"marker\":\"[scale365scale365company272day027]\",\"summary\":\"Scale365 Company 272 day 027...",
        "tier": "journal"
      },
      {
        "body": {
          "context_stats": {
            "milestone_count": 9,
            "simulated_days": 365,
            "topic_cycle_size": 10
          },
          "display_name": "Scale365 Company 272",
          "region": "Western Europe",
          "segment": "healthcare",
          "stakeholder_count": 3,
          "timeline_days": 365,
          "timeline_start": "2026-01-05"
        },
        "category": "company",
        "key": "run365-scale365-company-272",
        "snippet": null,
        "tier": "entity"
      }
    ],
    "expected_contains": [
      "Scale365 Company 272",
      "27",
      "2026-01-31",
      "renewal planning"
    ],
    "id": "topic_company_272_day_027",
    "query": "What topic was recorded for Scale365 Company 272 on day 27?",
    "retrieval_score": {
      "contains_ok": true,
      "forbidden_ok": true,
      "passed": true
    }
  },
  {
    "answer_score": {
      "contains_ok": false,
      "forbidden_ok": true,
      "passed": false,
      "retrieval_has_expected": true,
      "unknown_ok": true
    },
    "category": "temporal_topic",
    "context_sample": [
      {
        "body": {
          "acted": {
            "body": {
              "company": "Scale365 Company 486",
              "company_slug": "scale365-company-486",
              "date": "2026-01-23",
              "day_index": 19,
              "marker": "scale365scale365company486day019",
              "summary": "Scale365 Company 486 day 019: security approval update recorded.",
              "topic": "security approval"
            },
            "kind": "scale365_chronology_daily_update"
          },
          "evaluated": null,
          "extra": {
            "category": "chronology",
            "company": "run365-scale365-company-486",
            "marker": "scale365scale365company486day019",
            "name": "run365-scale365-company-486-day-019"
          },
          "forward": null
        },
        "category": null,
        "key": "95944ece-083c-4086-afb1-def9a2a492b7",
        "snippet": "...23\",\"topic\":\"security approval\",\"marker\":\"[scale365scale365company486day019]\",\"summary\":\"Scale365 Company 486 day 019...",
        "tier": "journal"
      },
      {
        "body": {
          "context_stats": {
            "milestone_count": 9,
            "simulated_days": 365,
            "topic_cycle_size": 10
          },
          "display_name": "Scale365 Company 486",
          "region": "North America",
          "segment": "construction",
          "stakeholder_count": 3,
          "timeline_days": 365,
          "timeline_start": "2026-01-05"
        },
        "category": "company",
        "key": "run365-scale365-company-486",
        "snippet": null,
        "tier": "entity"
      }
    ],
    "expected_contains": [
      "Scale365 Company 486",
      "19",
      "2026-01-23",
      "security approval"
    ],
    "id": "topic_company_486_day_019",
    "query": "What topic was recorded for Scale365 Company 486 on day 19?",
    "retrieval_score": {
      "contains_ok": true,
      "forbidden_ok": true,
      "passed": true
    }
  }
]
```