Depends on both the required-quality gate and the performance gate.
floor: required-quality AND performance gates01DETECTOR BENCHMARK
Detector Benchmark.
Public snapshot of the current DataSitr detector benchmark: current gate, public-safe suite results, and explicit claim boundaries.
Current benchmark: pass
Required suites currently passing.
floor: all required suites must passCurrent gating latency check for English 1K text.
floor: p95 < 75 ms targetTotal cases across the current frozen suites.
count across the current frozen suites02PERFORMANCE
Performance snapshot
The public page highlights the current 1K-character gating snapshot rather than publishing the full internal performance report.
// p95 vs the 75 ms gate, by language path
03PRECISION / RECALL
Detector precision / recall snapshot
Per-entity-type precision/recall is published against an adversarial-FP and Saudi-name-recall corpus. Dated in-repo snapshots on curated corpora — not an external audit and not a claim of production-wide coverage.
Dated detector precision/recall snapshot.
Total measured cases in the public JSON artifact.
Total false positives across the published slices.
Total false negatives across the published slices.
These misses are itemized in the linked JSON, with case id and character span (synthetic curated test tokens — not live customer traffic).
// each artifact is dated independently — see 06
04PUBLISHED SUITES
Current benchmark suites
These are the suites currently included in the public benchmark gate.
Published suites
05RESEARCH CORPORA
Research corpora coverage
These suites were folded in from the 2026-04-26 detector research package. They expand evaluation coverage across public-domain Arabic literature, Saudi code-switched business text, and adversarial PII attacks. This section is shown separately from the frozen public gate until the new corpora complete trend-history stabilization.
Dated in-repo benchmark over curated public-domain and synthetic research corpora; not an external audit or production-wide coverage guarantee.
Separate from the frozen public gate.
Across all research suites.
Across research corpora.
Across research corpora.
Per-suite breakdown
Adversarial attack-class metrics
// shown separately from the frozen public gate
06ARTIFACT & METHOD
Artifact and method
This page reads the published public JSON summary. It is intentionally narrower than the internal benchmark report.
Last public update:
2026-04-29T14:40:52Z
The precision/recall artifact (03) and the suite/gate artifact (this section) are dated independently — each is open-able above.
07CLAIM BOUNDARY
Claim boundary
This page is a benchmark snapshot, not a blanket claim that every customer payload or every future detector change is perfect. Public benchmark language should stay tied to a fresh artifact.
The public benchmark page shows only the suites currently included in buyer-facing claims.