Published synthetic ANLS record
| Field | Recorded value |
|---|---|
| Question | Can structured semantic state reduce aggregate bytes while retaining exact reconstruction and lineage? |
| Fixture | 80 project-generated synthetic records; 64 repeat-heavy and 16 heterogeneous |
| Representations | Literal canonical JSON, canonical JSONL, zlib level 9, structural templates, ANLS coordinate-plus-delta |
| Literal baseline | 27,975 B |
| ANLS result | 14,833 B · 46.9777% savings vs literal |
| Compression negative result | zlib: 2,961 B · 89.4155% savings vs literal · smaller in every measured cohort |
| Limitation | No universal compression, latency, throughput, intelligence, memory, cost, or production claim |
| Authority | Authority-null; exact reconstruction does not grant truth or promotion authority |
Required benchmark record
| Field | Requirement |
|---|---|
| Question | The exact claim under test |
| Fixture | The bounded input population and exclusions |
| Baseline | The simpler or incumbent comparison |
| Environment | Versioned runtime and relevant limits |
| Metrics | Predeclared measures and calculation rules |
| Result | Complete outcome, not a selected headline |
| Limitations | What the benchmark cannot establish |
| Reproduction | Public-safe steps and exact acceptance boundary |
No isolated ‘X% better’ number without the baseline and negative result beside it.ResBased benchmark policy