1 source filed · EN 1
Task: from 76 real policy documents, recover the requirements the author singled out, scored against the file's own OOXML formatting properties by a deterministic matcher.
0.690 to 0.150micro F1 on recovering author-flagged requirements, formatting-aware versus docling ingestion (0.075 with plain text)
1 source filed · EN 1
On 132 real, de-identified support cases, guidance was rated procedurally equivalent to ground truth on 99.2% and evidence-sufficient on 83.3%.
99.2%cases where the skill's guidance was judged procedurally equivalent to human-approved ground truth
1 source filed · EN 1
Structure-aware chunking is supported for nine languages (Kotlin, Java, Python, JavaScript, TypeScript, C#, PHP, Go, Rust); everything else falls back to line-based splitting.
32xstorage reduction from one-bit binary vectors versus 32-bit floats