← all sampled attempts · show highlighted in source

breadth-04

docs/spec-fabric-reconfigurable-op.md, lines 479–492

`format`, `source_format`, and `destination_format` are exact scalar floating types. `element_format` is the exact vector element type. Equal representation width does not make arithmetic formats equivalent. Scalar and fixed-vector sign manipulation use width because `f16` and `bf16` negate and absolute value are bit-identical sign-bit transforms. Compare/minmax `numeric_format` is the closed tagged sum `ExactFormat(canonical_type)` or `RepresentationWidth(u32)`. It uses `ExactFormat` whenever a reachable NaN-defined representative requires that exact format; it uses `RepresentationWidth` only for an uncovered `nnan`-normalized behavior. A mixed strict/`nnan` image therefore reuses its exact-format modes, while an all-`nnan` 16-bit image can collapse `f16` and `bf16` to one width mode. Fixed-vector shape and lane count remain admission facts and do not enter a floating arithmetic key. Physical filtering must establish at least one positive-lane actor witness before quotienting.

source passage artifact

Baseline outcome

blocked generator source gap

Anchoring reports missing float hw_params accepted domains and actor nnan spelling; both candidate stages unrun under paired readiness gate.

Coverage and minimized cases

obligation coverage: not measured / no validated evidence · code coverage: not measured / no validated evidence · coverage-preserving minimized case: not measured / no validated evidence

Retained evidence