Files
Aura/fieldtests/cycle-0106-research-artifacts/c0106_1_reformatted.json
T
Brummel 78806108d3 fieldtest: cycle 0106 research-artifact surface — GREEN core, authoring on-ramp findings
Downstream-consumer run (roles 5/6b, public interface only) over the
document-authoring loop: canonicalization byte-exact and stable across
reformatting (F8), intrinsic validation thorough and path-addressed (F9),
referential tier correct across the project boundary with progressive
resolution (F10). Findings: one bug (F2: introspect --block advertises an
identity_id process ref the validator refuses), four frictions (F1 envelope
not derivable from introspection incl. the block-id/field-name mismatch and
the un-blocked seed; F3 content:-prefixed id vs bare-hash refs breaking
referential resolution silently; F4 --unwired only reports omitted refs,
which validate then fails; F5 strategy refs unresolvable from the public
surface — no blueprint register/file-content-id/param-space verbs), one
doc-gap (F6 no worked examples, metric vocabulary unlisted), and the
spec-gap F7: a valid, registered campaign has no run path — the
intent-persistence re-test the executor decision waited on.

refs #189, #188
2026-07-03 16:51:36 +02:00

24 lines
681 B
JSON

{
"kind": "process",
"format_version": 1,
"name": "robust-sweep-v1",
"description": "Sweep with trials-deflation, gate on positive expectancy, then walk-forward confirm.",
"pipeline": [
{
"select": "argmax",
"block": "std::sweep",
"deflate": true,
"metric": "sqn"
},
{ "block": "std::gate", "all": [ { "cmp": "gt", "metric": "expectancy_r", "value": 0 } ] },
{
"block": "std::walk_forward",
"folds": 4,
"in_sample_bars": 5000,
"out_of_sample_bars": 1000,
"metric": "sqn",
"select": "argmax"
}
]
}