Asked to turn a written rule about what makes a feature admissible into something a machine can actually check. Came back with three runnable probes, one gate that refuses promotion when any axis fails, and a correction to what one of the three axes even meant.
| Quantity | Value | Meaning |
|---|---|---|
| Probes and gates built | 3 probes, 1 composed gate | orthogonal / parameterless / agnostic |
| Candidates swept for shared knobs | 40 | knob inventory across families |
| New constants recommended | 2 (MFDFA_DETREND_ORDER=1 over 16 members; TAKENS_EMBEDDING_TAU=1 over 4) | knobs that are conventions, not magic numbers |
| Candidates rescued by the constants | 16 | 8 ordinal/CECP by reuse plus 8 single-knob MF-DFA |
| Convergence-oracle agreement | 6.9e-18 and 0.0 absolute difference in 2 cases; 3.3% relative divergence in 1 | the divergent case is an unpinned embedding order |
| Firing | What it did |
|---|---|
| 01 | Transcribed the source ruling verbatim rather than paraphrasing it |
| 02 | Found the 'agnostic' axis had drifted to mean cross-asset; re-anchored it to 'two correct implementations agree' |
| 03 | Replaced by-hand inspection with a code scanner and a convergence oracle |
| 04 | Composed them into one cheapest-first gate that stops before any expensive database query |
| 05 | Swept every candidate's tuning knobs to find ones that are conventions |
Register a second reference implementation per candidate so the agnostic convergence test runs live (bar_svd_entropy is held pending on it); land the 2 recommended project-wide constants; feed the bigblack orthogonality run into the gate. The knob sweep is append-only and re-runs on every new candidate.
'FORMALIZED โ three probes + one promotion gate; agnostic axis provenance-corrected.' (manifest.json verdict; ledger adds: no open queue, no next_iteration)
Lifecycle status is process state, not a judgement of the findings. Results are stated as numbers with their uncertainty. Generated between CLOSING-RECONCILIATION markers โ regenerate rather than edit.
Bruntwork ยท Eon Labs ยท opendeviationbar-py ยท 2026-06-09
Terry's feature-column discipline โ orthogonal ยท parameterless ยท agnostic (msg id=428) โ turned into three runnable probes + one promotion gate, with the agnostic axis re-anchored to Terry's verbatim source.
Captures a dimension no other feature captures โ empirically, on real bars.
orthogonality_probe.py (+ ฮพ/CODEC cascade)No magic numbers, no tuned constants, no if n>=500 dispatch.
parameterless_probe.py (AST + constants_registry.toml)Algorithm-invariant: two correct implementations converge to the same answer.
agnostic_probe.py (no-dispatch + convergence oracle)promote = parameterless.PASS AND agnostic.PASS AND orthogonal.PASS| candidate impl | parameterless | agnostic | orthogonal | decision |
|---|---|---|---|---|
bar_svd_entropy (pinned to SVD_ORDER) | PASS | PENDING | PENDING | PENDING โ agnostic oracle needs a 2nd reference impl |
add_antropy (hardcoded order=3) | FAIL | SKIPPED | SKIPPED | BLOCKED โ parameterless (feature-tunable knob vetoes) |
The hardcoded impl is blocked on the FREE static axis โ before any ClickHouse cost. The pinned impl is held PENDING; the gate never fakes a PASS.
findings/evolution/shared_data/{parameterless,agnostic}_probe.py, three_axis_gate.py, constants_registry.toml