russell@unturf.com
508a25076d
Two items from the menu, fanned out:
1. time-series-quantized@v1 — last meaningful π* stub graduates.
Sample-array carrier (sensor / temporal data) joins the registry
alongside text · claim_lattice · code · arithmetic · logic.
Quantizes to (dt, dv) grid, sorts by timestamp, dedupes
collisions (last wins), serializes as integer-vector text:
dt=1;dv=0.1;n=2;t0=0:10|20
Equivalence classes preserved: timestamp jitter < Δ_t,
value jitter < Δ_v/2 (banker's rounding), out-of-order samples,
different JSON presentation. Distinct: any change to dt/dv grid,
any quantized value or timestamp difference. Projective —
canonical text is not valid JSON, so re-canonicalization raises.
- 13 unit tests in tests/test_pi_star.py (jitter, dedupe, sort,
fractional dv, error paths, idempotency-projective)
- 10 syntax + 12 semantics fixtures under bench/fixtures/5s/
(10/10 + 12/12 pass)
- bench-5s-time-series Makefile target
- time_series added to PHASE_1_CARRIERS whitelist
- tabular-pinned@v1 is now the only remaining stub
2. Substrate docs — first formal coverage of the registry, bench
harness, and v8 ForkScore at arborist.unturf.com:
- docs/_source/pi-star.rst: registry overview, cross-modality
discipline (carrier + pi_star_ref), math π* highlights
(arithmetic + logic-kernel worked examples), composition
algebra pointer, authoring checklist (8 steps).
- docs/_source/bench.rst: 5S/5T/5F/5R structure, sub-batteries,
phase-1 carriers, ForkScore integration, fixture format,
reproducibility (runtime_digest, fixture_digest).
- docs/_source/v8-fork-score.rst: formula, default weights,
verdict thresholds (ACCEPT/MARGINAL/REJECT), hard-regression +
NEG_INF_REGRESSION flags, CLI usage.
- index.rst gets a "Substrate" toctree section above the existing
module-reference autosummary.
Sphinx build clean (3 new pages, no new warnings).
Test suite: 1269 passed, 36 skipped.
134 lines
4.4 KiB
ReStructuredText
134 lines
4.4 KiB
ReStructuredText
v8 ForkScore
|
||
============
|
||
|
||
The Merkle-AGI v8 selection protocol's **scoring half**. Pure
|
||
function over a (parent, child) bench-result pair → a single
|
||
scalar with ACCEPT / MARGINAL / REJECT verdict. Phase 1a of
|
||
ticket ``#000012``.
|
||
|
||
The complementary canonicalization half (validator state machine,
|
||
acceptance protocol, slashing, fork-choice rule) is reserved for
|
||
the v8 paper itself; Phase 1a ships only the function ForkScore
|
||
without the consensus surface around it.
|
||
|
||
Formula
|
||
-------
|
||
|
||
.. code-block:: text
|
||
|
||
ForkScore =
|
||
α · Δ5S
|
||
+ β · Δ5T
|
||
+ γ · Δ5F (incl. efficiency-aware bonus)
|
||
+ δ · SelfModelCalibrationGain
|
||
+ ε · AuditCompleteness
|
||
+ ζ · ValidatorDiversity
|
||
- η · RegressionPenalty
|
||
- θ · CapitalCostPenalty
|
||
- ι · SecurityRiskPenalty (reserved; Phase 1a = 0)
|
||
- κ · ComplexityPenalty (reserved; Phase 1a = 0)
|
||
- λ · MemoryInvalidationPenalty
|
||
|
||
Each term consumes the metrics every 5S/5T/5F sub-battery emits in
|
||
its :class:`BatteryResult.metrics` dict. The Δ-rate per battery is
|
||
the mean of per-sub-battery rate deltas (child — parent).
|
||
|
||
Δ5F additionally consumes the inf-aware efficiency aggregations
|
||
landed under the 2026-05-08 ``fbd99a8`` review:
|
||
``adaptation_efficiency_mean_finite``,
|
||
``adaptation_efficiency_infinite_count``,
|
||
``adaptation_efficiency_neg_infinite_count``,
|
||
``feedback_efficiency_mean_finite``,
|
||
``feedback_efficiency_infinite_count``.
|
||
|
||
Verdict thresholds
|
||
------------------
|
||
|
||
========================== ================== ============
|
||
Score / flags Verdict CLI exit
|
||
========================== ================== ============
|
||
``score >= SIGNAL_FLOOR`` **ACCEPT** ``0``
|
||
``[0, SIGNAL_FLOOR)`` **MARGINAL** ``0``
|
||
``score < 0`` **REJECT** ``1``
|
||
hard-regression flag **REJECT** ``1``
|
||
``NEG_INF_REGRESSION`` flag **REJECT** ``1``
|
||
========================== ================== ============
|
||
|
||
``SIGNAL_FLOOR`` defaults to ``0.05`` (5pp; matches
|
||
:file:`docs/bench-maxing.md`'s noise floor).
|
||
|
||
Hard-regression flag fires if any single sub-battery rate drops by
|
||
≥ ``HARD_REGRESSION_FLOOR`` (default 5pp), regardless of net score.
|
||
``NEG_INF_REGRESSION`` flag fires when
|
||
``*_efficiency_neg_infinite_count`` increases parent → child:
|
||
*free regression* is unsafe regardless of other gains.
|
||
|
||
Default weights
|
||
---------------
|
||
|
||
.. code-block:: python
|
||
|
||
WeightSet(
|
||
alpha=1.0, # Δ5S
|
||
beta=1.0, # Δ5T
|
||
gamma=1.0, # Δ5F
|
||
delta=0.5, # SelfModelCalibrationGain
|
||
epsilon=0.3, # AuditCompleteness
|
||
zeta=0.0, # ValidatorDiversity (off in single-validator)
|
||
eta=2.0, # RegressionPenalty (heavy by design)
|
||
theta=0.5, # CapitalCostPenalty
|
||
iota=0.0, # SecurityRiskPenalty (reserved)
|
||
kappa=0.0, # ComplexityPenalty (reserved)
|
||
lambda_=0.5, # MemoryInvalidationPenalty
|
||
)
|
||
|
||
Override via JSON file passed to ``--weights``:
|
||
|
||
.. code-block:: json
|
||
|
||
{
|
||
"alpha": 1.5,
|
||
"eta": 5.0,
|
||
"lambda": 1.0
|
||
}
|
||
|
||
The JSON key ``"lambda"`` round-trips into ``WeightSet.lambda_``
|
||
because ``lambda`` is a Python reserved word.
|
||
|
||
CLI
|
||
---
|
||
|
||
.. code-block:: bash
|
||
|
||
arborist v8 score \
|
||
--parent parent-bench.json \
|
||
--child child-bench.json \
|
||
[--weights weights.json] \
|
||
[--capital-delta N] \
|
||
[--memory-invalidation-count N] \
|
||
[--audit-completeness 0..1] \
|
||
[--selfmodel-calibration-gain N]
|
||
|
||
``parent-bench.json`` and ``child-bench.json`` are the JSON output
|
||
of ``bench.batteries.runner --all``.
|
||
|
||
Output: :class:`arborist.v8.fork_score.ScoredFork` with
|
||
``score``, ``verdict``, per-term ``breakdown``, ``flags`` list,
|
||
and the active ``weights`` echoed back.
|
||
|
||
What's NOT in Phase 1a
|
||
----------------------
|
||
|
||
- Validator state machine (bonding / signing / slashing).
|
||
- Acceptance protocol (proposal / quorum / finalization).
|
||
- Challenge protocol (audit-replay disagreement).
|
||
- Fork-choice rule (which of two competing finalizations wins).
|
||
- Mesh wire format extensions for validator gossip.
|
||
- Stake mechanics + economic incentives.
|
||
- Cross-validator ZK proof exchange.
|
||
|
||
These are commissioned by the v8 paper itself
|
||
(``docs/merkle-agi-v8-consensus.rst``, still open under #000012).
|
||
Phase 1a's scoring function is the substrate the paper consumes;
|
||
landing it now lets the paper cite measured values instead of
|
||
stipulated ones.
|