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.
140 lines
5.4 KiB
ReStructuredText
140 lines
5.4 KiB
ReStructuredText
Benchmark surface
|
|
=================
|
|
|
|
Arborist ships the complete **Dav1DPrometheus 5S/5T/5F/5R** evaluation
|
|
suite — 21 sub-batteries, ~660 deterministic fixtures — as
|
|
first-class infrastructure. Every benchmark is reproducible, no
|
|
LLM-as-judge, and many sub-batteries route through the actual
|
|
arborist surface (parser, verifier, audit chain, π* registry) rather
|
|
than synthetic gold output.
|
|
|
|
Quick reference
|
|
---------------
|
|
|
|
.. code-block:: bash
|
|
|
|
make bench-suite # complete 5S + 5T + 5F + 5R suite
|
|
make bench-5s # representational discipline
|
|
make bench-5t # temporal / cross-reasoning
|
|
make bench-5f # operational quality (Phase 1a embedded)
|
|
make bench-5f-live # 5F bridged to live arborist surfaces (Phase 1b.2)
|
|
make bench-5r # workspace operators
|
|
make bench-5s-math # arithmetic@v1 + logic-kernel@v1 fixtures
|
|
make bench-5s-code # code-py-ast@v1 fixtures
|
|
|
|
Each invocation emits a JSON :class:`bench.batteries.base.BatteryResult`
|
|
with per-task pass/fail, fixture digest, runtime digest, and
|
|
sub-battery-specific metrics.
|
|
|
|
The four batteries
|
|
------------------
|
|
|
|
5S — representation discipline
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Five sub-batteries testing what the system understands at the
|
|
sign / meaning / derivation level:
|
|
|
|
- **Syntax** — does the named π* parse the input without raising?
|
|
- **Semantics** — do two surface forms canonicalize to the same
|
|
bytes when they should (and not when they shouldn't)?
|
|
- **Syllogism** — does each step in a deductive chain validly
|
|
follow under the named rule (categorical_transitivity, chain_3,
|
|
invalid_converse, missing_premise)?
|
|
- **Synthesis** — does the system assemble cited facts into a
|
|
coherent derivation supported by the fact set?
|
|
- **Semiotics** — is meaning preserved under controlled label
|
|
swaps?
|
|
|
|
5T — temporal / cross-reasoning discipline
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Six sub-batteries (legacy ``transfer`` plus the canonical
|
|
Dav1DPrometheus five):
|
|
|
|
- **Transfer Learning** — does a learned pattern carry across
|
|
task / domain / carrier?
|
|
- **Triangulation** — do independent strategies (substring,
|
|
token_subset, token_overlap, entity_match) agree at threshold?
|
|
- **Truthtables** — exhaustive propositional coverage at N=2..4
|
|
variables.
|
|
- **Transitivity** — typed-relation chains under whitelist
|
|
(``implies``, ``subset_of``, ``ancestor_of``, ``before``,
|
|
``less_than``).
|
|
- **Time** — temporal-context preservation across memory_root
|
|
snapshots; integrates with #000017 surface.
|
|
|
|
5F — operational quality
|
|
~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Five sub-batteries, all with **embedded** (Phase 1a synthetic) AND
|
|
**live** (Phase 1b.2, routes through real arborist surfaces) modes:
|
|
|
|
================ =============================================
|
|
Sub-battery Live surface
|
|
================ =============================================
|
|
Function ``arborist.qa.parse_claims.parse_pointer_claims``
|
|
Finetuning ``arborist.selfmodel.store_snapshot`` round-trip
|
|
Falsification ``arborist.qa.verify.verify_quotes``
|
|
Formulate ``arborist.qa.parse_claims.parse_pointer_claims``
|
|
Feedback Loop ``arborist.store.append_audit`` + ``memory.snapshot``
|
|
================ =============================================
|
|
|
|
Per-task ``detail.source`` reports ``"embedded"`` or ``"live"`` so
|
|
bench output distinguishes synthetic from production signal.
|
|
|
|
5R — workspace operators
|
|
~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Five sub-batteries testing operators applied to a workspace
|
|
(SelfModel + memory_root + audit chain):
|
|
|
|
- **React** — observations integrate into downstream state.
|
|
- **Rearrange** — restructure without semantic shift.
|
|
- **Restore** — retrieve prior facts from history.
|
|
- **Replicate** — π*-determinism across N replicas.
|
|
- **Resonate** — variance-zero across N runs.
|
|
|
|
Cross-modality discipline
|
|
-------------------------
|
|
|
|
Every fixture carries:
|
|
|
|
- ``carrier`` — domain whitelist enforced by
|
|
:data:`bench.batteries.base.PHASE_1_CARRIERS`. Phase 1
|
|
domains: ``text``, ``claim_lattice``, ``memory_snapshot``,
|
|
``selfmodel_snapshot``, ``providence_record``, ``audit_event``,
|
|
``code``, ``arithmetic``, ``logic``, ``time_series``.
|
|
- ``domain`` — sub-domain qualifier (e.g.,
|
|
``rational``, ``propositional``, ``python_ast``).
|
|
- ``pi_star_ref`` — registry key naming the canonicalizer.
|
|
- ``loss_report_refs`` — optional projection-loss links.
|
|
- ``modality_notes`` — scope note.
|
|
|
|
Unsupported carriers fail explicitly with
|
|
``reason="unsupported_carrier"`` — never silently accepted. Hidden-
|
|
channel work is defensive only (detection / flagging, never
|
|
generation).
|
|
|
|
ForkScore consumes battery output
|
|
---------------------------------
|
|
|
|
The v8 ForkScore (see :doc:`v8-fork-score`) reads BatteryResult JSON
|
|
from a parent and child organism, computes a weighted scalar
|
|
verdict with ACCEPT / MARGINAL / REJECT classes:
|
|
|
|
.. code-block:: bash
|
|
|
|
make bench-suite # generates parent.json
|
|
# ... apply changes ...
|
|
make bench-suite # generates child.json
|
|
arborist v8 score --parent parent.json --child child.json
|
|
|
|
Authoring new fixtures
|
|
----------------------
|
|
|
|
See :file:`docs/spec-methodology.md` (per-author checklist) and the
|
|
existing fixture files under :file:`bench/fixtures/`. New
|
|
sub-batteries follow the protocol in :mod:`bench.batteries.base` —
|
|
``Battery.run(fixtures_path) → BatteryResult``, deterministic, no
|
|
LLM-as-judge, carrier metadata mandatory.
|