fox 2026-05-21: 'gen 200W' was a bug — joules/window blends the ~400W
generation bursts with the sub-100W gaps (retrieval/verify/network) into
a power state the card never sits at. A card occupies DISTINCT states
(idle / middle-idle = resident-between-requests / generation), differing
per card×model×server.
watt_probe.classify_power_bands(): largest-gap split of the window
samples into a low band (serving floor) and high band (generation draw)
+ duty cycle. Data-derived, never hardcoded — tested at two scales. The
worker emits the decomposition + raw samples; RemoteProbe/LocalProbe
expose band_stats() uniformly.
energy_cogs: marginal now taken against the measured SERVING FLOOR (the
standing cost of being ready), not deep idle; the blend is kept but
labelled window_mean_w. Reports idle/serving-floor/gen-draw/duty.
Cache-miss certainty (fox's question): the arborist arm runs
burn_existing=True (force-deletes any live providence row before
inference) and asserts cache_hits==0 with a loud warning + real_inference
flag — so we time real generation, never a SQLite lookup. Solo has no
cache path. 11 tests (energy math + band split). Validated live on the
isolated 4090: solo gen 308W/70%-duty vs substrate 396W/8.6%-duty —
substrate marginal/tok is LOWER, gross/tok higher (it holds the card
longer for retrieval).
fox 2026-05-21: compute cost-of-goods-sold by kWh vs tokens, with the
three power states (idle / warm-idle / generation) MEASURED per
card×model×server — never hardcoded (his 40/127/380 W were illustrative
of one 3090). The only operator input is --price-per-kwh (default 0.33
USD/kWh, a configurable site rate).
energy_cogs() (pure, unit-tested) decomposes measured generation energy
against the measured warm-idle baseline:
* gross — all measured joules over the window (all-in, includes the
warm-idle cost of keeping the model hot, amortized).
* marginal — joules ABOVE warm-idle: what one more request's burst
actually costs (clamped >=0).
kWh = J/3.6e6; $/1k-tok is the unit that compares to API pricing. Both
surface per cell + a COGS print line.
watt_bench's arborist arm now loads the frozen bench.stock_v1 policy
(--answer-mode, drift-guarded on non-reasoning) so cost is measured for
the SAME substrate the campaign grades. Cells record
window_start/end_unix so a post-hoc load_monitor queue-depth cross-ref
can flag organic-traffic contamination on the non-isolated single-slot
endpoints. 6 COGS tests; full suite 2534 passed.
Two surgical fixes unblock 'arborist with synthesis LLM = Qwen-on-
llama.cpp' as a viable arm in the control sweep. Pre-existing
docstring said 'Arborist×Qwen needs proof-path guided_json+extra_body
surgery — coupled follow-up'; this is that follow-up.
Fix 1 — multi-engine structured-output extras
The runner / query JSON-mode paths previously sent only vLLM's
'guided_json' key for the claim_lattice schema. llama.cpp silently
drops it, leaving Qwen un-enforced (the parse-tolerant fallback did
all the work). Helper
claim_lattice_structured_output_extras() in arborist/qa/verify.py
now returns a dict carrying the schema under all three engine
conventions:
- guided_json (vLLM grammar-constrained sampling)
- json_schema (llama.cpp native shorthand)
- response_format (OpenAI-spec, honoured by llama.cpp and newer vLLM)
Each engine recognises its own key and silently drops the others.
Used at both inference call sites (runner.py:740, query.py:3324).
Hermes/vLLM path is unchanged — it picks up 'guided_json' and
ignores the other two.
Fix 2 — query() accepts user-supplied extra_body, merges with defaults
query() grew a keyword-only extra_body parameter (default None).
Per-model knobs (Qwen's {'chat_template_kwargs': {'enable_thinking':
False}} toggle, future template knobs) can flow from the caller to
the synthesis chat-completion call. Schema-enforcement extras are
added inside query() and merge under user keys — common case is
disjoint namespaces, but if a caller wants to override 'guided_json'
they can.
bench/control_sweep.py now passes MODELS[arborist_ref]['extra']
through to query() in the arborist branch, so --arborist-ref
qwen-nothink runs with reasoning disabled and --arborist-ref
qwen-think runs with reasoning enabled. Phase 1's arborist arm with
--arborist-ref=hermes is unaffected (MODELS['hermes']['extra'] is
None, merges to no-op).
Tests
+ 3 new in tests/test_verify_json.py covering helper default shape,
alternate-schema reuse, and query()'s new extra_body parameter
220 affected tests still green (verify / claim_lattice / judge /
runner suite)
pytest test_verify_json: 27/27
Next: small smoke run --arborist-ref qwen-nothink against 4-8 items
to confirm end-to-end before any full sweep. Phase 2 (qwen-think solo)
still running in background, unaffected — it doesn't touch the
arborist arm.
The Arborist arm runs answer_mode='claim_lattice' (per control_sweep.py
:179, control_ab.py:155) so its answers arrive as the JSON envelope
{"claims":[{"text":"...","evidence_ids":["E1"]},...]}.
_descaffold strips the [E1] evidence-pointer markup but the JSON
braces + key syntax remain. The verifier's strategy-2 (span) and
strategy-3 (proper-noun) extractors see brace noise instead of the
inner claim prose — every Arborist record degraded to UNGROUNDED.
The 2026-05-19T17-01-17Z sweep, re-graded with the freshly calibrated
judge (5a17f61), surfaced this: Arborist arm reported 0 CG across all
three variants in the live phase 1 output (the live run was pre-
calibration), and 29/120 CG (24%) under the calibrated rescore — clear
improvement just from theta_contra=0.85, but the JSON envelope was
still hobbling the verifier paths.
Fix: _unwrap_claim_lattice_json runs BEFORE all downstream rules.
Detection is conservative (three independent signals: starts-with-
brace AND "claims" key AND "text" key) so plain-prose answers
pass through unchanged. Multi-claim envelopes concatenate as discrete
sentences (extract_claim_spans treats each as its own span).
Malformed JSON falls back to the original answer — no silent
rewriting on broken input.
Smoke result on the Iceland Arborist case
ans: {"claims":[{"text":"The current president of Iceland is
Ólafur Ragnar Grímsson.","evidence_ids":["E1"]}]}
gold: {{Infobox Political post |post = President |body = Iceland
|incumbent = [[Ólafur Ragnar Grímsson]] ...}}
before: UNGROUNDED → FABRICATED (then WRONG after calibration)
after: short_entity_grounded → CORRECT_GROUNDED
pytest: 27/27 (added 7 unwrap-coverage tests covering single-claim
envelopes, multi-claim concatenation, plain-prose passthrough,
malformed-JSON tolerance, unrelated-JSON passthrough, and the
end-to-end Arborist-envelope CG flow). Self-test 4/4 unchanged.
Re-rescores of 17:01 sweep + phase 1 sweep run after this commit
to measure final Arborist scorecard improvement.
bench/judge_code.py — drop-in alternative to bench/judge.py with the
same Verdict shape & closed verdict vocabulary (CG/W/F/A/JE) but zero
quota cost: composes verifier + NLI + abstention + specificity into a
fixed-order pipeline. fox 2026-05-19: 'data first, judging later' —
this is the data-collection arm; LLM-based judging (Opus batched
needle-haystack, or Grok credit-card) is a separate downstream
concern that operates on the residue this judge cannot classify
deterministically.
Pipeline (first hit decides):
1. empty / no-gold guards
2. explicit abstention phrases (lexical regex)
3. NLI contradiction (arborist.qa.nli.shadow_check) — strongest
signal: gold contradicts the claim → WRONG
4. lexical verifier (arborist.qa.verify.verify_quotes) →
STRICT → CORRECT_GROUNDED
HYBRID + NLI entail >= 0.55 → CORRECT_GROUNDED
UNGROUNDED + specifics-not-in-gold → FABRICATED
UNGROUNDED + no specifics → ABSTAINED
HYBRID without NLI corroboration → JUDGE_ERROR (residue
for an LLM judge)
Threshold note: _CODE_JUDGE_THETA_ENTAIL_CORROBORATE=0.55 is distinct
from the NLI manifest's entailment_block_veto=0.9. The manifest's
threshold is calibrated for OVERRIDING a STRICT lexical signal with
negative evidence — high bar. The corroboration use here is the
opposite direction: additive positive evidence on an already-positive
anchor — moderate bar appropriate. Self-test case 1 measures NLI
entail=0.769 (clearly entailed, clear margin above 0.55).
Specificity for FABRICATED layers three scanners:
- verifier's multi-word proper-noun extractor (Higgs Boson, ...)
- local single-word capitalised-token scanner (Napoleon, Mars, ...)
deliberately separate because the verifier's gate is conservative
by design (multi-word only)
- numerics (years, dates, large counts, money)
Self-test: same 4 fixtures as bench/judge.py:self_test() so the two
instruments can be cross-checked when fox re-fires the Opus judge on
the residue later. Result: 4/4 INSTRUMENT TRUSTWORTHY.
tests/test_judge_code.py — pulls the contract into make test
(18 cases): module identifiers pinned, dataclass shape parity,
empty / no-gold guards, parametrised abstention phrases, specificity
layer behaviour, the canonical 4-case self-test, batch helper, and
graceful NLI-unavailable degradation. 18/18 pass.
Pre-existing known limitation, documented in the docstring: terse
correct answers ('In 1945.' against gold containing '1945') route to
ABSTAINED because the verifier's span extractor needs prose shape;
NLI sees no clause-level overlap at very short claims. The conservative
ABSTAINED label is correct deferral; tuning this is a calibration
question for real bench data, not the instrument's contract.
No callers touched yet — control_sweep.py & control_ab.py still
import the disabled Opus judge. Wiring this in is a separate ticket
move per fox's data-first sequencing.
The review's central, correct finding: _title_query_tokens is
hot-path (every query AND title) and its fold set (hyphen #000007 +
numeral/accent/honorific/brit) changes which documents retrieve, but
that normalization's version was bound nowhere → a replay cannot
identify which token-normalization produced an old providence
record's sources. Same provenance class as the #000001 keyword gap.
Severity is honest: replay-provenance gap, NOT cache corruption —
different folds → different sources → different context_root →
different cache_key, so no false answer-cache aliasing or false
STRICT. Verifier/proof path unchanged.
Fix follows the repo's OWN #000001 §5/§6 decision (bind retrieval
transforms into the run-DAG RetrievalPlan/retrieval_plan_hash, NOT
governance_policy_hash). The review suggested governance "Option A";
repo precedent is run-DAG binding (same status as retrieval_keywords
and #000056 MT-engine identity) — the discrepancy is surfaced for
fox as an explicit call, not silently overridden.
- RetrievalPlan.title_token_policy (empty default → omitted from
canonical() → every prior retrieval_plan_hash byte-identical; the
§5 zero-churn discipline, same as the #000056 MT fields).
- _TITLE_TOKEN_POLICY single source of truth in query.py, bound at
the plan construction site; bump on any fold change.
- Plus the review's edge cases: Roman-substring-in-word not folded,
out-of-range not folded, Unicode Roman explicitly unsupported,
hyphen∘numeral composition. Full suite 2498, 0 regressions.
Declined (not engineering, per don't-proliferate): the review's
SelfModel/MemoryRoot/5S-5T-5F/capital-ledger ceremony — the ticket
design log is the single source of truth; scope recorded there.
Two more MEASURED fold-search wins on mined ground-truth fixtures
(deterministic recall, no LLM), both lifting at @1/@3/@8 (not
coarse-k artifacts):
honorific (Mt/St/Dr <-> Mount/Saint/Doctor): recall@1 45% -> 75%
(+30pp), @8 62% -> 85%, misses 15 -> 6
brit (British <-> American spelling): recall@1 50% -> 70%
(+20pp), @8 70% -> 85%, misses 12 -> 6
Both _*_fold_variants are additive+symmetric, strict closed sets
(no English-word collision), no-op outside their class (verified
independent: brit no-ops on honorific titles & vice versa), unioned
into _title_query_tokens beside hyphen(#000007)/numeral/accent.
Full suite 2488 passed, 0 regressions (hot-path); real-path tests
(FakeSource->ingest->query()->real _Hit).
Fold-search FINAL across the survey backlog, ranked by MEASURED @1
headroom (not prevalence — the instrument's job):
SHIPPED: numeral (a3ac653) accent (b573c59) honorific brit (here)
NO-BUILD: hyphen — existing #000007 already delivers 90%@1
(the measure-the-unmeasured-thing check pays off)
NO-BUILD: amp — 82%@1 with no fold (prevalence-overranked;
instrument killed it cheaply, like digit-ordinal pre-build)
Net: 4 deterministic retrieval wins + a reusable mined-recall
instrument + the discipline codified in CLAUDE.md, from a goal that
4 prior hypotheses died on because the bench couldn't measure them.
Second MEASURED fold-search win, and the instrument correcting my own
premature call. accent-fold ON vs OFF on the mined accent fixture:
recall@1 55% -> 85% (+30pp), rank-1 22/40 -> 34/40. recall@8 was
flat (95->98) — a too-lenient k nearly got a real lever wrongly
reverted; @1/@3 is the resolution that drives primary-source
selection. _accent_fold_variants: ASCII-fold then re-tokenise so a
diacritic title ("Béla Bartók", which _TITLE_TOKEN_RE otherwise
fragments to junk) matches the ASCII form a user types. Additive+
symmetric, no-op on pure-ASCII (zero effect on non-accent
queries/titles), mirrors _hyphen_fold_variants (#000007).
Also fixes a defect I shipped in a3ac653: an orphaned duplicate
body left as dead code after `return base` in _title_query_tokens
(unreachable — numeral-fold behaviour/measurement were valid — but
cruft; removed).
Fold-search factory, fanned out across the full survey backlog
(deterministic recall, no LLM, parallel — serial-by-caution was
halting in disguise):
- recall_at_k.py: returns rank -> recall@1/@3/@k from one retrieval
(verified offline). A coarse k hides rank-only lifts.
- mine_questions.py: numeral/accent/hyphen/honorific/amp/brit
ground-truth classes; fixtures committed.
- Measured @1 headroom verdicts: accent SHIP (this commit);
honorific 45% / brit 50% = real headroom (build next); hyphen
90% = existing #000007 already delivers, NOTHING to build (the
measure-the-unmeasured-thing check pays off); amp 82% = no fold
needed (prevalence-overranked, instrument kills it cheaply).
CLAUDE.md bench-maxing: two measured lessons codified — report
recall@1/@3/@k (a lenient k hides rank lifts; prevalence != miss-
rate), and fan out independent measurements (serial-by-caution is
halting). Full suite 2488 passed, 0 regressions (accent-fold is
hot-path in _title_query_tokens); real-path test (FakeSource->
ingest->query()->real _Hit).
The first MEASURED, above-noise retrieval win this thread. The 75-q
n=3 audit_mode bench couldn't resolve any single lever (every failure
class <=3-5 q, sub the 5pp floor — four hypotheses died there). Fix
the instrument, not just the lever:
- bench/mine_questions.py + bench/recall_at_k.py: mine questions from
corpus titles (ground-truth target known by construction), grade by
deterministic retrieval recall@k via `query --dry-run` — no LLM, no
verifier, no n=3 noise, scalable to the 22K-deep numeral pool. The
curated qa_questions.txt stays the separate verifier-honesty/trap
gate; mined fixtures measure the answerable long tail per class.
- _numeral_fold_variants in query.py: ordinal-word ("Alexander the
second") <-> multi-char Roman ("Alexander II"), additive+symmetric,
unioned into _title_query_tokens exactly like _hyphen_fold_variants
(#000007). Strict 2..40 Roman set → no English-word collision;
single-char Romans (I/V/X) intentionally out of scope (universal
len>1 token filter — stated before building, ~4 of 10 residual
misses).
Measured on the mined numeral fixture: recall@8 22/40 (55%) -> 30/40
(75%), +20pp; 20 hits now rank-1. Discipline applied end to end:
measured-first, mirrored precedent, full-suite regression run (2482
passed, 0 regressions — numeral-fold is hot-path in
_title_query_tokens), real-path test (FakeSource->ingest->query()->
real _Hit, not a hand-built object), measured-after on a noise-free
instrument. The ~6 multi-char residual misses are a different
downstream cause the instrument now exposes for future iteration.
Three workstreams, full suite 2482 passed, experimental paths default-OFF.
#000055 — Windows quickstart without make
tasks.py (pure-stdlib runner) + make.bat shim + .gitattributes;
README Windows section rewritten. Quickstart needs only Python
3.10+ (no make/bzip2/curl/bash). Mirrors the Makefile quickstart
subset; drift-pinned by tests/test_tasks_runner.py.
#000001 §7 Phase 0 — deterministic cross-language guard
arborist/qa/crosslang.py: non-English signal (¿/¡/non-ASCII) + an
es function-word stoppack. Fail-closed to UNGROUNDED before
retrieval/LLM (mirrors the quantifier reject-DAG) when no content
token survives, else strips es stopwords from the retrieval query
only. English path byte-identical by construction. Default OFF
(crosslang_guard_enabled). Measured: the anarcocapitalismo field
case 10.4s -> 1.6s.
#000056 — Operation Sandwich (cross-language grounding)
arborist/qa/mt/: opus-mt es/fr/ru<->en, lazy per-pair memoised
singleton (fixes the 88%-engine-error concurrency defect),
manifest-pinned, [mt] extra; entity_mask wrapper. Sandwich =
translate query in (retrieval + LLM prompt) -> English answer ->
UNTOUCHED verifier grounds English-vs-English -> translate the
verified answer out as display-only (banner-labelled, zero
grounding). question_hash + verifier_policy_hash invariant; MT
engine identity binds into RetrievalPlan, not governance. CLI
--crosslang-translate / make XLANG_MT=1. Default OFF; entity_mask
default OFF (measured net-negative at bench scale). Fan-out bench
(bench/*.py): Spanish ~0% -> 71% grounded vs the real no-support
baseline; the round-trip predictor was tried and refuted; the
entity-mask lever failed at scale (corpus-title anchoring untried).
CLAUDE.md: cross-language bright-line convention + module map.
Pre-existing modified diagram files are intentionally excluded.
Five rule tightenings, each targeting a specific bench-qa STRICT
false-positive shape (the xfail regressions from the previous commit):
1. claim-lattice bracket-artifact skip — sentences matching
`\[E\d+\s*\|` (pointer markup) or `..."\]` (truncation tail)
are no longer parsed as natural-language assertions; `Such a
thesis was..."]` no longer fires vacuous.
2. Circular-rule differentia cap — circular now requires the
predicate to be (a) entirely vacuous OR (b) leads with a subject
token AND has ≤ 2 non-subject non-filler differentia tokens.
"Michael Jordan's Restaurant was a restaurant in Chicago,
Illinois, named after the basketball player Michael Jordan"
has 6 differentia → no longer fires. Pre-existing positive test
"The entity is the entity referring to the State of Israel"
has 2 differentia (state, israel) → still fires (under threshold).
3. phrase_component_reuse translation-chain exception — when the
predicate ALSO contains a quoted phrase (translation /
definition / etymology context), token reuse with the subject's
quoted phrase is legitimate, not circular. "The name 'Rosebud
River' is a translation … 'the river of the roses'" no longer
fires.
4. Vacuous-rule short-acronym escape — `_coherence_predicate_has_short_acronym_content`
recognizes title-cased element-symbols (Au, Fe, Pb…) and all-caps
2-5-char acronyms (DNA, FBI, USB, NASA…) as content even though
they're below the ≥3-char content-token filter. "The chemical
symbol for gold is Au." no longer fires; "Iron has the chemical
symbol Fe." also clean; tautology "DNA stands for DNA." still
correctly flagged circular.
5. (the 'term <X>' idiom xfail stays xfail — borderline, no clean
lexical fix.)
5 xfail → passing (the regression coverage is now executable proof
of fix); 1 xfail remains. Pooled bench-qa STRICT FP rate test ceiling
tightened from 7% to 2%. All 7 pre-existing positive coherence tests
still fire correctly. 110 total tests pass; 1 xfailed; no regressions
on doc-counts / nli / relevance.
§3.1 diagnose_coherence (now 19 tests, +10 from the parallel session's 9):
- 3 more positive shapes (multi-sentence vacuous, named-entity circular,
grammar-term phrase_component_reuse).
- 5 xfail regression tests for SHAPES THAT FALSE-FIRE on real bench-qa
STRICT data (44/808 = 5.4% FP rate measured on the pooled n=1+3+5
STRICT answers). Each xfail names the exact shape + why it should
ideally be 'ok' + which rule needs tightening:
* 'The chemical symbol for gold is Au.' → vacuous (short predicate)
* 'Michael Jordan's Restaurant was a restaurant ... named after
Michael Jordan.' → circular (named-after re-use)
* 'The Western X was the western half of the X' → circular
* 'The name <Phrase> is a translation ... of the <derivative>' →
phrase_component_reuse (translation/etymology)
* claim-lattice [E1 | … …"] tails → vacuous (truncated bracket
fragment)
* 'The term <X>' → phrase_component_reuse (idiomatic English)
- 1 load-bearing real-traffic test: FP rate on 808-cell pooled STRICT
must stay ≤ 7% (current 5.4%) — fires loud if a future change
regresses it. Skips on fresh-checkout (bench/qa_results/ gitignored).
§3.2 ShadowRelevance (now 20 tests, +7 from the round-1 scaffold):
- Manifest tests for round-2 primary (bge-reranker-large), the size
spectrum coverage (50-560MB), the candidate-bench findings block
(biggest-within-family / not-across-families / deeper-not-better /
capacity-floor).
- Pair-kind distinction (question_answer vs claim_source recorded
separately for downstream telemetry / governance hashing).
- Batch-order preservation (_score_batch must return scores in input
order — load-bearing for downstream zip-back).
- Empty-input handling (Q empty, D empty, whitespace-only).
- Zionist-entity discriminator sanity (on-topic > off-topic logit).
- demote_below_score-stays-null invariant (the §7 #18→#27 discipline:
no hardcoded threshold; must come from a real-traffic shadow sweep).
Total: 101 passed + 6 xfailed (5 §3.1 regressions documented + 1 from
parallel session). The 5 xfails are the bench-maxing receipts — they
document EXACTLY which shapes §3.1 false-fires on, with the rule that
needs tightening named in each reason.
arborist/qa/relevance/ — manifest pins cross-encoder/ms-marco-MiniLM-L-6-v2
(~80MB, Apache) as primary; alternates: L-12, BAAI/bge-reranker-base,
ms-marco-electra-base. demote_below_score=null on purpose — the
#000049 §7 #18→#27 discipline (proved 6× that clean-eval thresholds
don't transfer to bench-qa data) requires the threshold to be set by a
shadow sweep against pooled real STRICT, not by a literature number.
ShadowRelevance class mirrors ShadowNLI (lazy [nli]-extra import, cuda
auto-detect via ARBORIST_RELEVANCE_DEVICE or ARBORIST_NLI_DEVICE,
batched _score_batch, graceful degrade-to-available=False). Two surface
methods: check_question_answer (deflection / Q-A drift) and
check_claim_source (topic-collision mis-cite). 13 tests.
Sanity on the motivating field case (Zionist entity): ON-topic +9.96
vs OFF-topic -9.04 → 18-pt margin. Mona Lisa Q→A deflection: on +10.45
vs deflect +3.56 → ~7-pt margin. The model CLEANLY discriminates the
failure modes #000052 §1 named. It does NOT catch the
recombination-where-the-different-entity-clause-also-mentions-the-target
case (Kilimanjaro/Mount Kenya) — and that's the right architectural
split: aboutness (#000052 §3.2) and entailment (#000049 NLI) are
orthogonal axes; the Kilimanjaro recombination case needs the semantic
candidate selector (#000050/#000051 vec hybrid).
Remaining: build candidate-bench eval (~20-30 deflection + mis-cite
fixtures), shadow-sweep θ over pooled bench-qa STRICT (expect another
walk-back per the #000049 lesson), recall-side realism check, then
fox+dav1d sign-off. Still SHADOW; production verifier unchanged.
`arborist/concepts/extract.py:acronym_parens_synonym` — new
corpus-agnostic extractor. Scans each doc's lead chunk (first 4000
chars) for `<Multi-Word Phrase> (ACRO)` where the all-caps acronym's
letters strictly match the content-word initials of the phrase, in
order, after function-word filtering. Emits bidirectional synonym
edges between the lowercased acronym and each ≥3-char content token
of the phrase, evidence_kind="acronym_parens", anchored to that doc's
document_root. Idempotent like link_reciprocity_synonym.
Why this complements link_reciprocity: Wikipedia represents
abbreviation→expansion as a one-way *redirect* (CPU →
Central processing unit), which the ingest does not record as an
edge — so the existing reciprocal-link extractor never learned the
relation. The relation IS in body text by near-universal convention
("Central processing unit (CPU) is..."), which this extractor reads.
Corpus-agnostic: HTML, blogs, textbooks benefit equally.
Conservative: strict 1:1 acronym-to-atom match (rejects HTTP-shape,
where letters land mid-word), function words filtered, repeated
definitions deduped per doc, ≥3-char target floor. 8 new tests
covering CPU bidirectional emit, RAM idempotency, FBI function-word
filter, HTTP length-mismatch reject, XYZ initial-mismatch reject,
ROM hyphenated-word handling, per-doc dedupe, registry presence.
Retrieval-side only — synonym edges reshape FTS5 candidate selection
via synonym_expand at query time, never enter audit_mode / cache_key
/ audit_event_hash. No governance hash bump, no cache invalidation.
Closes#000050 §2a's CPU/GPU abbreviation rows *upstream* of vec;
the Orwell-shape conceptual-allusion row remains the genuine #000050
justification. Operational follow-up (not code): run on each shard
via `arborist concepts derive --extractor acronym_parens` (CLI
surface itself is aspirational in docstrings; extractors are called
programmatically today). Next ID 000054 -> 000055.
`arborist.qa.evidence._content_tokens` dropped every token under 4
chars, so a short all-caps acronym (CPU, GPU, DNA, FBI, USB…) never
registered as a content token — which defeated Rule 8
(_claim_title_overlap / TITLE_MISMATCH), the subject-tokens-absent
check (Rule 9), the bare-name-claim guard, and spotlight-excerpt token
selection whenever a question/claim's topic IS an acronym. The field
case: `what is a CPU?` cited to the "CPU design" article tripped
TITLE_MISMATCH even though claim and title both contain "CPU".
Fix: keep a token if it's an all-caps 2-3-char alpha run in the source
text; everything else unchanged. The change only ever ADDS tokens, so
TITLE_MISMATCH / SUBJECT_TOKENS_ABSENT / BARE_NAME_CLAIM can only stop
firing, never start — monotone toward fewer spurious demotes; no
STRICT→non-STRICT transition is possible from it.
Versioned: `content_token_rules: "v2-acronym-aware"` added to
runner.DEFAULT_POLICY + query.DEFAULT_QUERY_POLICY +
keys._VERIFIER_POLICY_FIELDS → folds into verifier_policy_hash, prior
cache records orphan on lookup (by design; same discipline as
base_version / hyphen_fold_v1). Does NOT touch the retrieval
abbreviation→expansion gap (CPU→Central processing unit — #000050 vec
hybrid / concepts/ synonym edges; the root cause of the satellite
retrieval). 8 new tests; full suite green (2502); bench-qa-smoke clean.
Next ID 000053 -> 000054.
Speedup (§3 plan): ShadowNLI._nli_batch batches forwards
(ARBORIST_NLI_BATCH=64); device auto-detect (ARBORIST_NLI_DEVICE, else
cuda-if-available); auto-prefer an ONNX export — bench/scripts/export_nli_onnx.py
/ make export-nli-onnx exports + int8-dynamic-quantizes the pinned
checkpoint into ~/.arborist/models/nli/<ver>/onnx/ (operator state, NOT
committed), _ensure_loaded loads model_quantized.onnx via
optimum.onnxruntime (backend onnx-int8), falls back to torch silently.
torch-cpu-batch1 ~120ms/pair → onnx-int8-cpu-batched ~32ms/pair (~4x);
seconds on a 4090. optimum[onnxruntime] added to the [nli] extra; 24
tests.
Gate-item-4 verdict at proper n: ARBORIST_NLI_SHADOW=1 make bench-qa
BENCH_QA_N=1 → 223 cells (89 STRICT / 90 HYBRID / 44 UNGROUNDED; also
surfaced + fixed a lone-surrogate bug). Shadow sweep over those: NLI-as-
runtime-veto on STRICT has ~26% FP at θc 0.5, ~8% at θc 0.90, ~0% only
at θc 0.99 — and θc 0.99 gives up most recombination recall (hard
synthetic recombinations bottom out ~0.76). FAILS the §7 #12 gate on
this design. Only untried path that might pass: a Phase-3 runtime hook
running NLI on the verifier's actual matched clauses (1-3), not
top-6-by-overlap. Until then: runtime NLI demotion stays off; the 2
fixtures stay permanent boundary markers; θc stays 0.5. Production
verifier unchanged; falsification-hard stays 10/12.
Per-sentence shape check (no model) emitting kind ∈
{phrase_component_reuse, circular, vacuous, ok, empty}:
- circular: subject content-tokens ⊆ predicate's and the predicate
leads with a subject token ("Water is water").
- phrase_component_reuse: subject quotes a phrase, predicate reuses
one of that phrase's own tokens as a bare "the/a/an <token>"
referent — the 2026-05-12 field case ("the phrase 'Zionist entity'
is used as the entity"), a token collision the verifier +
deflection + title-relevance all pass and NLI returns neutral on.
Copulas inside a quoted span are skipped so 'war is peace' doesn't
break the subject/predicate split.
- vacuous: predicate is only placeholder hypernyms + filler ("X is
a thing").
Conservative — no full token-salad parsing; legit definitions pass ok.
Surfaced in inspect_cache_key + the `arborist inspect` human view
(· incoherent: <kind>). Advisory only — never writes providence_cache
/ audit_events / run_dag_root; demote-only verifier hook deliberately
not wired. 9 tests; full suite green (2500 passed).
candidate_clauses() — NLI now runs only on the top-N source clauses by
content-token overlap with the answer claim (max_candidate_clauses=6),
not the whole context; records n_candidate_clauses / best_clause_overlap
/ recombination_risk. Synthetic sweep unchanged (28/28 recombination,
0/26 legit FP, mean 1.45 candidate clauses/record). Real-traffic smoke
re-run: STRICT would-demote 30% → 20%, overall 47% → 33% — better, not
fixed; recombination-risk split doesn't separate either. Residual STRICT
false-contras at ~0.83-0.92 → θc would need ≈ 0.90 (vs the clean-set
0.5); at θc=0.90 the data in hand gives 27/28 synthetic recall, 0/26
legit FP, 0/10 smoke STRICT FP — but n=10 is too small to set on.
Next: a fuller ARBORIST_NLI_SHADOW=1 bench-qa run → sweep θc on hundreds
of STRICT cells → confirm → set it. θc stays 0.5; runtime NLI demotion
stays off. Production verifier unchanged; falsification-hard stays 10/12.
arborist/qa/nli/ — SHADOW ONLY (never an audit_mode input; manifest not
yet in governance_policy_hash per §7 #2). manifest.json pins
cross-encoder/nli-MiniLM2-L6-H768 @ a fixed HF revision + the
bench-validated θc 0.5/θe 0.9 + 2 alternates + the Phase-3 TODO;
shadow.py = ShadowNLI/shadow_check (lazy transformers+torch behind a new
[nli] extra, clauses() segmenter, the §7 #5 clause-level Demote()
decision, degrades to available=False when [nli] absent);
bench/scripts/nli_shadow_sweep.py + make bootstrap-nli / bench-nli-shadow
(the gate-item-4 instrument); 16 tests.
First sweep (116 records — 5f-falsification packs + the arborist-nli-bench
eval sets): 28/28 synth recombination demoted, 0/26 FP on legit summaries,
0/9 fires on already-STRICT_SPAN records, 25/50 on UNGROUNDED (the
contradiction half; quiet on non-sequiturs). Gate items 1/2/3/5/6 clear
on available data; item 4 — shadow FP rate on a real live-bench-qa
sample — remains the open measurement. Production verifier unchanged;
falsification-hard stays 10/12.
The cache lookup in ask()/query()/canonical-persist runs outside the
write transaction, so two concurrent callers on the same cache_key can
both miss and both reach the providence_cache INSERT — the loser raised
`UNIQUE constraint failed: providence_cache.cache_key` and ask() crashed
(MOAD-0005 / TOCTOU; sibling of the af870bb append_audit fix). All three
write sites (qa/runner.py, qa/query.py, qa/canonical_cache.py) now end in
`ON CONFLICT(cache_key) DO NOTHING`, so the loser no-ops (its answer is
equivalent — same question/model/policy ⇒ same cache_key; canonical
answers are deterministic). With busy_timeout on every connection
(af870bb) the loser waits on the writer's lock then no-ops.
test_qa.py::test_concurrent_ask_same_cache_key_no_unique_crash — 6
threads run ask() on the same question concurrently; must not raise;
exactly one cache row lands. Verified it fails without the fix (5 of 6
threads raise IntegrityError).
Closes the 8 mis-segments #000046 left in formulate-hard-v1.jsonl.
The parser was line/bullet-only — one line ⇒ one claim — so a line
that crammed several pointered claims onto one row ("Water is wet
[E1]; fire is hot [E2]", "X happened [E1]. Y followed [E2]") became
one monolithic claim with all the pointers, and a wrapped bullet
became two.
arborist/qa/parse_claims.py: _SEGMENT_SEP_RE splits a line on ';',
sentence boundaries ('. '/'! '/'? ' then a Capital), spaced dashes
(' - '/' — '/' – '), ' and '/' or '/' because '/' although '/' since
'/' while ', inline '(N)' enumeration markers, and commas — with
'(?![^\[]*\])' so a comma inside a [E1, E2] bracket never splits it.
_segment_line keeps the split ONLY IF every resulting non-empty
segment is a well-pointered claim — a legit single claim ("The cat
is black and white [E1].", "The cast: A, B, C [E1].") is never
broken because splitting it would manufacture pointer-less prose
fragments → guard rejects; a leading colon-terminated header with no
pointer ("Two facts:", "Key points:") is allowed and dropped. Plus a
wrapped-bullet join: a continuation line (leading whitespace then a
lowercase letter, no bullet glyph) folds its text + pointers into the
previous claim.
Effect: formulate-hard rate 4/12 → 12/12 (the pack is now at ceiling
— a harder Formulate tier would re-open below-ceiling headroom; a
#000046 follow-up). Remaining #000048 headroom: 2 STRICT_PARAPHRASE
recombinations in falsification-hard (Mercury, Einstein — step 2.2).
Bench gate: make bench-qa (n=3 × 75 × 3 = 675 cells; parse_pointer_claims
feeds the 450 claim_lattice_pointer + claim_lattice cells) after
(bench/qa_results/2026-05-11T20-26-37Z) vs the pre-step-2.4 baseline
(...T17-12-41Z = HEAD's parse_claims.py). STRICT-rate quote 0.54→0.55,
pointer 0.22→0.22, lattice 0.43→0.45 — all within the 5-pp noise
floor. Per-row diff: the segmenter changed the parsed-claim count on
the SAME answer text for 7 of the 450 lattice cells (0 in
claim_lattice, 7 in claim_lattice_pointer); of those, 2 caused an
audit_mode change — both correct: a wrap-join recovered an answer's
intended structure (4 claims, 2 pointer-less wrap-fragments → HYBRID)
into 2 well-pointered claims → STRICT; and a crammed-one-line blob (1
monolithic claim, all pointers → STRICT) split into 8 claims, some
not individually verifying → HYBRID (the honest verdict — false-
positive STRICT was the corruption). Every other lattice/quote delta
is LLM re-answer variance. No regression — the segmenter's only
visible effects on real traffic are honest improvements. Summarized
in qa-modes-bench.md Addendum 7 + ticket-000048 §5 step 2.4.
Tests: 8 new in test_claim_lattice.py (semicolon/sentence/conjunction
splits; pointerless-fragment + cast-list guards; leading-colon-header
drop; wrapped-bullet join; pointer-order/multi-pointer); existing
parse_pointer_claims tests pass untouched; test_5f_formulate_hard_pack
re-pinned 4/12 → 12/12. make test 2358 passed, 28 skipped.
#000048 → steps 2.1 + 2.4 landed; #000046 / #000012 §8 / TICKETS.md /
Makefile / fixture _meta + notes updated.
Closes the 4 HYBRID_ENTITY over-grounds #000046 left in
falsification-hard-v1.jsonl. The entity strategy grants HYBRID when a
multi-word proper noun matches the source — but "Insulin was
discovered by Alexander Fleming" against "Penicillin was discovered by
Alexander Fleming" matches on the shared "Alexander Fleming" while the
swapped subject "Insulin" (the falsehood) is ignored.
arborist/qa/verify.py: _entity_salient_disagrees(answer_text, norm_ctx)
flags a >4-char Capitalized content token (stopword-filtered) or a
digit-number in the answer absent from the source.
_is_single_sentence(text) — no internal '. '/'! '/'? ' break. Gated in
verify_quotes' entity branch (proximity policy) in the weakest-grounding
slot only: not cluster AND len(verified) <= 1 AND _is_single_sentence
AND _entity_salient_disagrees → UNGROUNDED. The narrow caller-gate is
what keeps a structured multi-claim summary untouched — the Matrix cast
list (many entities, a tight cluster) and the TMNT answer (a numbered
list with parenthetical nicknames the source omits): model-added
accurate detail in a real summary isn't a contradiction, only the
single-sentence-one-weak-match shape is. The Matrix/TMNT/hybrid
entity-path regression tests still pass, pinned untouched.
Effect: falsification-hard rate 6/12 → 10/12 = 0.833 (Insulin / Berlin
/ 1889 / Pacific now correctly UNGROUNDED). The 2 live-pack fixtures it
newly demotes — 5f-fal-live-003 (the exact gap #000046 built its hard
pack around) and 5f-fal-live-028 — had expected_reason updated
HYBRID_ENTITY → UNGROUNDED (the live pack records what verify_quotes
actually does). Remaining hard-pack headroom: 2 STRICT_PARAPHRASE
recombinations (Mercury, Einstein — step 2.2) + 8 Formulate
mis-segments (step 2.4).
Bench gate: make bench-qa (n=3 × 75 × 3 = 675 cells) after
(bench/qa_results/2026-05-11T17-12-41Z) vs the pre-step-2.1 baseline
(...T14-19-51Z = HEAD's verify.py). STRICT-rate quote 0.50→0.54,
pointer 0.25→0.22, lattice 0.45→0.43 — all within the 5-pp noise
floor. Per-row diff (675 common cells, 30 quote-mode rows changed
audit_mode): 0 quote-mode rows demoted to UNGROUNDED from the entity
path — the gate fired on 0 legitimate QA answers in the whole bench.
Every transition was LLM re-answer variance (verifier quote→quote with
the verdict flipping); pointer/lattice deltas are noise too (the gate
is in verify_quotes / quote mode, not the claim-lattice verifier). No
regression — the gate is provably narrow on real traffic. Summarized in
qa-modes-bench.md Addendum 6 + ticket-000048 §5 step 2.1.
Tests: 4 new in test_verify.py (_is_single_sentence helper,
_entity_salient_disagrees helper, swapped-subject → UNGROUNDED,
gate-narrow-on-multi-claim); test_5f_falsification_hard_pack_below_ceiling
re-pinned 6/12 → 10/12; test_fork_score_positive_gamma_5f_... updated
(positive γ·Δ5f on the real lift — possibly MARGINAL given the ÷5
dilution; ACCEPT via a degraded-parent sub-scenario).
make test 2343 passed, 28 skipped.
#000048 → step 2.1 landed; #000046 / #000012 §8 / TICKETS.md /
Makefile / fixture _meta + notes / baseline JSON updated.
Wire vector quantization (the §3.1 production knob): arborist embed
--quant int8 [--rebuild]. The chunk_vecs vec0 column becomes int8[384]
vs float[384] per quant; the quant folds into VEC_BACKEND_VERSION
(...-384int8-... / ...-384float32-...) and vec_meta records it per
shard. Switching quant on an existing chunk_vecs requires --rebuild
(the vec0 element type can't be altered in place — embed_documents
raises ValueError telling you to --rebuild).
int8 serialization: scale each bge component by 127 (theoretical
[-1,1] range), clamp to [-127,127], round, serialize_int8. The same
scaling on the query vector → distances comparable; cosine is
scale-invariant so the uniform x127 cancels in the ranking.
sqlite-vec v0.1.9 quirk worked around: a bare blob inserted into a
vec0 column is interpreted as float32 regardless of the column's
declared type — int8 vectors MUST be wrapped in vec_int8(...). So
the INSERT and the MATCH now wrap the blob in vec_f32(?) (float32)
or vec_int8(?) (int8) — constructor name from a fixed dict, no
injection surface. (Discovered the hard way: a bare int8 blob into
an int8[384] column → "expected int8, but a float32 vector was
provided".)
VecBackend reads the quant from the existing chunk_vecs schema (or
defaults to float32) so search uses the matching wrapper. New module
exports: QUANTS, EMBED_QUANT, vec_backend_version(quant), existing_quant.
int8 head-to-head on crawl_appliedcombinatorics_org.db (168 chunks):
- storage: float32 1,597,440 B -> int8 417,792 B = 3.8x smaller
(~4x at corpus scale where the 1024-vector blocks fill; the
~28 KB of vec0 metadata doesn't quarter, hence 3.8 not 4.0).
- recall vs the float32 baseline:
Q "how many ways to choose k things from n":
identical top-5 (Combinations, Permutations, Exercises,
Derangements, Graph Coloring).
Q "pigeonhole principle counting":
identical top-2 (Graph Coloring, Exercises); ranks 3-4 swap
Derangements <-> Permutations at Δdistance 0.002 — sub-noise.
- embed speed unchanged (~3.9 chunks/s — model-load-dominated).
Conclusion: int8 is the obvious production config (§3.1's +6%-tax
recommendation confirmed empirically). v1 default stays float32 for
max fidelity; flipping the default to int8 is a fox call.
CLI (arborist/cli.py): arborist embed --quant {float32,int8}; output
JSON gains "quant"; embed_documents ValueError → exit 2 with the
"--rebuild" hint.
tests/test_search_vec.py (9 -> 16): test_int8_quant_roundtrips
(int8[384] schema, vec_meta version, search round-trip, quant
inferred by VecBackend), test_quant_mismatch_requires_rebuild,
test_invalid_quant_rejected.
#000039 status updated. Full suite: 2343 passed, 28 skipped.
(Unrelated parallel-clone work in the tree — Makefile, arborist/qa/
verify.py, bench/fixtures/5f/*, tests/test_bench_batteries.py,
tests/test_verify.py — is #000046's hard-fixture tier, not touched.)
Closes the harder-fixture-tier ticket: a real verify_quotes
tightening lifts the falsification-hard rate 4/12 → 6/12, bench-gated,
ForkScore's bench-Δ goes positive on it — the loop is closed
end-to-end.
arborist/qa/verify.py: _numeric_signature(text) extracts comma-
stripped digit-runs ('8,849' and '8849' collapse; '300' stays
distinct from '300000' ← '300,000'). _check_each_with_paraphrase
gains a gate: a span that token-covers the source ≥ paraphrase_coverage
but asserts a digit-number the source lacks (modulo thousands-comma)
is no longer paraphrase-grounded — it goes to unverified. Catches the
near-miss the lexical coverage check is blind to ("Water boils at 50
degrees" against a source saying 100 token-covers 100% because
'50'/'100' aren't >4-char content tokens). Narrow by construction:
fires only on the paraphrase fallback (verbatim/span/entity/claim-
lattice paths untouched), only on a digit-number. A rounding-
paraphrase demoting here is the honest verdict — it isn't a verbatim
grounding.
Hard pack: lifts 5f-fal-hard-004 (50 vs 100) and -007 (300 vs
300,000) to UNGROUNDED → falsification-hard rate 4/12 → 6/12 = 0.5.
The other 6 over-grounds (4 HYBRID_ENTITY + 2 recombined-no-number
STRICT_PARAPHRASE) and the Formulate hard pack are unaffected —
headroom for a bigger order/dependency-aware verifier upgrade, an
optional follow-up, not a #000046 blocker.
Bench gate: make bench-qa (n=3 × 75 questions × 3 modes = 675 cells)
before / after. STRICT-rate quote 0.53→0.50, pointer 0.23→0.25,
lattice 0.44→0.45 — all within the 5-pp noise floor. Per-row diff
(675 common cells, 74 changed audit_mode): the only clearly
gate-attributable QA shift was the fictional "our cold fusion
breakthrough" year-claim demoting STRICT→HYBRID (×3 samples) — a
correct demotion; every other transition was quote→quote /
claim_lattice→claim_lattice LLM re-answer variance. No regression on
legit answers. Artifacts: bench/qa_results/2026-05-11T13-42-38Z (before)
and ...T14-19-51Z (after) — gitignored; summarized in qa-modes-bench.md
Addendum 5 + ticket-000046 §5 Phase 3.
Worked example: fork_score on the real change — parent {5f/
falsification: 4/12} → child {5f/falsification: 6/12} → γ·Δ5f =
(1/6)/5 ≈ +0.033 > 0 (positive; a single improvement of this size is
MARGINAL by the ÷5 dilution, the test pins the full-lift-to-1.0 case
at ACCEPT).
Tests: 5 new in tests/test_verify.py (numeric_signature normalization
+ subset-matches-comma-variant + disagreement-rejected +
gate-is-narrow + number-present-still-verifies);
test_5f_falsification_hard_pack_below_ceiling re-pinned 4/12 → 6/12.
make test 2339 passed, 28 skipped.
#000046 → closed; #000012 §8 §4 + TICKETS.md row + falsification-hard
_meta / hard-004,007 notes + Makefile 8/12→6/12 comments updated.
(Makefile also carries an uncommitted chain-check-SQL improvement from
the concurrent session — NOT in this commit; staged only the
#000046-comment hunks.)
Fox: "i like both" — keep the lazy out-of-band pass as the default
AND add the eager opt-in. Plus the Phase-1 gap fix (incremental embed).
Key insight folded into the design (new ticket section 14): a chunk_id's
content is immutable in arborist — same content → same chunk_id;
different content → a NEW chunk_id (re-ingest makes a new doc_root +
new chunk_ids linked by supersedes; a chunker bump re-chunks → new
chunk_ids). So a chunk, once embedded, never needs re-embedding — the
ONLY re-embed trigger is the embedder changing (VEC_BACKEND_VERSION
bump). That makes the idempotency story clean.
arborist/search/vec.py — embed_documents() now:
- incremental=True (default): embed only chunk_ids NOT already in
chunk_vecs (chunk_id NOT IN (SELECT chunk_id FROM chunk_vecs)).
This is the after-ingest / cron / Prometheus-Sigma-sweep path —
it picks up exactly the newly-ingested chunks; re-running is a
cheap no-op once everything's embedded.
- incremental=False: re-embed every chunk with content (delete-then-
insert all) — the embedder-changed case.
- rebuild=True: DROP + recreate chunk_vecs first, then a full pass —
the clean VEC_BACKEND_VERSION-bump path (a search mid-rebuild never
mixes old- and new-model embeddings: the recreated table starts
empty and grows new-model as the pass runs). Implies non-incremental.
- Cold-evicted chunks (content NULL) still skipped; vec rows persist
and stay valid (content is identical on rehydrate).
CLI (arborist/cli.py):
- arborist embed --rebuild — the DROP+recreate+full-re-embed path
(default is incremental). Output JSON now reports "mode".
- arborist ingest --embed — eager opt-in: after the chunk+Merkle-
commit pass, incremental-embed this run's new chunks. Default
ingest does NOT embed. ingest output gains "chunks_embedded" when
--embed is set. Only surfaced when the [vec] extra is installed.
- Hoisted the _vec_ok check up to the top of build_parser so both
the ingest --embed flag and the search --backend / embed subcommand
can gate on it.
tests/test_search_vec.py (7 -> 9): test_embed_incremental_only_embeds
_new_chunks (second pass after a follow-up ingest embeds only the new
chunk; third pass is a no-op), test_embed_rebuild_re_embeds_all
(DROP+recreate+full pass; vec_meta still records the version).
Verified on crawl_appliedcombinatorics_org.db: incremental on an
already-embedded shard reports chunks_embedded=0 in ~1.8s; --rebuild
re-embeds all 168 in ~61s; semantic search after rebuild still returns
topically-correct hits ("pigeonhole principle counting" -> "AC Graph
Coloring" chunk containing "Generalized Pigeon Hole Principle").
Ticket section 14 added: the idempotency table (re-ingest / chunker
bump / cold eviction / embedder bump / superseded docs), the two
integration models (lazy default + eager opt-in; the lazy pass's
natural home is a Prometheus-Sigma unconscious-sweep task per #000037
section 3.1), the command matrix, concurrency notes, versioning.
Status line updated.
Full suite: 2339 passed, 28 skipped.
(Unrelated parallel-clone work in the working tree — Makefile,
arborist/qa/verify.py, bench/fixtures/5f/*, tests/test_bench_batteries.py,
tests/test_verify.py — is #000046's hard-fixture tier, not touched here.)
Extends the #000046 hard tier to the Formulate sub-battery.
bench/fixtures/5f/formulate-hard-v1.jsonl — 12 prose inputs that
arborist.qa.parse_claims.parse_pointer_claims SHOULD segment into a
particular claim lattice (recorded in expected_lattice). The parser
is line/bullet-based — one line ⇒ one claim, [E#] tokens attach to
it — so 8 of 12 it mis-segments: merges and-/semicolon-/dash-joined
or (1)(2)-enumerated multi-claim lines into one claim with all the
pointers, or splits a wrapped bullet into two. Those 8 fail at HEAD
on claim-count mismatch; the other 4 are well-formed bullet/numbered
lists / single claims the parser handles right. Rate at HEAD = 4/12
= 0.333, stable (parse_pointer_claims is deterministic). A
claim-lattice parser that does sentence/clause segmentation (split on
'. ', ';', subordinating conjunctions, inline enumerations) + joins
wrapped bullets lifts the rate toward 1.0 → positive γ·Δ5f for that
child fork.
make bench-5f-formulate-hard runs it (|| true past the runner's
nonzero-on-failures exit). Not in `make bench-5f` / `runner --all`.
tests/test_bench_batteries.py — test_5f_formulate_hard_pack_below_ceiling
(pins rate 4/12, source=live, the 8 fails are claim-count
mis-segments).
#000046 → "Phase 1 + Phase 2 landed"; two below-ceiling 5F subs now
exist (falsification, formulate). Closure still pending an actual
surface improvement (verify_quotes tightening — bench-gated — or
parse_pointer_claims segmentation) that lifts a rate. §5 + §6 +
TICKETS.md row updated.
(Makefile also carries an uncommitted chain-check-SQL improvement
from the concurrent #000039 session — NOT included in this commit;
staged only the bench-5f-formulate-hard hunk + the .PHONY line.)
qa.db carried a 2-way fork at seq 7724/7725 — two providence_burn events
whose prev_event_hash both pointed at row 7723's event_hash. Cause:
append_audit read the chain head and INSERTed as two separate autocommit
statements (the burn caller ran it OUTSIDE its transaction() block), so
two concurrent appenders both chained off the same head; seq AUTOINCREMENT
serialized the rows but not the hash linkage.
- append_audit wraps head-read + insert in its own BEGIN IMMEDIATE/COMMIT
when the connection isn't already in a transaction (folds in otherwise).
- connect() now sets busy_timeout=5000 on every connection (not just the
migration pass) so a peer mid-write makes us wait, not fail-fast — and
a fail-and-retry appender can't re-read a stale head.
- test_audit_chain_concurrency.py: 8 threads x 20 append_audit() on one
shard must yield a linear chain (one genesis, no forked parents);
+ the in-transaction fold-in / rollback behaviour. Verified the
concurrency test fails without the fix (8 genesis rows).
The #000025 §10.14 calibration showed _delta_5{s,t,f} mean over a
battery's 5 subs, so a single-sub gain weighs 1/5 of face value (the
5× dilution). #000047 ships the knob to pick the aggregation, default
unchanged.
WeightSet.delta_aggregator ∈ {"mean","max","sum"} (default "mean") —
a categorical field, validated in __post_init__ against
DELTA_AGGREGATORS; from_dict takes it as a string. Default unchanged →
ScoredFork output byte-identical → no fork_score.ESTIMATOR_VERSION
bump.
fork_score._aggregate(deltas, how): mean = arithmetic mean, max =
max(0.0, max_i Δ_i), sum = Σ Δ_i; empty → 0.0. _delta_5s/_delta_5t/
_delta_5f take an aggregator arg (default "mean"); the 5F efficiency
bonus is added after the aggregated base (aggregator-independent).
fork_score passes weights.delta_aggregator. The per-sub
HARD_REGRESSION_FLOOR flags are computed before aggregation, so a
single-sub regression still forces REJECT under max/sum. The chosen
aggregator is recorded in ScoredFork.weights["delta_aggregator"] (via
WeightSet.as_dict()); fork_score_branches traceability stays via the
opaque weights_id — no schema migration.
bench/scripts/fivef_threshold_calibration.py gained §5 — runs the
#000046 below-ceiling pack (5f/falsification at 0.333) and shows the
verdict / γ·Δ5f under each aggregator; bench/results/5f-threshold-
calibration-2026-05-11.md §5 is the captured record. Default stays
"mean" — the conservative, noise-robust, regression-symmetric choice
matching docs/bench-maxing.md's per-rate floor framing; v8 picks
max/sum per-deployment.
Tests: 8 new in tests/test_fork_score.py + 1 anchor in
tests/test_fivef_threshold_calibration.py; tests/test_weights.py
as_dict field-set test updated to include delta_aggregator;
test_fork_score.py AUTOCOUNT tags (#000012 §286, warrant-substrate-
cookbook.md ×2) bumped 23 → 31.
#000047 closed; #000012 §8 §3 + TICKETS.md row updated.
Full suite: 2330 passed, 28 skipped.
Implements the optional vec backend from the #000039 doc, with the
"obvious" v1 tuning, and demonstrates it on a real corpus shard.
arborist/search/vec.py (new):
- VecBackend(SearchBackend) — ANN over chunk_vecs, UNGROUNDED hits
(same as FTS5; vec changes recall, never warrant — embeddings are
soft signal, never in the proof path).
- chunk_vecs vec0 virtual table + vec_meta — sibling tables, additive,
don't touch chunks/documents/the audit chain.
- embed_documents() — batched ingest; delete-then-insert per chunk_id
(vec0 doesn't honor INSERT-OR-REPLACE — re-inserting an existing PK
is a hard UNIQUE error), so re-runs are idempotent and content-
changed → re-embed works. Skips cold-evicted chunks (content NULL).
- Pluggable Embedder callable; default = fastembed bge-small-en-v1.5
(~130 MB ONNX, downloads on first use). load_vec_extension(conn)
toggles enable_load_extension + sqlite_vec.load.
- v1 hyperparams (VEC_BACKEND_VERSION = vec-v1-bge-small-en-v1.5-
384float32-cosine-flat): model bge-small-en-v1.5, dim 384, quant
float32 (int8/binary = the production storage knob per §3.1, not
wired in v1), metric cosine (bge outputs L2-normalized, so cosine
ranking ≡ L2 ranking), ANN flat (vec0 default), top_k 20. These
five fold into governance_policy_hash in a later phase (§6).
CLI (arborist/cli.py):
- — populate chunk_vecs
for --db; prints progress + timing.
- — semantic ANN search (errors with
an install/embed hint if [vec] missing or chunk_vecs empty).
- Both surfaced only when sqlite_vec imports (mirrors the [html] /
selectolax pattern).
pyproject.toml: [vec] optional extra (sqlite-vec>=0.1.9, fastembed>=0.4);
added to [dev]. Note: sentence-transformers is the heavier "official"
embedder path §5 names; fastembed is the lightweight ONNX one.
tests/test_search_vec.py (7 tests, skip-if-no-[vec]): deterministic
stub embedder (hash → unit vector) so the suite exercises the
sqlite-vec plumbing — ext load, schema, ingest, KNN, JOIN, Hit shape,
limit, idempotent re-embed, --limit cap, empty/unpopulated — without
the heavy fastembed model. Semantic quality is demonstrated on a
shard, not unit-tested.
Demonstrated on ~/.arborist/shards/crawl_appliedcombinatorics_org.db:
168 chunks embedded in ~37 s (mostly model load); semantic queries
return topically-correct hits — "how many ways to choose k things
from n" → top hit "AC Combinations", "binomial coefficient counting"
→ "AC Introduction" (integer-solution counting) + "AC Combinatorial
Proofs". None of the query tokens need stem-match the chunk — the
semantic-allusion-gap closure the ticket promised. chain-check on
that shard reports 0 after embedding (chunk_vecs is a sibling table).
#000039 status flipped to "in progress · Phase 1 landed"; Phase 2
(RRF hybrid fusion in query.py) gated on a ≥5pp recall-lift
measurement with no STRICT-rate regression (§8).
(Unrelated: tests/test_weights.py::test_as_dict_returns_all_eleven_fields
fails in the working tree — that's a parallel-clone in-flight change
to arborist/substrate/weights.py + its test, not touched here.)
Closes the "everything is at rate 1.0 so fork_score's bench-Δ terms
are inert" gap the #000025 §10.14 calibration surfaced — at least on
the 5F/falsification axis.
bench/fixtures/5f/falsification-hard-v1.jsonl — 12 near-misses, each a
FALSE/unsupported claim whose correct verdict is UNGROUNDED (recorded
in expected_reason). 8 of 12 are over-grounded by
arborist.qa.verify.verify_quotes at HEAD — its paraphrase
token-coverage strategy returns STRICT_PARAPHRASE, its entity-proximity
strategy returns HYBRID_ENTITY, both matching on incidental overlap
(shared entities/numbers, the same key terms stated in the opposite
direction) — so those tasks fail by design; the other 4 the verifier
handles correctly. Rate at HEAD = 4/12 = 0.333, stable (verify_quotes
is pure-lexical / deterministic). Built around the pre-documented gap
5f-fal-live-003.
make bench-5f-falsification-hard runs the pack; make
bench-fork-baseline-hard pins it to
bench/results/baseline-falsification-hard.json. Both targets `|| true`
past the runner's nonzero-on-failures exit (8 fixtures fail by design;
the JSON is still written).
tests/test_bench_batteries.py — test_5f_falsification_hard_pack_below_ceiling
(pins rate 4/12, source=live, every fixture asserts UNGROUNDED, the 8
fails are over-grounds not abstentions) +
test_fork_score_positive_gamma_5f_on_hard_falsification_improvement
(the worked example: fork_score(parent={5f/falsification: 1/3},
child={5f/falsification: 1.0}) → gamma*Delta5f ≈ +0.133 > 0, verdict
ACCEPT, no regression flags — the bench Δ-rate carrying signal it
can't carry while every canonical pack is at ceiling).
NOT in `make bench-5f` / `make bench-5s5t5f` / `make
bench-fork-baseline` / `runner --all` — the hard pack is a separate,
deliberately-failing artifact pinned on its own.
#000046 flipped to "in progress · Phase 1 landed"; closure pending an
actual verify_quotes tightening that lifts the rate (a separate,
larger task). ticket-000012 §8 §4 + TICKETS.md row updated.
Full suite: 2314 passed, 28 skipped.
"One more iteration then close" (fox): added committed KAT-regeneration
scripts for both the T3 calculator and φ_PRG — the regen step was a
throwaway temp script before; now it's reproducible and the phi_prg
test's skipif reason ("run scripts/generate_phi_prg_kat.py") points at
a file that exists. Then closed#000036.
New scripts:
- scripts/generate_t3_bound_kat.py — regenerates
bench/fixtures/t3-bound/known-answer-tests.jsonl from a fixed 12-config
list (the §7 worked examples under max_envelope + non-default-C_B*
+ g=0 edge + explicit-b1_model pins for the other three models).
- scripts/generate_phi_prg_kat.py — regenerates
bench/fixtures/phi-prg/known-answer-tests.jsonl from a fixed 10-entry
list (placeholder/random seeds, one-bit-flip variants, block-boundary
dim_h=16/17, 4096 counter-rollover stress).
- Both verified to reproduce the committed fixture data lines byte-
for-byte (only the header comments changed, to reference the script).
Each docstring states: run after any algorithm change, then bump the
module version (CALCULATOR_VERSION / PHI_PRG_VERSION) so the fixture's
version field changes too.
Doc/test:
- test_t3_bound_calculator.py skipif reason now references the regen
script (matches the phi_prg test pattern).
- #000035 §3.3 + t3-bound.md §10.1 reference the regen scripts.
Closure (#000036):
- Status → closed · 2026-05-11 in the ticket file + TICKETS.md row.
Phase 1 + dav1d Tier-1/Tier-2 (Option B in v1) + KAT-regen tooling
all landed; all §5 acceptance criteria met; both dav1d closure
blockers cleared. Continuation: empirical C_B1/C_B2/C_B3 tightening
under #000043 (parks on v7 deployment data); landing the bound's
framing into a v7 plastic-training spec parks on that spec gaining
a deployment target; R2's architectural integrations (Merkle audit-
event commitment, SQD canonicalization, CTI clause-lattice, 5F
trigger, ForkScore security-risk) are separate tickets if wanted.
- t3-bound.md header flipped to "closed 2026-05-11".
Full suite: 2312 passed, 28 skipped.
v7's canonical integer byte-order was confirmed little-endian by
inspecting merkle-agi-dag_v7.txt §A1 — every to_bytes / astype in the
TLV encoding is little-endian (TLV length prefixes to_bytes(4,'little'),
enc_int to_bytes(8,'little'), quantized tensors '<i8'); no big-endian
anywhere. Per dav1d's 2026-05-11 review rule ("if v7 TLV canonical
integer encoding is little-endian, flip §3.4 to little-endian before
KAT freeze"), flip done — this is the -le variant.
Implementation (arborist/substrate/anchor_prg.py):
- PHI_PRG_VERSION → "phi-prg-v1-hmac-sha512-le" (still "v1";
the -le suffix records the endianness; future re-flip MUST bump).
- _expand: counter.to_bytes(4, 'big') → 'little'.
- _bytes_to_floats: int.from_bytes(..., 'big') → 'little' (the
uint32-word interpretation, for full consistency with v7).
- Module + function docstrings updated: little-endian throughout,
with the merkle-agi-dag_v7.txt §A1 verification note.
- Note: at counter=0 the bytes are identical regardless of
endianness, so 5 of the 10 KAT entries (dim_h ≤ 16, single block)
keep the same output_sha256; the 5 multi-block entries (dim_h 17/
32/64×3/4096) change.
KAT fixture (bench/fixtures/phi-prg/known-answer-tests.jsonl):
- Regenerated under the little-endian counter. Each entry now also
carries a "version" field (phi-prg-v1-hmac-sha512-le). Header
comment updated.
Tests (tests/test_anchor_prg.py, 30 → 31):
- test_module_exports_version_string: assert the -le suffix.
- test_bytes_to_floats_midpoint_maps_to_zero: 2^31 is b'\x00\x00\x00\x80'
in little-endian, not b'\x80\x00\x00\x00'.
- New test_bytes_to_floats_reads_little_endian: pins the byte-order
so an accidental re-flip is caught.
- test_phi_prg_first_block_matches_direct_hmac: uint32-word reads
little-endian (counter=0 bytes unchanged either way).
- test_phi_prg_known_answer_tests: assert kat['version'] == module
version when present.
Spec text (#000035 §3.4): folded the little-endian variant of
dav1d's §9.10 wording — counter_le32, uint32_le word reads, an
"all integers little-endian, matching v7 TLV §A1" preamble, and an
"Endianness — RESOLVED 2026-05-11" note replacing the open
big-vs-little question. soft-hash-channel-analysis.md §9.2/§11 +
#000035 status + TICKETS.md row updated. AUTOCOUNT for
test_anchor_prg.py bumped 30 → 31; PHI_PRG_VERSION refs in docs
bumped to -le.
Full suite: 2312 passed, 28 skipped.
Closes the three open Phase-1b items of #000025; every §10 closure
criterion is now met, so the ticket flips to closed.
§10.14 — ForkScore threshold-calibration handoff to #000012.
bench/scripts/fivef_threshold_calibration.py (make bench-5f-threshold-
calibration) runs the canonical 5S/5T/5F packs + the 5F live packs and
reports baseline rates, observability granularity (1/n), and fork_score
verdicts on the parent vs synthetic child perturbations →
bench/results/5f-threshold-calibration-2026-05-11.md. Findings written
into ticket-000012 §8: keep SIGNAL_FLOOR / HARD_REGRESSION_FLOOR at
0.05; the small 5S packs (syntax n=10, semantics n=8) are coarser than
the floors so any regression there trips hard-reject (intended zero-
tolerance); the 5x averaging dilution in _delta_*; ceiling saturation
(every pack at 1.0 -> delta-rate terms <= 0). No constant change
shipped. 6 tests in tests/test_fivef_threshold_calibration.py.
§10.13 — feedback latency / efficiency on real workload.
run_feedback_loop now computes feedback_latency (listed in §5.5 since
Phase 1a, never implemented) — wall-clock seconds to apply a live
chain against its temp shard, surfaced per-task
(feedback_latency_seconds) + battery (feedback_latency_mean_seconds,
feedback_live_task_count). For live chains feedback_efficiency's cost
denominator switched from len(chain) (count of requested ops) to the
persisted footprint _persisted_cost = audit-event rows the chain
actually wrote + their body bytes / 1e6. Embedded chains keep
len(chain) and report feedback_latency_seconds = None. Latency is a
wall-clock field (run-to-run variable, like BatteryResult.timestamp)
and is not a fork_score input. 3 tests in tests/test_bench_batteries.py.
§10.11 — real selfmodel finetuning chains.
bench/scripts/selfmodel_chain_snapshot.py (make bench-5f-selfmodel-
snapshot) appends one chained SelfModel snapshot per run to a
persistent shard (~/.arborist/shards/selfmodel-chain.db, override via
ARBORIST_SELFMODEL_CHAIN_DB) with one CapabilityClaim per sub-battery
(metric = "5S-syntax" etc., measured_value = that pack's rate,
eval_digest = the pack's fixture digest, threshold = SIGNAL_FLOOR).
snapshot() auto-parents, so each snapshot is a distinct root and the
lineage grows by one per run. run_finetuning gains a third dispatch
mode — shard-chain (gated on a task's selfmodel_shard key) — via
_chain_finetuning_measure: reads the two most-recent snapshots
(latest() = child, its parent_selfmodel_root = parent) and measures
improvement on target_capability between them. This is the real
lineage replacing Phase-1a's synthetic parent->child pairs; the
chained delta reflects genuine cross-run drift (0.0 today — the
embedded packs are at ceiling). Operator pack
bench/fixtures/5f/finetuning-shardchain-v1.jsonl (6 tasks) + make
bench-5f-finetuning-shardchain; not in `make bench-5f`, `make test`,
or a fresh checkout (a missing/too-short chain fails honestly). The
real chain shard was bootstrapped 2-deep on 2026-05-11; make
chain-check-shards reports 0 breaks on it (and all other shards).
10 tests in tests/test_selfmodel_chain.py.
Full suite: 2311 passed, 28 skipped.
`arborist analyze` crashed during orientation with
`sqlite3.OperationalError: table fork_score_branches already exists`:
check-sqlite_master-then-CREATE forward migrations let two connect()
calls racing a fresh shard both pass the probe and both issue CREATE.
- CREATE TABLE/INDEX inside the _migrate_* helpers now IF NOT EXISTS
(probe stays as the fast-path skip).
- _migrate_audit_mode's ALTER ADD COLUMN routes through
_add_column_if_missing (PRAGMA fast-path + duplicate-column catch).
- connect() raises busy_timeout=5000 for the one migration pass so a
racing connect() waits on a peer's _rebuild_* write txn.
- test_store_migration_concurrency.py: source-level "all CREATE is
IF NOT EXISTS" pin, busy_timeout assertion, 8-thread connect smoke.
- test_store_migration_memoization.py: _MigrationProbeCounter.NAMES
was missing two migrations; synced + de-hardcoded counts.
dav1d returned the §3.4 φ_PRG anchor-map review with a decision set:
HMAC-SHA-512 / 32-byte seed / uint32-be counter from 0 / SHALL-replace
all LOCKED; manifest field renamed; float-map prose corrected; two
ADDs (exhaustion guard + seed-independence rule); M1-policy separation.
Spec text (#000035 §3.4):
- Folded dav1d's full corrected §9.10 wording (RESPONSE_1 §1).
- Manifest field phi_prg_seed → anchor_prg_seed (purpose-scoped, not
implementation-scoped; phi_prg_seed kept only as a code-local alias;
phi_seed / m1_anchor_seed rejected as too vague / too policy-tied).
- Float map 2·(u32/2^32)−1 unchanged (KAT compat) but the prose now
says "uniform over a 2^32-point grid in [-1, 1) with negligible
finite-grid mean −2^−32" — NOT "unbiased". -1.0 reachable, +1.0
not. If exact zero-mean is ever needed → midpoint map x =
2·((u32+0.5)/2^32)−1 with a PHI_PRG_VERSION bump + new KATs, never
a silent change.
- Added dim_h ≤ 16·2^32 exhaustion guard (4-byte counter ceiling).
- Added seed-independence + single-purpose-seed requirements (seed
must be generated independently of model/data, not adversary-
selected, not reused for other PRG domains — no domain-separation
tag in v1).
- Added §9.10.1: M1 enablement is a mitigation-selection-policy
decision (e.g. skippable under #000034 NO_ALIGNMENT), not a §9.10
function-definition question; "MUST NOT claim M1 while still using
embed_hard_to_vec" prevents fake-M1 deployments.
- Added an endianness-confirmation note: big-endian is pinned to the
impl + KATs; flip only if v7 TLV convention turns out little-endian
(would need a PHI_PRG_VERSION bump).
- SHALL-replace wording kept (RFC-2119 strong mandate inside M1).
Implementation (arborist/substrate/anchor_prg.py):
- New dim_h > 16·2^32 → ValueError guard (clean message naming the
ceiling rather than overflowing the counter deep in _expand).
- bool dim_h now rejected explicitly (isinstance(True, int) is True).
- Module + function docstrings updated: manifest field is
anchor_prg_seed; seed-independence / single-purpose rules; corrected
float-map distribution wording (negligible mean −2^−32, not exactly
zero); endianness note.
Tests (tests/test_anchor_prg.py, 27 → 30):
- test_phi_prg_rejects_bool_dim_h (True/False params).
- test_phi_prg_rejects_dim_h_above_counter_ceiling.
Doc cross-refs: soft-hash-channel-analysis.md §9.2 + §11 status note
the dav1d-reviewed §9.10 wording + anchor_prg_seed field name.
#000035 ticket status + TICKETS.md row updated. AUTOCOUNT markers
for test_anchor_prg.py bumped 27 → 30 across 5 doc files.
Full suite: 2291 passed, 28 skipped.
Per fox: apply the conservative max_envelope B1 model by changing the
v1 calculator's default — NOT by forking a v2. CALCULATOR_VERSION stays
"t3-bound-v1-bottou-refinement" (the descriptor names the unchanged B3
term); b1_model is echoed in the output AND the inputs dict so KAT
replays are unambiguous about which model produced a row.
Calculator (bench/scripts/t3_bound_calculator.py):
- New b1_model kwarg + --b1-model CLI flag, choices:
max_envelope (default) max(fraction_channels, aggregate_bias)
fraction_channels g · W · log₂(1 + G/σ)
aggregate_bias W · log₂(1 + g·G/σ)
effective_control_v1 g · W · log₂(1 + g·G/σ) (old non-worst-case)
- Default is now max_envelope — genuinely upper-bounding across both
interpretations of g (dav1d review §3 closure blocker, RESOLVED).
- Every output reports all three concrete B1 variants
(B1_fraction_channels / B1_aggregate_bias / B1_effective_control_v1),
b1_selected, and both SNR readings (snr_grad = g·G/σ,
snr_per_channel = G/σ) regardless of which b1_model was requested.
- model_assumptions[] now carries f"B1_model_{b1_model}".
- inputs echo now includes c_b1/c_b2/c_b3/b1_model (replay-complete).
- Invalid b1_model rejected with a ValueError naming the field.
- Baseline I_window: 625.8716 (effective_control_v1) → 6183.0154
(max_envelope: B1=aggregate_bias 5849.63 dominates fraction_channels
1729.72), certification_status NOT_CERTIFIED_BY_BOUND at W=10000.
KAT fixture (bench/fixtures/t3-bound/known-answer-tests.jsonl):
- Regenerated 2026-05-11 — 12 entries: the 8 §7-derived configs under
the new max_envelope default, a g=0 edge case, plus explicit-mode
pins for effective_control_v1 / fraction_channels / aggregate_bias.
- Each entry carries b1_model, expected_b1_selected,
expected_b1_{fraction_channels,aggregate_bias,effective_control_v1},
expected_snr_per_channel, expected_certification_status.
Tests (tests/test_t3_bound_calculator.py, 75 → 83):
- test_t3_bound_known_answer_tests no longer skips (fixture active);
pins b1_model, b1_selected, certification_status + numbers, tolerates
optional new fields on older fixtures.
- New: test_b1_max_envelope_exact_formula, test_invalid_b1_model_rejected,
test_cli_b1_model_flag (effective_control_v1 / fraction_channels /
aggregate_bias). test_b1_exact_formula renamed
test_b1_effective_control_v1_exact_formula and now passes the explicit
model. Updated baseline / below-256 / CLI tests for the new numbers.
Doc (docs/soft-hash-channel-t3-bound.md):
- Header + §0 + §3.1 + §6 + §7 (worked examples) + §8 (operator
guidance W-solving) + §10 (closure blockers RESOLVED) + §10.1 +
§11 (calculator schema) + §12 all updated for the max_envelope
default. §8: target-256 W drops from ~4196 to ~415 steps under the
conservative model — the ~10× cost of not assuming which g-reading
holds; operators who can measure effective-control applies can use
--b1-model effective_control_v1 for the looser W (a calibration
claim they must justify, not a default).
Status (#000036 ticket + TICKETS.md): both prior dav1d closure
blockers cleared (B1 worst-case model + active KAT fixture); remaining
= fox's final close-or-iterate call.
AUTOCOUNT markers bumped 75 → 83. Full suite: 2288 passed, 28 skipped.
trigger_1_branch_density in bench/prometheus_sigma_trigger_probe.py read
the fork_score_branches table via branch_set_density() instead of the
"density check not yet implemented" stub. It groups rows by branch_set_id,
fires when the most-recently-recorded checkpoint carries >= 4 branches
(BRANCH_DENSITY_FLOOR), and surfaces n_checkpoints / latest_density /
max_density / n_checkpoints_clearing_floor in the markdown report so
section 12's "regularly" qualifier stays visible. Density sums across
shards per branch_set_id.
With no branch sets persisted yet the probe reports "table present but
empty across shards" (data_available True, fires False) rather than a
false negative. Re-ran the probe against the live shards:
bench/results/prometheus-sigma-triggers-2026-05-11.md.
6 new tests in tests/test_prometheus_trigger_probe.py (probe loaded via
importlib): no-table to no-data, empty-table to data-available-no-fire,
latest-checkpoint->=4 to fires, earlier-dense-but-latest-sparse to no-fire,
density-sums-across-shards, report-renders-density-lines.
Updated #000012 Phase 1c landing receipt, #000037 section 12 Trigger 1
note, and the TICKETS.md index rows for both. Pure measurement: no
mutation, no LLM call, no schema change.
dav1d's review (RESPONSE_1 + RESPONSE_2) returned 2026-05-11. This
lands the Tier-1 items — everything that doesn't change numeric
outputs or invalidate the KAT discipline. The Tier-2 B1 conservative-
envelope (v2 calculator) is a separate decision and stays a closure
blocker.
Calculator (bench/scripts/t3_bound_calculator.py):
- Recommendation wording: "M2's single-window guarantee is broken"
→ "this conservative bound CANNOT CERTIFY M2's residual". An upper
bound exceeding 256 bits means we cannot certify, NOT that the
adversary can steer 256 bits — the prior wording overclaimed.
- New structured output fields: b1_model ("effective_control_v1"),
certification_status ∈ {CERTIFIED_BY_BOUND, NOT_CERTIFIED_BY_BOUND},
certification_threshold_bits (256), model_assumptions[]. Callers
read a machine-readable status, not just prose.
- Input validation hardening: _require_finite_float / _require_positive_int
helpers reject bools (isinstance(True, int) is True in Python — a
real leak risk for a security calculator) and NaN / ±inf for every
numeric input and constant.
- gradient_fraction = 0 now accepted (no T2 surface; B1 = 0; T3's
LR + batch-order channels still contribute) — improves component
isolation. CLI help + module docstring updated accordingly.
- Numeric outputs UNCHANGED: baseline still 625.8716 / 292.4813 /
300.0 / 33.3904; b1_model stays effective_control_v1; KAT discipline
intact.
Tests (tests/test_t3_bound_calculator.py, 53 → 75):
- Hard-coded cwd="/home/fox/git/arborist" → pathlib.Path(__file__).
resolve().parents[1] so the suite runs on any checkout.
- New: test_gradient_fraction_zero_accepted, test_bool_rejected_for_int_fields,
test_bool_rejected_for_float_fields, test_nonfinite_numbers_rejected,
test_output_carries_b1_model_and_certification_fields,
test_certification_status_certified_below_threshold.
- test_recommendation_exceeds_sha256 now also asserts "CANNOT CERTIFY"
+ certification_status == NOT_CERTIFIED_BY_BOUND.
Doc (docs/soft-hash-channel-t3-bound.md):
- §0 reworked into a reviewer brief recording dav1d's findings
(§2 accepted, §4 accepted, §5 accepted as model-bound, §3 = closure
blocker, wording/validation = applied).
- New §3.1: the B1-double-g issue spelled out — effective_control_v1
vs fraction_channels vs aggregate_bias vs max_envelope, with the
baseline-spread table (292 / 1730 / 5850 / 5850 bits); v2 path
described.
- §5: "B3 is a model-bound, not a directly-quoted theorem" note.
- §10: items 1-2 are now the closure blockers (B1 envelope v2; active
KAT fixture); items 3-7 are tightening paths (#000043). New §10.1
records what the 2026-05-11 hardening pass already landed.
- §11: calculator-output example updated to show the new fields +
corrected recommendation wording.
- §12: references add the dav1d review + clarify Bottou-Bousquet
"inspires" (not "underlies") the §5 model-bound.
Status (#000036 ticket + TICKETS.md row): review-returned + Tier-1-
applied; closure blockers = B1 v2 envelope (awaits fox go/no-go) +
active KAT fixture. R2's architectural integrations (Merkle audit-
event commitment, SQD canonicalization, CTI clause-lattice, 5F
trigger, ForkScore security-risk) noted as out-of-scope (separate
tickets if wanted).
AUTOCOUNT markers in docs/calculator-test-patterns.md +
docs/warrant-substrate-cookbook.md bumped 53 → 75.
Full suite: 2264 passed, 28 skipped.
Phase 1a scores one (parent, child) fork at a time; Phase 1b is the
consensus paper. Neither persists multiple candidate branches at the
same checkpoint — and #000037 §12 Trigger 1 ("ForkScore regularly
receives ≥4 candidate branches per checkpoint") gates the multi-
branch path of the Prometheus-Σ controller on this data existing.
Phase 1c lands the missing seam.
Schema (arborist/store.py): _migrate_fork_score_branches creates the
sibling table with PK (branch_set_id, branch_id) + indexes on
branch_set_id and parent_root. Sibling — never enters
audit_events.event_hash preimage, so re-scoring or back-filling
cannot break the audit chain.
Helpers (arborist/substrate/fork_score.py): persist_branch_score
upserts one row via ON CONFLICT (branch_set_id, branch_id) DO UPDATE
so re-scoring the same fork under the same checkpoint is a clean
overwrite, not a duplicate. branch_set_density(conn, branch_set_id)
returns the count of distinct branches recorded under a checkpoint
— the function the #000037 §12 Trigger 1 probe reads.
ESTIMATOR_VERSION = "fork-score-v1" pins the producer generation on
every persisted row.
CLI (arborist/cli.py): arborist substrate score gains six new flags
(--branch-set, --branch-id, --parent-root, --child-root,
--persist-shard, --weights-id). Default off — --branch-set absent
preserves Phase 1a pure-function semantics for every existing
caller. When present, requires --parent-root and either --branch-id
or --child-root; missing inputs return exit code 2.
Tests (tests/test_fork_score.py, count 18 → 23): migration creates
the table + both indexes; persist writes one row carrying
parent/child roots + verdict + weights_id + estimator_version;
upsert on the PK refreshes child_root + weights_id + recorded_at
without duplicating; branch_set_density counts per-checkpoint and
ignores cross-set rows; breakdown_blob round-trips as canonical
JSON whose values sum to the persisted score.
Status sync: #000012 §7 Phase 1c flipped from "proposed, not yet
open" to "landed 2026-05-10" with the original proposal preserved
below as design log. TICKETS row 117 mirror-updated. AUTOCOUNT
counters in #000012 + cookbook bumped 18 → 23 plus the cookbook's
fork_score.py LOC row refreshed (298 → 386 module, 403 → 609
tests, density 1.35 → 1.58).
End-to-end smoke verified: arborist substrate score writes a
fork_score_branches row with the expected schema (verdict / weights_id
/ estimator_version) and the row survives a clean SQLite read.
Two coupled changes that wire the §13 Step 11 proposal stream from
in-memory-and-discarded to persisted-and-harvestable.
(A) emit_controller_events now writes a 4th event kind
controller_falsification_proposal, one row per
decision.falsification_proposals entry. Body carries branch_id +
witness_divergence + reason; label column carries the reason for
terminal-table inspection. Deterministic ordering by (branch_id,
witness_divergence) so canonical-body hashes are stable. Idempotent
under the existing UNIQUE (event_kind, body_hash) constraint. The
audit-chain semantics remain unchanged (still a sibling table; no
event_hash preimage entry). The CLI inspector's --kind choices gain
the new event kind so operators can filter for it directly.
(B) bench/scripts/harvest_falsification_proposals.py gains a third
source bucket CONTROLLER_PROPOSAL alongside the existing HYBRID +
UNGROUNDED providence_cache buckets. Reads
controller_falsification_proposal rows from controller_events,
extracts the 16-char cache_key prefix from branch_id (qa:<prefix>
pattern from the QA-runner advisory), joins back to providence_cache
for fixture enrichment (answer_text + audit_mode + verifier_method),
and tags _harvest_meta.harvested_from = "controller_events" so the
two source paths stay distinguishable in the fixture pack. Dedup
against the providence_cache buckets by fixture id.
Today this typically yields 0 new fixtures because (i) no live QA
has fired since Phase 2 wiring landed, and (ii) the QA-runner
single-branch advisory's proposals overlap providence_cache content
the harvester already finds. Real net value comes from Phase 3
(#000045) sweep emissions, which will produce multi-branch chunk
proposals that providence_cache rows can't predict.
Tests: 3 new in tests/test_prometheus_audit.py (proposal-row
emission, no-proposal no-row, idempotency); 1 new in
tests/test_bench_batteries.py (synthetic qa.db with both
providence_cache + controller_events rows; asserts the
controller_events bucket surfaces a fixture invisible to the
divergence-thresholded providence_cache buckets). The pre-existing
harvested-pack-runs-clean test relaxes its harvested_from pin from
"providence_cache"-only to {"providence_cache", "controller_events"}.
The Phase 2 advisory writes (_emit_qa_controller_advisory) populate
the controller_events sibling table on every QA cycle. Until now
the only way to inspect was raw SQL. This adds a top-level
arborist subcommand that walks every shard, surfaces decision /
difficulty / budget_allocation rows, and renders either a compact
terminal table or JSON.
Flags:
- --limit (default 20)
- --kind {controller_decision|controller_difficulty|controller_budget_allocation}
- --organism-prefix PREFIX (LIKE prefix; "qa:" matches QA-runner advisories)
- --since-seconds N (rows recorded within the last N seconds)
- --body (include JSON body_blob in --json output)
- --json (machine-readable {summary, rows})
Reads via sqlite3 read-only URI; silently skips shards without a
controller_events table. No writes, no schema migration triggered.
Wires into the #000045 Retrigger 1 measurement story (need ≥1000
advisory rows from Phase 2 wiring before Phase 3 implementation
opens) — operators now have a one-line check for that signal.
Tests: 5 new in tests/test_prometheus_audit.py — happy-path table
output, --kind filter, --organism-prefix filter, --json shape,
graceful skip of non-arborist sqlite files in the shards-dir.
test_cli_smoke parameterized list updated so the argparse-
construction smoke test also covers the new subcommand.
arborist.qa.runner.ask() now emits one controller_decision +
controller_difficulty + controller_budget_allocation triple per QA
cycle via _emit_qa_controller_advisory(conn, cache_key, verdict).
Single-branch synthesis from the verdict's audit_mode (Δ5F mapping
matching the dry-run simulator) and n_unverified/n_quotes
(witness_divergence). Wrapped in try/except so any advisory failure
never blocks the QA result; pure audit-only — does not enter
audit_events.event_hash preimage, audit chain semantics unchanged.
Lazy import keeps the QA hot path free of substrate-module load on
calls that never reach this helper (cache hits + early returns).
Tests: 3 new in tests/test_prometheus_audit.py — happy-path emits
all three event kinds, defensive parsing tolerates malformed verdict
without raising, second call with same (event_kind, body_hash) is
idempotent under the existing UNIQUE constraint.
Per §22 Finding 2: flat capital_cost=1.0 made every utility negative
in the dry-run sim. Split capital_cost into kernel_cost (~0.05 kernel
re-probe) + llm_cost (~1.0 LLM witness fan-out); ControllerBranch
now exposes effective_cost = kernel_cost + llm_cost when either is
positive, falling back to legacy capital_cost when both are zero.
Pre-1.c callers don't migrate. _utility() reads effective_cost so
split-cost and legacy-cost branches with the same total cost produce
byte-identical utility values.
Per §22 Finding 3 (partial): add sweep_weights() profile —
gamma_5f=1.5, lambda_capital_cost=0.25, nu_witness_divergence=0.5.
Sweep work willingly pays capital for falsification discovery and
treats high witness divergence as desirable signal (§13 step 11).
Registered in WEIGHT_PROFILES["sweep"]; folds into governance_policy
selection alongside safe / conservative / exploratory.
Tests: 6 new in tests/test_prometheus.py — effective_cost split path,
legacy fallback, _utility byte-identity across the two cost shapes,
kernel-only vs LLM-only ranking, sweep-vs-safe divergence on a
marginal branch (DEFERRED under safe, ACCEPT under sweep), and
WEIGHT_PROFILES registry now pins all four profiles.
Lock the AUTOCOUNT regression-test pattern as the design log
canonical record. Previously declined when surface was 1-metric
+ 29 tags; now mature enough (4 metrics + 58 tags + 1 same-day
drift-catch since landing) to formalize.
== Ticket content ==
10 sections covering:
1. Why this exists — the 4-drift-day baseline (6cbbf95 / 14bcb99 /
5c21e83 / 30a9488) that motivated mechanization. Five-step
walk through justifying each choice (Step 5 last).
2. Format — `<!--AUTOCOUNT:metric:path-->N<!--/AUTOCOUNT-->`.
3. Four supported metrics with examples + skip semantics:
`tests`, `fixture-rows`, `db-rows`, `db-where`.
4. Skip-on-absence — operator state (shards, qa.db) absence is a
logged skip, not a fail. Smoke verified 2026-05-10 with
HOME=/tmp/empty.
5. What NOT to tag — closed-ticket point-in-time snapshots,
aggregate floors ("2000+"), historical journey arcs.
6. Install discipline at write time + at refresh time.
7. Future metrics deferred (file-lines, gh-pr-comments-count,
module-loc, commit-hash-exists) with the "add a metric"
recipe.
8. Empirical baseline at landing (3 test functions, 58 active
tagged claims across 8 doc files, harness runtime 2-4s).
9. Scope boundaries — does NOT auto-rewrite, does NOT validate
prose quality, does NOT scan docstrings, does NOT lock
values, does NOT add deps.
10. References — every landing commit + sister doc.
Closed at landing (status quo since fc5ba50 2026-05-10 morning;
this ticket is retroactive design log per the convention "every
ticket flips to `closed · landed in commit <sha>` when the work
ships").
== Code-fence parser fix ==
Adding the ticket itself surfaced an oversight: my AUTOCOUNT
examples in §3.3 + §3.4 used literal tag pairs in ``` fenced
code blocks. The parser was reading them as live claims and
firing on the illustrative `db-rows:002.db:concept_relations`
claim (compared 1234 vs live 72576 — both meaningless because
it's an example).
Fix: `_strip_fenced_code_blocks` substitutes the body of every
triple-backtick block with newlines before regex scanning. Line
numbers stay aligned (newline-preserving substitution); tags
inside fences are skipped because their parent text no longer
matches the regex.
Both helper functions (`_iter_claims` and the well-formed-tags
test) walk through the stripped text, so the strip discipline
is consistent across all three test functions.
== TICKETS.md index ==
Added #000044 row marked closed with the 5-commit landing trail.
Bumped Next ID 000044 → 000045.
== Verification ==
$ pytest tests/test_doc_counts.py
3 passed in 2.80s
$ pytest tests/ -q
2337 passed, 37 skipped in 108.29s
Hygiene: fox's in-flight changes to arborist/qa/runner.py +
arborist/substrate/prometheus.py + tests/test_prometheus*.py
left untouched in working tree.
Fan-out follow-up: extends AUTOCOUNT with a new metric for filtered
SQL-row claims, then tags fox's prometheus controller test surfaces
shipped this evening under #000037.
== Task 3: db-where metric ==
New metric ``db-where`` for tagging single-column equality
predicates. Target syntax::
<table>?<column>=<value>
<shard>:<table>?<column>=<value>
Resolves to ``SELECT COUNT(*) FROM <table> WHERE <column> = ?``
with ``<value>`` bound as a SQL parameter (no string
interpolation), so author typos or stray content can't escape
the predicate. Column + table names validated as bare
identifiers before string-interpolating into the query template;
sqlite3 connection opens with ``mode=ro`` URI flag.
Same skip-on-absence semantics as ``db-rows``: missing DB or
table yields a logged skip note, not a test failure. Sentinel
returns reuse the same _DB_MISSING / _TABLE_MISSING / _DB_ERROR
constants.
Smoke verified::
_live_db_where('documents?source_type=claim_pack') → 92
_live_db_where('documents?source_type=wikipedia_xml') → 866782
_live_db_where('001.db:documents?source_type=wikipedia_xml')
→ 867695
_live_db_where('documents') # malformed (no ?) → -4
Tagged claims using the new metric (cookbook):
- L36 ``92 records total`` for the claim-pack source
- L349 ``The 92 chains have three quality tiers``
Both resolve to ``documents WHERE source_type='claim_pack'``
in shard ``000.db`` — the live count of claim-pack records.
L5 ``18/92 → 92/92`` historical narrative left untagged
(expressing a journey arc, not current state).
== Task 2: tag prometheus controller test surfaces ==
fox shipped two test files this evening under #000037 that
weren't previously inventoried in any reference doc:
- ``tests/test_prometheus.py`` — 36 tests covering Phase 1
controller (commits ``f625cac`` + ``f9f5ae4``). Verifier-style
discipline (NOT calculator pattern — it's a pure-function
state-machine controller with no closed-form math).
- ``tests/test_prometheus_audit.py`` — 14 tests covering Phase 2
``controller_events`` sibling table (commit ``a786d6d``). Pins
no-chain-mutation invariant (advisory writes never enter
audit_events.event_hash preimage).
Added two paragraphs to cookbook §"Substrate-paper-spec'd
primitives" describing the test discipline + algorithmic surfaces
each pins. Renamed section header from
"(#000012 + #000018 + #000034)" to
"(#000012 + #000018 + #000034 + #000037)" to keep the
ticket-set roster current.
Two new rows in the test/code-density table:
| substrate/prometheus.py | 893 | 804 (36 tests) | 0.90 |
| substrate/prometheus_audit.py | 200 | 388 (14 tests) | 1.94 |
All four counts AUTOCOUNT-tagged (2 inline prose + 2 table rows
= 4 new tags). prometheus_audit's ratio of 1.94 is high because
the test file pins a lot of write-path invariants for what is
nominally a small (200 LOC) sibling-table module — appropriate
for foundation-level audit-discipline code.
== Task 4: test_full_suite_total_fixture_count flake — investigated ==
Earlier today's transient ``-x`` flake (1 failed, 1799 passed)
did NOT reproduce in current tree state (2328 passed, 37 skipped
under same flags). Root-cause investigation:
- ``_DEFAULT_FIXTURES`` is read-only at module scope; no test
mutates it.
- The test reads JSONL fixtures from ``bench/fixtures/`` via
``_run_one``; those files weren't being written by parallel
tests.
Hypothesis (not confirmed, since flake didn't repro): transient
filesystem state during heavy-parallel-commit window
(``f625cac`` / ``a786d6d`` / ``6142437`` / ``f9f5ae4`` all
landed in succession around 17:23-17:24 EDT 2026-05-10 while my
test run was in flight). No structural defect identified. If
flake recurs, capture stdout + filesystem state at failure time
to confirm.
== Task 1: Walked fox's 6 evening commits via Explore agent ==
Agent reported what shipped under #000037 + #000012 evening
push (Prometheus-Σ Phases 0/1/2/dry-run + v8 consensus paper).
Findings used to drive task 2 above. Notable design choices
worth surfacing as reference:
- prometheus.py is **pure function** (no DB / LLM / scheduler);
returns advisory ``ControllerDecision`` + optional proposal
records, never mutations. Verifier-style test discipline.
- ``controller_events`` sibling table never enters
``audit_events.event_hash`` preimage — audit chain unaffected.
- Phase 3 sleep-sweep scheduler **deferred** in favor of
read-only dry-run simulator surfacing 5 design constraints
(chunk_size = Hermes concurrency NOT candidate pool;
capital_cost flat=1.0 needs split; τ_qa per audit_mode;
Target B = 4.4% canonical-shape match; quarantined-row veto
exercises end-to-end). Calibration substrate for eventual
scheduler.
- Per-branch controller latency 12.5 µs at chunk_size=4 → not
the bottleneck; Hermes witness fan-out is.
v8 consensus paper at ``docs/_source/merkle-agi-v8-consensus.rst``
(834 lines; 11 parts) closes the loop from single-validator
Proof-of-Upgrade to multi-validator BFT selection. Phase 1c
(branch-set persistence) remains proposed-not-opened.
== Coverage ==
Total tags after this commit: 54 (was 49; +5)
Tags by metric:
tests: 45 (+4 new prometheus + table rows)
fixture-rows: 2
db-rows: 3
db-where: 2 (new metric, both 92 claim-pack)
Files with tags:
docs/warrant-substrate-cookbook.md 32 (+5)
docs/calculator-test-patterns.md 8
docs/soft-hash-channel-analysis.md 5
docs/tickets/ticket-000006-bench-emergent... 4
docs/seven-point-program.md 3
docs/tickets/ticket-000035-prg-choice-phi-prg.md 2
== Verification ==
$ pytest tests/test_doc_counts.py -v
3 passed in 2.60s
$ pytest tests/ -q
2328 passed, 37 skipped in 106.06s
Closes the controller → 5F battery loop fox designed: #000037 Phase
1 produces FalsificationFixtureProposal records from high-divergence
providence_cache rows; this commit lands the harvester that turns
those proposals into a real 5F fixture pack the falsification
battery exercises every test run.
bench/scripts/harvest_falsification_proposals.py — reads qa.db,
filters live rows with witness_divergence = (n_unverified / n_quotes)
>= 0.5, stratifies by audit_mode, picks 20 HYBRID + 20 UNGROUNDED
top-by-cache_key for determinism, writes embedded-mode fixtures
to bench/fixtures/5f/falsification-harvested-v1.jsonl.
Each fixture carries `_harvest_meta` with the source cache_key,
divergence at harvest time, audit_mode at harvest time, and the
ticket reference (#000037 §13 step 11). Embedded mode — uses
`observed_violations` directly without calling verify_quotes
again; `answer_text` preserved verbatim for debugging.
Pack composition (initial harvest 2026-05-10):
20 UNGROUNDED (expected_reason: UNGROUNDED)
9 HYBRID_QUOTE (NEW motif — not in falsification-v1.jsonl)
7 HYBRID_CLAIM_LATTICE (NEW motif — not in falsification-v1.jsonl)
4 HYBRID_PARAPHRASE (already covered in v1)
Two harness tests pin the pack:
- test_5f_falsification_harvested_pack_runs_clean: 100% pass-rate,
every fixture carries traceable _harvest_meta.
- test_5f_falsification_harvested_pack_widens_motif_coverage: the
HYBRID_QUOTE / HYBRID_CLAIM_LATTICE motifs surface from real
corpus (loud-fail if harvest rotation drops them).
Makefile: `make bench-5f-harvest` re-runs the harvester. Parameters
exposed: HARVEST_QA_DB, HARVEST_OUT, HARVEST_THRESHOLD,
HARVEST_SAMPLE_PER_BUCKET.
Full suite: 2328 passed, 37 skipped (+2 from the two new pins).
Closes four gaps in the initial Phase 1 landing (commit f625cac):
1. §14 row 4 — Hermes-saturation guard. `hermes_utilization` was on
the input contract but never consumed. Now: `utilization >=
budget` → DEFERRED with HERMES_SATURATED note + advisory event
carrying (utilization, budget) for Phase 2 audit. Three new
tests (saturation-equal, saturation-overflow, headroom-exists).
2. §13 step 11 — falsification-fixture proposal emission.
New `FalsificationFixtureProposal` dataclass; controller now
emits one per branch whose `witness_divergence >=
falsification_divergence_threshold` (weight-tunable, default
0.5). Emission fires BEFORE the all-vetoed cascade so vetoed-
AND-diverged branches still surface as 5F-fixture candidates
per #000025. Four new tests (high-divergence emits, low-
divergence stays silent, threshold is weight-tunable, vetoed-
diverged emits anyway).
3. Entropy + memory gating moved from module-level constants
(`H_LOW=0.3`, `H_HIGH=0.7`, `KAPPA_MEMORY=0.5`) to weight
fields (`h_low`, `h_high`, `kappa_memory`). Constants stay as
back-compat exports; defaults match exactly so byte-identical
behavior when neither override fires. Three new tests
(h_low/h_high tunable, kappa_memory tunable, back-compat
match).
4. Veto-class cascade hardening. Added explicit tests for the
`replay_window_unbounded` → ESCALATE path and the
`soft_hash_signal` → QUARANTINE path (§6 + §14 documented but
previously untested). Plus tests for the §6 fail-loud
priority ordering: ESCALATE > QUARANTINE > REJECT when mixed.
Dry-run regenerated against ~/.arborist/shards corpus:
Target A at τ_qa=1d surfaces **576 FalsificationFixture
proposals** from witness_divergence >= 0.5 (24% of swept
candidates). These rows are now an actionable funnel for 5F
fixture mining under #000025 §3.
Module: arborist/substrate/prometheus.py (+117 LOC, 899 total)
Tests: tests/test_prometheus.py (+196 LOC, 22 → 36 tests)
Dryrun: bench/scripts/prometheus_sigma_sweep_dryrun.py +
bench/results/prometheus-sigma-sweep-dryrun-2026-05-10.md
track the new falsification_proposals_total counter.
Full suite: 2326 passed, 37 skipped (+14 net from the new tests).
Pure-function recursive-falsification controller implementing
ticket #000037 §13 algorithm (steps 1-9 + 12), §5 Shannon-entropy
fork-selection with stable softmax, §6 8-class hard-veto order,
§7 Kelly-bounded allocation with 4 safety guards, §7.1 EMA-smoothed
difficulty update, §14 exception-matrix dispatch, and §15 three
named weight profiles (safe/conservative/exploratory).
No DB, no LLM, no scheduler — advisory pure function over already-
committed state. Phase 2 (controller_events sibling table) lands
in companion commit a786d6d. Phase 3 (sleep sweep scheduler) is
not in this commit.
Module: arborist/substrate/prometheus.py (782 lines)
Tests: tests/test_prometheus.py (22 passing tests — the 17 named
contracts from §16.2 plus 5 boundary cases for the §6 veto-class
priority dispatch and §7.1 EMA stability).
Also removes obsolete tests/test_prometheus_sigma.py — pre-Phase-1
scaffolding placeholder whose 17 tests all called pytest.fail()
with "Phase 1 implementation pending" and the @skip_until_phase_1
decorator never auto-flipped to pass-on-import. The contract is
now in tests/test_prometheus.py.
Sibling table `controller_events` for advisory persistence of
ControllerDecision output from #000037 Phase 1. Same pattern as
`capital_ledger` — forward-migrated, indexed, but does NOT enter
audit_events.event_hash preimage. Audit chain semantics are
unaffected.
Three event kinds:
controller_decision — one per ControllerDecision
controller_difficulty — one per ControllerDecision (records
the difficulty_next value)
controller_budget_allocation — one per branch with nonzero
allocation in decision.allocations
Idempotent on (event_kind, body_hash) UNIQUE constraint.
sha256 of canonical-JSON-encoded body is the dedupe key.
Tests: tests/test_prometheus_audit.py — 14 cases covering
migration, idempotency, no-chain-mutation invariant, query paths.
Uses stub ControllerDecision so tests run independently of Phase
1's controller_decide implementation.
