fox asked: JIT-trained, gossip-pulled, or repo-embedded?
Added §2.4 — three shapes, two dead ends:
- JIT-trained per deployment: ❌ — GPU-hours over MNLI/SNLI/ANLI, not
a per-deployment step; non-deterministic across runs → different
audit_mode → breaks the verifier's reproducibility invariant.
"Training" is a one-time act by someone; the distributed thing is
the resulting fixed blob, not the recipe.
- Embedded in the git repo as data: ❌ — a few-hundred-MB binary in
.git blows the standing "fresh clone = python3.12 + venv + sqlite3"
invariant; Git LFS adds a dep and still bloats; the repo is source
+ tiny fixtures + docs, not a model registry.
- One-time obtained, content-addressed, fetched on demand, mesh-
distributable: ✓ — the repo carries a tiny manifest
(arborist/qa/nli/manifest.json: {checkpoint_sha256, source_url,
license, nli_model_version}); the weights live under
~/.arborist/models/nli/<hash>/, fetched on first use (make
fetch-nli or auto-fetch on first --enable-nli query) with the
sha256 verified fail-closed against the manifest; nli_model_version
folds into governance_policy_hash (a swap stales the cache, like
chunking_version / canonicalization_version), keeping audit_mode a
deterministic function of (answer, source, policy, pinned hash);
and once arborist's mesh grows blob-sync, a deployment with peers
pulls the checkpoint from a peer (AXFR-style, like ClouDNS slaves
pulling a zone, like a shard rehydrating from snapshot.db) instead
of the origin URL — content-addressing makes peer-pull and
origin-pull interchangeable, the mesh is the optimization not the
canonical source, cold start falls back to origin. Source: a
published off-the-shelf NLI checkpoint (MIT/Apache, recorded) or a
one-time fox/blackops-trained-and-published one.
Bottom line: not JIT-trained, not repo-embedded weights — a
content-addressed hash-pinned checkpoint, manifest in the repo,
weights under ~/.arborist/, fetched on demand (origin or peer), hash
in governance_policy_hash. Precedents cited: the textbook manifest
(pointers + licenses not texts), the [vec] extra (fastembed's
bge-small fetched not committed — #000039), ~/.arborist/ operator-
state, docs/mesh.md + snapshot rehydrate. All presupposes the §2.2/§5
discipline call came back "yes" (is a fixed NLI model allowed in the
audit_mode path?); if "no", none of it builds. Also wired §2.2 con
(b)/(c), §3, §5, §6 to point at §2.4. Doc-only.
bge-small-en-v1.5 batched on a 4090 ≈ 10^3-10^4 chunks/s → full
6.24M-chunk corpus in minutes. Drop a CUDA Embedder (fastembed
CUDAExecutionProvider, or sentence-transformers device=cuda) into
default_embedder()'s pluggable callable; int8 quant stays CPU-side
post-embed; CUDA stack lives only on the producer box. Determinism
note: GPU backfill isn't byte-identical to CPU — irrelevant, soft
data, pin model revision + recipe not output bytes.
#000051: gossip the embedding backfill over mesh — backfill once on any
CPU box, publish a vecpack (leaf_hash-keyed, soft data, cheap structural
gate, never proof path), peers pull + bulk-load. The laptop never runs
the transformer; this is the mechanism behind whitepaper §1's "the
embedding pass runs off the device". Supplies #000050's backfill prereq
as a distributable artifact.
#000050: fold the Dav1dPrometheus-review high-value items into Phase-2
scope — accept-path-5 (vec hits clear the title gate via span-level
warrant, not similarity score, so the gate doesn't drop the semantic
candidates vec exists for), six vec config fields into
governance_policy_hash + a cache-write guard until wired, run-DAG
records the vec stage, four-condition bench (A/B/C/D, C-beats-D) on
semantic-allusion + curated + adversarial-semantic-neighbor fixtures.
Backfill prereq now routes through #000051.
Next ID 000051 -> 000052.
The #000012 top-of-file Status line still said "Phase 1c (branch-set
persistence) remains proposed-not-opened" — but Phase 1c landed
2026-05-10 (d53115e: fork_score_branches table + persist_branch_score
/ branch_set_density + the default-off CLI flags), the #000037 §12
Trigger 1 probe was wired to it 2026-05-11 (dbe8249), and the ticket's
own §7 Phase 1c section + the TICKETS.md index row already say
"landed". Only the header was stale.
Refreshed: Phase 1c landed (with the probe wire — measurable, not yet
fired); §8 = the ForkScore threshold-calibration handoff from #000025
§10.14 (delta_aggregator knob #000047; harder-fixture-tier line
#000046 closed / #000048 closed / #000049 open); Phase 2 (the v8
multi-validator consensus implementation) noted as gating on a
multi-validator deployment, like #000045. Doc-only.
make bench-emergent EMERGENT_N=30 — 30 fresh 3-word-triangulation
cycles appended to bench/emergent_log.jsonl.
Aggregate: 29/30 UNGROUNDED, 1/30 HYBRID, 0 STRICT — the expected
healthy null result. The triangulator generates absurd questions
("How does the depth of one's music-making abilities on a kazoo …")
with no real corpus support; the verifier ladder honestly returns
UNGROUNDED rather than hallucinating-then-STRICTing. 0 false-positive
STRICT on garbage input.
The one HYBRID (perversely/succeeds/disagreeably) is a re-run of
failure shape E ("total deflection to unrelated trivia"): the common
words pulled Hirabah / Original-righteousness chunks via FTS5; the
model quoted them verbatim (3/4 claims verify) but the answer is
total topic-drift → DEFLECTION_DETECTED + CITATION_MISMATCH → capped
at HYBRID, not STRICT. The deflection sidecar + verbatim verifier
holding on adversarial-by-construction input — nothing new, logged as
a confirmation.
No new failure shape or correctness concern. #000006 amend records
it; the 30 entries join the --print-pending queue if a future
teacher-review pass wants a closer look. Doc + log only.
Capture the positioning fox articulated: arborist's per-document ingest
is ~10-100x cheaper than building a vector-DB representation — same
SQLite substrate, different retrieval philosophy — which is the
difference between "ingest + search runs on a phone" and "the NPU is
now a hand-warmer."
New docs/lexical-first-rationale.md (positioning/architecture
reference, not a ticket): the cost asymmetry with the measured numbers
(FTS5 + SHA-256 leaf + Merkle commit + sqlite + zstd pipeline << 1 ms/
chunk vs bge-small ONNX inference ~5-30 ms/chunk, worse contended; the
query side too — a vec query embeds the query string first, an FTS5
query is B-tree lookups); the same-SQLite-different-philosophy table
(inverted index vs dense vectors + ANN; build cost; query cost;
matching; proof-bearing); the deep version of the point — arborist IS
the Merkle Providence model and that model is cheap by construction,
embeddings are a soft signal (CLAUDE.md "soft hash vs hard hash") that
never enter a proof and are the expensive bolt-on; the edge/mobile
consequence; the honest caveat (lexical-first trades the semantic
allusion gap — which is why vec is opt-in/additive, never the default,
and the embed pass is lazy/out-of-band so the heavy transformer work
runs off-device/off-peak; int8 keeps the storage tax at +6%).
Wired in: TICKETS.md "Distinction from other docs" reference list gains
the doc; #000039 §14.6 gains a "Strategic framing" pointer to it.
(A possible follow-up: fold the mobile-viability argument into the
Merkle Providence Reverse RAG whitepaper proper — noted in the doc's
references; not done here, that's a deliberate cross-repo paper edit.)
Doc-only.
fox 2026-05-12: the attribution-aware path (#000048's deferred §2.3 —
closing the 2 recombination over-grounds in falsification-hard) is its
own ticket, not a #000048 phase. So:
#000048 → closed (at 2.1 + 2.4). Steps 2.1 + 2.4 landed 2026-05-11
(12 of 16 residual items: 4 HYBRID_ENTITY over-grounds + 8 Formulate
mis-segments → formulate-hard 12/12, falsification-hard 10/12; each
bench-gated, no STRICT-rate regression). Step 2.2 (single-clause-
containment paraphrase check) attempted + reverted — recombination-
vs-summary isn't lexical (§5 "What we learned"). The 2 residual
falsification-hard fixtures (hard-003 Mercury, hard-005 Einstein)
stand as a documented marker of where the lexical verifier stops.
Header + §5 Closure + §2.3 updated; cross-refs in #000046 / #000012
§8 / TICKETS.md repointed from "#000048 §2.3" to "#000049".
#000049 opened (doc-only, awaiting go/no-go) — "Attribution-aware
grounding check (the recombination boundary)". The recombination
class needs an attribution / dependency-parse or mini-NLI check
(distinguishing "Mercury is the largest" against "Jupiter is the
largest; Mercury is the smallest" from a legit cross-sentence
summary). Options: 2.1 hand-rolled dependency-attribution heuristic
(no model, brittle — same threshold-can't-separate problem one rung
up); 2.2 small purpose-built NLI model ([nli] extra, policy-gated,
off-by-default, bench-gated — the right capability, but forces the
"is a fixed NLI model an LLM-judge?" discipline call + a model
dependency + a non-determinism surface to pin); 2.3 do nothing (the
2 fixtures are a boundary marker, no observed real-traffic harm).
Recommends 2.3 until real-traffic recombination over-grounds show up,
then 2.2 *if* fox rules a fixed NLI model is acceptable in the
proof-adjacent path; the first decision the ticket needs is that
discipline question. Next ID 000049 → 000050. #000048 follow-up.
Doc-only — no code change.
New §14.6 captures the 2026-05-11 findings:
- Measured embed rate: ~4.3 chunks/s on the contended dev box (load
~11 on 8 cores; the embed process got ~28% of one core). One wiki
shard (~1.56M chunks) at that rate ≈ 100h ≈ 4+ days; all four ≈
~16 days. The full int8 backfill was abandoned as not feasible to
brute-force there.
- The 54K-chunk partial on 000.db confirmed ~409 B/chunk apparent
→ 384 B amortized → ~2.4 GB for the full 6.24M-chunk corpus at
int8 — the deterministic number a full backfill would only
re-confirm, so finishing it bought nothing.
- On an idle healthy box (batching + all cores) bge-small does
~50-200 chunks/s → full corpus ≈ ~9-35h (the ticket's earlier
"~17h" is the optimistic end).
- Per-chunk cost breakdown: bge-small ONNX inference ~5-30 ms/chunk
dominates; the existing arborist ingest steps (chunker + SHA-256
leaf + Merkle commit + sqlite INSERTs + zstd + FTS5) are well
under 1 ms total. So adding vec multiplies ingest by ~10-100×,
entirely in the ONNX matmuls — the non-vec ingest path is
unchanged and still runs at hundreds of chunks/s.
- Implication for §14.2: this is *why* lazy-out-of-band is the
default and `arborist ingest --embed` is the opt-in. Production
guidance: a corpus-wide backfill is a one-time batch job (hours
on idle / days on contended), best run off-peak or on a dedicated
box; it does not slow ongoing ingest (which never embeds unless
--embed is passed); a GPU/accelerated embedder is a drop-in via
the pluggable Embedder callable if backfill latency matters.
Status line updated to point at §14.6. Doc-only.
What we learned from the (reverted) step-2.2 attempt, stated as a
general principle in #000048 §5 "What we learned":
A recombination ("Mercury is the largest planet …" reusing the
source's "largest planet …" with its "Mercury") and a legitimate
cross-sentence summary ("Batman, who is the alias of Bruce Wayne,
lives in Gotham City." reusing two adjacent source sentences) are
the same SHAPE to any lexical signal — both scatter the answer's
content tokens across source clauses, and the recombination's
best-single-clause coverage (4/5 = 0.8) sits ABOVE the legit
summary's (4/6 = 0.67), so no token-coverage / clause-containment /
bigram threshold separates them in the safe direction. The
discriminating thing is *attribution* — in the source, are these
tokens attached to the same subject/predicate the answer attaches
them to? — which is a dependency / NLI question, not a string
metric. That's the boundary of the deterministic, no-LLM-judge
lexical verifier: absence signals (#000046 numeric gate, #000048
step 2.1 entity gate) and structure-of-the-model's-own-output
signals (step 2.4 segmenter) are lexical and work; "the source
contradicts this pairing" is not, and proxying it with a coverage
cut trades a small contrived-fixture win for honest demotions of
real summaries — a net loss against bench-maxing's 5-pp floor.
Updated: #000048 §2.2 (the attempted idea kept as design log + the
no-threshold-separates finding), §2.3 (now framed as the only path to
the last 2 — attribution / mini-NLI, its own ticket if ever), §3
(original plan annotated with the LANDED / ATTEMPTED+REVERTED / NOT
DONE outcome), §5 (the step-2.2 receipt + the "What we learned"
subsection + the closure recommendation). Stale cross-refs fixed:
TICKETS.md #000048 + #000046 rows, #000046 ticket Headroom section,
#000012 §8 #4 — all of which said "#000048 step 2.2 closes the last
2", now corrected to "step 2.2 attempted + reverted; the 2 recombination
fixtures stand as documented residue; #000048 §2.3 is the path if
ever wanted".
Recommendation unchanged: close#000048 at 2.1+2.4 (12 of 16 residual
items closed — formulate-hard 12/12, falsification-hard 10/12). Doc-
only — no code change.
Tried a single-clause-containment check on the paraphrase path (and
the entity path's weakest slot): a span is grounded only if a single
source clause (;/. -delimited) covers >= paraphrase_coverage of its
content tokens — a recombination spreads them across clauses. On the
contrived fixtures it works (hard-003 Mercury, hard-005 Einstein →
UNGROUNDED → falsification-hard 10/12 → 12/12). But it ALSO rejects
legitimate cross-sentence summaries — the established fox-2026-04-29
Batman case ("Batman, who is the alias of Bruce Wayne, lives in
Gotham City." against "Batman is the alias of Bruce Wayne. Batman
lives in Gotham City.": spans two clauses, best clause covers 4/6 =
0.67 → demoted, but it's a correct paraphrase). And there's no
threshold that separates the two directions — the recombination
("Mercury …": best clause covers 4/5 = 0.8) sits ABOVE the legit
summary's 0.67, so any cut that rejects Mercury also rejects Batman.
Distinguishing "recombined into a different statement" from
"summarized two adjacent sentences" needs attribution / dependency
parsing or a mini-NLI model (the §2.3 territory), not a conservative
lexical proxy.
Reverted — verify.py stays at its post-step-2.4 state; falsification-
hard stays at 10/12 with hard-003 + hard-005 as documented residue.
#000048 §5 records the attempt + the no-threshold-separates argument;
recommendation: close#000048 at 2.1+2.4 (12 of 16 residual items
closed), with the 2 recombination fixtures a marker for a future
attribution-aware verifier (its own ticket). Awaiting fox's call.
Doc-only — no code change in this commit.
#000035 closed 2026-05-11 (commit 4b85eb1: v7 substrate spec into the
repo at docs/_source/merkle-agi-dag-v7.rst, § 9.10 folded in). Update
soft-hash-channel-analysis.md §9 open-question 2 from "Phase 2 lands
when v7 gains a deployment target" to resolved: φ_PRG = HMAC-SHA-512
with a 32-byte committed seed, little-endian.
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.
Brought the Merkle-AGI v7 formal substrate spec into the repo as
docs/_source/merkle-agi-dag-v7.rst (previously referenced only as the
un-version-controlled ~/Downloads/merkle-agi-dag_v7.txt). Section
structure converted to reStructuredText; inline math kept in the
source's literal notation; added to the docs/_source/index.rst
"Substrate" toctree (also added the pre-existing merkle-agi-v8-consensus
entry that was missing from it).
Folded ticket #000035's § 9.10 + § 9.10.1 (anchor PRG map φ_PRG;
dav1d-reviewed-final, little-endian, HMAC-SHA-512 / 32-byte seed) in at
their numbered positions, after § 9.9, with a .. note:: citing the
reference implementation (arborist/substrate/anchor_prg.py). #000035 ->
closed (Phase 1 + Phase 2 both landed); #000018 §9.2 ("which PRG?")
resolves to HMAC-SHA-512 with a 32-byte committed seed. Full upstream
v7 spec revision stays exogenous; this lands the amendment into the
tracked in-repo copy where future amendments also go.
(docs/TICKETS.md also carries the in-flight #000048 index-row update
from a concurrent session.)
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.)
Tracks the headroom #000046 (closed) left: the 6 over-grounds still
in falsification-hard-v1.jsonl (4 HYBRID_ENTITY where the
entity-proximity strategy matches a shared proper noun while the
answer's other salient term is wrong; 2 STRICT_PARAPHRASE where the
false claim recombines source tokens into a different true statement —
"Mercury is the largest" — and lexical token-coverage can't tell
recombination from grounding) + the 8 mis-segments in
formulate-hard-v1.jsonl (line/bullet-only parse_pointer_claims merges
multi-claim lines / splits wrapped bullets).
Options + recommended order: 2.1 verify_quotes entity
salient-token-disagreement gate (the direct analogue of #000046's
numeric gate — narrow, lexical, bench-safe; catches the 4
HYBRID_ENTITY) → 2.4 parse_pointer_claims sentence/clause
segmentation (closes the Formulate pack) → 2.2 sequence-aware
paraphrase match (conservative threshold; catches the 2
recombinations); defer 2.3 mini-NLI (heavier; only if 2.1+2.2 leave a
residue worth a model dep). Each landing bench-gated — verify_quotes
changes run `make bench-qa` before/after, parse_pointer_claims changes
run the Formulate fixtures + a QA smoke. Doc-only proposal; no code in
this ticket.
Next ID 000048 → 000049; #000046 "Headroom" section + TICKETS.md
index updated to point at #000048.
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.)
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.
The 5F threshold calibration (#000025 §10.14) surfaced two loose ends
that #000012's v8 acceptance protocol owns; opening them as proper
proposals so they don't get lost.
#000046 — Harder 5S/5T/5F fixture tier (below-ceiling baselines).
Every canonical 5S/5T/5F pack runs at rate 1.0 at HEAD, so fork_score's
α·Δ5s+β·Δ5t+γ·Δ5f terms are inert (a child can only move them ≤ 0).
The embedded packs can't be made "harder" (their evaluator is the
gold); a harder tier is necessarily a live-path tier where a real,
imperfect arborist surface produces wrong/partial output. Recommends
Option A scoped narrow: a `falsification-hard-v1.jsonl` built around
the verify_quotes entity-strategy gap already documented by
5f-fal-live-003, confirm the rate sits below 1.0 and is stable, pin it
via `make bench-fork-baseline-hard`, demonstrate a planted surface fix
lifting the rate. Status: open · awaiting go/no-go.
#000047 — ForkScore _delta_* aggregator (mean vs max vs sum). _delta_*
means over a battery's 5 sub-batteries, so a single-sub gain is worth
a fifth of face value (the 5× dilution from the §10.14 calibration:
+0.06 on one 5F sub → MARGINAL, same +0.06 on all five → ACCEPT).
Recommends Option D: parameterize delta_aggregator on WeightSet,
default "mean", record it in the breakdown + fork_score_branches; bump
ESTIMATOR_VERSION only if the default changes. Defer implementation
until #000046 lands a below-ceiling baseline so the aggregator choice
is benchable, not guessed. Status: open · awaiting go/no-go; parks
behind #000046.
TICKETS.md index rows + Next ID bump (000046 → 000048) landed in
8599ce3 (swept in by a concurrent commit; content is correct).
ticket-000012 §8 §3/§4 updated to name #000047 / #000046.
"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.
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.
Per fox's just-codified §-status drift discipline (#000044 commit
4e41c73), close the doc loop on this evening's commits before
moving on. Three surfaces synced to truth:
(1) Header status line — was "Phases 0 + 1 + 1.b + 2 landed",
silent on Phase 1.c, the 4th event kind, the inspector, the live-
harvest pipeline, the §22 Findings 2 + 3 resolution, and #000045.
Now mentions all of them in one tight paragraph.
(2) §20 Status detail rows — Phase 1 LOC count refreshed
893 → 944 + test count 36 → 42; new Phase 1.c bullet (commit
4b85a0a) describes the kernel_cost/llm_cost split + effective_cost
back-compat property + sweep_weights() profile + §15.4
documentation; Phase 2 row collapsed multi-commit history
(a786d6d + 43380b1 + cc72784 + 70c2184) into a single bullet
covering all four event kinds, the QA-runner wiring, the live
inspector subcommand, and the live-harvest pipeline; LOC 200 → 239,
tests 14 → 25.
(3) TICKETS.md row 103 — mirror of (1) at index granularity. Now
includes Phase 1.c, the 4 event kinds, both downstream consumers
(inspector + harvest), and the #000045 gating-ticket pointer.
No code changes — pure status-drift cleanup. 91/91 tests still
green (test_directives + test_prometheus + test_prometheus_audit).
fox's commit `bb6a89c` (2026-05-09, "30% reduction") deleted
seven docs but the indexes weren't updated to remove the dangling
references. End-of-session sweep caught + cleared:
== Phantom refs in TICKETS.md "Distinction from other docs" ==
5 dangling references to deleted docs:
- concept-relations-design.md → deleted in bb6a89c
- mesh-deploy.md → deleted in bb6a89c
- self-reference-design.md → deleted in bb6a89c
- verifier-semantic-gap-design.md → deleted in bb6a89c
- qa-modes-bench-2026-04-30.md → deleted in bb6a89c
Replaced with the high-value arch docs fox's bb6a89c commit
message explicitly named as kept:
- seven-point-program.md (north-star directive)
- cti-architecture.md (kept)
- mesh.md (mesh-deploy removed; mesh.md kept)
- benchmarks.md (operational; kept per commit message)
- bench-maxing.md (operational; kept)
- qa-modes-bench.md (rolling addenda — distinct from the
dated -2026-04-30 file that was deleted)
- soft-hash-channel-analysis.md (#000018 closure)
- soft-hash-channel-t3-bound.md (#000036 derivation)
- tool-action-dag-design.md (already present; kept)
== Phantom refs in CLAUDE.md `## Docs index` ==
5 dangling references (one of them duplicated — fox typo'd
self-reference-design.md on two consecutive lines with the
same description):
- mesh-deploy.md
- qa-modes-bench-2026-04-30.md
- bench-emergent-design.md
- verifier-semantic-gap-design.md
- self-reference-design.md (duplicate entry)
Replaced with current arch docs:
- mesh.md (mesh wire + group-key)
- soft-hash-channel-analysis.md + soft-hash-channel-t3-bound.md
- calculator-test-patterns.md (#000044 sister discipline)
- spec-methodology.md (#000019)
- v7w-frontier-catalog.md (#000013)
- v8-fork-score.md (#000012)
- pi-star-composition.md (#000015)
== Inline ref in CLAUDE.md §"Retrieval pipeline" ==
L328 cited `docs/concept-relations-design.md` for the
1.6%-storage-tax rationale. Doc deleted; rationale now lives
inline in `arborist/concepts/extract.py` + the data is
self-describing. Updated the prose to note the deletion +
where the design now lives.
== Why this matters ==
A phantom doc reference is the doc-index equivalent of a stale
phase descriptor — it sends future readers to a file that
doesn't exist. Same root cause as today's §-status drift
(in-progress prose freezing while load-bearing surface updates).
The bb6a89c commit was thorough about deletion but didn't
sweep the indexes; this commit closes that loop.
Hygiene: doc-only commit, no schema, no tests touched. Full
suite 2347 passed + 37 skipped earlier; 60 active AUTOCOUNT
claims still clean (3 passed in 2.80s).
Two doc-only fixes from #000045 walk-through:
== #000045 §4 — `sweep_weights()` swap marked resolved ==
§4 "Out of scope" included:
"**No `sweep_weights()` swap in the dry-run.** ... A later
change can swap it ... that is a follow-up inside #000037,
not this ticket."
But fox's commit `6734f80` (2026-05-10 19:22 EDT) already did
the swap — landed ~3 minutes before #000045 was opened. The §4
item was stale at the moment it was written; the follow-up
already happened. Strike-through marker + resolved note added,
explaining that the dry-run report numbers were intentionally
allowed to drift from prior-bench comparability since sweep
profile is operationally correct for sleep-sweep economics
(γ_5f=1.5 / λ_capital_cost=0.25 / ν_witness_divergence=0.5),
not the safe profile.
This is a third-order drift: a ticket's "deferred follow-up"
marker becoming stale because the follow-up landed concurrently.
Caught by reading #000045 §4 line-by-line during the walk.
== Cookbook prometheus_audit count 22 → 25 ==
Third same-day AUTOCOUNT drift catch since the harness landed:
- 36 → 42 (catch 1, during cookbook write — fox in-flight work)
- 17 → 22 (catch 2, after fox's `cc72784` inspector CLI landed)
- 22 → 25 (catch 3, fox's in-flight further additions during
#000045 walk)
Each refresh has been the same shape — file+line+claim/live diff
fires, 60-second turnaround. The discipline is structurally
holding under heavy commit pressure.
fox's 6 currently-uncommitted files (cli.py + prometheus_audit
+ harvest_falsification_proposals + test_bench_batteries +
test_prometheus_audit + the touched docs) preserved in working
tree — my doc-only commit stages only these two doc files
explicitly.
Verification:
$ pytest tests/test_doc_counts.py
3 passed in 2.81s
Harness fired immediately on `cc72784` landing (fox's
controller-events inspector CLI — adds 5 tests to
test_prometheus_audit.py, count went 17 → 22). Cleaned up 2
inline references + the test/code-density table row.
== What cc72784 + earlier follow-ups added ==
`a786d6d` (Phase 2 initial): controller_events sibling table +
migration tests
`43380b1` (Phase 2 wiring): QA-runner advisory writes + 3 tests
`cc72784` (inspector CLI): `arborist controller-events`
subcommand + 5 tests covering kind / organism-prefix filters,
JSON output, graceful skip on non-arborist sqlite files
Cookbook entry now lists all three landing commits + names the
new test surfaces (QA-runner advisory non-blocking on bad
verdict, inspector CLI surface). Single-line update grew to
multi-line description since the surface tripled in scope from
the original Phase 2 entry.
== Table row LOC refresh ==
substrate/prometheus_audit.py: 200 → 239 LOC (fox's cc72784
added inspector-side helpers); test LOC 477 → 595; ratio
2.39 → 2.49.
== Harness signal ==
This is the second same-day catch since the AUTOCOUNT harness
landed (first was the 36→42 prometheus catch during the cookbook
edit earlier today). Both fired within minutes of fox's commit
landing, both surfaced clear file+line+claim/live diff. Refresh
turnaround was 60 seconds both times.
The discipline is structurally working — the AUTOCOUNT tags from
fc5ba50 / 03c0f6a / 6c6defb are now catching real drift on every
fox commit that lands test additions.
Verification:
$ pytest tests/test_doc_counts.py
3 passed in 2.64s
The dry-run was still using safe_weights(); Phase 1.c shipped
sweep_weights() (γ_5f=1.5, λ_capital_cost=0.25,
ν_witness_divergence=0.5) precisely for sleep-sweep economics. Swap
both call sites in prometheus_sigma_sweep_dryrun.py and label the
report Weight profile: sweep (§15.4).
§15.4 adds the sweep profile alongside §15.1 safe / §15.2
conservative / §15.3 exploratory so the named-profile registry has
a single doc source of truth and the dry-run report's §15.4
reference resolves.
§22 dry-run-runs table (3 rows: initial uniform-τ-1d under safe;
per-mode τ under safe; per-mode τ under sweep) replaces the prior
inline narrative count. Includes a Phase-3-design observation: the
sweep profile flattens the softmax (DEFERRED 271 → 369; REJECT
205 → 110; ACCEPT 1 → 0; MARGINAL 2 → 3) because reducing
λ_capital_cost + ν_witness_divergence shrinks the gap between
high-Δ5F and low-Δ5F branches, so fewer branches reach Kelly's
p_i > 0.5 floor. Falsification-fixture proposal count stayed flat
(447 → 449) — the §13 step 11 emission path is upstream of decision
labeling, so sweep mode preserves information-gathering value while
concentrating action-taking on the high-confidence tail. Phase 3
ticket #000045 §2 deliberately leaves softmax temperature un-pinned
because of this trade-off.
Today's audit wave (820409b + 952abc5 + 3b30126) surfaced a
sibling drift class to AUTOCOUNT: ticket body §-status sections
freeze at landing time while file headers update inline. 5 of 6
in-progress tickets audited had this drift. Codify the two
distinct rules (in-progress: refresh in place; closed: archival)
as new §10 of #000044 so future blackops shifts have a structured
reference instead of having to re-derive the discipline.
== New §10 — Sibling discipline — §-status section drift ==
Three sub-sections:
§10.1 In-progress tickets — body §-status must match file
header. Walk pattern when amending: (1) update header, (2) walk
body §-status + refresh, (3) walk TICKETS.md index row + refresh.
The header is the load-bearing surface; lagging body sections
are pure drift.
§10.2 Closed tickets — body §-status is archival. Do NOT
rewrite when later phases land. Phase 2/2.5/B-1/B-2 of a closed
ticket (e.g. #000031) go in:
- The file header (consolidated)
- A NEW section appended below ("Subsequent phases" /
"Phase B follow-ups")
Rewriting §8 of #000031 with Phase 2 content would erase the
Phase 1 landing record — the design log.
§10.3 The rule in one line:
**In-progress §-status must match header. Closed §-status is
archival and stays frozen.**
Table at the top shows the 6 in-progress tickets audited today:
- #000034 §7 lead stale → refreshed
- #000035 §7 lead CLEAN
- #000036 §7 lead + closure(c) stale → refreshed
- #000037 §20 + §17.1 stale → refreshed
- #000025 §11 lead stale → refreshed
- #000012 §7 lead + Phase 1a tests stale → refreshed (file rename
caught: test_v8_fork_score.py →
test_substrate_fork_score.py per a4058a4)
Rule is NOT machine-checked. The audit pattern is manual +
periodic. Sweep-triggers documented:
- Any in-progress → closed flip (final § refresh before freezing)
- Any in-progress gains a new phase landing (refresh §)
- Quarterly housekeeping pass
Long-term, could become a tagged claim (an AUTOCOUNT-like metric
asserting §-status text matches header text up to whitespace
normalization). Deferred until the audit pattern recurs enough
to justify the surface. Speculative; currently below threshold.
== Numbering ==
References renumbered §10 → §11 (one section pushed; new §10
inserted between §9 Scope boundaries and §10 References → §11).
No other content moved.
== Why land this in #000044 specifically ==
#000044 already documents doc-drift discipline (the AUTOCOUNT
mechanism). §-status drift is a parallel manifestation of the
same root cause (point-in-time snapshots freezing while the
load-bearing surface updates inline). Both deserve a single
home. The alternative — a separate #000046 ticket for §-status
drift — would split the discipline into two designs that share
99% of the rationale.
== Verification ==
$ pytest tests/test_doc_counts.py
3 passed in 2.73s
No new tags. No code change. Doc-only.
§7 lead "In progress · Phase 1a landed 2026-05-08" was stale —
file header (current) says "Phase 1a (ForkScore) landed
2026-05-08; Phase 1b (consensus paper) landed 2026-05-10; Phase
1c (branch-set persistence) remains proposed-not-opened."
Refresh to match file header so the index claim and the body
section are saying the same thing.
§7 Phase 1a body referenced "tests/test_v8_fork_score.py — 25
cases" on two counts of drift:
1. **Filename stale**: file was renamed to
`tests/test_substrate_fork_score.py` in `a4058a4` 2026-05-10
under the v-prefix-retirement convention (substrate-paper
version vs schema-version disambiguation). The original path
no longer resolves.
2. **Count + scope conflated**: 25 cases at the time, but the
surface has since split into two test files:
- `tests/test_fork_score.py` (18 tests) pins the pure
ScoredFork dataclass + scoring contract.
- `tests/test_substrate_fork_score.py` (27 tests) pins the
`arborist substrate score` CLI surface.
Refresh: name both files explicitly + AUTOCOUNT-tag each count
so future drift fires (#000044 discipline). Note the rename
provenance for future readers walking the design log.
Six in-progress tickets audited for §-status drift in today's
sweep wave:
#000034 §7 lead stale (now refreshed in 952abc5)
#000035 §7 lead clean
#000036 §7 + closure stale (refreshed in 952abc5)
#000037 §20 + §17.1 stale (refreshed in 3b30126 + 952abc5)
#000025 §11 lead stale (refreshed in 3b30126)
#000012 §7 lead stale (THIS COMMIT)
5 of 6 had body-section drift. Pattern is consistent: file
header is the load-bearing surface fox updates; body sections
are point-in-time prose snapshots that freeze at landing time.
Sweep-on-amend is the right discipline; this commit closes the
last in-progress ticket §-status drift surface for today.
#000006 (rolling research log) and #000044 (closed today,
retroactive design log) excluded from sweep — different shapes.
Closed tickets prior to today excluded entirely per #000044 §5
discipline ("closed-ticket point-in-time snapshots stay
UNtagged / refreshing them changes archival meaning").
Verification:
$ pytest tests/test_doc_counts.py
3 passed in 2.48s
Tags by metric after this commit: 48 tests + 6 fixture-rows +
3 db-rows + 3 db-where = 60 active claims (was 58; +2 from this
commit's two new tests-metric tags on fork_score test files).
Two parallel landings in one commit:
== §-status sweep on in-progress tickets ==
Checked #000034 / #000035 / #000036 §7 Status sections against
their file-header status. Same pattern as earlier sweep on
#000037 / #000025 / #000006 — body-section prose freezes at
earlier snapshots while file headers stay current. 2 of 3 had
drift.
**#000034 §7** lead: was "Open · awaiting go/no-go" + "Phase 1a
proposed below" + body subsection "Phase 1a (landed 2026-05-10)".
The lead line was a 2-versions-old prose snapshot contradicting
the same section's own subsection. Refresh: "In progress · Phase
1a landed 2026-05-10 (commit 1dfb8b9; test backfill a4b3056).
Phase 1b parks until v7 reference checkpoint..."
**#000035 §7**: already says "In progress · Phase 1 landed
2026-05-10". No drift; sample-confirmed clean.
**#000036 §7** lead: was "Awaits fox + cryptographer review of
constants." Refresh to current state — "pre-review polish pass
in 8916bf3; math review in flight with dav1d (forwarded
2026-05-10 Asia/Kuala_Lumpur as Tier 2 bundle: t3-bound.md +
soft-hash-analysis.md + t3_bound_calculator.py +
test_t3_bound_calculator.py + this ticket). Empirical tightening
tracked separately under #000043." Matches file header verbatim.
**#000036 closure criterion (c)** was marked "[pending —
docs-only commit]" but soft-hash-channel-analysis.md §9.3 line
475 already reads:
"§9.3 closed 2026-05-10 via the T3 per-window bound at
docs/soft-hash-channel-t3-bound.md (under #000036)"
So criterion (c) is done. Refresh: "[done — §9.3 closure landed
in line 475 of that doc]". Also clarify criterion (d) gates on
the dav1d review verdict (was ambiguous as just "explicitly
accepted by fox").
== #000037 §20 — reference #000045 follow-on ==
fox opened #000045 (Prometheus-Σ Phase 3 sleep-sweep scaffold)
in commit 0379e4c. My §20 refresh from 3b30126 said "Phase 3
gates on a renewed §12 trigger plus a Phase 3 ticket" — now
that Phase 3 ticket is named: #000045. Refresh to point at it
explicitly so future readers don't have to grep TICKETS.md to
find the follow-on.
== CLAUDE.md — AUTOCOUNT discipline rule ==
Added a paragraph to "Operational rules" pointing future
blackops shifts at the AUTOCOUNT discipline (#000044 + the
harness at tests/test_doc_counts.py). Without this, the harness
is discoverable only by accidentally hitting a test failure or
reading commit messages. With it, "tag at write time" is a
documented operational rule alongside Python-only, PYTHONUNBUFFERED,
and fail-closed.
Rule names: format, 4 metrics (tests / fixture-rows / db-rows /
db-where), code-fence-skip behavior, closed-ticket-stay-untagged
discipline, pointer to #000044 + the harness module.
== Verification ==
$ pytest tests/test_doc_counts.py
3 passed in 2.80s
No drift introduced. fox's parallel 4 commits (4b85a0a /
43380b1 / 1f882df / 0379e4c) landed independently; my
modifications stack on top cleanly. fox's commits added 155 +
89 lines to test_prometheus.py + test_prometheus_audit.py but
collected counts stayed at 42 + 17 — those landings modified
existing tests (parametrize additions / refactors), didn't add
new test functions. AUTOCOUNT claims from 3b30126 still match.
Phase 3 of #000037 (the actual sleep-sweep scheduler that runs the
Phase 1 controller on a cadence over real shards) gates on a
measured retrigger, not a calendar date. This ticket is the gate.
§2 commits 8 governance parameters that fold into governance_policy_hash
when Phase 3 lands: chunk_size (Hermes concurrency), per-mode τ_qa
seconds (CP/LLM split from Finding 3), weight profile (default
"sweep" from Phase 1.c), active sweep targets, per-window budget
cap, scheduling cadence, quarantined-row policy.
§3 names 4 retrigger gates: ≥1000 advisory rows from Phase 2 wiring
showing reproducible REJECT/DEFERRED structure (Retrigger 1); three
consecutive weekly dry-runs with sustained ACCEPT/MARGINAL on Target
A (Retrigger 2); 5F-fixture funnel demand from #000025 plateauing
on Target A's stream and needing Target B's larger candidate pool
(Retrigger 3); operator mission need (Retrigger 4, mirrors #000037
§12 Trigger 4).
§4 explicitly excludes implementation, schema migration,
governance_policy_hash bump, dry-run sweep_weights swap, and
Hermes-call planner — all deferred to the implementation ticket
that this ticket gates.
Includes TICKETS.md index row + Next ID bump 000045 → 000046.
Per Finding 3, a uniform τ_qa=7d filtered out every recent
CANONICAL_PROJECTION row (the π* graduations from #000027/#000030/
#000032 are all younger than 7d), so the sweep saw zero high-value
kernel-only work. Splitting τ_qa by audit_mode lets the cheap kernel
re-probe path (CP) run on a short cycle while the expensive LLM
re-witness path (STRICT/HYBRID/UNGROUNDED) keeps the long cycle.
bench/scripts/prometheus_sigma_sweep_dryrun.py: new build_tau_by_mode()
helper + per-mode CASE in iter_target_a_candidates; sweep_target_a now
takes the dict instead of a single seconds value. New CLI flag
--tau-qa-cp-days (default 1d); --tau-qa-days now scopes to LLM-witness
modes only (default 7d). Report renders the per-mode τ table in the
header and marks Findings 2 and 3 RESOLVED with their landing commits.
Makefile: PROMETHEUS_SWEEP_TAU_DAYS bumped to 7 (was 1, the prior
Finding-3 workaround); new PROMETHEUS_SWEEP_TAU_CP_DAYS=1 makevar.
bench/results/prometheus-sigma-sweep-dryrun-2026-05-10.md: regenerated
under the new defaults — 9 CP rows surface alongside 1,904 LLM-
witness candidates → 1,913 total Target A candidates → 1 ACCEPT,
2 MARGINAL, 205 REJECT, 271 DEFERRED chunks; 2 cache_drift vetoes
preserved end-to-end.
docs/tickets/ticket-000037 §22: Findings 2 + 3 marked RESOLVED with
landing-commit references; total dry-run cost line updated to the
new measurements (37.6 ms / 3,913 branches / 9.6 µs per branch).
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.
Three coordinated doc landings tying together fox's evening
#000037 → #000025 closed-loop work (commits f625cac through
ff1752c + 8999b55):
== #000037 §20 Status — stale prose refresh ==
§20 said "open · awaiting go/no-go" but file header + TICKETS.md
both say "in progress" with phases 0/1/1.b/2 all landed. Refresh
§20 to reflect actual state with per-phase commit anchors:
- Phase 0 (doc): landed; David review applied per §21
- Phase 1 (pure-function controller): f625cac
(arborist/substrate/prometheus.py + test_prometheus.py)
- Phase 1.b (gap-close): f9f5ae4 (§14 row 4 Hermes-saturation
guard, §13 step 11 falsification-fixture proposal, §15 entropy
+ memory gates weight-tunable, ESCALATE > QUARANTINE > REJECT
priority cascade)
- Phase 2 (advisory audit writes): a786d6d
(prometheus_audit.py + controller_events sibling table; does
NOT enter audit_events.event_hash preimage)
- §12 Trigger 2 fired 2026-05-10: divergence variance ratio
0.575 > 0.5 with N=37 — Phase 1 opening is now empirically
gate-satisfied per 8999b55
- Phase 3: deliberately NOT landed; replaced with read-only
dry-run simulator surfacing five design findings (see §22)
- Closed-loop signal: 40 corpus-derived 5F fixtures harvested
per ff1752c
== #000037 §17.1 — "78 atomic claim-pack records" → 92 ==
§17.1 said "#000031 Phase 2 has 78 atomic claim-pack records
that max out at ANCHOR-WARRANTED". #000031 closed at 92 records
(78 was an interim count during Phase 2). Refresh with the
journey (78 → 92) + AUTOCOUNT-tagged via db-where metric so
future drift fires immediately. Note the resolution context: all
92 now resolve via 74 citation-aliases + 13 term-aliases under
#000031 Phase 2.5 + B-1 + B-2. The unconscious sweep drains the
ANCHOR-WARRANTED → EVIDENCE-WARRANTED promotion backlog
(derivations.proof_blob rows still need computation even on
resolved chains).
== #000025 §11 Status — Phase 1f closure note ==
#000025 file header lists Phase 1a/1b.2/1c/1d/1e but the §11
Status section was frozen at "Open · awaiting go/no-go" — a
two-versions-old prose snapshot. Refresh with the per-phase
landing trail + add a Phase 1f section for the corpus-derived
falsification harvest that ff1752c shipped:
- Phase 1f closes the controller → 5F battery loop fox designed
in #000037 §3 ("Divergence → candidate falsification fixture")
- bench/scripts/harvest_falsification_proposals.py reads qa.db,
stratifies top-20-by-cache_key per audit_mode (HYBRID +
UNGROUNDED), writes the 41-line JSONL pack (1 _meta + 40
fixtures, AUTOCOUNT-tagged via fixture-rows)
- Every fixture row carries _harvest_meta with cache_key,
witness_divergence at harvest time, audit_mode_at_harvest,
harvest_threshold, source_ticket: "#000037 §13 step 11"
- 5F battery exercises them every test run;
test_5f_falsification_harvested_pack_runs_clean asserts
error_detection_rate == 1.0 by construction (every harvested
row IS a falsification)
- Self-amplifying — coverage grows with corpus, not with
hand-curation
Listed open items (§10.11 / 10.13 / 10.14) preserved verbatim
from file header so the index claim "still open" stays in sync.
== Cookbook: new "Adjacent: live-corpus → bench-fixture
harvest" section ==
New section in warrant-substrate-cookbook.md between "Re-running
the substrate build" and "References" documenting the harvest
pattern. Three discipline patterns reused from the textbook
substrate noted explicitly:
1. Attribution metadata on every derived artifact (same shape as
derivations.proof_blob carrying inclusion proofs back to
source chunks)
2. Determinism via sort-and-cap (same shape as citation-alias
cascade's "top 5 AND-join then top 3 OR-join" stratification)
3. Pin the metadata contract in tests (same shape as the
cookbook appendix's discipline pins — silent regression
becomes loud test failure)
Plus the reusable recipe for any controller emitting Proposal
records: define the dataclass, write a harvester filtering +
stratifying, pin metadata in tests, wire a make target.
References section gets four new entries pointing to #000037,
#000025, the harvest script, and the fixture pack.
== Drift caught + refreshed during this commit ==
While editing the cookbook, the AUTOCOUNT regression test
(from fc5ba50 / 6c6defb) caught two stale counts from fox's
in-flight prometheus work:
- test_prometheus.py: 36 → 42 (fox's uncommitted +6 for
Phase 1.c sweep weight profile)
- test_prometheus_audit.py: 14 → 17 (fox's uncommitted +3)
Refreshed both inline + in the test/code-density table
(prometheus row test LOC also bumped 804 → 955 to match wc -l).
This is the harness firing exactly as designed — fox's
uncommitted tests changed live state and my doc claims went
stale within minutes. The test message named the file + line
+ claimed-vs-live, refresh was a 60-second turnaround.
== Verification ==
$ pytest tests/test_doc_counts.py
3 passed in 2.92s
$ pytest tests/ -q
2337 passed, 37 skipped in 107.43s
Hygiene: only docs/ paths staged. fox's in-flight changes to
arborist/qa/runner.py + arborist/substrate/prometheus.py +
tests/test_prometheus.py + tests/test_prometheus_audit.py
remain in their working tree, untouched by this commit.
Re-running `make prometheus-trigger-probe` after today's controller
landings shows the divergence-variance trigger has crossed both
thresholds:
Trigger 2 — divergence variance
Sample count: 37 (N_min = 30 ✓)
Mean: 0.7568, σ: 0.435
σ/mean ratio: 0.5748 (> 0.5 threshold)
Absolute σ: 0.435 (> 0.1 threshold)
Same-day morning probe (commit baseline) had only 16 samples and
did not fire; the additional witness-sweep / dry-run / harvest
activity through the afternoon brought sample count above N_min.
Agreement-label distribution across all shards:
KERNEL-LLM-DIVERGED 22
KERNEL-LLM-AGREE 6
LLM-DIVERGED 6
STRICT-WITNESSED 3
Trigger 1 (branch density) and Trigger 3 (witness cost share) did
NOT fire. Per §12 a single trigger firing is sufficient for Phase 1
gating — and Phase 1 has already landed. This commit captures the
empirical evidence that Phase 1 was on the right side of the gate.
Trigger 1 remains structurally blocked on #000012 Phase 1c
(fork_score_branches sibling table); that's the natural next move
if anyone wants to surface multi-branch consensus signals.
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
Two drifts caught in TICKETS.md sweep after today's wave:
1. **#000006 status row drift** — fox amended ticket
#000006's file header on 2026-05-10 to:
Status: open · rolling research log (verifier-ladder
healthy at 134 cycles; emergent gems still being
mined)
But the TICKETS.md index row still said just `open · rolling`.
Convention from peer rows (#000031, #000037, #000025) is for
the index status field to carry the same descriptors that the
ticket file header carries — the index is the load-bearing
surface for at-a-glance reading. Refresh.
2. **calculator-test-patterns.md description drift** — the
description in §"Distinction from other docs" was authored
when the doc was a 9-item-checklist codification of a
three-module pattern bench (t3_bound_calculator /
phi_alignment_probe / anchor_prg, 2026-05-10 morning). Today
evening's commit `f5dbfab` extended the doc with three new
patterns (projective-contract, dispatch-order pin,
tie-breaking-rule pin) sourced from fox's overnight π*
kernel commits, plus four new exemplar test files
(pi_star_arithmetic / _logic / _code / _time_series). The
description should reflect the 12-pattern split (9 core +
3 domain-specific contract pins) and the now-seven-exemplar
inventory. Refresh.
Spot-checked status text in 9 in-progress / open / parked
tickets against their file headers — all in sync:
#000043#000037#000036#000035#000034#000033#000025#000016#000012#000006 was the only divergence. Closed-ticket alias counts
(74 / 13 / 92/92) all match live; refreshed in earlier commits
this session.
Hygiene: docs-only commit, no code, no tests touched.
Verification: ``pytest tests/test_doc_counts.py`` 3/3 pass in 1.97s.
