- pilot 30 cards -> 25 agent-MATCH (0 refuted) -> 16 banked; 29 instances banked tonight
(89 incl. propagation); 2.7M tokens haiku-tier ~= 30k/banked instance vs a crack wave's ~75k.
- R22 213/213 BYTE-IDENTICAL from clean; fleet 96.53% fn / 95.1% instr / 89.8% distinct;
stubs 12,613 -> 12,584; dedup 2,029/0.
- R14 CORRECTION: a banked cousin usually does NOT propagate (2 of 8; cousins are byte-variant).
The card 'reach' column is cousin fuel, not dedup copies — priced wrong in my earlier framing.
- FINDING: the 9 gate failures are per-TU INTEGRATION (standalone-MATCH, host-TU-rejected),
clustered 5+2 in two binaries — the reconcile-ladder class, not codegen.
- TWO INCIDENTS (mine): an outer timeout tighter than gate_stage's own scaled timeout killed a
healthy 5-bank group mid-write AND orphaned its dedup_propagate child, which kept rewriting
src/ through a git checkout. Killed, inspected, reverted; the same 5 drafts banked 5/5 untimed.
Law: never wrap a self-timing tool in a tighter cap; kill process GROUPS, not pids.
- cookbook §169 (the lane + the three laws + the threshold sizing table).
sig_image emits lowercase func_<hex> names; splat writes the .s with UPPERCASE hex, so
corpus.asm_path returned None for every address containing a hex letter — 60% of the cards
would have shipped agents a 'null/func_x.s' path. resolve_asm() tries the sig spelling
(authoritative for CURATED names), then both hex cases; a card with no resolvable .s is
now DROPPED, not emitted (R32). 518 cards, 0 bad paths.
- family_cousins.py --adapt-cards: per seeded-unit member, drift classified vs the seed
(LI-ONLY 27 / SMALL-EDIT 491 / MIXED 310 excluded); cards carry the seed C location + the
aligned diff blocks with the member's raw words + disasm (the new constant is readable in
the card). 518 cards / 1,101 instances / 23,820 ins; 514 haiku-band.
- tools/wave/adapt_wave.js: the EDIT-contract wave (crack_wave contracts preserved: per-agent
dirs, sha1-last, UNVERIFIED != refuted); symbol surface from the TARGET .s; haiku<=60/sonnet.
- regen chain absorbed the 48 lane-A banks (A-prop open ins -6,475 == the report's instr
delta exactly — two independent derivations agree); pilot slate .run/wave7a_pilot.json (30).
- R37: pilot before scaling to the 518-card pool.
- lane-A jr re-sweep: 9/9 siblings banked (SC03_001/002/124/125, SC04_015/019/020,
SC05_017/018), per-binary SHA-gated by the carve driver; new jr splits + yaml carves.
- func_80189540 family 0/4: reconcile-transform defect ('syntax error before *') — tool
class, ledgered, NOT codegen. §154-A md probe x4: fresh refusal 'jump tables only, not
an island of mixed included data' — 20 md jr members ledgered as the known structural gap.
- FINDING (Drew's smell, byte-verified): the '4,513 unique singletons' picture is substantially
an h_seq exact-hash artifact — 86/120 near-pairs in the 0.85-0.99 band differ by PURE
insertion/deletion (li-expansion tell in 25). Specimen: ov_SC06_010:0x8017bebc (753 ins,
'singleton') is 0.987-similar to a MATCHED fn in the same binary.
- NEW tools/family_cousins.py: distinct open skeletons -> shingle index -> >=0.85 union-find ->
matched-seed attachment -> .run/family_cousins.json + docs/family-cousins.md. R32 BOTH ways
(independent stub recount fails loud on a stale map — negative-control-proven; partition
assert). Reproduced the probe within +-1%; totals EXACT (11,627 inst / 584,448 ins).
- Unit table: A-prop 197u/68,729ins · seeded 418u/50,422 · cousin-multi 1,552u/249,799 ·
cold 3,240u/215,498 — the genuinely-unique tail is 37% of the remainder, not 90%.
Main's 'structurally barren' HOLDS at the similarity tier (94% mass <0.70).
- --targets wave slate: .run/wave7_targets.json = 40 targets / 33,304 unit ins (+33% vs
family-ranked), 9 resolved seed C paths, size-routed 2 haiku/20 sonnet/18 opus.
- LAWS (§168): a cousin is a SEEDED CRACK never a remap; rank waves by UNIT weight; discount
short-fn similarity. Byte-gate stays the sole arbiter (G3/P9).
- docs/family-hseq.md: this session's frontier regen (post-S48 propagations) rides along.
- cookbook §168 + SETUP inventory row (R16/R21/R30); CURRENT_PHASE S49 entry.
Fresh-session safe. 197 commits; six waves (bank rates 67/79/69/68/73/60%);
cookbook 508 sections with all six idiom harvests banked (§162-§167).
Resume order: T5/phase close is a LIVE option (the >=95% instr milestone is met
and holding); otherwise wave 7 from tools/wave/crack_wave.js after a regen.
§167's saturation signal is the strategic finding: COVERED+UNSOUND went
57% -> 64% -> 76% across three harvests, five new laws from 197 claims. Stop
mining waves for idioms; spend the tokens on cracks.
Carries the session's central lesson: four times a tool asserted a conclusion it
never reached, and I repeated the pattern once myself. A confident wrong label
costs more than a missing one.
27 note-sets, 197 claims, one skeptic each, against a cookbook already holding
§162-§166 from this campaign:
NEW 5 · SHARPENS 43 · COVERED 126 · UNSOUND 23
byte-probed 92 · single-instance 75 · asserted 30
COVERED+UNSOUND: 57% (§164) -> 64% (§165) -> 76% (here). The duplicate rate
rises monotonically as the base grows. FIVE genuinely new laws out of 197
claims is the signal that the idiom well for this class of function is
approaching dry — future waves should spend tokens on cracks, not on mining
notes for idioms, and harvest only what a skeptic grades byte-probed.
The skeptics ran their own A/Bs this round. Best example: a crack agent claimed
"the source STATEMENT BOUNDARY decides whether the scheduler hoists a
far-consumed load". The vetter built that spelling and got .text BYTE-IDENTICAL
to the inline form, then swept eight POSITIONS and got five distinct objects —
showing the lever is statement position (the already-banked INSN_LUID
tie-break), not the boundary. Plausible mechanism, refuted by measurement, true
lever named in its place.
46 entries banked as §167-01..46; §167z records the 23 refutations.
cookbook_index.py: 508 sections.
I banked the crack agent's story that a wrong-TU citation CAUSED
func_8017F2D4's seven gate refusals, and relayed it to Drew, without checking
it. corpus.stubs() derives each stub's TU from the actual INCLUDE_ASM site and
gate_stage splices via corpus — the harness was always editing the right file.
Only the PROSE was wrong.
Measured: func_8017F2D4 is still a stub, still classifies DIFF, and is a
has_mid_jr function referencing jtbl_801CC504 — so it carries a jump table the
standalone gate cannot see. The real residual is CAUSE NOT DETERMINED.
The ORACLE stands on its own evidence (the asm subdir's third component IS the
TU stem, by construction from the split config). The causal story does not, and
is now marked as such. This entry was written to stop a tool printing an
unmeasured cause and its first draft printed one.
Wave 6 added 110 (24 cracks + 23/24 families propagated). Fleet 95.1% instr /
89.7% distinct / 96.51% fn-count. R22 clean-fleet run 9x this session, 213/213
every time. Bank rate across six waves: 67/79/69/68/73/60%.
Records §166a (the destination-TU oracle) and the four-instance pattern it
completes: a tool asserting a conclusion it never reached. A confident wrong
label costs more than a missing one.
Drew T