core/generate/derivation
Shay 475d44d245
feat(adr-0163-f2): EX-6 hyphen-bonded unit extraction — pseudo-accumulation confusers refuse (wrong 7->5) (#473)
The confuser probe's two pseudo-accumulation misfires (0005 ->796, 0007 ->996)
both traced to the same extraction blind spot: a number bonded to its unit by a
hyphen (`25-foot sections`, `20-inch pieces`) was invisible to the base
`number + space + word` pattern, so the self-verification completeness clause
never saw the divisor and the bare `buys ... gives` accumulation read as
"complete". This is the highest-leverage lever the 2026-05-29 session named
("the gate must see the fractions/25-foot it currently misses").

EX-6 adds a tight, ADR-0165-safe lexeme pass: a digit run, a single hyphen, an
alphabetic unit word. The alphabetic-only unit group keeps numeric ranges (`3-5`)
out; taking only the first hyphen segment keeps the postmodifier tail
(`25-year-old`) from inflating the unit — so it stays clear of the deferred EX-3
multi-word-unit traps. Over-extraction here is strictly refuse-preferring: making
the divisor visible drives 0005/0007 to refuse via the polarity-None
`cuts`/`splits` clause, never to a wrong answer.

Evidence (deterministic, the microscope):
- confuser probe: wrong 7 -> 5; pseudo-accumulation 0 wrong / 4 refused;
  genuine positives still 7 solved; pair-tells unchanged (4).
- train_sample (capability): 3/47/0 byte-identical.
- practice accumulation: 3/47/0 (wrong=0) byte-identical.
- smoke 67 passed; lane-SHA freeze 8/8 (serving frozen).

Tests:
- TestEX6HyphenatedUnitNumbers pins the new lexeme (value+unit, decimal, no
  double-count, word-compound unaffected, numeric range not read as a unit).
- TestProbeBaseline tightened wrong 7->5; new test_pseudo_accumulation_does_not_misfire
  is the failing-under-violation obligation (fails loudly if the pass regresses).
- TestSlashFractionLeakHazard pins the deferred `1/4`->`4` denominator leak: not
  fixed here because suppressing the leaked operand *removes* a quantity and can
  unblock the completeness clause (not unambiguously refuse-preferring), so it
  needs its own train_sample + probe validation.
2026-05-29 12:23:26 -07:00
..
__init__.py feat(adr-0178-gb3b1): single-referent accumulation chaining (practice 0 -> 55) (#465) 2026-05-29 10:41:51 -07:00
accumulate.py feat(adr-0178-gb3b1): single-referent accumulation chaining (practice 0 -> 55) (#465) 2026-05-29 10:41:51 -07:00
clauses.py feat(adr-0178-gb1): clause segmentation + clause-local sub-derivation 2026-05-28 17:19:50 -07:00
comparatives.py feat(adr-0176-ms2): multi-step chain model — text + comparative operands 2026-05-28 16:35:41 -07:00
compose.py feat(adr-0178-gb3a): clause-scoped referent guard — refuse cross-clause aggregation (#456) 2026-05-29 09:15:52 -07:00
extract.py feat(adr-0163-f2): EX-6 hyphen-bonded unit extraction — pseudo-accumulation confusers refuse (wrong 7->5) (#473) 2026-05-29 12:23:26 -07:00
model.py feat(adr-0176-ms2): multi-step chain model — text + comparative operands 2026-05-28 16:35:41 -07:00
multistep.py feat(adr-0177-cp2a): cue-precision ledger training + measurement (+ unit hygiene) (#461) 2026-05-29 10:21:58 -07:00
search.py feat(adr-0175-phase3b): bounded multiplicative search in the sealed practice lane 2026-05-28 15:29:08 -07:00
target.py feat(adr-0176-ms1): question-targeting 2026-05-28 16:21:40 -07:00
verify.py feat(adr-0176-ms2): multi-step chain model — text + comparative operands 2026-05-28 16:35:41 -07:00