arborist/docs
russell@unturf.com 38cfea1983
qa(verify): FORMAT_COLLAPSED soft-demote + open #000008 (broad-quantifier preflight)
Sister rule to Rule 9 (SUBJECT_TOKENS_ABSENT) landed in the same
session. Both demote STRICT → HYBRID but on orthogonal signals:
Rule 9 catches premise-parroting; FORMAT_COLLAPSED catches
protocol abandonment.

Surfaced by fox's "winners of all major sports?" 2026-05-02 case:
Hermes-3-8B melted under an under-specified broad-quantifier
question, dumped 50+ free-form prose claims with zero [E\d+]
pointer tags. Verifier honestly returned UNGROUNDED 0/2 (parser
caught two line fragments), but operators couldn't distinguish
"tried & failed to ground" from "abandoned the protocol." This
soft-demote separates the two failure shapes at audit-line glance.

verify_claim_lattice (pointer-mode only — JSON collapse already
shows as SCHEMA_INVALID):
- count meaningful_lines (>20 chars after strip) and [E\d+ regex
  matches in raw answer
- ≥5 meaningful lines AND 0 bracket tags → FORMAT_COLLAPSED
  violation, soft-demote STRICT → HYBRID
- format_collapsed: bool added to verdict dict

Plumbing:
- claim_lattice_format_collapse_check_enabled: True in DEFAULT_POLICY
  and DEFAULT_QUERY_POLICY
- _VERIFIER_POLICY_FIELDS in keys.py adds the field so it folds
  into verifier_policy_hash
- threaded through ask() and query() call sites

CLI:
- _SOFT_DEMOTE_VIOLATION_KINDS includes FORMAT_COLLAPSED so the
  audit-line ladder rendering treats it as a soft demote
- _render_warrant_tail appends "· format collapsed" tail

Bench fixture: new "under-specified 'all'" section in
qa_questions.txt with `winners of all major sports?` and rationale
about cross-model resilience signal.

Tests:
- test_format_collapsed_fires_on_bracketless_multi_line_prose
- test_format_collapsed_does_not_fire_when_pointer_tags_present
- CLI render coverage
Full suite: 781 passed (up from 776).

Open Ticket #000008 — Broad-quantifier preflight guard. Cleaner
upstream fix: detect quantifier-intensity at query layer and
apply a per-model claim ceiling BEFORE the 13-second LLM call.
FORMAT_COLLAPSED stays as the downstream catch; #000008 proposes
the upstream prevention. TICKETS.md index + Next ID 000008→000009.
2026-05-02 16:43:41 -04:00
..
diagrams docs: README label refresh + per-module reference + Graphviz diagrams 2026-05-01 23:19:01 -04:00
tickets qa(verify): FORMAT_COLLAPSED soft-demote + open #000008 (broad-quantifier preflight) 2026-05-02 16:43:41 -04:00
bench-emergent-design.md bench: emergent stress-test — 3-word triangulation (blue-moon cadence) 2026-05-02 12:42:56 -04:00
bench-maxing.md docs(bench): rename qa-modes-bench-2026-05-02.md → qa-modes-bench.md 2026-05-02 12:27:38 -04:00
concept-relations-design.md make: speed up tests + automate concept backfill (test 38s→11s) 2026-05-02 10:11:16 -04:00
cti-architecture.md docs: tickets/ subdir + delete naming-deferral, ref-frame, coverage-audit 2026-05-02 12:51:09 -04:00
mesh-deploy.md docs: mesh-deploy runbook for two-host gossip setup 2026-04-28 17:24:37 -04:00
mesh.md docs: mesh multiplayer protocol with dot diagrams 2026-04-28 12:54:36 -04:00
modules.md docs: consolidate docs/modules/* → docs/modules.md (single file) 2026-05-02 13:23:43 -04:00
qa-modes-bench-2026-04-30.md docs(qa): final stop-sequence bench row, day-journey net summary 2026-04-30 16:32:41 -04:00
qa-modes-bench.md docs(bench): rename qa-modes-bench-2026-05-02.md → qa-modes-bench.md 2026-05-02 12:27:38 -04:00
self-reference-design.md docs: consolidate self-reference design — flat MVP + fact-Core distillation 2026-05-02 12:39:42 -04:00
seven-point-program.md qa(frame): #000002 land — reference-frame polarity contract (D3 → ✓) 2026-05-01 20:18:13 -04:00
TICKETS.md qa(verify): FORMAT_COLLAPSED soft-demote + open #000008 (broad-quantifier preflight) 2026-05-02 16:43:41 -04:00
verifier-semantic-gap-design.md docs(qa): design proposal for verifier semantic-gap NLI sidecar 2026-04-30 19:50:05 -04:00