docs: seven-point-program north-star — directive matrix + status snapshot

The 2026-05-01 distilled architectural directive becomes the audit lens applied before every new ticket / feature / prompt edit. Each of the seven directives gets: - status (✓ / ½ / ✗) - code anchors (verifier paths, renderer hooks) - pinning tests (per-rule coverage in tests/) - tickets covering remaining work - bench signal (which row column reports it) Status snapshot at landing: D1 (no LLM in verifier) ✓ D2 (pointer clauses) ✓ D3 (CTI internally) ½ → ticket #000002 D4 (retrieval map AND evidence map) ½ → ticket #000001 D5 (deterministic pointer verify) ✓ D6 (anchor-class warrant) ½ → ticket #000003 (this commit pair) D7 (honest labels) ✓ D8 (test-pinning before automation) discipline CLAUDE.md docs index gains a "North-star" section pointing at the program; ticket entries gain a "Directive" column threading them back to the program.
2026-05-01 16:19:50 -04:00 · 2026-05-01 16:19:50 -04:00 · c1dcd3142e
commit c1dcd3142e
parent 7ba1b405ee
3 changed files with 230 additions and 7 deletions
--- a/CLAUDE.md
+++ b/CLAUDE.md
@ -275,6 +275,12 @@ Full discipline + worked examples in `docs/bench-maxing.md`. Headlines:

 ## Docs index

+North-star:
+
+- `docs/seven-point-program.md` — the architectural directive distilled
+  2026-05-01. Every new ticket / feature / prompt edit walks past this.
+  Bench harness reports per-mode directive coverage.
+
 Architecture / ongoing work:

 - `docs/cti-architecture.md` — CTI Clause Tree Intelligence.
@ -291,9 +297,12 @@ Architecture / ongoing work:
 Tickets: `docs/TICKETS.md` (index + Next ID). Open tickets:

 - `docs/ticket-000001-retrieval-keywords-audit-gap.md` — provenance
-  binding for `--retrieval-keywords`.
+  binding for `--retrieval-keywords`. Directive D4.
 - `docs/ticket-000002-reference-frame-polarity-contract.md` —
-  Module L: multi-frame answer compilation.
+  Module L: multi-frame answer compilation. Directive D3.
+- `docs/ticket-000003-anchor-class-warrant.md` — anchor-class
+  warrant generalization (entity-list / count / why-cause shapes).
+  Directive D6.

 ## Orientation protocol

--- a/docs/TICKETS.md
+++ b/docs/TICKETS.md
@ -53,11 +53,12 @@ implementation cost, it's a ticket. Otherwise it's reference.

 Newest first. Update on every open/close.

-| ID       | Title                                          | Status  | Opened     |
-|----------|------------------------------------------------|---------|------------|
-| #000002  | Reference-Frame Polarity Contract (Module L)   | open    | 2026-05-01 |
-| #000001  | Retrieval-keywords audit gap                   | open    | 2026-05-01 |
+| ID       | Title                                          | Status  | Opened     | Directive |
+|----------|------------------------------------------------|---------|------------|-----------|
+| #000003  | Anchor-class warrant generalization (Module H+)| open    | 2026-05-01 | D6        |
+| #000002  | Reference-Frame Polarity Contract (Module L)   | open    | 2026-05-01 | D3        |
+| #000001  | Retrieval-keywords audit gap                   | open    | 2026-05-01 | D4        |

 ## Next ID

-`000003`
+`000004`
--- a/docs/seven-point-program.md
+++ b/docs/seven-point-program.md
@ -0,0 +1,213 @@
+# Seven-point program — the north-star directive
+
+**Distilled 2026-05-01, Asia/Kuala_Lumpur**:
+
+> Stop making Hermes prove things. Make Hermes emit pointer clauses;
+> build CTI internally; bind the retrieval map and evidence map;
+> verify pointers deterministically; add general anchor-class warrant
+> before semantic NLI; rename labels honestly; and automate only after
+> these invariants are test-pinned.
+
+This is the architecture's north-star. Every new feature, prompt edit,
+schema change, and ticket walks past these seven directives before
+landing. The discipline frames how `bench/qa_sweep.py` and
+`tests/test_qa_quality_live.py` cover the substrate: the bench is the
+scoreboard, the live fixtures are the gates, and **this doc names what
+the scoreboard and gates measure for**.
+
+## The seven directives
+
+### D1 — Stop making Hermes prove things
+
+The verifier never calls the LLM. Faithfulness classification is a
+deterministic property of (answer text, evidence map, source corpus),
+not a model self-grade.
+
+- **Status**: ✓ enforced.
+- **Code anchors**:
+  `aborist/qa/verify.py:verify_quotes`,
+  `verify_claim_lattice`, `verify_claim_lattice_json` — pure functions
+  with no chat-client parameter.
+- **Pinning tests**: `tests/test_verify*.py`,
+  `tests/test_claim_lattice.py` — every verifier path runs without a
+  network call.
+- **Smell-test**: if a future PR adds a `chat_client` argument to a
+  verifier, D1 violated.
+
+### D2 — Make Hermes emit pointer clauses
+
+The model's prose surface is *citation-style* prose with bracketed
+evidence-id tags (`Claim. [E12]`) or schema-constrained JSON
+(`{"claims":[{"text":"...", "evidence_ids":["E12"]}]}`). The model
+never types the quote string itself.
+
+- **Status**: ✓ enforced for lattice modes.
+- **Code anchors**:
+  `aborist/qa/parse_claims.py:parse_pointer_claims`,
+  `aborist/qa/verify.py:CLAIM_LATTICE_JSON_SCHEMA`,
+  `aborist/qa/runner.py` (system prompts).
+- **Pinning tests**: `tests/test_claim_lattice.py`,
+  `tests/test_verify_json.py`.
+- **Bench signal**: rows with `answer_mode ∈
+  {claim_lattice_pointer, claim_lattice}` fall under this directive;
+  rows with `answer_mode == "quote"` predate it (legacy).
+
+### D3 — Build CTI internally
+
+Clause-tree intelligence (frame lattice + multi-frame answer
+compilation) lives **on our side of the wire**. The model proposes
+clauses; the runtime composes them. Reference-frame queries get
+multiple frames acknowledged in the answer (literal vs
+fictional-actual vs in-universe-propaganda) rather than picking one
+frame and discarding the others.
+
+- **Status**: ½ — phrase-route closed the **retrieval** side
+  (commit `1b8677d`); answer-side compilation pending.
+- **Code anchors**: today, none. Future:
+  `aborist/qa/frame.py:detect_frame`, runtime-side polarity contract
+  emission.
+- **Pinning tests**: today, only the phrase-route tests in
+  `test_query.py::test_phrase_match_surfaces_topical_doc`. Future:
+  per-shape frame-detector tests + multi-frame answer-shape live
+  fixtures.
+- **Open ticket**:
+  [#000002 Reference-Frame Polarity Contract](ticket-000002-reference-frame-polarity-contract.md).
+- **Bench signal**: today, `phrase_match_surfaced` flag on bench rows
+  (true when phrase route fired). Once Module L lands, additionally
+  `frame_kind ∈ {literal, reference, ambiguous}`.
+
+### D4 — Bind the retrieval map AND the evidence map
+
+Provenance binding covers both *what got retrieved* (sources) and
+*how retrieval got there* (the operator-influenceable inputs:
+keywords, top_k, over_fetch, max_context_chars, shard set).
+
+- **Status**: ½ — `evidence_map_root` lives in the 9-stage run-DAG
+  (`aborist/qa/dag.py`); retrieval-plan binding (the input side) is
+  the open work.
+- **Code anchors**: `aborist/qa/dag.py:build_run_dag`,
+  `aborist/qa/evidence.py:evidence_map_root`.
+- **Pinning tests**: `tests/test_qa_dag.py`,
+  `tests/test_evidence.py`.
+- **Open ticket**:
+  [#000001 Retrieval-keywords audit gap](ticket-000001-retrieval-keywords-audit-gap.md).
+- **Bench signal**: every lattice-mode row has `run_dag_root`
+  populated; future bench column will report on `retrieval_plan_hash`
+  presence once #000001 lands.
+
+### D5 — Verify pointers deterministically
+
+The hard verifier runs only deterministic checks (parser succeeded,
+evidence_id resolves, source_role allowed, claim text non-empty,
+citation coverage, pointer-count cap, lexical anchor warrant).
+No NLI, no embeddings, no model self-grading.
+
+- **Status**: ✓ enforced.
+- **Code anchors**: `aborist/qa/verify.py:verify_claim_lattice` —
+  seven hard checks documented inline.
+- **Pinning tests**: `tests/test_claim_lattice.py` (per-rule
+  coverage), `tests/test_verify_json.py`,
+  `tests/test_verify.py`.
+- **Bench signal**: every row carries `verifier_method ∈ {quote,
+  span, entity, paraphrase, claim_lattice, none}` (CHECK constraint
+  in `aborist/store.py`).
+
+### D6 — General anchor-class warrant before semantic NLI
+
+The lexical anchor check (Rule 7 in `verify_claim_lattice`) catches
+the lazy-anchor failure where pointer / role / coverage all pass but
+the cited chunk never names the answer entity. Today this fires
+only on relation-shape questions. Generalizing the anchor-class
+detector to entity-list / why-cause / when-date shapes pins a
+broader class of failures structurally before any NLI substrate
+exists in the proof path.
+
+- **Status**: ½ — relation-shape only. Entity-list / why-cause /
+  when-date shapes pass through unchecked.
+- **Code anchors**:
+  `aborist/qa/verify.py:_extract_anchor_candidates`,
+  `aborist/qa/verify.py:_question_is_relation_shape`.
+- **Pinning tests**: `tests/test_claim_lattice.py` covers
+  relation-shape; entity-list / cause / date shapes have no warrant
+  test today.
+- **Open ticket**:
+  [#000003 Anchor-class warrant generalization](ticket-000003-anchor-class-warrant.md).
+- **Bench signal**: future column `warrant_fired: bool` (true when
+  Rule 7 ran on the row, regardless of pass/fail).
+
+### D7 — Rename labels honestly
+
+`STRICT` for claim-lattice modes overclaims because synthesis-heavy
+claims pass all hard checks without semantic entailment of the
+joined assertion. The renderer relabels at display time:
+
+```
+STRICT     → EVIDENCE-LINKED · via claim_lattice
+HYBRID     → EVIDENCE-LINKED-PARTIAL · via claim_lattice_pointer
+UNGROUNDED → UNGROUNDED · via claim_lattice
+```
+
+Quote / span / entity / paraphrase modes keep their original tokens
+(they verify against pinned spans, not synthesis). The schema column
+stays `STRICT`/`HYBRID`/`UNGROUNDED` so v9.8 cache_key invariants
+hold.
+
+- **Status**: ✓ enforced for lattice modes.
+- **Code anchors**: `aborist/cli.py:_render_audit_label`.
+- **Pinning tests**: `tests/test_cli_render.py` —
+  `test_render_label_strict_in_claim_lattice_becomes_evidence_linked`
+  and siblings.
+
+### D8 — Automate only after the invariants are test-pinned
+
+The five-step algorithm in CLAUDE.md applies to automation in
+particular: bench harnesses, distill runners, ingest CLIs all earned
+their automation only after the underlying ops were simplified into
+single-purpose stages. **The bench harness IS the automation
+substrate**, so it must enforce the directives before any feature
+gets layered on top.
+
+- **Status**: ongoing discipline.
+- **Code anchors**: `bench/qa_sweep.py`,
+  `tests/test_qa_quality_live.py`.
+- **Bench signal**: per-row `directive_compliance` column maps
+  each directive to a pass/fail boolean; the markdown summary
+  aggregates per-mode-per-directive coverage.
+
+## How to use this doc
+
+1. **Before opening a new ticket**, scan the seven directives. Which
+   one does the work serve? Add the directive number to the ticket
+   header (`Directive: D6`) so the design log threads back here.
+
+2. **Before merging a feature**, audit it against D8: does a test
+   pin the new invariant? If not, the feature is automation
+   pretending to be code-level discipline.
+
+3. **When reading a bench summary**, the per-directive coverage row
+   tells you which directives are passing on the corpus today and
+   which are pending implementation. Bench scores that climb without
+   directive coverage climbing are graveyard-digging (step 4 of
+   the five-step algorithm).
+
+4. **When triaging a fixture failure**, identify which directive
+   the fixture pins. A fixture that fails by name maps to a specific
+   regression in the directive's structural invariant; an unnamed
+   bench delta is just noise.
+
+## Status snapshot at landing
+
+| # | Directive                                    | Status | Tickets   |
+|---|----------------------------------------------|--------|-----------|
+| 1 | Stop making Hermes prove things              | ✓      |           |
+| 2 | Hermes emits pointer clauses                 | ✓      |           |
+| 3 | Build CTI internally                         | ½      | #000002   |
+| 4 | Bind retrieval map AND evidence map          | ½      | #000001   |
+| 5 | Verify pointers deterministically            | ✓      |           |
+| 6 | Anchor-class warrant before NLI              | ½      | #000003   |
+| 7 | Rename labels honestly                       | ✓      |           |
+| 8 | Automate only after test-pinning             | discipline |       |
+
+Three of seven structural directives are partial (D3, D4, D6). All
+three have open tickets. D8 is the meta-discipline that gates how
+all of the above land.