docs(positioning): record post-publication + research-program non-goals; ship cross-paper workflow guide (#397) (#403)

POSITIONING.md gains a "Recorded non-goals" section (same recording
discipline as Rejected mechanisms — boundary + review criterion, not
a runtime guarantee):

- Post-publication lifecycle: out of scope; the front is
  research-to-publication. monitoring_agent unaffected (alerts on
  cited literature, not the scholar's own output).
- Research-program-level state: no cross-paper memory of any kind;
  the per-paper Material Passport stays the only state carrier
  (anti-leakage consequence).

New docs/cross-paper-workflow.md shows the no-mechanism carry-forward
for returning authors: re-feed the prior passport (stamps re-derive,
prior ok is a head start not a waiver), bring prior limitations /
reviewer points as scholar-supplied Socratic input (Kong L2 — ARS
asks, never derives next-RQ candidates), and the assistant-memory
caveat (gates never read it; the workflow must work identically on a
memoryless machine).

Closes #397

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

CHANGELOG.md

@@ -10,6 +10,8 @@ All notable changes to this project will be documented in this file.
 
 ### Added
 
+- **POSITIONING records two non-goals; cross-paper workflow guide ships (#397, blindspot-audit F-1B/F-7).** POSITIONING.md's recording discipline (five Rejected mechanisms with rationale) had two adjacent boundaries existing only as silence. A new "Recorded non-goals" section records both with the same boundary-plus-review-criterion treatment: **post-publication lifecycle** (own-paper citation tracking / errata / OA self-archiving — the front is research-to-publication; `monitoring_agent` is unaffected since it alerts on *cited* literature, not the scholar's own output) and **research-program-level state** (no cross-paper claim registry / limitations memory / reviewer-history profile — the per-paper Material Passport stays the only state carrier, a deliberate anti-leakage consequence). The supported no-mechanism path for returning authors ships as `docs/cross-paper-workflow.md`: (1) re-feed the prior paper's passport through the existing input port — a prior `ok` is a head start, not a waiver, stamps re-derive under current policies; (2) bring prior limitations / unresolved reviewer points to RQ incubation as scholar-supplied Socratic input — ARS asks about *your* reading, never derives next-RQ candidates (Kong L2 cross-linked); (3) Claude Code assistant memory may serve as a personal reminder layer with the load-bearing caveat that ARS gates never read or trust it — the workflow must work identically on a machine with no memory at all. Documentation only; no schema, flags, or cross-run mechanism.
+
 - **Intake Step 13: citation-verification level surfaced at the configuration interview (#392, blindspot-audit F-8, adjudicated "keep default, add a prompt so the user chooses").** The v3.11 citation-existence gate's `strict` mode existed only in README prose and the v3.10/v3.11 specs — a QUICKSTART user had no signal the choice existed. The intake interview gains Step 13: "Citation verification: **mark only** (default) / **strict**", with one sentence of field guidance (strict suits DOI-dense fields; mark-only suits grey-literature-heavy fields). **Byte-equivalence is load-bearing**: a `strict` answer seeds `terminal_policies.citation_existence: strict` on the Material Passport at the point it is materialized (the finalizer stays the sole policy *evaluator*); a `mark only` or absent answer records the PCR row and **writes nothing** — per-key absence already means advisory (Invariant 7), so an unprompted run is byte-identical to pre-#392. Plan mode exempt (mirrors Step 12). No default changes anywhere. Guarded by `scripts/check_392_citation_verification_intake.py` (4 invariants, mutation-verified): Step 13 heading present (rename = fail-loud parse error), the no-handoff directive affirmatively reaches Step 13 (`then Step 13` — the exact #327 P1 orphaning that hit Step 12), PCR row present, and the advisory write-nothing rule + strict seeding target retained. 8 unit tests; wired into `spec-consistency.yml` + the CI pytest manifest.
 
 - **Layer-5 contribution-significance probes extended into plan mode and revision coaching (#393, blindspot-audit F-2, adjudicated shape 1).** ARS quality machinery was defect-oriented end-to-end — a paper could pass every gate and still be a micro-extension, because the only constructive contribution coaching (socratic_mentor Layer 5, SIGNIFICANCE & CONTRIBUTION) lived at the RQ-incubation stage. Layer 5 now defines three **later-stage anchored forms** with stable IDs — **L5-W1** "Ten years from now, what will citers say this paper established?", **L5-W2** "Remove this paper from the literature — what is missing?", **L5-W3** "If this paper succeeds, who would make different decisions as a result?" — and two later-stage surfaces consume them strictly by ID (the question text lives in Layer 5 and only there; a Layer-5 edit propagates by reference instead of forking — the cross-model review's P1 on a first draft that carried labeled copies): **(1)** `academic-paper` plan mode gains Step 2.5 CONTRIBUTION SHARPENING between chapter negotiation and the argument stress test — the mentor asks the user to articulate the contribution their own Chapter Summaries claim, quoting only user-written text; if the user articulates one, `[INSIGHT: contribution_claim]` records it in the user's words, otherwise the open question is carried into Step 3, never filled in; **(2)** `academic-paper-reviewer` Phase 2.5 gains step 3, a contribution framing probe alongside the existing prioritization steps (5→6 steps; no external step-number references existed), anchored to what the manuscript already claims. The orchestrator's Stage 3→4 coaching sketch now explicitly defers to the reviewer SKILL.md six-step list as authoritative (net-zero line edit — the surface has 1 line of v3.6.7 budget headroom left). Boundary is load-bearing (Kong L2 verb test, per the #393 adjudication that rejected shapes 2–3): questions only — never propose, substitute, rank, expand, or select a contribution claim. Prose-layer only; no schema, scoring, or agent-roster change. Two review gates, all findings adopted: codex cross-model (1 P1 + 2 P2 + 1 P3 — ID-based single-sourcing, verb-test tightening, orchestrator deferral, conditional INSIGHT) and an independent context reviewer (1 P1 + 1 P2 — the repo has TWO same-named `socratic_mentor_agent.md` files and plan mode dispatches the academic-paper variant, which had no Layer 5 and no Step 2.5 in its own flow, so the probe would never have fired: the agent prompt gains a Step 2.5 section referencing L5-W IDs by full path, the protocol's inline reference is path-disambiguated, and L5-W3's anchor permission is tightened to noun-phrase-swap-only).

POSITIONING.md

@@ -22,6 +22,13 @@ These are not "out of scope" footnotes. They are the load-bearing boundary that
 
 These are first-party scope boundaries and review criteria for future changes, not runtime guarantees. First-party ARS treats each as out of scope; adding one would require changing this recorded boundary, not merely adding a feature.
 
+## Recorded non-goals (scope boundaries without a mechanism)
+
+Unlike the Rejected mechanisms above — capabilities ARS refuses on principle — these are lifecycle stages and state layers ARS deliberately does not enter. They were adjudicated out of scope in the 2026-06-10 researcher-blindspot audit and are recorded here so the boundary is reviewable, not improvised (the same recording discipline as the Rejected mechanisms; boundary + review criterion, not a runtime guarantee).
+
+- **Post-publication lifecycle.** Tracking citation contexts of the scholar's own published papers, errata/corrigenda workflows, and OA self-archiving compliance are out of scope. ARS's front is research-to-publication; what happens to a paper after it ships belongs to the scholar and their institutional tooling. The existing `monitoring_agent` is unaffected — it alerts on developments in the *cited* literature (an input to current work), not on the scholar's own published output. Review criterion: a proposed feature whose value begins *after* the manuscript is accepted extends the front, and requires changing this recorded boundary first.
+- **Research-program-level state.** ARS keeps no memory across papers: no registry of the scholar's prior claims, no carried-forward limitations list, no reviewer-history profile. The per-paper Material Passport remains the only state carrier, and every run starts from what the scholar explicitly feeds it. This is a deliberate consequence of the anti-leakage philosophy — gates that trusted an ambient cross-paper memory would be evaluating state nobody declared this run. The supported way for a returning author to carry their own prior work forward without any new mechanism is the [Cross-paper workflow guide](docs/cross-paper-workflow.md). Review criterion: a proposed feature that reads or writes scholar state outside the current run's passport crosses this boundary.
+
 ## Allowed uses
 
 - Research assistance: literature search, source verification, citation checking

docs/cross-paper-workflow.md

@@ -0,0 +1,31 @@
+# Cross-paper workflow — carrying your own prior work forward
+
+ARS deliberately keeps no memory across papers ([POSITIONING.md § Recorded non-goals](../POSITIONING.md#recorded-non-goals-scope-boundaries-without-a-mechanism)): no claim registry, no carried-forward limitations, no reviewer-history profile. The per-paper Material Passport is the only state carrier. That is not a missing feature — gates that trusted ambient cross-paper memory would be evaluating state nobody declared in the current run, which is exactly the laundering channel the anti-leakage discipline closes.
+
+A returning author still has everything needed to build on their own prior work. The carry-forward is **scholar-initiated, explicit, and per-run** — three moves, no new mechanism:
+
+## 1. Re-feed the prior paper's Material Passport
+
+Passports are already the pipeline's only input port. If your previous paper was written with ARS, its literature corpus + passport is a complete, verification-stamped record of what you cited and what the gates found. Feed it to the new run the same way you would feed any corpus:
+
+- The new run treats it as declared input — every entry re-enters the normal verification path (cache hits make re-verification cheap; the 90-day SQLite cache is keyed per citation, not per paper).
+- Nothing is trusted *because* it came from your prior paper. A prior `ok` is a head start, not a waiver — stamps are re-derived under the current run's policies.
+- If the prior paper was not written with ARS, its reference list enters through the standard adapter path ([SETUP.md § adapters](SETUP.md#material-passport-literature_corpus-adapters-v364-optional): you own the adapter; the passport is the contract).
+
+## 2. Surface your own prior limitations as Socratic input
+
+The highest-value cross-paper carry is usually not the bibliography — it is the **Limitations section and the unresolved reviewer points** from the last paper. Bring them to RQ incubation (deep-research socratic mode) as material *you* supply:
+
+- Paste the prior limitations / reviewer comments and say what you think they imply. The Socratic mentor asks about *your* reading of them — gap-value, decision-impact, feasibility — exactly as it does for any scholar-supplied material.
+- ARS will **not** derive next-RQ candidates from your prior paper. That is the advisory-not-generation line (Kong L2, [design lesson](design/2026-06-08-kong-255-l2-advisory-not-generation.md)): it may surface patterns in what you wrote and ask; it must never propose, substitute, rank, expand, or select research questions for you. The next question stays authored by you.
+
+## 3. (Claude Code users) Assistant memory as a personal reminder layer
+
+If you run ARS inside Claude Code, the assistant's own memory can serve as a *personal* reminder layer — "last paper's reviewer 2 flagged the sampling frame," "I promised a follow-up on X." Two caveats, both load-bearing:
+
+- **ARS gates never read or trust assistant memory.** Passports remain the only state of record. A memory note is a prompt to *you* to supply the material explicitly (moves 1-2 above); it is never itself evidence, provenance, or input to a gate.
+- Memory is a convenience of your environment, not part of the workflow contract. The workflow above must work identically on a machine with no memory at all — if it doesn't, state has leaked outside the passport.
+
+---
+
+*Decision trail: 2026-06-10 researcher-blindspot audit (F-1B/F-7, #397); maintainer adjudicated "no mechanisms, record the boundaries, ship the workflow guide."*