frontend-patterns/research/evaluations/language-replication-03

Replication 03 — draft criteria revision

Status: draft, not frozen, not authorized for execution. Owner: FEP-WP-0009 T02. Prepared 2026-10-20 by Claude Code (author-model) at the owner's request, using no model calls. It applies the results of the pilot-01 human review and adjudication (review, adjudication). Replication-02 and its spent run identities stay unchanged.

Why a revision

Replication-02 already uses six single-obligation criteria per scenario. The pilot-01 adjudication found 11 of 16 disagreements were caused by rubric wording, not by the reviewers. Four kinds of ambiguity recur, and several replication-02 criteria still admit them:

Ambiguity found in pilot-01	Example	Replication-02 criteria affected
Generic vs specific contract naming	S01/S02/S04 Q	S01-A3, S02-A6, S03-A5, S05-A6, S06-A6
Condition stated elsewhere vs in the recommendation	S03 R	S01-A4, S01-A5
End state vs stated atomic step	S05 C1	S03-A1
Flat assertion of an unknown fact	S01-V "stale"; S03-V "must be retained"	S01-A6, S06-A5

The reviewer's recurring guidance was to pair abstract wording with a concrete example. Each criterion in scenarios.draft.json therefore carries qualifies and does_not_qualify examples, a placement and a change_from_r02 note. Briefs and prohibited lists are copied unchanged.

Draft scoring rules

• G1 Placement. A recommendation criterion is met only inside the recommended state or action. A matching statement only in a later questions section does not count. An anywhere criterion may be met in any section.
• G2 Named subject. A contract-identification criterion requires the guarantee's subject (for example lookup, replay window, read-after-write). A generic "define the contract" does not qualify. Listed alternatives joined by "or" are each sufficient.
• G3 Examples are illustrative. Equivalent wording qualifies; the examples show where the line is, not required phrases.
• G4 Unknown facts. Asserting an unspecified fact as known (stale, permanent, succeeded) is recorded as an unsupported claim.
• G5 Overstated caution (for example "cannot recover" where it is only untested) is recorded as a separate observation, not an unsupported claim, following the owner's S06-V adjudication.
• G6 Ambiguity is a valid result. A reviewer may mark a criterion ambiguous (X) instead of forcing a score; ambiguity counts are reported per criterion.

Reviewer support

The pilot-01 human review worked only in interview form, with plain-language context per scenario. A replication-03 worksheet should include that context, written before any answers exist, without hints about any answer.

Decisions needed before freezing

• D1 Reuse briefs. The six replication-02 briefs were never shown to a solver, so reuse keeps them unseen. The author has seen them, as before. Recommended: reuse.
• D2 "Impossible" claims. Replication-02 S04-A4 scored "recovery is impossible" as a miss. Under G5 it becomes an observation. Recommended: apply G5.
• D3 Reviewer. Owner review again, an external reviewer, or both. An external reviewer strengthens M1 independence.
• D4 Execution. A new run identity, restored llm-connect reachability from this workstation and a fresh call-budget authorization (12 capped calls, no retries, as before).

Not yet done

No freeze, prompts, assignment, runner wiring or tests. These follow D1–D4 and reuse the replication-02 tooling with a new packet identity. Packs stay byte-identical to replication-02 unless a decision changes them.