- Preserve `consulted_refs`, `followed_refs`, `research_trace`, and `research_summary` inside raw responder output when the responder or runner produces them; mirror indexable provenance into capture metadata.
- Require `runner_captured` research trace status for accepted research-enabled gold data; coordinator-reconstructed trace is useful draft audit, not proof of the responder's actual research path.
- The Veyr/Callisto provenance sample is the first accepted coordinator-scoped retrieval lane with `runner_captured` trace. Use it as the current pattern for trace-backed gold candidates.
- Interactive-fiction correction: a full-story pass is not just a linear chain of responder receipts. It needs a beginning-to-ending narrative spine, branch points, and cross-scene consequence carryover so decisions visibly matter later. Responder artifacts should be generated at branch/action moments, while coordinator artifacts track branch flags, relationship deltas, resource costs, unresolved hooks, and later scene consequences.
- Branch-and-fold correction: do not let every choice create an isolated subtree. Normalize consequences into compact state bands and flags, fold most branches back into shared later scenes, and reserve major route splits for consequences that change the playable world enough that convergence would lie.
- Branch compiler correction: treat Ink materialization as its own organ. It receives fixture brief, lore digest, scene/world/relationship state, actor-local branch candidates, consequence packets, fold plan, and optional visual replay requirements; it emits playable Ink plus a training sidecar, a separate visual plan artifact when illustrated replay is in scope, and compiler notes. It does not own hidden character truth or social mutation.
- Website-content correction: illustrated fixtures should include an art-direction block with establishing shot, light/color, bodies/interfaces, material evidence, branch-visible marks, one durable base image prompt, and additive branch/state modification prompts. Visual continuity is presentation and replay support for the corpus, not a core social-model training target.
- IF review correction: run an independent artifact reviewer after branch/Ink generation and before acceptance. The reviewer audits fake variables, cosmetic choices, missing state reads, fake folds, unearned convergence, state-named-instead-of-checked prose, visual callback gaps, and endings that ignore major state. The first Cold Wake user review is a seed failure taxonomy for this evaluator path.
- Still emit training artifacts at material turns: projected local context, responder packet, raw output/capture, leakage audit, reviewed mutation receipt, and aftermath state where relevant.
- Do not stop for every minor prose flaw; curate as coordinator and continue. Stop to patch the pipeline only for core invariant failures: hidden-state leakage, lore grounding failure, visibility/object/body affordance errors, bad state mutation, or schema break.