Plan: manuscript-evidence-completion
Plan-set orchestration model: GPT-5.4 (codex) — effort
highRouted:
carter route -c complex -r planner→gpt-5.4/high(bar 83, capability 89.8)Coordinating this set is a planner-grade job: five phases, three of them multi-sub-layer, all converging on one manuscript whose LaTeX build must stay green and whose “production data only” norm must not be violated. A weaker orchestrator would mis-sequence the shared-
.texlandings and corrupt the two-class figure numbering.
Scope
Close the evidence gaps catalogued in the 2026-06 manuscript review (the “missing items / replacements” inventory). The manuscript currently:
- presents five benchmark/engineering figures from synthetic data (CF04, CF11, CF14, CF15, CF16), clearly labelled but not production;
- leaves two V2.2 aspirational figures unrealised (import/export workflow; tool-integration round-trip);
- carries real-data coverage caveats (MANC non-finite metrics, NeuroMorpho-dominated morphometry, narrow dual-network set, single developmental dataset);
- has two submission blockers (empty
syndb.datasetstable served from out-of-band manifests; placeholder archival DOI).
This plan converts what can be made real, honestly reframes what cannot, and clears the submission blockers — without inventing data.
Current state (entry conditions)
- Manuscript builds clean:
lualatex --shell-escape SynDB_Manuscript.tex+bibtex, 38pp, 0 undefined / 0 multiply-defined refs. - Two-class figure system in place: main Figs 1–5 (CF01,02,05,03,06), Supplementary Figs S1–S11, Tables S1–S9.
- Biology numerals come from the
2026-06-03production reproducibility run (article/reproducibility/biological-analyses-full-2026-06-03/). - Recovered external data:
article/reproducibility/external/ofer_2022_confocal_spines.md.
Phase table
| Phase | File | Outcome | Depends on | Blocking? | Parallel with | Model / Effort |
|---|---|---|---|---|---|---|
| 01 | 01-honesty-pass.md | Prose precisely separates real vs synthetic; federation correctness≠latency; cross-modality framing final | — | no | 02,03,04,05 | DeepSeek v4 Flash (opencode) / high |
| 02 | 02-deployment-submission/ | syndb.datasets populated + served from DB; archival DOI minted | — (cluster/DB) | submission | 01,03,04 | GPT-5.4-mini (codex) / medium |
| 03 | 03-synthetic-to-live-figures/ | CF04/CF11/CF14/CF16 regenerated from live cluster; CF15 honestly resolved | — (cluster) | no | 01,02,05 | GPT-5.4 (codex) / high |
| 04 | 04-ingestion-tool-integration-demo.md | One real import→query→export round-trip documented (V2.2 Fig5+Fig7 substitute) | — (cluster) | no | 01,02,05 | DeepSeek v4 Pro (opencode) / high |
| 05 | 05-coverage-expansion/ | MANC finite metrics + ≥1 added dataset per weak analysis, numerals regenerated | — (cluster+ETL) | no | 01,03,04 | GPT-5.4 (codex) / high |
No phase has a hard logical dependency on another — every phase’s
substantive work (cluster runs, ETL, DB ops, prose drafting) can begin from
the current tree. The coupling is entirely shared-file serialization on
the manuscript .tex (below).
Parallelism layer
The expensive work parallelises; only the manuscript-.tex commits
serialise, and only on specific hot files.
Wave 0 — fan out everything (no cross-conflict in the work)
Run concurrently; none of these block on another’s output:
- 01 drafts honesty/prose edits (results.tex federation framing + methods.tex wording).
- 02 populates the
syndb.datasetstable on the cluster and mints the Zenodo DOI. - 03 runs the live MV / storage / scale benchmarks and regenerates the composites (Python + artifacts).
- 04 executes one real import→query→export round-trip and captures it.
- 05 ingests the additional datasets and re-runs the analyses harness.
Serialization points — landing the .tex (do these one at a time)
Because the manuscript shares a few hot files, the commits that touch them must serialise. Each phase owns a disjoint file set except these overlaps:
| Hot file | Phases that land in it | Order |
|---|---|---|
article/sections/supplementary_figures.tex | 03 (CF04/11/14/15/16 captions), 04 (if it adds a supp figure) | 03 → 04 |
article/sections/discussion.tex (Limitations) | 02 (datasets-table bullet), 05 (coverage bullets) | 02 → 05 |
article/sections/methods.tex | 01 (synthetic-data wording), 04 (new import/export subsection) | 01 → 04 |
article/sections/results.tex | 01 only | — |
article/sections/bio/*.tex | 05 only | — |
article/SynDB_Manuscript.tex / back_matter.tex | 02 (DOI) only | — |
Rule: after each .tex landing, run the build gate (below) before the next
phase rebases onto it. Pull/rebase article/ before starting a phase whose
hot files another phase already landed.
Final wave — reconciliation
After all landed: a full lualatex ×2 + bibtex + lualatex pass; confirm
figure/table numbering and the main/supplement split are intact; prompt
verify.
Whole-set acceptance criteria
-
cd article && lualatex --shell-escape … && bibtex … && lualatex ×2→ exit 0, 0 undefined, 0 multiply-defined. - No figure presents synthetic data as production. Every remaining synthetic panel is captioned as a labelled control or has been converted to live data with provenance under
article/reproducibility/. -
syndb.datasetsreturns DOI/licence/owner from the database (not out-of-band manifests); the corresponding Limitations bullet is removed. -
article/sections/back_matter.texcarries a real archival DOI (no “will be added”). - Federation correctness (CF03) and federation latency (CF15/synthetic) are textually separated; no sentence implies the latency numbers are production.
- Any biology numeral change came from a re-run of
run_biological_analyses, not a hand edit; the reproducibility anchor is updated. - Main Figs 1–5 and Supplementary Figs S1–S11 / Tables S1–S9 numbering preserved.
Global constraints (apply to every phase)
- Build gate after every
.texland:cd article && lualatex -interaction=nonstopmode -halt-on-error --shell-escape SynDB_Manuscript.tex(twice; addbibtex SynDB_Manuscriptbetween if citations changed). 0 errors, 0 undefined refs. - Production-data norm: never present synthetic as production. New quantitative claims come from the live Nautilus cluster or a cited published source, with provenance recorded under
article/reproducibility/. - Never hand-edit biology numerals. Regenerate via
python -m syndb_plot.manuscript.run_biological_analyseswith--macros-output article/generated_values.tex; prose cites the generated\bv…macros. - Preserve the two-class figure system (
\synfiguremain vs\suppfigure/supptabS-numbered) defined inarticle/macros.tex. - No
\todo/placeholder may survive in a phase’s deliverable section. - Signed commits using the user’s global git config as-is (no
--no-gpg-sign, no overridinggpg.*). If signing blocks, stop and report.
Dispatch notes
- opencode phases (DeepSeek v4 Flash/Pro):
opencode run --model <id>; carter’s reported effort is already the effective tier. - codex phases (GPT-5.4 / -mini): set effort via
-c model_reasoning_effort=high|medium. - If dispatched via the Claude Code Agent tool, set
/effort <tier>before spawning (the Agent tool inherits parent effort).
Reference
- Gap inventory: this session’s “missing items / replacements” reply.
- Manuscript audit:
article/NARRATIVE_AUDIT.md. - Recovered external data:
article/reproducibility/external/ofer_2022_confocal_spines.md. - Manuscript skill:
.claude/skills/manuscript/. - Run the phases yourself; prompt
verifywhen done to audit acceptance criteria.