superlab 0.1.24 → 0.1.26

package/package-assets/shared/skills/lab/references/paper-writing/examples/experiments/main-results-and-ablation-latex.md

@@ -0,0 +1,83 @@
+# Main Results and Ablation LaTeX Example
+
+This file is a complete paper-facing LaTeX example for the experiments section.
+Reuse the structure, caption logic, and prose-to-table linkage. Replace the
+placeholder methods, metrics, and values with the current project's evidence.
+
+Source inspiration:
+- full table/figure organization examples from
+  `guanyingc/latex_paper_writing_tips`
+- full paper-source organization from
+  `evaluating-adversarial-robustness/adv-eval-paper`
+
+## Main Results Table
+
+```tex
+\begin{table}[t]
+\caption{Main benchmark results under the frozen evaluation protocol. Higher is better on all metrics.}
+\label{tab:main-results}
+\centering
+\resizebox{0.92\linewidth}{!}{
+\begin{tabular}{lccc}
+\toprule
+Method & AUUC $\uparrow$ & Qini $\uparrow$ & Calibration Error $\downarrow$ \\
+\midrule
+Strongest baseline & 0.1421 & 0.0873 & 0.0612 \\
+Closest prior work & 0.1488 & 0.0915 & 0.0544 \\
+Ours & \textbf{0.1564} & \textbf{0.0987} & \textbf{0.0418} \\
+\bottomrule
+\end{tabular}
+}
+\end{table}
+```
+
+Table message:
+- `Does the proposed method beat the strongest baselines under the frozen protocol?`
+
+## Ablation Table
+
+```tex
+\begin{table}[t]
+\caption{Ablations that isolate which design choices create the gain.}
+\label{tab:ablations}
+\centering
+\begin{tabular}{lc}
+\toprule
+Variant & AUUC $\uparrow$ \\
+\midrule
+Ours & \textbf{0.1564} \\
+w/o structure module & 0.1497 \\
+w/o calibration stage & 0.1510 \\
+w/ shuffled auxiliary signal & 0.1458 \\
+\bottomrule
+\end{tabular}
+\end{table}
+```
+
+Table message:
+- `Which design choices create the gain, and which ones are neutral?`
+
+## Experiments Section Stitching Example
+
+```tex
+\section{Experiments}
+\label{sec:experiments}
+
+Table~\ref{tab:main-results} answers the main ranking question: whether the full
+method remains stronger than the closest prior work and the strongest practical
+baseline under the frozen protocol. Our method achieves the best AUUC and Qini
+while also reducing calibration error, which means the gain is not coming from
+trading ranking quality against stability.
+
+Table~\ref{tab:ablations} then asks a narrower mechanism question. Removing the
+structure module causes the largest drop, so the main gain is tied to structured
+signal modeling rather than to a generic increase in capacity. Removing the
+calibration stage leads to a smaller but still visible drop, which supports the
+claim that calibration improves final ranking quality without being the sole
+driver of the result. The shuffled-signal variant acts as a negative control and
+shows that the gain does not survive when the auxiliary information is broken.
+
+One caveat is that the calibration gain may remain neutral on some benchmarks,
+so the paper should not overclaim that every component helps equally on every
+dataset.
+```

package/package-assets/shared/skills/lab/references/paper-writing/examples/experiments-examples.md

@@ -0,0 +1,17 @@
+# Experiments Example Patterns
+
+Use these examples when turning validated results into paper-facing LaTeX assets.
+The referenced files contain complete LaTeX environments and section-level prose
+glue, not just checklists.
+
+## Required Asset Pattern
+
+1. Main results should live in a real `table` environment.
+2. Ablations should live in a separate `table` environment.
+3. Method and experiments should each have at least one figure placeholder with an explicit `Figure intent`.
+4. Captions should explain the table or figure message briefly; longer interpretation belongs in prose.
+
+## Example Files
+
+- `examples/experiments/main-results-and-ablation-latex.md`
+- `examples/experiments/figure-placeholder-and-discussion.md`

package/package-assets/shared/skills/lab/references/paper-writing/examples/index.md

@@ -1,6 +1,7 @@
 # Example Bank Index
 
-Use this folder for concrete writing patterns and locally organized cite targets.
+Use this folder for concrete writing patterns, complete LaTeX snippets, and
+locally organized cite targets.
 
 ## Files
 
@@ -12,10 +13,18 @@ Use this folder for concrete writing patterns and locally organized cite targets
 6. Introduction pipeline files: `references/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.md`, `references/examples/introduction/pipeline-version-2-two-contributions.md`, `references/examples/introduction/pipeline-version-3-new-module-on-existing-pipeline.md`, `references/examples/introduction/pipeline-version-4-observation-driven.md`, `references/examples/introduction/pipeline-not-recommended-abstract-only.md`
 7. Method examples index: `references/examples/method-examples.md`
 8. Method detail files: `references/examples/method/pre-writing-questions.md`, `references/examples/method/module-triad-neural-body.md`, `references/examples/method/neural-body-annotated-figure-text.md`, `references/examples/method/module-design-instant-ngp.md`, `references/examples/method/module-motivation-patterns.md`, `references/examples/method/section-skeleton.md`, `references/examples/method/overview-template.md`, `references/examples/method/example-of-the-three-elements.md`, `references/examples/method/method-writing-common-issues-note.md`
+9. Related work examples index: `references/examples/related-work-examples.md`
+10. Related work files: `references/examples/related-work/closest-prior-gap-template.md`, `references/examples/related-work/topic-comparison-template.md`
+11. Experiments examples index: `references/examples/experiments-examples.md`
+12. Experiments files: `references/examples/experiments/main-results-and-ablation-latex.md`, `references/examples/experiments/figure-placeholder-and-discussion.md`
+13. Conclusion examples index: `references/examples/conclusion-examples.md`
+14. Conclusion files: `references/examples/conclusion/conservative-claim-boundary.md`
 
 ## Usage
 
 1. Pick one template from a section guide.
 2. Open the matching examples file.
-3. Reuse the sentence logic, not exact wording.
-4. Keep citation links in your notes for traceability.
+3. Prefer the complete LaTeX examples when the section needs tables, figures,
+   citations, or section-level stitching.
+4. Reuse the structure and command patterns, not exact wording.
+5. Keep citation links in your notes for traceability.

package/package-assets/shared/skills/lab/references/paper-writing/examples/related-work/closest-prior-gap-template.md

@@ -0,0 +1,20 @@
+# Closest Prior Then Gap LaTeX Example
+
+Use this example when one family of papers is the closest technical anchor and
+the paragraph needs to explain the gap precisely.
+
+```tex
+\paragraph{Closest prior work.}
+The closest prior line improves uplift ranking by sharpening the treatment-aware
+scoring objective rather than by changing the final decision rule
+itself~\cite{lee2021uplift,wang2022counterfactual}. These methods are strong
+references because they already optimize for ranking quality and outperform
+simple pointwise baselines on standard benchmarks. However, they still assume
+that the learned score can be used directly as the final ranking signal across
+datasets with different calibration behavior. That assumption is limiting in our
+setting, where the raw score often contains useful relative information but is
+not always aligned with the final protocol-level target. Our method keeps the
+ranking-focused backbone but changes the final stage by inserting a post-hoc
+calibration module, so the method can preserve the stronger internal signal
+while adapting the exposed score to the benchmark-specific decision scale.
+```

package/package-assets/shared/skills/lab/references/paper-writing/examples/related-work/topic-comparison-template.md

@@ -0,0 +1,24 @@
+# Topic Comparison LaTeX Example
+
+Use this example when the related-work section needs a compact, citation-driven
+comparison paragraph rather than a bullet list of papers.
+
+```tex
+\paragraph{Structure-aware ranking methods.}
+A second line of work improves ranking by injecting structured inductive bias
+into the scoring function~\cite{smith2021structured,lee2022pairwise}. These
+methods are attractive because they often stabilize training and can exploit
+known relationships among samples or treatment groups. However, they typically
+assume that the structured module alone is sufficient to produce well-calibrated
+scores at evaluation time. In our setting, that assumption is too strong: the
+raw ranking signal remains useful, but it is not always aligned with the final
+decision scale required by the frozen protocol. We therefore keep the
+structure-aware backbone but add a separate calibration stage, which lets us
+reuse the stronger signal while correcting its final score mapping.
+```
+
+What this paragraph does:
+1. groups one literature line by topic
+2. states why the line is attractive
+3. identifies the exact limitation that matters here
+4. positions the current method as a narrower, testable change

package/package-assets/shared/skills/lab/references/paper-writing/examples/related-work-examples.md

@@ -0,0 +1,17 @@
+# Related Work Example Patterns
+
+Use these examples to structure `related work` around technical gaps instead of
+citation dumping. The referenced files are complete citation-driven LaTeX
+paragraph examples.
+
+## Recommended Pattern
+
+1. Open with the topic line.
+2. Summarize 2-4 representative methods compactly.
+3. State the exact limitation that matters for the current problem.
+4. End with a transition sentence that positions the current method.
+
+## Example Files
+
+- `examples/related-work/closest-prior-gap-template.md`
+- `examples/related-work/topic-comparison-template.md`

package/package-assets/shared/skills/lab/references/paper-writing-integration.md

@@ -2,13 +2,13 @@
 
 `/lab:write` vendors the paper-writing references directly into `skills/lab/references/paper-writing/`.
 The goal is to keep the upstream writing discipline while removing brittle runtime dependence on a separately installed skill.
-It also vendors the upstream example bank for the sections that currently have curated examples, so drafting can reuse concrete structure rather than only abstract guidance.
+It also vendors the upstream example bank for the sections that currently have curated examples, and adds local manuscript-delivery examples for missing sections, so drafting can reuse concrete structure rather than only abstract guidance.
 
 ## Role Split
 
 - `lab` controls stage boundaries, evidence discipline, and durable artifacts.
 - the vendored paper-writing references control section structure, paragraph logic, and reviewer-facing polish.
-- the vendored example bank controls example-driven structure selection for `abstract`, `introduction`, and `method`.
+- the vendored example bank controls example-driven structure selection for section prose and paper-facing LaTeX assets.
 - `/lab:write` links evidence-backed research outputs to paper-ready text.
 
 ## Required Shared Constraints
@@ -41,26 +41,35 @@ It also vendors the upstream example bank for the sections that currently have c
 - `paper-writing/examples/abstract-examples.md`
 - `paper-writing/examples/introduction-examples.md`
 - `paper-writing/examples/method-examples.md`
+- `paper-writing/examples/related-work-examples.md`
+- `paper-writing/examples/experiments-examples.md`
+- `paper-writing/examples/conclusion-examples.md`
 - `paper-writing/examples/abstract/*`
 - `paper-writing/examples/introduction/*`
 - `paper-writing/examples/method/*`
+- `paper-writing/examples/related-work/*`
+- `paper-writing/examples/experiments/*`
+- `paper-writing/examples/conclusion/*`
 
 ## Write-Time Rule
 
-For `abstract`, `introduction`, and `method`:
+For `abstract`, `introduction`, `method`, `related work`, `experiments`, and `conclusion`:
 
 1. read the section guide first
-2. read the matching examples index
+2. if the section has a bundled examples index, read it
 3. read 1-2 concrete example files that match the intended structure
-4. reuse structure and sentence logic without copying wording
-
-For `related work`, `experiments`, and `conclusion`:
-
-1. use the section guide directly
-2. do not invent non-existent example-bank files
+4. reuse structure, sentence logic, and LaTeX asset patterns without copying wording
 
 ## Attribution
 
 These references are adapted from:
 
 - `https://github.com/Master-cai/Research-Paper-Writing-Skills/tree/main/research-paper-writing/references`
+
+The local manuscript-delivery examples for missing sections are additionally informed by public LaTeX guidance and real paper-source repositories, including:
+
+- `https://github.com/guanyingc/latex_paper_writing_tips`
+- `https://github.com/evaluating-adversarial-robustness/adv-eval-paper`
+- `https://github.com/lightningnetwork/paper`
+
+These sources are used as structure references for complete LaTeX snippets, table/figure organization, and manuscript assembly patterns, so `/lab:write` can enforce tables, figure placeholders, and bibliography-ready drafts rather than prose-only section text.

package/package-assets/shared/skills/lab/stages/report.md

@@ -16,6 +16,7 @@
 - experiment setup
 - validated main results
 - managed main tables artifact under `<deliverables_root>/main-tables.md`
+- internal artifact-status artifact under `<deliverables_root>/artifact-status.md`
 - how-to-read-the-tables guide
 - ablations
 - failed attempts
@@ -27,6 +28,7 @@
 
 - `.lab/context/mission.md`
 - `.lab/context/state.md`
+- `.lab/context/workflow-state.md`
 - `.lab/context/decisions.md`
 - `.lab/context/evidence-index.md`
 - `.lab/context/data-decisions.md`
@@ -38,6 +40,7 @@
 - `.lab/context/mission.md`
 - `.lab/context/eval-protocol.md`
 - `.lab/context/state.md`
+- `.lab/context/workflow-state.md`
 - `.lab/context/evidence-index.md`
 
 ## Evidence Rules
@@ -56,7 +59,7 @@
 - When citing prior work or baselines in the method overview, include only the few anchor references a collaborator needs, and summarize their role and limitation in one short line each.
 - Report only the few references a collaborator needs to orient themselves quickly; do not turn `report.md` into a full bibliography dump.
 - In `Background Sources`, `Method and Baseline Sources`, and `Metric Sources`, every anchor must include a citation line, one short line about what it established or measures, and one limitation or caveat.
-- Internal provenance belongs in `Artifact Status` or `.lab/context/evidence-index.md`, not in the external-review-ready source sections.
+- Internal provenance belongs in `<deliverables_root>/artifact-status.md` or `.lab/context/evidence-index.md`, not in the external-review-ready source sections.
 - If the report depends on a deviation from an original metric or implementation, state that deviation explicitly instead of smoothing it over.
 - Carry the approved `Claim boundary` into the collaborator-facing report instead of implying broader validity than the protocol allows.
 - If the `Academic Validity Checks` or `Integrity self-check` sections are incomplete, contradictory, or obviously violated by the evidence, degrade the report instead of presenting it as collaborator-ready.
@@ -67,7 +70,7 @@
 - If collaborator-critical fields still remain missing after hydration, downgrade the output to an `artifact-anchored interim report` instead of presenting it as a final collaborator-ready report.
 - If the existing `report.md` or `main-tables.md` is missing required collaborator-facing sections from the managed templates, treat that as a report deficiency. A rerun must repair the missing sections instead of declaring "no content change" or treating the rerun as a no-op.
 - After drafting or rerunning the report, run `.lab/.managed/scripts/validate_collaborator_report.py --report <deliverables_root>/report.md --main-tables <deliverables_root>/main-tables.md`. If it fails, keep editing until it passes; do not stop at a no-op audit rerun.
-- Do not mix workflow deliverable status, rerun ids, or manuscript skeleton status into validated scientific findings; keep those in a separate artifact-status section.
+- Do not mix workflow deliverable status, rerun ids, or manuscript skeleton status into validated scientific findings; keep those in `<deliverables_root>/artifact-status.md`.
 - If `.lab/config/workflow.json` sets the workflow language to Chinese, write `report.md` and `<deliverables_root>/main-tables.md` in Chinese unless a file path, code identifier, or literal metric name must remain unchanged.
 - Prefer conservative interpretation over marketing language.
 - Leave a clear handoff path into `/lab:write` with evidence links that section drafts can cite.

package/package-assets/shared/skills/lab/stages/write.md

@@ -45,6 +45,9 @@ When the current target has a bundled example bank, load the examples index and
 - abstract -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/abstract-examples.md`, plus one matching file under `skills/lab/references/paper-writing/examples/abstract/`
 - introduction -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/introduction-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/introduction/`
 - method -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/method-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/method/`
+- related work -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/related-work-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/related-work/`
+- experiments -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/experiments-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/experiments/`
+- conclusion -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/conclusion-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/conclusion/`
 
 Run these on every round:
 
@@ -61,17 +64,42 @@ Run these on every round:
 - If the user chooses the default scaffold, persist that choice in `.lab/config/workflow.json` by setting `paper_template_decision` to `default-scaffold`.
 - If the user chooses to attach a template, stop the drafting loop and route to `superlab paper attach-template --path <dir>` instead of silently falling back.
 - If `paper_template_decision` is `default-scaffold`, use the managed default LaTeX scaffold under the deliverable paper directory.
+- When using the managed default scaffold, use the managed paper asset templates as the starting point for new manuscript assets:
+  - `.lab/.managed/templates/paper.tex`
+  - `.lab/.managed/templates/paper-section.tex`
+  - `.lab/.managed/templates/paper-table.tex`
+  - `.lab/.managed/templates/paper-figure.tex`
+  - `.lab/.managed/templates/paper-references.bib`
 - If the current round is a final manuscript export or final-draft pass, `paper_template_root` is still empty, `paper_template_decision` is `default-scaffold`, and `paper_template_final_reminder_acknowledged` is `false`, ask one final reminder question about switching to a template before finalizing.
 - If the user confirms staying on the default scaffold at that final reminder, persist `paper_template_final_reminder_acknowledged: true`.
 - Load only the current section guide. Do not load every section guide at once.
-- Reuse example-bank structure, paragraph roles, and sentence logic when examples are bundled, but never copy wording verbatim.
+- Reuse example-bank structure, paragraph roles, sentence logic, and paper-facing LaTeX asset patterns when examples are bundled, but never copy wording verbatim.
 - Treat example cites and example file names as writing references, not as evidence for the current paper.
 - Build a compact mini-outline before prose.
+- Build the paper asset plan before prose when the section carries experimental or method claims:
+  - decide which tables the section needs
+  - decide which figure placeholders the section needs
+  - decide which citations must appear in the section
 - For each subsection, explicitly include motivation, design, and technical advantage when applicable.
 - Avoid a writing style that reads like incremental patching of a naive baseline.
 - Keep terminology stable across the full paper.
 - Tie every new or revised claim to explicit evidence.
 - If a claim cannot be supported by results, weaken or remove it.
+- Do not treat section prose alone as a completed manuscript round.
+- For paper-facing final drafts, maintain a non-empty `references.bib` with real citation keys instead of TODO placeholders.
+- Keep paper-facing LaTeX free of absolute local paths, shell logs, rerun ids, and workflow-only provenance.
+- Replace raw engineering notation such as `+/-` with proper LaTeX formatting such as `\pm`.
+- If the current paper contains experimental claims, materialize real LaTeX table assets instead of leaving all results in prose:
+  - `<deliverables_root>/paper/tables/main-results.tex`
+  - `<deliverables_root>/paper/tables/ablations.tex`
+- If the current paper contains method or experiments claims, materialize figure placeholders with captions, labels, and explicit figure intent:
+  - `<deliverables_root>/paper/figures/method-overview.tex`
+  - `<deliverables_root>/paper/figures/results-overview.tex`
+- Table assets must use paper-facing LaTeX structure with `booktabs`, caption, label, and consistent precision.
+- Figure placeholders must explain what the final figure should show and why the reader needs it.
+- Run `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before accepting a final-draft or export round.
+- If the manuscript validator fails, keep editing and asset generation until it passes; do not stop at prose-only completion.
+- Run a LaTeX compile smoke test when a local LaTeX toolchain is available; if not available, record the missing verification in the write iteration artifact.
 - Record what changed and why in a write-iteration artifact.
 - Return paragraph-level roles for the revised prose when drafting.
 - Run the five-dimension self-review checklist before accepting a round.
@@ -85,7 +113,12 @@ Run these on every round:
 - `.lab/writing/plan.md`
 - `.lab/writing/iterations/<n>.md`
 - `<deliverables_root>/paper/main.tex`
+- `<deliverables_root>/paper/references.bib`
 - `<deliverables_root>/paper/sections/<section>.tex`
+- `<deliverables_root>/paper/tables/main-results.tex`
+- `<deliverables_root>/paper/tables/ablations.tex`
+- `<deliverables_root>/paper/figures/method-overview.tex`
+- `<deliverables_root>/paper/figures/results-overview.tex`
 
 ## Stop Conditions
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.24",
+  "version": "0.1.26",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",