superlab 0.1.27 → 0.1.28

package/package-assets/shared/lab/.managed/templates/paper-plan.md

@@ -24,6 +24,13 @@
 - Limitation sources:
 - Claims that still need more evidence:
 
+## Asset Coverage Targets
+
+- Core asset floor:
+- Required coverage categories:
+- Current planned core assets:
+- Coverage risks or gaps:
+
 ## Table Plan
 
 - Main results table:
@@ -41,6 +48,12 @@
 
 ## Figure Plan
 
+- Problem setting or teaser figure:
+  - Asset file:
+  - Section:
+  - Figure intent:
+  - Evidence:
+  - Status:
 - Method overview figure:
   - Asset file:
   - Section:
@@ -54,6 +67,16 @@
   - Evidence:
   - Status:
 
+## Analysis Asset Plan
+
+- Analysis asset:
+  - Asset file:
+  - Asset type:
+  - Section:
+  - Asset intent:
+  - Evidence:
+  - Status:
+
 ## Citation Plan
 
 - Background anchor:
@@ -74,6 +97,7 @@
 
 ## Section-to-Asset Map
 
+- Introduction:
 - Method:
 - Experiments:
 - Related Work:

package/package-assets/shared/lab/config/workflow.json

@@ -7,5 +7,6 @@
   "deliverables_root": "docs/research",
   "paper_template_root": "",
   "paper_template_decision": "unconfirmed",
-  "paper_template_final_reminder_acknowledged": false
+  "paper_template_final_reminder_acknowledged": false,
+  "paper_language_finalization_decision": "unconfirmed"
 }

package/package-assets/shared/lab/context/auto-mode.md

@@ -68,4 +68,4 @@ If `eval-protocol.md` declares structured rung entries, auto mode follows those
 
 - Stop conditions:
 - Escalation conditions:
-- Canonical promotion writeback: update `.lab/context/data-decisions.md`, `.lab/context/decisions.md`, `.lab/context/state.md`, and `.lab/context/session-brief.md`.
+- Canonical promotion writeback: update `.lab/context/data-decisions.md`, `.lab/context/decisions.md`, `.lab/context/state.md`, and `.lab/context/workflow-state.md`.

package/package-assets/shared/lab/context/next-action.md

@@ -5,15 +5,15 @@
 - Action:
 - Success signal:
 
-## If Success
+## After Completion
 
 - Next action:
 
-## If Failure
+## If Blocked
 
 - Fallback action:
 
-## Human Decision Needed
+## Escalation
 
 - Question:
-- Why it blocks progress:
+- Escalate when:

package/package-assets/shared/lab/context/session-brief.md

@@ -3,6 +3,8 @@
 ## Active Stage
 
 - Stage:
+- Current objective:
+- Immediate next action:
 
 ## Mission
 
@@ -11,10 +13,15 @@ One sentence describing the active research mission.
 ## Best Current Path
 
 - Approved direction:
-- Why this is the active path:
+- Strongest supported claim:
 - Auto mode:
 - Auto objective:
 - Auto decision:
+- Collaborator report mode:
+- Canonical context readiness:
+- Method name:
+- Primary metrics:
+- Secondary metrics:
 
 ## Main Risk
 

package/package-assets/shared/lab/context/summary.md

@@ -1,12 +1,23 @@
 # Research Summary
 
 ## Current Direction
-
-Summarize the current approved research direction in 5-10 lines.
-
+- Mission:
+- Approved direction:
+- Active stage:
+- Current objective:
 - Auto mode:
 - Auto objective:
 - Auto decision:
+- Collaborator report mode:
+- Canonical context readiness:
+- Method name:
+- Contribution bullets:
+- Eval objective:
+- Primary metrics:
+- Secondary metrics:
+- Dataset package:
+- Benchmark role:
+- Comparison suite:
 
 ## Strongest Evidence
 

package/package-assets/shared/skills/lab/SKILL.md

@@ -34,17 +34,22 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 ### `/lab:idea`
 
 - Search relevant literature, baselines, datasets, and evaluation metrics before proposing a plan.
+- Build a literature-scoping bundle before claiming novelty. The default target is 20 relevant sources unless the field is genuinely too narrow and that exception is written down.
 - Read `.lab/context/mission.md` and `.lab/context/open-questions.md` before drafting.
+- Read `.lab/config/workflow.json` before drafting and follow its `workflow_language` for idea artifacts.
 - Ask one clarifying question at a time when critical ambiguity remains.
-- State the problem, the failure case, and why the problem matters before proposing solutions.
+- State the scenario, the problem, the failure case, and why the problem matters before proposing solutions.
 - Classify the idea by contribution category and breakthrough level.
 - Compare against existing methods explicitly and state why the idea should be better.
+- Include a closest-prior-work comparison and a plain-language description of how the proposed direction would work.
 - Distinguish sourced evidence from generated innovation claims.
 - End with three meaningful points that are clear, short, and easy to scan.
 - Produce 2-3 candidate approaches with trade-offs before recommending one.
 - Critique the idea before converging on it.
+- Include a minimum viable experiment before approval.
 - Keep an explicit approval gate before `/lab:spec`.
 - Write idea artifacts with the template in `.lab/.managed/templates/idea.md`.
+- Run `.lab/.managed/scripts/validate_idea_artifact.py --idea <idea-artifact> --workflow-config .lab/config/workflow.json` before treating the idea as converged.
 - Update `.lab/context/mission.md`, `.lab/context/decisions.md`, and `.lab/context/open-questions.md` after convergence.
 - Do not leave `.lab/context/mission.md` as a template shell once the problem statement and approved direction are known.
 - Do not implement code in this stage.
@@ -91,9 +96,9 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - Reuse `/lab:run`, `/lab:iterate`, `/lab:review`, `/lab:report`, and optional `/lab:write` instead of inventing a second workflow.
 - Do not automatically change the research mission, paper-facing framing, or core claims.
 - You may add exploratory datasets, benchmarks, and comparison methods inside the approved exploration envelope.
-- You may promote an exploratory addition to the primary package only after the promotion policy in `auto-mode.md` is satisfied and the promotion is written back into `.lab/context/data-decisions.md`, `.lab/context/decisions.md`, `.lab/context/state.md`, and `.lab/context/session-brief.md`.
+- You may promote an exploratory addition to the primary package only after the promotion policy in `auto-mode.md` is satisfied and the promotion is written back into `.lab/context/data-decisions.md`, `.lab/context/decisions.md`, `.lab/context/state.md`, and `.lab/context/workflow-state.md`.
 - Poll long-running commands until they complete, time out, or hit a stop condition.
-- Update `.lab/context/auto-status.md`, `.lab/context/state.md`, `.lab/context/workflow-state.md`, `.lab/context/decisions.md`, `.lab/context/data-decisions.md`, `.lab/context/evidence-index.md`, and `.lab/context/session-brief.md` as the campaign advances.
+- Update `.lab/context/auto-status.md`, `.lab/context/state.md`, `.lab/context/workflow-state.md`, `.lab/context/decisions.md`, `.lab/context/data-decisions.md`, and `.lab/context/evidence-index.md` as the campaign advances, then refresh the derived handoff files.
 - Keep an explicit approval gate when a proposed action would leave the frozen core defined by the auto-mode contract.
 
 ### `/lab:spec`
@@ -165,26 +170,21 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 
 - Start only after `report` artifacts are stable enough to support paper claims.
 - Start only after an approved framing artifact exists at `.lab/writing/framing.md`.
-- Read `.lab/config/workflow.json` before drafting and enforce its `paper_language` and `paper_format`.
-- If `paper_template_root` is empty and `paper_template_decision` is `unconfirmed`, ask once whether to continue with the managed default scaffold or attach a template directory first; persist the answer before drafting `.tex`.
-- If the project is still on the default scaffold at a final export or final-draft boundary and `paper_template_final_reminder_acknowledged` is `false`, ask one final reminder question before finalizing.
+- Read `.lab/config/workflow.json` before drafting and enforce its `workflow_language`, `paper_language`, and `paper_format`.
 - Read `.lab/context/mission.md`, `.lab/context/decisions.md`, `.lab/context/evidence-index.md`, and `.lab/context/data-decisions.md` before drafting.
 - Write one paper section or one explicit subproblem per round.
+- Ordinary manuscript drafting rounds should follow `workflow_language`.
+- If `workflow_language` and `paper_language` differ, the first final-draft or export round must ask once whether to keep the draft language or convert the final manuscript to `paper_language`, then persist that choice.
 - Bind each claim to evidence from `report`, iteration reports, or normalized summaries.
-- Write planning artifacts with `.lab/.managed/templates/paper-plan.md`, `.lab/.managed/templates/paper-section.md`, and `.lab/.managed/templates/write-iteration.md`.
-- Write final manuscript artifacts with `.lab/.managed/templates/paper.tex`, `.lab/.managed/templates/paper-section.tex`, `.lab/.managed/templates/paper-table.tex`, `.lab/.managed/templates/paper-figure.tex`, and `.lab/.managed/templates/paper-references.bib`.
-- Use the vendored paper-writing references under `skills/lab/references/paper-writing/`.
-- For any section with a bundled example bank, also use the vendored example-bank files under `skills/lab/references/paper-writing/examples/`.
-- Load only the current section guide, the matching examples index when one exists, 1-2 matching concrete example files, plus `paper-review.md` and `does-my-writing-flow-source.md`.
-- Build a compact mini-outline before prose.
-- Build the paper asset plan before prose when the section carries method or experiments claims.
+- Use the write-stage contract in `.codex/skills/lab/stages/write.md` or `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section-specific references, validator calls, asset coverage, and final manuscript gates.
+- Use the vendored paper-writing references under `skills/lab/references/paper-writing/` and the matching example-bank files under `skills/lab/references/paper-writing/examples/`.
+- Treat `.lab/writing/plan.md` as the write-time source of truth for tables, figures, citations, and asset coverage.
+- Treat section-quality, claim-safety, and manuscript-delivery checks as the canonical acceptance gates for final-draft or export rounds.
 - For each subsection, explicitly cover motivation, design, and technical advantage when applicable.
 - Keep terminology stable across rounds and sections.
 - If a claim is not supported by evidence, weaken or remove it.
 - Treat tables, figures, citations, and bibliography as core manuscript content rather than optional polish.
 - Keep paper-facing LaTeX free of absolute local paths, rerun ids, shell transcripts, and internal workflow provenance.
-- Materialize real LaTeX tables and figure placeholders instead of leaving all evidence inside prose paragraphs.
-- Run `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before accepting a final-draft or export round.
 - Before finalizing a round, append and answer the five-dimension self-review checklist and revise unresolved items.
 - Apply paper-writing discipline without changing experimental truth.
 - If the evidence is insufficient, stop and route back to `review` or `iterate`.
@@ -199,7 +199,8 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - No unconstrained auto mode. Every `/lab:auto` campaign must declare allowed stages, stop conditions, and a promotion policy in `.lab/context/auto-mode.md`.
 - No auto start without an explicit autonomy level and `Approval status: approved`.
 - No final report without validated normalized results.
-- No paper-writing round without stable report artifacts, an approved framing artifact, evidence links, LaTeX manuscript output, and a passing manuscript-delivery validation for final-draft or export rounds.
+- No paper-writing round without stable report artifacts, an approved framing artifact, evidence links, and LaTeX manuscript output.
+- No final-draft or export round without passing section-quality, claim-safety, and manuscript-delivery validation.
 
 ## References
 

package/package-assets/shared/skills/lab/references/paper-writing/examples/abstract/template-b.md

@@ -16,7 +16,7 @@
 
 % Introduce the technical contribution that implements the insight in one to two sentences (usually mention the technical term/name only, without describing every detailed step. The term should be easy to understand and should not create a jump in reading. This ability is very important for writing a good abstract.)
 %% Example 1: To do this, we first present a label-efficient depth estimation framework using the internal representations of diffusion models. At the sampling phase, we utilize two guidance techniques to self-condition the generated image using the estimated depth map, the first of which uses pseudo-labeling, and the subsequent one uses a depth-domain diffusion prior.
-%% Example 2: To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh
+%% Example 2: To this end, we propose AnchorField, a structured representation in which different observations share the same set of latent codes anchored to a deformable support.
 
 % Introduce the benefits of technical novelty
 %% Example 2: so that the observations across frames can be naturally integrated. The deformable mesh also provides geometric guidance for the network to learn 3D representations more efficiently.
@@ -29,6 +29,6 @@
 1. `This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views.`
 2. `... representation learning will be ill-posed if the views are highly sparse.`
 3. `To solve this ill-posed problem, our key idea is to integrate observations over video frames.`
-4. `To this end, we propose Neural Body ...`
+4. `To this end, we propose AnchorField ...`
 5. `... observations across frames can be naturally integrated ... provides geometric guidance ...`
 6. `Experiments show [main result].`

package/package-assets/shared/skills/lab/references/paper-writing/examples/conclusion/conservative-claim-boundary.md

@@ -6,22 +6,22 @@ boundary explicit.
 ```tex
 \section{Conclusion}
 
-This paper shows that adding a structured ranking backbone together with a
-post-hoc calibration stage improves uplift ranking under the frozen benchmark
-protocol. Across the three benchmark families used in this work, the full model
+This paper shows that adding a structured intermediate module together with a
+lightweight adjustment stage improves performance under a fixed evaluation
+protocol. Across the benchmark families used in this work, the full model
 consistently matches or exceeds the strongest baselines and remains stronger
 than the key ablated variants. This makes the main claim narrower than a
-universal superiority claim but stronger than a single-dataset win.
+universal superiority claim but stronger than a single-setting win.
 
-We do not claim that the current method solves uplift modeling in every domain
-or that every design choice helps equally on every benchmark. In particular, the
-calibration stage appears beneficial on some datasets and neutral on others,
-which means its value should be interpreted as setting-dependent rather than as
-a guaranteed gain. That boundary is consistent with recent benchmarking
-practice, which argues for claim discipline and protocol-specific interpretation
-rather than broad overgeneralization~\cite{carlini2019evaluating}.
+We do not claim that the current method solves the broader problem in every
+domain or that every design choice helps equally on every benchmark. In
+particular, the adjustment stage appears beneficial in some settings and
+neutral in others, which means its value should be interpreted as
+setting-dependent rather than as a guaranteed gain. That boundary is consistent
+with recent benchmarking practice, which argues for claim discipline and
+protocol-specific interpretation rather than broad overgeneralization~\cite{carlini2019evaluating}.
 
 The most useful next step is to extend the evaluation to a broader set of
-benchmark slices and to test whether the same ranking-versus-calibration split
-remains useful when the label distribution shifts more aggressively.
+benchmark slices and to test whether the same backbone-versus-adjustment split
+remains useful when the data distribution shifts more aggressively.
 ```

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

@@ -1,6 +1,6 @@
 # Main Results and Ablation LaTeX Example
 
-This file is a complete paper-facing LaTeX example for the experiments section.
+This file is a complete manuscript-ready 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.
 
@@ -14,13 +14,13 @@ Source inspiration:
 
 ```tex
 \begin{table}[t]
-\caption{Main benchmark results under the frozen evaluation protocol. Higher is better on all metrics.}
+\caption{Main benchmark results under the fixed 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 $\downarrow$ \\
+Method & Primary Metric $\uparrow$ & Secondary Metric $\uparrow$ & Error Metric $\downarrow$ \\
 \midrule
 Strongest baseline & 0.1421 & 0.0873 & 0.0612 \\
 Closest prior work & 0.1488 & 0.0915 & 0.0544 \\
@@ -32,7 +32,7 @@ Ours & \textbf{0.1564} & \textbf{0.0987} & \textbf{0.0418} \\
 ```
 
 Table message:
-- `Does the proposed method beat the strongest baselines under the frozen protocol?`
+- `Does the proposed method beat the strongest baselines under the fixed evaluation protocol?`
 
 ## Ablation Table
 
@@ -47,7 +47,7 @@ Variant & AUUC $\uparrow$ \\
 \midrule
 Ours & \textbf{0.1564} \\
 w/o structure module & 0.1497 \\
-w/o calibration stage & 0.1510 \\
+w/o final adjustment stage & 0.1510 \\
 w/ shuffled auxiliary signal & 0.1458 \\
 \bottomrule
 \end{tabular}
@@ -65,19 +65,20 @@ Table message:
 
 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.
+baseline under the fixed evaluation protocol. Our method achieves the best
+primary and secondary metrics while also reducing the error metric, which means
+the gain is not coming from trading one objective 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.
+structure module causes the largest drop, so the main gain is tied to explicit
+structure modeling rather than to a generic increase in capacity. Removing the
+final adjustment stage leads to a smaller but still visible drop, which
+supports the claim that the adjustment helps the exposed prediction 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.
+One caveat is that the final adjustment gain may remain neutral in some
+settings, 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

@@ -1,6 +1,6 @@
 # Experiments Example Patterns
 
-Use these examples when turning validated results into paper-facing LaTeX assets.
+Use these examples when turning validated results into manuscript-ready LaTeX assets.
 The referenced files contain complete LaTeX environments and section-level prose
 glue, not just checklists.
 

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

@@ -12,7 +12,7 @@ locally organized cite targets.
 5. Introduction technical-challenge files: `references/examples/introduction/technical-challenge-version-1-existing-task.md`, `references/examples/introduction/technical-challenge-version-2-existing-task-insight-backed-by-traditional.md`, `references/examples/introduction/technical-challenge-version-3-novel-task.md`, `references/examples/introduction/novel-task-challenge-decomposition.md`
 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`
+8. Method detail files: `references/examples/method/pre-writing-questions.md`, `references/examples/method/module-triad-anchored-representation.md`, `references/examples/method/annotated-figure-to-text.md`, `references/examples/method/module-design-multiresolution-encoding.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`

package/package-assets/shared/skills/lab/references/paper-writing/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.md

@@ -5,7 +5,7 @@
 
 ```latex
 % In this paper, we propose a novel framework …
-%% Example: In this paper, we introduce a novel implicit neural representation for dynamic humans, named Neural Body, to solve the challenge of novel view synthesis from sparse views.
+%% Example: In this paper, we introduce a structured anchor-based representation, named AnchorField, to solve the challenge of reconstructing a changing target from sparse observations.
 In this paper, we propose a novel framework/representation, named [method name] for [xxx task].
 
 % Teaser for basic idea
@@ -13,11 +13,11 @@ In this paper, we propose a novel framework/representation, named [method name]
 The basic idea is illustrated in [xxx Figure].
 
 % One-sentence key novelty/contribution (very important ability)
-%% Example: For the implicit fields at different frames, instead of learning them separately, Neural Body generates them from the same set of latent codes.
+%% Example: Instead of learning each observation-specific field separately, AnchorField generates them from the same set of anchor codes.
 Our innovation is in [one sentence for key novelty].
 
 % Method details
-%% Example: Specifically, we anchor a set of latent codes to the vertices of a deformable human model (SMPL in this work), namely that their spatial locations vary with the human pose. To obtain the 3D representation at a frame, we first transform the code locations based on the human pose, which can be reliably estimated from sparse camera views. Then, a network is designed to regress the density and color for any 3D point based on these latent codes. Both the latent codes and the network are jointly learned from images of all video frames during the reconstruction.
+%% Example: Specifically, we anchor a set of latent codes to a reference support structure so that their spatial locations follow the current observation. To obtain the target representation for one condition, we first transform the code locations using the available alignment signal. Then, a prediction network estimates the required outputs at each query point from these codes. Both the anchor codes and the prediction network are jointly learned from all observations.
 Specifically, [how it works in detail].
 
 % Advantage 1

package/package-assets/shared/skills/lab/references/paper-writing/examples/introduction/pipeline-version-2-two-contributions.md

@@ -5,7 +5,7 @@
 
 ```latex
 % In this paper, we propose a novel framework …
-%% Example: In this paper, we introduce a novel implicit neural representation for dynamic humans, named Neural Body, to solve the challenge of novel view synthesis from sparse views.
+%% Example: In this paper, we introduce a structured anchor-based representation, named AnchorField, to solve the challenge of reconstructing a changing target from sparse observations.
 In this paper, we propose a novel framework/representation, named [method name] for [xxx task].
 
 % One-sentence key novelty

package/package-assets/shared/skills/lab/references/paper-writing/examples/method/annotated-figure-to-text.md

@@ -0,0 +1,66 @@
+# Annotated Figure (Text Conversion)
+
+This file converts an annotated method figure into reusable writing notes.
+
+## Purpose
+
+Use this mapping to understand how one Method section can explicitly separate:
+
+1. Module motivation
+2. Module design (data structure)
+3. Module design (forward process)
+4. Technical advantages
+
+## Block-by-Block Mapping
+
+### Section 3.1: Structured Anchor Codes
+
+1. **Module design (data structure)**
+- The paragraph defines structured codes anchored to a reference support structure.
+- It explains what is constructed: latent codes, anchor positions, and the condition-dependent transformation that keeps them aligned with the current instance.
+
+2. **Technical advantages**
+- The paragraph explains why this design works better: it preserves correspondence across observations and keeps the representation aligned with changing geometry.
+- It highlights why anchoring codes to a structured support is beneficial.
+
+### Section 3.2: Code Diffusion
+
+1. **Motivation of this module**
+- The paragraph states the remaining problem: direct interpolation of sparse anchor codes leaves many query locations weakly represented.
+- This motivates propagation from anchor locations to nearby continuous space.
+
+2. **Module design (forward process)**
+- The paragraph explains the execution pipeline: build sparse feature volumes, run sparse convolutions, interpolate codes at query points, and feed those codes to prediction networks.
+- This is a canonical input -> steps -> output module description.
+
+### Section 3.3: Field Regression
+
+1. **Module design (forward process) for the first prediction head**
+- The first paragraph defines how one target quantity is regressed from the latent code and condition inputs.
+
+2. **Module design (data structure) for the second prediction head**
+- The next paragraph introduces required inputs or embeddings such as latent code, query direction, spatial location, or condition tokens.
+
+3. **Module design (forward process) for the second prediction head**
+- The following paragraph describes how those inputs are encoded and passed into the second prediction network for the final estimate.
+
+### Section 3.4: Output Aggregation
+
+1. **Module design (forward process)**
+- The paragraph describes the final aggregation process that converts pointwise predictions into the output seen by the reader or evaluator.
+
+## Reusable Writing Pattern from This Figure
+
+For each module subsection, follow this order:
+
+1. `Motivation`: state unresolved challenge and technical reason.
+2. `Design-1`: define structure/representation/network.
+3. `Design-2`: describe forward process in execution order.
+4. `Advantage`: explain why this module improves over alternatives.
+
+## Suggested Paragraph Starters
+
+1. Motivation: `A remaining challenge is ...`
+2. Data structure design: `We represent ... with ...`
+3. Forward process: `Given [input], we first ... then ... finally ...`
+4. Technical advantage: `Compared with previous methods, this design ... because ...`

package/package-assets/shared/skills/lab/references/paper-writing/examples/method/example-of-the-three-elements.md

@@ -18,27 +18,27 @@ Each `% ...` annotation explains the paragraph(s) immediately below it.
 \subsection{3.1. Structured latent codes}
 
 % Module design: introduce the module's data structure
-To control the spatial locations of latent codes with the human pose, we anchor these latent codes to a deformable human body model (SMPL) [38]. SMPL is a skinned vertex-based model, which is defined as a function of shape parameters, pose parameters, and a rigid transformation relative to the SMPL coordinate system. The function outputs a posed 3D mesh with 6890 vertices. Specifically, we define a set of latent codes \( Z = \{z_1, z_2, ..., z_{6890}\} \) on vertices of the SMPL model. For the frame \( t \), SMPL parameters \( S_t \) are estimated from the multi-view images \( \{I_t^c \mid c = 1, ..., N_c\} \) using [26]. The spatial locations of the latent codes are then transformed based on the human pose \( S_t \) for the density and color regression. Figure 3 shows an example. The dimension of latent code \( z \) is set to 16 in our experiments.
+To keep latent codes aligned with the current instance, we anchor them to a deformable reference structure [38]. This structure is parameterized by shape variables, condition variables, and a rigid transformation relative to its own coordinate system, and outputs a posed mesh or support geometry. Specifically, we define a set of latent codes \( Z = \{z_1, z_2, ..., z_M\} \) on the support points of that reference structure. For one observation \( t \), the condition parameters \( S_t \) are estimated from the available inputs \( \{I_t^c \mid c = 1, ..., N_c\} \) using an external alignment procedure [26]. The spatial locations of the latent codes are then transformed according to \( S_t \) before the downstream prediction heads consume them. Figure 3 shows an example. The latent-code dimension is set to 16 in this example.
 
 % Technical advantages of this module
-Similar to the local implicit representations [25, 5, 18], the latent codes are used with a neural network to represent the local geometry and appearance of a human. Anchoring these codes to a deformable model enables us to represent a dynamic human. With the dynamic human representation, we establish a latent variable model that maps the same set of latent codes to the implicit fields of density and color at different frames, which naturally integrates observations at different frames.
+Similar to local implicit representations [25, 5, 18], the latent codes are used with a neural network to represent local structure and attributes. Anchoring these codes to a deformable support lets the model stay aligned with changing geometry instead of relearning a separate representation for every condition. This yields a latent-variable view in which the same anchor codes can explain multiple observations while sharing information across them.
 
 \subsection{3.2. Code diffusion}
 
 % Motivation of this module
-Figure 3(a) shows the process of code diffusion. The implicit fields assign the density and color to each point in the 3D space, which requires us to query the latent codes at continuous 3D locations. This can be achieved with the trilinear interpolation. However, since the structured latent codes are relatively sparse in the 3D space, directly interpolating the latent codes leads to zero vectors at most 3D points. To solve this problem, we diffuse the latent codes defined on the surface to nearby 3D space.
+Figure 3(a) shows the process of code propagation. The target fields assign outputs to each point in the domain, which requires querying the latent codes at continuous locations. This can be achieved with trilinear interpolation. However, because the structured anchor codes are sparse, directly interpolating them leaves many query points weakly represented. To solve this problem, we propagate the codes defined on the support structure to nearby space.
 
 % Module design: introduce module design by describing the module forward process
-Inspired by [65, 56, 49], we choose the SparseConvNet [21] to efficiently process the structured latent codes, whose architecture is described in Table 1. Specifically, based on the SMPL parameters, we compute the 3D bounding box of the human and divide the box into small voxels with voxel size of \( 5mm \times 5mm \times 5mm \). The latent code of a non-empty voxel is the mean of latent codes of SMPL vertices inside this voxel. SparseConvNet utilizes 3D sparse convolutions to process the input volume and output latent code volumes with \( 2\times, 4\times, 8\times, 16\times \) downsampled sizes. With the convolution and downsampling, the input codes are diffused to nearby space. Following [56], for any point in 3D space, we interpolate the latent codes from multi-scale code volumes of network layers 5, 9, 13, 17, and concatenate them into the final latent code. Since the code diffusion should not be affected by the human position and orientation in the world coordinate system, we transform the code locations to the SMPL coordinate system.
+Inspired by [65, 56, 49], we choose a sparse convolutional backbone [21] to efficiently process the structured latent codes, whose architecture is described in Table 1. Specifically, based on the reference-structure parameters, we compute a 3D bounding box around the active support and divide that box into small voxels with voxel size \( 5mm \times 5mm \times 5mm \). The latent code of a non-empty voxel is the mean of the anchor codes that fall inside it. The sparse backbone applies 3D sparse convolutions to this input volume and outputs latent code volumes at \( 2\times, 4\times, 8\times, 16\times \) downsampled scales. With convolution and downsampling, the input codes are propagated to nearby space. Following [56], for any point in the domain, we interpolate the latent codes from multi-scale code volumes of network layers 5, 9, 13, and 17, and concatenate them into the final latent code. Since propagation should not be affected by global position and orientation, we transform code locations to the reference coordinate system.
 
-For any point \( \mathbf{x} \) in 3D space, we query its latent code from the latent code volume. Specifically, the point \( \mathbf{x} \) is first transformed to the SMPL coordinate system, which aligns the point and the latent code volume in 3D space. Then, the latent code is computed using the trilinear interpolation. For the SMPL parameters \( S_t \), we denote the latent code at point \( \mathbf{x} \) as \( \psi(\mathbf{x}, Z, S_t) \). The code vector is passed into MLP networks to predict the density and color for point \( \mathbf{x} \).
+For any query point \( \mathbf{x} \), we obtain its latent code from the propagated code volume. Specifically, the point \( \mathbf{x} \) is first transformed to the reference coordinate system so that the query and code volume are aligned. Then, the latent code is computed with trilinear interpolation. For condition parameters \( S_t \), we denote the latent code at point \( \mathbf{x} \) by \( \psi(\mathbf{x}, Z, S_t) \). The resulting code vector is passed to prediction networks that estimate the target outputs at \( \mathbf{x} \).
 
 \subsection{3.3. Density and color regression}
 
-Figure 3(b) overviews the regression of density and color for any point in 3D space. The density and color fields are represented by MLP networks. Details of network architectures are described in the supplementary material.
+Figure 3(b) overviews the regression of the target outputs for any query point. The corresponding fields are represented by MLP networks. Details of the network architectures are described in the supplementary material.
 
 % Module design: introduce module design by describing the module forward process
-\textbf{Density model.} For the frame \( t \), the volume density at point \( \mathbf{x} \) is predicted as a function of only the latent code \( \psi(\mathbf{x}, Z, S_t) \), which is defined as:
+\textbf{First prediction head.} For condition \( t \), the first target quantity at point \( \mathbf{x} \) is predicted as a function of only the latent code \( \psi(\mathbf{x}, Z, S_t) \), which is defined as:
 
 \[
 \sigma_t(\mathbf{x}) = M_{\sigma}(\psi(\mathbf{x}, Z, S_t)),
@@ -48,20 +48,20 @@ Figure 3(b) overviews the regression of density and color for any point in 3D sp
 where \( M_{\sigma} \) represents an MLP network with four layers.
 
 % Module design: introduce the module's data structure
-\textbf{Color model.} Similar to [37, 44], we take both the latent code \( \psi(\mathbf{x}, Z, S_t) \) and the viewing direction \( \mathbf{d} \) as input for the color regression. To model the location-dependent incident light, the color model also takes the spatial location \( \mathbf{x} \) as input. We observe that temporally-varying factors affect the human appearance, such as secondary lighting and self-shadowing. Inspired by the auto-decoder [48], we assign a latent embedding \( \ell_t \) for each video frame \( t \) to encode the temporally-varying factors.
+\textbf{Second prediction head.} Similar to [37, 44], we take both the latent code \( \psi(\mathbf{x}, Z, S_t) \) and an observation-dependent direction \( \mathbf{d} \) as input for the second target. To model location-dependent effects, this head also takes the spatial location \( \mathbf{x} \) as input. We further observe that condition-specific factors can change the target output. Inspired by the auto-decoder [48], we assign a latent embedding \( \ell_t \) for each condition \( t \) to encode those varying factors.
 
 % Module design: introduce module design by describing the module forward process
-Specifically, for the frame \( t \), the color at \( \mathbf{x} \) is predicted as a function of the latent code \( \psi(\mathbf{x}, Z, S_t) \), the viewing direction \( \mathbf{d} \), the spatial location \( \mathbf{x} \), and the latent embedding \( \ell_t \). Following [51, 44], we apply the positional encoding to both the viewing direction \( \mathbf{d} \) and the spatial location \( \mathbf{x} \), which enables better learning of high frequency functions. The color model at frame \( t \) is defined as:
+Specifically, for condition \( t \), the second target at \( \mathbf{x} \) is predicted as a function of the latent code \( \psi(\mathbf{x}, Z, S_t) \), the observation direction \( \mathbf{d} \), the spatial location \( \mathbf{x} \), and the latent embedding \( \ell_t \). Following [51, 44], we apply positional encoding to both \( \mathbf{d} \) and \( \mathbf{x} \), which enables better learning of high-frequency functions. The second prediction head at condition \( t \) is defined as:
 
 \[
 c_t(\mathbf{x}) = M_c(\psi(\mathbf{x}, Z, S_t), \gamma_d(\mathbf{d}), \gamma_x(\mathbf{x}), \ell_t),
 \tag{2}
 \]
 
-where \( M_c \) represents an MLP network with two layers, and \( \gamma_d \) and \( \gamma_x \) are positional encoding functions for viewing direction and spatial location, respectively. We set the dimension of \( \ell_t \) to 128 in experiments.
+where \( M_c \) represents an MLP network with two layers, and \( \gamma_d \) and \( \gamma_x \) are positional encoding functions for direction and spatial location, respectively. We set the dimension of \( \ell_t \) to 128 in this example.
 
 \subsection{3.4. Volume rendering}
 
 % Module design: introduce module design by describing the module forward process
-Given a viewpoint, we utilize the classical volume rendering techniques to render the Neural Body into a 2D image. The pixel colors are estimated via the volume rendering integral equation [27] that accumulates volume densities and colors along the corresponding camera ray. In practice, the integral is approximated using numerical quadrature [41, 44]. Given a pixel, we first compute its camera ray \( \mathbf{r} \) using the camera parameters and sample \( N_k \) points \( \{\mathbf{x}_k\}_{k=1}^{N_k} \) along camera ray \( \mathbf{r} \) between near and far bounds. The scene bounds are estimated based on the SMPL model. Then, Neural Body predicts volume densities and colors at these points. For the video frame \( t \), the rendered color \( \hat{C}_t(\mathbf{r}) \) ...
+Given an observation direction, we utilize a standard aggregation procedure to render the predicted field into a 2D output. Pixel values are estimated via a volume-integration equation [27] that accumulates the predicted quantities along the corresponding ray. In practice, the integral is approximated using numerical quadrature [41, 44]. Given a pixel, we first compute its ray \( \mathbf{r} \) using the camera parameters and sample \( N_k \) points \( \{\mathbf{x}_k\}_{k=1}^{N_k} \) along that ray between near and far bounds. The scene bounds are estimated from the reference structure. Then, the model predicts the target outputs at these points. For condition \( t \), the rendered value \( \hat{C}_t(\mathbf{r}) \) ...
 ```

package/package-assets/shared/skills/lab/references/paper-writing/examples/method/{module-design-instant-ngp.md → module-design-multiresolution-encoding.md}

@@ -1,4 +1,4 @@
-# Module Design Example 
+# Module Design Example (Multiresolution Encoding)
 
 This example uses `%` comments as annotations.
 Each `% ...` annotation explains the paragraph(s) immediately below it.

package/package-assets/shared/skills/lab/references/paper-writing/examples/method/{module-triad-neural-body.md → module-triad-anchored-representation.md}

@@ -1,11 +1,11 @@
-# Module Triad Example (Neural Body)
+# Module Triad Example (Anchored Representation)
 
-`Use Neural Body to understand the three elements of a module: design, motivation, and technical advantages.`
+`Use this anchored-representation example to understand the three elements of a module: design, motivation, and technical advantages.`
 
 Local source references:
 
 1. Annotated figure showing motivation/design/advantages split.
-3. Text-converted annotation notes: `references/examples/method/neural-body-annotated-figure-text.md`
+3. Text-converted annotation notes: `references/examples/method/annotated-figure-to-text.md`
 
 Triad mapping template:
 
@@ -15,5 +15,5 @@ Triad mapping template:
 
 Direct usage:
 
-1. Read `neural-body-annotated-figure-text.md` to map each paragraph to one triad element.
+1. Read `annotated-figure-to-text.md` to map each paragraph to one triad element.
 2. Rebuild your own Method subsection with the same triad order.

package/package-assets/shared/skills/lab/references/paper-writing/examples/method/overview-template.md

@@ -18,12 +18,12 @@
 %% Example: The overview of the proposed model is illustrated in Figure 3.
 
 % Explain what Section 3.1 covers
-%% Example 1: Neural Body starts from a set of structured latent codes attached to the surface of a deformable human model (Section 3.1).
-%% Example 2: In this section, we first describe how to model 3D scenes with MLP maps (Section 3.1).
+%% Example 1: The model starts from a set of structured anchor codes attached to a reference support structure (Section 3.1).
+%% Example 2: In this section, we first describe how to model the target space with learnable field maps (Section 3.1).
 
 % Explain what Section 3.2 covers
-%% Example 1: The latent code at any location around the surface can be obtained with a code diffusion process (Section 3.2) and then decoded to density and color values by neural networks (Section 3.3).
-%% Example 2: Then, Section 3.2 discusses how to represent volumetric videos with dynamic MLP maps.
+%% Example 1: The code at any nearby location is obtained with a propagation process (Section 3.2) and then decoded into the target outputs by prediction networks (Section 3.3).
+%% Example 2: Then, Section 3.2 discusses how to represent changing scenes with dynamic field maps.
 
 % Explain what Section 3.3 covers
 %% Example 3: Finally, we introduce some strategies to speed up the rendering process (Section 3.3).