Add reproducible pred CLI commands to paper examples

.claude/CLAUDE.md

@@ -87,7 +87,7 @@ make release V=x.y.z  # Tag and push a new release (CI publishes to crates.io)
   - `misc/` - Unique input structures
   - Run `pred list` for the full catalog of problems, variants, and reductions; `pred show <name>` for details on a specific problem
 - `src/rules/` - Reduction rules + inventory registration
-- `src/solvers/` - BruteForce solver, ILP solver (feature-gated)
+- `src/solvers/` - BruteForce solver, ILP solver (feature-gated). To check if a problem supports ILP solving (via reduction path), run `pred path <ProblemName> ILP`
 - `src/traits.rs` - `Problem`, `OptimizationProblem`, `SatisfactionProblem` traits
 - `src/rules/traits.rs` - `ReduceTo<T>`, `ReductionResult` traits
 - `src/registry/` - Compile-time reduction metadata collection

.claude/skills/add-model/SKILL.md

@@ -247,6 +247,8 @@ The body goes AFTER auto-generated sections (complexity table, reductions, schem
 
 **Evaluation:** Show the objective/verifier computed on the example solution (can be woven into example text).
 
+**Reproducibility:** The example section must include a `pred-commands()` call showing the create/solve/evaluate pipeline. See `write-model-in-paper` skill for the full pattern.
+
 ### 6d. Build and verify
 
 ```bash

.claude/skills/add-rule/SKILL.md

@@ -159,6 +159,8 @@ Step-by-step walkthrough with concrete numbers from JSON data. Required steps:
 
 Use `graph-colors`, `g-node()`, `g-edge()` for graph visualization — see reference examples.
 
+**Reproducibility:** The `extra:` block must start with a `pred-commands()` call showing the create/reduce/solve/evaluate pipeline. See `write-rule-in-paper` skill for the full pattern.
+
 ### 5d. Build and verify
 
 ```bash

.claude/skills/final-review/SKILL.md

@@ -400,27 +400,20 @@ Use `AskUserQuestion` only when needed:
    ```bash
    gh pr review <number> --approve || true
    ```
-5. Post a community call validation checklist as a comment on the **linked issue** (not the PR). All CLI commands must be copy-pastable — substitute actual problem names from the PR diff (no angle-bracket placeholders). Example for a rule PR adding `Satisfiability` → `MaximumIndependentSet`:
+5. Post a community call validation checklist as a comment on the **linked issue** (not the PR). Substitute actual problem names from the PR diff (no angle-bracket placeholders). Example for a rule PR adding `Satisfiability` → `MaximumIndependentSet`:
    ````bash
    COMMENT_FILE=$(mktemp)
    cat > "$COMMENT_FILE" <<'EOF'
    Please kindly check the following items (PR #123):
-   - [ ] **Paper** ([PDF](https://github.com/CodingThrust/problem-reductions/blob/main/docs/paper/reductions.pdf)): check definition, proof sketch, and example figure
-   - [ ] **CLI demo** (build from source: `cargo install --path problemreductions-cli`):
-     ```bash
-     pred show Satisfiability
-     pred create --example Satisfiability -o instance.json
-     pred reduce instance.json Satisfiability MaximumIndependentSet -o reduced.json
-     pred solve reduced.json MaximumIndependentSet
-     ```
+   - [ ] **Paper** ([PDF](https://github.com/CodingThrust/problem-reductions/blob/main/docs/paper/reductions.pdf)): check definition, proof sketch, example figure, and reproducible `pred` commands
    - [ ] **Implementation (Optional)**: spot-check the source files changed in this PR for correctness
 
    💬 Join the discussion on [Zulip](https://julialang.zulipchat.com/#narrow/channel/365542-problem-reductions) — feel free to ask questions or leave feedback there.
    EOF
    gh issue comment <ISSUE_NUMBER> --body-file "$COMMENT_FILE"
    rm -f "$COMMENT_FILE"
    ````
-   For model PRs, omit the `pred reduce` / `pred solve` lines. If there is no linked issue, post the checklist as a PR comment instead.
+   If there is no linked issue, post the checklist as a PR comment instead.
 6. Present the PR link for the reviewer to merge:
    > CI green, commits pushed, PR approved. Community call checklist posted on #<ISSUE_NUMBER>. Please merge when ready:
    > **<PR URL>**

.claude/skills/fix-issue/SKILL.md

@@ -130,7 +130,7 @@ Tag each issue as:
 |--------------|-------------|
 | Undefined symbol in overhead/algorithm | Add definition derived from context (e.g., "let n = \|V\|") |
 | Inconsistent notation across sections | Standardize to the most common usage in the issue |
-| Missing/wrong code metric names | Look up correct names via `pred show <target> --json` → `size_fields` |
+| Missing/wrong code metric names | Look up correct names via `pred show <target> --json` → `size_fields`. If `size_fields` is empty, use the plain-text `pred show <target>` output which lists Fields directly |
 | Formatting issues (broken tables, missing headers) | Reformat to match issue template |
 | Incomplete `(TBD)` in fields derivable from other sections | Fill from context |
 | Incorrect DOI format | Reformat to `https://doi.org/...` |
@@ -158,16 +158,46 @@ For each `mechanical` issue:
 2. Apply the fix
 3. Record what was changed (for presenting to human in Step 4)
 
-Use `pred show <problem> --json` to look up:
+Use `cargo run -p problemreductions-cli --bin pred -- show <problem>` (or `./target/debug/pred show <problem>` after `make cli`) to look up:
 - Valid problem names and aliases
-- `size_fields` for correct metric names
+- `size_fields` for correct metric names (via `--json`); if empty, use plain-text output which lists Fields directly
 - Existing variants and fields
 
 **Do NOT edit the issue on GitHub yet** — collect all fixes (mechanical + substantive) first.
 
 ---
 
-## Step 4: Present Auto-Fixes to Human
+## Step 4: Present Full Context and Auto-Fixes to Human
+
+**IMPORTANT: Show all context BEFORE asking for any decisions.** The human needs full visibility into the check report findings, research results, and classification before being asked to choose.
+
+### 4a: Show the check report summary
+
+Print the parsed check report summary table (from Step 2) so the human can see the starting state:
+
+```
+## Check Report Summary (Issue #<NUMBER>)
+
+| Check | Result | Details |
+|-------|--------|---------|
+| Usefulness | ✅ Pass | ... |
+| Non-trivial | ✅ Pass | ... |
+| Correctness | ⚠️ Warn | ... |
+| Well-written | ⚠️ Warn | ... |
+```
+
+For each `Fail` or `Warn` result, include the key details from the check report's detailed section (not just the one-liner — include the specific sub-issues identified).
+
+### 4b: Show research results
+
+If web searches, `pred show` lookups, or other research was performed during classification (Step 2–3), present those findings now. For example:
+- Web search results that confirm or contradict references
+- `pred show` output for source/target problems
+- Companion issue status (exists / missing)
+
+This ensures the human has all the evidence before any decisions.
+
+### 4c: Show auto-fixes and substantive issues
 
 Print a summary of all mechanical fixes applied:
 
@@ -179,12 +209,13 @@ Print a summary of all mechanical fixes applied:
 | 1 | Size Overhead | Symbol `m` undefined | Added ... |
 ```
 
-Then present the substantive issues that need discussion:
+Then list the substantive issues that need discussion:
 
 ```
 ## Issues requiring your input
 
 1. **Decision vs optimization:** ...
+2. **Reference accuracy:** ...
 ```
 
 ---
@@ -193,10 +224,11 @@ Then present the substantive issues that need discussion:
 
 For each substantive issue, present it to the human **one at a time**:
 
-1. State the problem clearly
-2. Offer 2-3 concrete options when possible (with your recommendation)
-3. Wait for the human's response
-4. Apply the chosen fix to the draft issue body
+1. **Show the evidence first** — quote the relevant check report section, web research results, or `pred show` output that informs this decision. The human should be able to evaluate the options based on the evidence shown, not just the option labels.
+2. State the problem clearly
+3. Offer 2-3 concrete options when possible (with your recommendation)
+4. Wait for the human's response
+5. Apply the chosen fix to the draft issue body
 
 Use web search if needed to help resolve issues:
 - Literature search for correct complexity bounds

.claude/skills/write-model-in-paper/SKILL.md

@@ -157,6 +157,22 @@ caption: [Caption describing the figure with key parameters],
 ) <fig:problem-example>
 ```
 
+#### Reproducibility Commands
+
+Add a `pred-commands()` block after the `*Example.*` paragraph and before the `#figure`. Commands are constructed dynamically from loaded example data:
+
+```typst
+#pred-commands(
+  "pred create --example <ALIAS> -o <name>.json",
+  "pred solve <name>.json",
+  "pred evaluate <name>.json --config " + x.optimal_config.map(str).join(","),
+)
+```
+
+Where `<ALIAS>` is the shortest alias for the problem (e.g., `MIS`, `MVC`, `SAT`). Use the bare alias when the default variant matches the loaded example; use the full variant path (e.g., `MIS/SimpleGraph/i32`) when a non-default variant is needed. Check `pred list` for available aliases.
+
+For satisfaction problems, replace `pred solve` with `pred solve <name>.json --solver brute-force` if the problem has no ILP reduction path.
+
 **For graph problems**, use the paper's existing graph helpers:
 - `petersen-graph()`, `house-graph()` or define custom vertex/edge lists
 - `canvas(length: ..., { ... })` with `g-node()` and `g-edge()`
@@ -189,4 +205,5 @@ make paper
 - [ ] **Evaluation shown**: objective/verifier computed on the example solution
 - [ ] **Diagram included**: figure with caption and label for graph/matrix/set visualization
 - [ ] **Paper compiles**: `make paper` succeeds without errors
+- [ ] **Pred commands present**: `pred-commands()` block after example text, before figure, with create/solve/evaluate pipeline
 - [ ] **Complexity consistency**: written complexity and auto-generated variant table are compatible (note any discrepancies for later review)

.claude/skills/write-rule-in-paper/SKILL.md

@@ -145,6 +145,13 @@ Detailed by default. Only use a brief example for trivially obvious reductions (
   example: true,
   example-caption: [Description ($n = ...$, $|E| = ...$)],
   extra: [
+    #pred-commands(
+      "pred create --example <ALIAS> -o <name>.json",
+      "pred reduce <name>.json --to " + target-spec(src_tgt) + " -o bundle.json",
+      "pred solve bundle.json",
+      "pred evaluate <name>.json --config " + src_tgt_sol.source_config.map(str).join(","),
+    )
+
     // Optional: graph visualization
     #{
       // canvas code for graph rendering
@@ -163,6 +170,23 @@ Detailed by default. Only use a brief example for trivially obvious reductions (
 )
 ```
 
+### 4a2. Reproducibility Commands
+
+Add a `pred-commands()` block at the top of the `extra:` content, before any data display or visualization. Commands are constructed dynamically from loaded example data:
+
+```typst
+#pred-commands(
+  "pred create --example <SOURCE_ALIAS> -o <source>.json",
+  "pred reduce <source>.json --to " + target-spec(src_tgt) + " -o bundle.json",
+  "pred solve bundle.json",
+  "pred evaluate <source>.json --config " + src_tgt_sol.source_config.map(str).join(","),
+)
+```
+
+Where `<SOURCE_ALIAS>` is the shortest alias for the source problem (e.g., `MVC`, `MIS`, `SAT`). Use the bare alias when the default variant matches; use the full variant path (e.g., `MIS/SimpleGraph/i32`) when a non-default variant is needed. Check `pred list` for available aliases.
+
+The `target-spec()` helper handles empty variant dicts automatically. The `--config` is composed from `src_tgt_sol.source_config`.
+
 ### 4b. Step-by-Step Content
 
 Each step should:
@@ -232,6 +256,7 @@ make paper
 - [ ] **Example uses JSON data**: concrete values come from `load-example`/`load-results`, not hardcoded
 - [ ] **Solution verified**: at least one solution checked end-to-end in the example
 - [ ] **Witness semantics**: text treats `solutions.at(0)` as the canonical witness; any multiplicity claim is derived mathematically, not from fixture length
+- [ ] **Pred commands present**: `pred-commands()` block at top of example with create/reduce/solve/evaluate pipeline
 - [ ] **Paper compiles**: `make paper` succeeds without errors
 - [ ] **Completeness check**: no new warnings about missing edges in the paper
 

.gitignore

@@ -89,4 +89,5 @@ claude-output.log
 docs/test-reports/
 docs/superpowers/
 *.log
-docs/src/reductions/*.json
+docs/src/reductions/*.json
+.claude/projects/