dsh-aris-panel 0.1.0

package/skills/skills-codex/paper-claim-audit/SKILL.md

@@ -0,0 +1,350 @@
+---
+name: paper-claim-audit
+description: "Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh Codex reviewer with no prior context; base output is same-family provisional. Use when user says \"审查论文数据\", \"check paper claims\", \"verify numbers\", \"论文数字核对\", or before submission to ensure paper-to-evidence fidelity."
+argument-hint: "[paper-directory]"
+allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob
+---
+
+# Paper Claim Audit: Zero-Context Evidence Verification
+
+> **Codex assurance:** write `review_independence: same-family` and
+> `acceptance_status: provisional` into base audit JSON. A fresh Codex PASS may
+> advance the pipeline but cannot produce submission-ready yes. Missing/failed
+> review emits BLOCKED; overlay/deterministic acceptance uses accepted.
+
+Verify that every claim in the paper matches raw evidence for: **$ARGUMENTS**
+
+## Why This Exists
+
+The executor writes experiments AND writes the paper. It "knows" what the results should be. This creates confirmation bias:
+- Rounding 84.7% up to 85.3%
+- Reporting best seed instead of average
+- Citing metrics from a different experiment config
+- Claiming "improves by 15%" when the delta is actually 12.8%
+
+A **fresh reviewer with zero prior context** catches these because it has no expectations — it just compares paper text vs raw files.
+
+## How This Differs From Other Audit Skills
+
+| Skill | Question it answers |
+|-------|-------------------|
+| `/experiment-audit` | Is the experiment code honest? (fake GT, normalization fraud) |
+| `/result-to-claim` | Does the data scientifically support this claim? |
+| **`/paper-claim-audit`** | **Does the paper report the data truthfully and precisely?** |
+
+## Core Principle
+
+**Zero-context, fresh reviewer.** The auditor receives ONLY:
+- Paper .tex files (the claims)
+- Raw result files (the evidence)
+
+It does NOT receive:
+- ❌ EXPERIMENT_LOG.md
+- ❌ EXPERIMENT_TRACKER.md
+- ❌ AUTO_REVIEW.md
+- ❌ NARRATIVE_REPORT.md
+- ❌ Any executor summary or interpretation
+- ❌ Any prior audit results
+- ❌ Any conversation history
+
+This is **stricter than reviewer-independence** — it's zero-context evidence audit.
+
+## Workflow
+
+### Step 1: Collect Files (Executor — Codex)
+
+Locate paper and result files WITHOUT reading or interpreting them.
+
+**Paper files** (claims) — paths shown relative to the shell's working
+directory so you can find them with `ls`; when writing them into
+`audited_input_hashes`, use paths relative to the paper dir (no `paper/`
+prefix) per the "Submission Artifact Emission" section below:
+```
+paper/main.tex                # → hash key: main.tex
+paper/sections/*.tex          # → hash key: sections/*.tex
+paper/tables/*.tex (if separate)   # → hash key: tables/*.tex
+```
+
+**Result files** (evidence):
+```
+results/*.json, results/*.jsonl, results/*.csv, results/*.tsv
+outputs/*.json, outputs/*.csv
+wandb-summary.json (if exists)
+**/metrics.json, **/eval_results.json
+**/config.yaml, **/args.json (experiment configs)
+```
+
+**Exclude** (no summaries, no interpretations):
+```
+EXPERIMENT_LOG.md, EXPERIMENT_TRACKER.md, AUTO_REVIEW*.md
+NARRATIVE_REPORT.md, PAPER_PLAN.md, findings.md
+Any .md file that is an executor-written summary
+```
+
+### Step 2: Fresh Reviewer Audit (GPT-5.6-Sol — NEW thread, no reply)
+
+**CRITICAL: Use a fresh reviewer agent every run.** Never reuse an old reviewer context for this audit.
+
+```text
+spawn_agent:
+  model: gpt-5.6-sol
+  reasoning_effort: ultra
+  message: |
+    You are a paper-to-evidence auditor. You have ZERO prior context about
+    this research. You will receive only paper source files and raw result
+    files. Your job is to verify that every number in the paper exactly
+    matches the raw evidence.
+
+    Paper files to read:
+    [list .tex file paths]
+
+    Result files to read:
+    [list .json/.csv/.yaml file paths]
+
+    ## Audit Protocol
+
+    ### A. Extract Every Quantitative Claim
+    For each number, percentage, comparison, or scope statement in the paper:
+    - Location (section, table, caption, or inline text)
+    - Exact claim text
+    - The number or comparison being made
+
+    ### B. Trace Each Claim to Evidence
+    For each extracted claim, find the supporting raw data:
+    - Which result file contains this number?
+    - What is the EXACT value in that file?
+    - Match status: exact_match / rounding_ok / mismatch
+
+    ### C. Check These Specific Failure Modes
+
+    1. **Number inflation**: Paper says 85.3%, raw file says 84.7%
+       Rule: only standard rounding to displayed precision is allowed
+
+    2. **Best-seed cherry-pick**: Paper says "achieves 90.2%" but
+       that's the best of 5 seeds; mean is 87.1%
+       Rule: check if paper specifies "average" / "best" / "median"
+
+    3. **Config mismatch**: Paper compares Method A vs Baseline B,
+       but they used different hyperparameters / datasets / splits
+       Rule: verify config files show same settings for compared methods
+
+    4. **Aggregation mismatch**: Paper says "average over 5 seeds"
+       but result files show only 3 runs
+       Rule: count actual runs vs claimed count
+
+    5. **Delta error**: Paper says "improves by 15%" but
+       actual delta is (85.3 - 73.1) / 73.1 = 16.7%
+       Rule: verify arithmetic of all relative improvements
+
+    6. **Caption-table mismatch**: Figure caption describes
+       something different from what the figure/table actually shows
+       Rule: cross-check every caption against its content
+
+    7. **Scope overclaim**: Paper says "consistently outperforms"
+       but only tested on 2 datasets
+       Rule: check if language matches actual evaluation scope
+
+    ## Output Format (per claim)
+    For each claim, report:
+    - claim_id: sequential number
+    - location: section/table/figure
+    - paper_text: exact quote from paper
+    - paper_value: the number claimed
+    - evidence_file: which raw file
+    - evidence_value: the actual number
+    - status: exact_match | rounding_ok | ambiguous_mapping |
+              missing_evidence | config_mismatch | aggregation_mismatch |
+              number_mismatch | scope_overclaim | unsupported_claim
+    - details: explanation if not exact_match
+
+    Overall verdict: PASS | WARN | FAIL
+```
+
+### Step 3: Write Report (Executor — Codex)
+
+Parse the reviewer's response and write `PAPER_CLAIM_AUDIT.md`:
+
+```markdown
+# Paper Claim Audit Report
+
+**Date**: [today]
+**Auditor**: GPT-5.6-Sol ultra (fresh zero-context thread)
+**Paper**: [paper title from tex]
+
+## Overall Verdict: [PASS | WARN | FAIL]
+
+## Claims Verified: [N total]
+- exact_match: [count]
+- rounding_ok: [count]
+- ambiguous_mapping: [count]
+- missing_evidence: [count]
+- mismatch: [count]
+
+## Issues Found
+
+### [FAIL/WARN] Claim #N: [description]
+- **Location**: Section X / Table Y / Figure Z
+- **Paper says**: "..."
+- **Evidence shows**: ...
+- **Status**: [status]
+- **Fix**: [specific correction needed]
+
+## All Claims (detailed)
+
+| # | Location | Paper Value | Evidence Value | Status |
+|---|----------|-------------|---------------|--------|
+| 1 | Table 2 | 85.3% | 85.28% | rounding_ok |
+| 2 | Abstract | "15% improvement" | 12.8% | number_mismatch |
+| ... |
+```
+
+Also write `PAPER_CLAIM_AUDIT.json` for machine consumption.
+
+### Step 4: Print Summary
+
+```
+📋 Paper Claim Audit Complete
+
+  Claims verified: 24
+  exact_match:     18
+  rounding_ok:      3
+  ambiguous:         1
+  ⚠️ mismatch:      2
+
+  Overall: ⚠️ WARN
+
+  See PAPER_CLAIM_AUDIT.md for details.
+```
+
+## When to Run
+
+1. **After `/paper-write`** — first check before improvement loop
+2. **After `/auto-paper-improvement-loop`** — recheck if improvement loop changed numbers
+3. **Before submission** — final verification
+
+## Integration with Other Skills
+
+### Read by `/auto-paper-improvement-loop` (if exists)
+
+```
+if PAPER_CLAIM_AUDIT.json exists:
+    read mismatched claims
+    fix them as priority items in the improvement round
+```
+
+### Advisory, Never Blocking
+
+Same pattern as `/experiment-audit`:
+- `PASS` → continue normally
+- `WARN` → print warning, continue, flag draft as "check numbers before submission"
+- `FAIL` → print alert, continue, but do NOT mark as submission-ready
+
+## Render HTML view (auto, when `RENDER_HTML = true`, default)
+
+After writing `paper/PAPER_CLAIM_AUDIT.md` and `paper/PAPER_CLAIM_AUDIT.json`, invoke `/render-html` on the audit report:
+
+```
+/render-html "paper/PAPER_CLAIM_AUDIT.md" --json "paper/PAPER_CLAIM_AUDIT.json"
+```
+
+Uses **full review gate** (audit-class artifact; base Codex review is fresh same-family provisional). Output: `paper/PAPER_CLAIM_AUDIT.html` with embedded source SHA256 + `.review.json` sidecar.
+
+**Non-blocking**: if `/render-html` fails (helper missing, secondary Codex agent unavailable, file write error), log the failure and treat the audit as complete — the JSON + MD verdict files are canonical; the HTML view is a human-reader convenience.
+
+Skip if `RENDER_HTML = false` is set in `AGENTS.md` / `CLAUDE.md` or passed as `— render html: false`.
+
+## Key Rules
+
+- **Fresh thread EVERY run.** Never use a continuation reply. Never carry context.
+- **Zero executor interpretation.** Only file paths. No summaries.
+- **Only raw results.** No EXPERIMENT_LOG, no AUTO_REVIEW, no human summaries.
+- **Rounding rule.** Only standard rounding to displayed precision. 84.7% → 84.7% or 85% is OK. 84.7% → 85.3% is NOT OK.
+- **Review class.** Base Codex reviewer is same-family provisional; only an overlay may record cross-family accepted.
+
+## Review Tracing
+
+After each reviewer agent call, save the trace following `shared-references/review-tracing.md` (Policy C — forensic; never silently skip). Use `save_trace.sh` (resolved per the chain in `shared-references/integration-contract.md` §2) or write files directly to `.aris/traces/<skill>/<date>_run<NN>/`. Respect the `--- trace:` parameter (default: `full`).
+
+## Submission Artifact Emission
+
+This skill **always** writes `paper/PAPER_CLAIM_AUDIT.json`, regardless of
+caller or detector outcome. A detector-negative run (paper has no numeric
+claims) emits verdict `NOT_APPLICABLE`; a paper-with-numeric-claims-but-no-
+raw-results run emits `BLOCKED`. Silent skip is forbidden — `paper-writing`
+Phase 6 and `verify_paper_audits.sh` both rely on this artifact
+existing at a predictable path.
+
+The artifact conforms to the schema in `shared-references/assurance-contract.md`:
+
+```json
+{
+  "audit_skill":      "paper-claim-audit",
+  "verdict":          "PASS | WARN | FAIL | NOT_APPLICABLE | BLOCKED | ERROR",
+  "reason_code":      "all_numbers_match | rounding_drift | missing_raw_results | ...",
+  "summary":          "One-line human-readable verdict summary.",
+  "audited_input_hashes": {
+    "main.tex":                              "sha256:...",
+    "sections/5.evidence.tex":               "sha256:...",
+    "/abs/path/to/results/run_2026_04_19.json": "sha256:..."
+  },
+  "trace_path":       ".aris/traces/paper-claim-audit/<date>_run<NN>/",
+  "thread_id":        "<codex mcp thread id>",
+  "executor_model":   "codex-gpt-5.6-sol",
+  "executor_family":  "openai",
+  "reviewer_model":   "gpt-5.6-sol",
+  "reviewer_family":  "openai",
+  "review_independence": "same-family",
+  "acceptance_status": "provisional",
+  "reviewer_reasoning": "ultra",
+  "generated_at":     "<UTC ISO-8601>",
+  "details": {
+    "total_claims":   <int>,
+    "mismatches":     [ ... per-claim issue records ... ],
+    "result_files":   [ ... raw files consulted ... ]
+  }
+}
+```
+
+### `audited_input_hashes` scope
+
+Hash the **declared input set** passed into this audit invocation — i.e. the
+exact `.tex` files and raw result / config files this run read — not a
+repo-wide union and not the reviewer's self-reported subset. If a caller
+passed only `main.tex` + a single result file, hash those two files and no
+others. The external verifier rehashes these entries; any mismatch flags
+`STALE`.
+
+**Path convention** (must match what `verify_paper_audits.sh`
+expects): keys are **paths relative to the paper directory** (the arg
+passed to the verifier) for in-paper files — so `main.tex`, not
+`paper/main.tex` — and **absolute paths** for out-of-paper files such as
+external `results/` dirs. The verifier resolves relative entries via
+`os.path.join(paper_dir, key)`; prefixing with `paper/` produces
+`paper/paper/main.tex` and false-fails as STALE.
+
+### Verdict decision table
+
+| Input state                                           | Verdict          | `reason_code` example |
+|-------------------------------------------------------|------------------|-----------------------|
+| No numeric claims detected in paper                   | `NOT_APPLICABLE` | `no_numeric_claims`   |
+| Numeric claims detected, no raw result files found    | `BLOCKED`        | `no_raw_evidence`     |
+| All claims reconcile to raw data                      | `PASS`           | `all_numbers_match`   |
+| Minor rounding drift only, no material mismatch       | `WARN`           | `rounding_drift`      |
+| Any material mismatch (wrong number, config mismatch) | `FAIL`           | `claim_mismatch`      |
+| Reviewer invocation failed (network / malformed)      | `ERROR`          | `reviewer_error`      |
+
+### Thread independence
+
+Every invocation uses a fresh reviewer agent. Never continue a prior audit via
+`send_input`. Do not accept prior audit outputs (PROOF_AUDIT, CITATION_AUDIT,
+EXPERIMENT_LOG, AUTO_REVIEW summaries) as input to this audit — the fresh
+thread preserves reviewer independence per
+`shared-references/reviewer-independence.md`.
+
+### Human-readable sibling
+
+`paper/PAPER_CLAIM_AUDIT.md` is written alongside the JSON for readers.
+The JSON is authoritative for `verify_paper_audits.sh`; the Markdown
+is for humans. The parent skill (`paper-writing` Phase 6) plus the verifier
+decide whether the verdict blocks finalization — this skill itself never
+blocks; it only emits.

package/skills/skills-codex/paper-compile/SKILL.md

@@ -0,0 +1,253 @@
+---
+name: "paper-compile"
+description: "Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \\\"\u7f16\u8bd1\u8bba\u6587\\\", \\\"compile paper\\\", \\\"build PDF\\\", \\\"\u751f\u6210PDF\\\", or wants to compile LaTeX into a submission-ready PDF."
+---
+
+# Paper Compile: LaTeX to Submission-Ready PDF
+
+Compile the LaTeX paper and fix any issues: **$ARGUMENTS**
+
+## Constants
+
+- **COMPILER = `latexmk`** — LaTeX build tool. Handles multi-pass compilation automatically.
+- **ENGINE = `pdflatex`** — LaTeX engine. Options: `pdflatex` (default), `xelatex` (for CJK/custom fonts), `lualatex`.
+- **MAX_COMPILE_ATTEMPTS = 3** — Maximum attempts to fix errors and recompile.
+- **PAPER_DIR = `paper/`** — Directory containing LaTeX source files.
+- **MAX_PAGES** — Page limit. ML conferences: main body to Conclusion end (excluding references & appendix). ICLR=9, NeurIPS=9, ICML=8. **IEEE venues: references ARE included in page count.** IEEE journal ≈ 12-14 pages, IEEE conference ≈ 5-8 pages (all inclusive).
+- **RESCUE_ON_REPEAT_FAILURE = true** — If the same compile class fails after two attempts, preserve `compile.log` and ask for a focused rescue / second opinion before further edits.
+
+## Workflow
+
+### Step 1: Verify Prerequisites
+
+Check that the compilation environment is ready:
+
+```bash
+# Check LaTeX installation
+which pdflatex && which latexmk && which bibtex
+
+# If not installed, provide instructions:
+# macOS: brew install --cask mactex-no-gui
+# Ubuntu: sudo apt-get install texlive-full
+# Server: conda install -c conda-forge texlive-core
+```
+
+Verify all required files exist:
+
+```bash
+# Must exist
+ls $PAPER_DIR/main.tex
+
+# Should exist
+ls $PAPER_DIR/references.bib
+ls $PAPER_DIR/sections/*.tex
+ls $PAPER_DIR/figures/*.pdf 2>/dev/null || ls $PAPER_DIR/figures/*.png 2>/dev/null
+```
+
+### Step 2: First Compilation Attempt
+
+```bash
+cd $PAPER_DIR
+
+# Clean previous build artifacts
+latexmk -C
+
+# Full compilation (pdflatex + bibtex + pdflatex × 2)
+latexmk -pdf -interaction=nonstopmode -halt-on-error main.tex 2>&1 | tee compile.log
+```
+
+### Step 3: Error Diagnosis and Auto-Fix
+
+If compilation fails, read `compile.log` and fix common errors:
+
+**Missing packages:**
+```
+! LaTeX Error: File `somepackage.sty' not found.
+```
+→ Install via `tlmgr install somepackage` or remove the `\usepackage` if unused.
+
+**Undefined references:**
+```
+LaTeX Warning: Reference `fig:xyz' on page 3 undefined
+```
+→ Check `\label{fig:xyz}` exists in the correct figure environment.
+
+**Missing figures:**
+```
+! LaTeX Error: File `figures/fig1.pdf' not found.
+```
+→ Check if the file exists with a different extension (.png vs .pdf). Update the `\includegraphics` path.
+
+**Citation undefined:**
+```
+LaTeX Warning: Citation `smith2024' undefined
+```
+→ Add the missing entry to `references.bib` or fix the citation key.
+
+**`[VERIFY]` markers in text:**
+→ Search for `[VERIFY]` markers left by `/paper-write`. These indicate unverified citations or facts. Search for the correct information or flag to the user.
+
+**Overfull hbox:**
+```
+Overfull \hbox (12.5pt too wide) in paragraph at lines 42--45
+```
+→ Minor: usually ignorable. If severe (>20pt), rephrase the text or adjust figure width.
+
+**BibTeX errors:**
+```
+I was expecting a `,' or a `}'---line 15 of references.bib
+```
+→ Fix BibTeX syntax (missing comma, unmatched braces, special characters in title).
+
+**`\crefname` undefined for custom theorem types:**
+→ Ensure `\crefname{assumption}{Assumption}{Assumptions}` and similar are in the preamble after `\newtheorem{assumption}`.
+
+### Step 4: Iterative Fix Loop
+
+```
+for attempt in 1..MAX_COMPILE_ATTEMPTS:
+    compile()
+    if success:
+        break
+    parse_errors()
+    auto_fix()
+```
+
+For each error:
+1. Read the error message from `compile.log`
+2. Locate the source file and line number
+3. Apply the fix
+4. Recompile
+
+### Step 5: Post-Compilation Checks
+
+After successful compilation, verify the output:
+
+```bash
+# Check PDF exists and has content
+ls -la main.pdf
+# Check page count
+pdfinfo main.pdf | grep Pages
+
+# macOS: open for visual inspection
+# open main.pdf
+```
+
+**Automated checks:**
+
+- [ ] PDF file exists and is > 100KB (not empty/corrupt)
+- [ ] Total page count is reasonable (MAX_PAGES + appendix + references)
+- [ ] No "??" in the PDF (undefined references — grep the log)
+- [ ] No "[?]" in the PDF (undefined citations — grep the log)
+- [ ] Figures are rendered (not missing image placeholders)
+
+```bash
+# Check for undefined references
+grep -c "LaTeX Warning.*undefined" compile.log
+
+# Check for missing citations
+grep -c "Citation.*undefined" compile.log
+```
+
+### Step 6: Page Count Verification
+
+**CRITICAL**: Verify paper fits within MAX_PAGES.
+
+**For ML conferences (ICLR/NeurIPS/ICML/CVPR/ACL/AAAI):** Main body = first page through end of Conclusion section (not necessarily §5 — could be §6, §7, or §8 depending on structure). References and appendix are NOT counted.
+
+**For IEEE venues:** The TOTAL page count (including references) must fit within the limit. There is no separate "main body" counting — everything up to and including the references counts.
+
+**Precise check using `pdftotext`:**
+```bash
+# Extract text and find where Conclusion ends vs References begin
+pdftotext main.pdf - | python3 -c "
+import sys
+text = sys.stdin.read()
+pages = text.split('\f')
+for i, page in enumerate(pages):
+    if 'Ethics Statement' in page or 'Reproducibility' in page:
+        print(f'Conclusion ends on page {i+1}')
+    if any(w in page for w in ['References', 'Bibliography']):
+        lines = [l for l in page.split('\n') if l.strip()]
+        for l in lines[:3]:
+            if 'References' in l or 'Bibliography' in l:
+                print(f'References start on page {i+1}')
+                break
+"
+```
+
+If Conclusion ends mid-page and References start on the same page, the main body is that page number (e.g., if both are on page 9, main body = ~8.5 pages, which is fine for a 9-page limit since it leaves room for the References header).
+
+If over limit:
+- Identify which sections are longest
+- Suggest specific cuts (move proofs to appendix, compress tables, tighten writing)
+- Report: "Main body is X pages (limit: MAX_PAGES). Suggestion: move [specific content] to appendix."
+
+### Step 6.5: Stale File Detection
+
+Check for orphaned section files not referenced by `main.tex`:
+
+```bash
+# Find all .tex files in sections/ and check which are \input'ed by main.tex
+for f in paper/sections/*.tex; do
+    base=$(basename "$f")
+    if ! grep -q "$base" paper/main.tex; then
+        echo "WARNING: $f is not referenced by main.tex — consider removing"
+    fi
+done
+```
+
+This prevents confusion from leftover files when section structure changes (e.g., old `5_conclusion.tex` left behind after restructuring to 7 sections).
+
+### Step 7: Submission Readiness
+
+For conference submission, additional checks:
+
+- [ ] **Anonymous**: no author names, affiliations, or self-citations that reveal identity
+- [ ] **Page limit**: main body within MAX_PAGES (to end of Conclusion)
+- [ ] **Font embedding**: all fonts embedded in PDF
+  ```bash
+  pdffonts main.pdf | grep -v "yes"  # should return nothing (or only header)
+  ```
+- [ ] **No supplementary mixed in**: appendix clearly after `\newpage\appendix`
+- [ ] **File size**: reasonable (< 50MB for most venues, < 10MB preferred)
+- [ ] **No `[VERIFY]` markers**: search the PDF text for leftover markers
+
+### Step 8: Output Summary
+
+```markdown
+## Compilation Report
+
+- **Status**: SUCCESS / FAILED
+- **PDF**: paper/main.pdf
+- **Pages**: X (main body to Conclusion) + Y (references) + Z (appendix)
+- **Within page limit**: YES/NO (MAX_PAGES = N)
+- **Errors fixed**: [list of auto-fixed issues]
+- **Warnings remaining**: [list of non-critical warnings]
+- **Undefined references**: 0
+- **Undefined citations**: 0
+
+### Next Steps
+- [ ] Visual inspection of PDF
+- [ ] Run `/paper-write` to fix any content issues
+- [ ] Submit to [venue] via OpenReview / CMT / HotCRP
+```
+
+## Key Rules
+
+- **Never delete the user's source files** — only modify to fix errors
+- **Keep compile.log** — useful for debugging
+- **Don't suppress warnings** — report them, let the user decide
+- **If LaTeX is not installed**, provide clear installation instructions rather than failing silently
+- **Font embedding is critical** — some venues reject PDFs with non-embedded fonts
+- **Page count rules differ by venue** — ML conferences: main body to Conclusion (refs excluded). **IEEE venues: total pages including references.**
+
+## Common Venue Requirements
+
+| Venue | Style File | Citation | Page Limit | Refs in limit? | Submission |
+|-------|-----------|----------|------------|----------------|------------|
+| ICLR 2026 | `iclr2026_conference.sty` | `natbib` (`\citep`/`\citet`) | 9 pages (to Conclusion end) | No | OpenReview |
+| NeurIPS 2025 | `neurips_2025.sty` | `natbib` (`\citep`/`\citet`) | 9 pages (to Conclusion end) | No | OpenReview |
+| ICML 2025 | `icml2025.sty` | `natbib` (`\citep`/`\citet`) | 8 pages (to Conclusion end) | No | OpenReview |
+| IEEE Journal | `IEEEtran.cls` [journal] | `cite` (`\cite{}`, numeric) | ~12-14 pages (Transactions) / ~4-5 (Letters) | **Yes** | IEEE Author Portal / ScholarOne |
+| IEEE Conference | `IEEEtran.cls` [conference] | `cite` (`\cite{}`, numeric) | 5-8 pages (varies by conf) | **Yes** | EDAS / IEEE Author Portal |