L4 ⚡ L3-002-001-001-T1-reference-topup ⊙ Testnet

baseline:reference

⬇ Download bundle 🚀 Submit to mainnet — earn 55% of mining pool royalty

🎁 Contribute & earn PWM

Improve L3-002-001-001-T1-reference-topup — submit with or without uploading. Accepted submissions earn the 1/16 modify share of A(t).

✨ Submit without uploading free check · 1×

One click — no files, no typing. We submit a check of L3-002-001-001-T1-reference-topup for you; it goes through review and earns the 1/16 share once. One free no-upload Solution per account.

You'll be asked to log in first — then it's one click, no files.

⬆ Or submit by uploading your files

Upload your .md + .json + code/ & reports/ files as a modification of L3-002-001-001-T1-reference-topup. Unlimited.

🛠 Helper: build your files in ChatGPT / Gemini / Claude

Layer template

⬇ solution.md ⬇ solution.json ⬇ code/ (.zip)

Fork L3-002-001-001-T1-reference-topup

⬇ L3-002-001-001-T1-reference-topup.md ⬇ L3-002-001-001-T1-reference-topup.json

Prompt — copy into your LLM

You are helping me submit a MODIFICATION of L3-002-001-001-T1-reference-topup (baseline:reference) to the PWM Protocol — a Solution (L4) artifact.

I will paste a Markdown template (or the current L3-002-001-001-T1-reference-topup.md).
1. Rewrite the Markdown so the science is correct and clearly explained for my change.
2. Regenerate the sibling L3-002-001-001-T1-reference-topup.json so EVERY field matches the Markdown.
3. Keep the schema in the "File Mapping" footer at the bottom of the MD.
4. Keep the parent reference unchanged unless I ask otherwise.
5. Also produce code/solver.py and reports/reproduce.md. reports/results.md must come from ACTUALLY RUNNING the solver — never fabricated.
Rules: the Markdown is the source of truth; use SI units; do NOT invent benchmark scores.
Output each file in its own fenced code block tagged with the filename.

Here is my template:
[PASTE THE .md HERE]

Markdown — human-readable source of truth

⚙ auto-generated

⬇ L3-002-001-001-T1-reference-topup.md

# ⚡ L4 Solution — baseline:reference **ID:** `L3-002-001-001-T1-reference-topup` · **Status:** ⊙ Testnet (genesis catalog) **Parents:** ⬆ Benchmark [`L3-002-001-001-T1`](/artifact/l3/L3-002-001-001-T1) > **🛠 Solver:** `baseline:reference` > **📊 Performance:** **Q = `0.8`** · difficulty `0.14` > **🔖 Status:** `testnet` --- ## 1. Solver **`baseline:reference`** ## 2. Performance | Property | Value | |---|---| | Difficulty score | 0.14 | | Quality ratio | 0.8 | | Reward pwm | 0 | ## 3. Operating Point (Ω_s) | Parameter | Unit | Value | |---|---|---| | H | px | 512 | | W | px | 512 | | Na | — | 1.4 | | Dz nm | nm | 0 | | Pixel nm | nm | 65 | | Sigma bg | — | 0 | | Peak photons | photons | 50 | ## 4. Certificate **Hash:** `92a33be3385c3eb0bb68836c1b0099517e44d38adca7634baadabb15e5cbe836` **Status:** `testnet` ## 5. Code Reference implementation — see [`code/`](/artifact/l4/L3-002-001-001-T1-reference-topup/raw/code/) when present. ## 6. Reproduction Report Reconstruction results on the parent benchmark — see [`reports/`](/artifact/l4/L3-002-001-001-T1-reference-topup/raw/reports/) when present. --- ## File Mapping This bundle consists of: `L3-002-001-001-T1-reference-topup.md`, `L3-002-001-001-T1-reference-topup.json`, `code/`, `reports/`. | File | Role | How to regenerate | |------|------|-------------------| | `L3-002-001-001-T1-reference-topup.md` | Source of truth — edit this | Human or LLM | | `L3-002-001-001-T1-reference-topup.json` | Structured metadata for the registry | LLM regenerates from the sections above | | `code/solver.*` | Reference implementation | LLM regenerates from §1 Solver and §2 Operating point | | `reports/results.md` | Reconstruction results | **Generated by running the solver** — do not fabricate | | `reports/reproduce.md` | Step-by-step verification recipe | LLM regenerates as a recipe matching what was actually run | **Prompt for your LLM after editing this Markdown:** > Read the attached Markdown. Regenerate the sibling `.json` so every field matches. > Also regenerate `code/solver.*` and `reports/reproduce.md` per the schema. > Output each file in its own fenced code block tagged with the filename. > Do NOT fabricate `reports/results.md` — it must come from actually running the solver. _This Markdown was auto-synthesized from the catalog row for `L3-002-001-001-T1-reference-topup`._ _Edit it, regenerate the JSON, and submit at [/submit](/submit) to claim the artifact._

💬

Ask the PWM AI agent AI

Ask about this baseline:reference — or how to improve it & earn PWM

Free to search; log in to chat with the agent & earn PWM. How it works ↗

⌥ Hierarchy

Upstream lineage and downstream children

↑ Upstream

L4 Solutions are terminal — no downstream children.

⬇ Download bundle

2 files · click to download

📋 JSON metadata

{
  "artifact_id": "L3-002-001-001-T1-reference-topup",
  "certificate_hash": "92a33be3385c3eb0bb68836c1b0099517e44d38adca7634baadabb15e5cbe836",
  "difficulty_score": 0.14,
  "layer": "L4",
  "omega_s": {
    "H": 512,
    "NA": 1.4,
    "W": 512,
    "dz_nm": 0.0,
    "peak_photons": 50,
    "pixel_nm": 65,
    "sigma_bg": 0.0
  },
  "parent_l3": "L3-002-001-001-T1",
  "quality_ratio": 0.8,
  "reward_pwm": 0.0,
  "solver_id": "baseline:reference",
  "status": "testnet",
  "title": "baseline:reference"
}

🎁

Earn PWM by promoting this to mainnet

• PWM emission on accept — your share of A(t) (1/16 modify · 3/16 new)
• 55% of mining pool upstream royalty on every downstream L4 mining event, forever
• Your wallet is enrolled the moment the founder accepts

🚀 Go to submit ↑

How: use the “Contribute & earn PWM” panel at the top — either Submit without uploading (one click) or upload your files. Then the review runs and, on accept, it’s promoted to mainnet.