PulseCast paper

Two versions of the paper, plus the research trail.

File What it is Status
main.md Version A — 4–5 page hackathon technical report Draft; ~3,600 words, 5 figures, 4 tables
main-extended.md Version B — 10–12 page Zenodo paper Draft; ~10,000 words, 44 references
references.md Canonical reference list and verification checklist Draft
OUTLINE.md Writing plan, claims/non-claims, figures/tables Working document
figures/ Generated figures used by both versions Draft figures
research/ Research notes (code audit, privacy law, sensing, heatmap, PETs, applications, data quality) Complete

Build

There is no Pandoc/LaTeX in this workspace. Render with any Markdown-to-PDF tool, or use a two-column template. Figure paths are relative to paper/:

paper/figures/fig_sensor_map.png
paper/figures/fig_hourly_profile.png
paper/figures/fig_quantization.png
paper/figures/fig_architecture.png
paper/figures/fig_plan.png
paper/figures/fig_forecast.png

fig_plan.png is a print reconstruction of the provided live plan screen (same values: 5 staff, 100% coverage, €3,360, 25 h over / 0 h under). Replace it with the raw screenshot file if you prefer the exact pixels.

Verification status

  • Numbers: checked against OKF_Vault/mission/data.md, the generated metrics.json, and paper/research/07-data-quality.md.
  • Canonical metrics: production 7-day 3.32 / 27.5% / 0.777; day-ahead weather 3.36 / 27.8% / 0.763; seasonal naive 5.40 / 44.7% / 0.462. The mission brief’s 3.36/27.8/0.779 was the quick baseline; the paper explains the difference once.
  • Deployment: live app https://pulse.noelsabia.dev; API https://api-pulse.noelsabia.dev.
  • v1.1 images: api 16.9 MB, web 249 MB, ml 952 MB.
  • Plan latency: 19 ms cold on v1.1; contract < 2 s.
  • v1.1 120-client Cloudflare k6: 120/120 SSE opened and closed, 0 connection errors, p95 event 331 ms, p95 scenario 646 ms, presenter POST 49.60 ms, 4m57.9s. The v1.0 baseline was 1.03 s / 194 ms / 82.69 ms / 4m53s; the papers report v1.1.
  • Per-sensor MAE: computed from the production 7-day model; n ≈ 669 per sensor.
  • Figures: generated from the raw CSV and the trained model; the plan screen is a print reconstruction of the provided screenshot.
  • References: 9 in Version A, 44 in Version B; all are real sources from the research notes. Verify DOIs/URLs before submission.
  • AI disclosure: included in both versions; the text says the authors checked each number and citation, and flags legal/guidance/inference sources rather than claiming universal verification.

Known TODOs

  • Canonical metrics (3.32/27.5/0.777 production; 3.36/27.8/0.763 day-ahead).
  • 120-client k6 result, image sizes, and plan latency.
  • Live app/API URLs.
  • Plan figure: currently reconstructed from the provided screenshot for print legibility. Replace with the raw screenshot file if you prefer the exact pixels.
  • Code release timing documented (after the hackathon); public URL to be added then.
  • Author name and ORCID (Noel Sabia, 0009-0008-3064-7573); affiliation intentionally blank.
  • Cold deployment time.
  • Replace internal project-note citations with public artifacts if a venue requires it.
  • Final page-count trim for Version A if a strict 4–5 page limit applies.

Source-of-truth rules

  • Never invent a number, citation, dataset, result, or quote.
  • Every number must match OKF_Vault/mission/data.md, the generated metrics.json, or a measured result.
  • Weather is observed in training; forecast/current weather is used in the dashboard and scenarios.
  • Values are estimated devices, not people; device penetration is unknown.
  • The 8-sensor / 5-month / 580 m limitation is explicit.
  • No city-wide heatmap, no annual seasonality, no live sensor feed, no proven ROI.
  • The deployment description matches the real system: Nuxt SSR + Onyx, Go API/SSE, FastAPI, SKE namespace-only, Cloudflare Tunnel, build-time batch, cached fallback.
S
Description
This is a paper that will be (or is already) published on zenodo (zenodo.org)
Readme
6.4 MiB
0 Stars 1 Watchers 0 Forks
Languages
Python 100%