Witching Hour: even a ghost has to cite its sources

Описание и применение

Веб‑приложение Witching Hour объединяет измерения света, звука и движения, использует модели TabPFN и Gemma для анализа и генерации рассказов, а также хранит доказательства с временными метками, обеспечивая прозрачность и воспроизводимость расследований призраков.

Задача

Ghost‑hunting teams need a way to combine real sensor data, machine‑learning analysis, and narrative storytelling while ensuring evidence is traceable and claims are cited.

Результат

The app produces a structured dossier containing timestamped evidence, ML‑estimated anomaly ranges, crew accounts with citations, and a recorded séance, enabling transparent and reproducible ghost‑hunting investigations.

Рабочий процесс

• 1. Load the Witching Hour web app (PARANORMAL.exe).
• 2. Select a case (The House, The Unheard, or The Room).
• 3. For The Unheard, upload or play the recording; the browser measures light, sound and motion and marks events.
• 4. The app presents evidence events with timestamps in an evidence locker.
• 5. TabPFN estimates anomaly ranges for each sensor reading.
• 6. Gemma reads evidence cards and writes crew accounts, attaching citation chips to each sentence.
• 7. The crew’s dialogue is displayed with a glass‑board interface; the glass moves based on scripted responses.
• 8. The final dossier is downloadable, separating evidence, crew accounts and the board conversation.

Доказательства

I built an interactive ghost‑hunting web app that reimagines the Ouija board, known in Brazil as brincadeira do copo, with real measurements, machine learning and data science.

Источник

Two open‑model tools give the crew something to work with: TabPFN is a foundation model for tables. Gemma is Google's family of open models.

Источник

The evidence locker separates the staged scene into light, sound and motion events.

Источник

Generated crew sentences must point to known evidence, and their numerical claims must pass the validator.

Источник