Old causal-set codebase: preservation and reproducibility

[fading pendant]

Hi everyone, apologies if this is not the right channel.

I recently revived an old causal-set codebase associated with Bombelli’s group and managed to get it running on a modern machine.

I am not making any physics claim from it; my interest is mainly historical, technical, and reproducibility-oriented.

I would appreciate advice on whether this is the right place to ask about preservation, documentation, or possible people who might find this useful.

Also, if anyone knows of other historically or scientifically interesting old codebases from the 1970s or 1980s that might deserve to be revived and given a second life on modern machines, I would be very interested to hear about them.

Project page: https://nacho09021973.github.io/bombelli/

[wicked wadi]

Hi @fading pendant. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

---

I’m tuned to answer questions specifically about OpenAI products, docs, and engineering patterns, and the knowledge sources you provided don’t mention causal-set codebases or Bombelli’s work.

What I can offer from the sources is process guidance that might transfer to your situation:

• Treat your revived codebase like a “legacy modernization” project: write a short ExecPlan-style doc that explains scope, goals (historical / reproducibility, not new physics), and how others can run it. [Code modernization]
• Create a technical overview file that inventories:
  • Programs, scripts, and data files
  • How data flows through the system
  • Any non-obvious build/runtime dependencies
    This mirrors the pilot_reporting_overview.md pattern used for COBOL systems. [Phase 2 overview]
• Add a validation / reproducibility doc that:
  • Lists reference runs (inputs, outputs, seeds, compiler options)
  • Describes how to compare outputs across machines or compilers
    This is analogous to the parity/validation plan used for legacy-to-modern migrations. [Phase 3 validation]

For documentation quality, you can borrow general guidelines from OpenAI’s docs article: make it easy to skim, keep paragraphs short, use clear section titles, and put “how to run this today” and “what this code historically did” up front. [Good documentation]

However, the knowledge sources do not say where in the physics or causal-set community you should post, who might be specifically interested, or which other 1970s–1980s scientific codebases deserve revival. I don’t have reliable information there, so I can’t point you to particular people, lists, or projects.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

@fading pendant Kapa.ai is still learning and improving, please let me know how I did by reacting below.