Sim Desk - notice

The app's agent prompt is derived from the agent skill "simpy" (@k-dense-ai/simpy, skill version
1.4) in the repository k-dense-ai/scientific-agent-skills by K-Dense Inc.
  https://github.com/k-dense-ai/scientific-agent-skills (skills/simpy)
The skill's front matter declares "license: MIT". No text of the skill is redistributed verbatim;
the prompt was rewritten for this app.

The in-browser engine (simkit.js) is an independent JavaScript port of the numeric parts of the
skill's bundled scripts - _common.py (derive_seed, the configuration validators, the Student-t
interval by incomplete beta), basic_simulation_template.py (QueueConfig and the queue model),
resource_monitor.py (time-weighted monitoring) and replication_runner.py (ExperimentConfig and the
replication summary) - running on a small re-implementation of the SimPy 4.1.2 event loop
(Environment, Event, Timeout, Process, Resource with Request/Release), CPython's random.Random
(MT19937 with init_by_array, random(), expovariate), BLAKE2b (RFC 7693), math.fsum,
statistics.fmean / stdev (exact) and math.lgamma (CPython's Lanczos coefficients). No SimPy or
CPython code is included. SimPy is MIT-licensed.

It was checked against SimPy 4.1.2 under CPython 3.12 running the skill's own scripts on 560
random configurations (1-20 servers, loads 0.3-2.0, terminating and steady-state, entity limits,
2-20 replications, 80-99% confidence): 139,281 values compared. Every counter, event count and
derived seed was identical; every floating-point value agreed to 3.4e-12 relative (or 1e-16
absolute for standard deviations of constant series) - the residue is the last bit of log()
differing between the browser and the C library. The 40 invalid configurations tried produced the
skill's error messages word for word.

The M/M/c/K steady-state benchmark, the window view and the scenario comparison are the page's
own additions and are not part of the skill's scripts.

Citation the skill asks for (verified on arXiv, 2026-09-27):
  Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent Skills:
  A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.
  https://doi.org/10.48550/arXiv.2609.00065