Experiment 1a
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Experiment 1a has 13 facts recorded in Dontopedia across 2 references, with 3 live disagreements.
Mostly:has iteration count(3), has training set size(2), has test set size(2)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (2)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
describesDescribes(1)
- Chat Message 2026 03 21 18 44
ex:chat-message-2026-03-21-18-44
reportsResultsReports Results(1)
- Xenonfun
ex:xenonfun
Other facts (12)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Has Iteration Count | 200 | [1] |
| Has Iteration Count | 200 | [2] |
| Has Iteration Count | 200 Value | [2] |
| Has Training Set Size | 5000 | [2] |
| Has Training Set Size | 5000 Value | [2] |
| Has Test Set Size | 1000 | [2] |
| Has Test Set Size | 1000 Value | [2] |
| Has Train Test Split | 5k/1k | [1] |
| Uses Dataset | Mnist | [1] |
| Presupposes Overfitting Risk | True | [1] |
| Rdf:type | Experiment | [2] |
| Has Dataset | Mnist | [2] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (2)
ctx:discord/blah/watt-activation/part-469ctx:discord/blah/watt-activation/467- full textwatt-activation-467text/plain2 KB
doc:agent/watt-activation-467/c930d82c-5d05-4a3d-8a95-fd7a748d10a1Show excerpt
[2026-03-21 18:44] xenonfun: ``` Experiment 1a: MNIST (5k/1k, 200 iter) ┌────────────────┬─────────────────────────────┬─────────┐ │ │ Python │ Rust │ ├────────────────┼───────────────────────…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.