Val Set
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Val Set has 6 facts recorded in Dontopedia across 5 references, with 1 live disagreement.
Mostly:rdf:type(2), exists(1), subset of(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (6)
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.
computesAvgLossComputes Avg Loss(1)
- Eval Loss Computation
ex:eval-loss-computation
doesForwardPassDoes Forward Pass(1)
- Small Probe Script
ex:small-probe-script
involvesRunningModelOnInvolves Running Model on(1)
- Eval Loss Computation
ex:eval-loss-computation
measuredOnMeasured on(1)
- Loss Progression
ex:loss-progression
onDatasetOn Dataset(1)
- Forward Pass
ex:forward-pass
usesUnseenDataUses Unseen Data(1)
- Val Loss
ex:val-loss
Other facts (6)
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 |
|---|---|---|
| Rdf:type | Dataset Split | [4] |
| Rdf:type | Dataset | [5] |
| Exists | Implicit | [1] |
| Subset of | Train Clean Txt | [2] |
| Exists for Testing | true | [3] |
| Has Token Count | 1353823 | [4] |
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 (5)
ctx:discord/blah/watt-activation/part-27ctx:discord/blah/watt-activation/part-41ctx:discord/blah/watt-activation/part-223ctx:discord/blah/watt-activation/137- full textwatt-activation-137text/plain2 KB
doc:agent/watt-activation-137/9608fbdb-8ce7-4e5b-ac20-5c329d46eadeShow excerpt
[2026-03-09 06:07] xenonfun: ``` ❯ are you sure this is principaled? ⏺ No, you're right to push back. L1 normalization is ad-hoc — it bounds the magnitude but it's not derived from the manifold. The principled fix is to normalize the mean…
ctx:discord/blah/watt-activation/222- full textwatt-activation-222text/plain3 KB
doc:agent/watt-activation-222/d8201f0f-b5d1-4b50-9f4e-2aca2c0d4c1eShow excerpt
[2026-03-11 05:02] xenonfun: ⏺ mx.compile with RotationalAdamW is a dead end — the optimizer creates new array objects on each step, so inputs=[model.state] captures stale references. The error "array without primitive" is exactly what CL…
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.