rolling best is better on holdout
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-18.)
rolling best is better on holdout has 11 facts recorded in Dontopedia across 4 references, with 1 live disagreement.
Mostly:statement text(1), subject(1), effect(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (7)
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.
Other facts (9)
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 |
|---|---|---|
| Statement Text | aKAN m32 now matches or beats KAN at L512 and L2048 | [1] |
| Subject | Learned Gate | [2] |
| Effect | adding parameters | [2] |
| Utility | not helping | [2] |
| Scope | this timescale | [2] |
| Rdf:type | Color Preference Assertion | [4] |
| Is Conjoined With | Assertion 2 | [4] |
| Has Subject | Speaker | [4] |
| Is Unqualified | true | [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 (4)
ctx:discord/blah/watt-activation/74- full textwatt-activation-74text/plain3 KB
doc:agent/watt-activation-74/f0e790ce-8e1d-4951-819d-93d9164a6692Show excerpt
[2026-03-07 18:16] xenonfun: The loop formulation exactly matches the quadratic reference A_ij = Σ_a w_ia * w_ja. Now the user has sent a second message with an even better approach — the streaming prefix-state formulation using two eins…
ctx:discord/blah/watt-activation/409- full textwatt-activation-409text/plain2 KB
doc:agent/watt-activation-409/27cf5bf6-23d3-4bb2-8da9-9ee785b7e6a7Show excerpt
[2026-03-19 13:28] xenonfun: ``` ⏺ Interesting contrast: ┌─────┬──────┬──────┬──────┬─────────┬──────┐ │ LR │ Step │ BPB │ r │ SNR │ DC │ ├─────┼──────┼──────┼──────┼─────────┼──────┤ │ 0.1 │ 350 │ 4.58 │ 0.41 │ -6.9dB …
ctx:discord/blah/watt-activation/709- full textwatt-activation-709text/plain2 KB
doc:agent/watt-activation-709/36543d9d-2b37-4d57-856d-7c91bebc2f83Show excerpt
[2026-05-02 01:44] xenonfun: Ran Chinchilla `validation` holdout eval, `20 batches × B=2 × T=2048`. - `best.pt` / step **180**: **validation BPB 1.2845** - `latest.pt` / step **2000**: **validation BPB 1.3714** So the rolling best is stil…
ctx:claims/lme/f2d22df6-d7f7-4b2c-8e29-0617f707f3f0- full textbeam-chunktext/plain49 B
doc:beam/f2d22df6-d7f7-4b2c-8e29-0617f707f3f0Show excerpt
My favorite color is teal and I work as a welder.…
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.