CNN benchmark
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
CNN benchmark has 10 facts recorded in Dontopedia across 3 references, with 1 live disagreement.
Mostly:uses datasets(3), compares(1), significantly slower on cpu vs cuda(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (3)
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.
canRunNowCan Run Now(1)
- Symbiogenesis
ex:symbiogenesis
isTypeOfIs Type of(1)
- Experiment 1
ex:experiment-1
partOfReplicationPart of Replication(1)
- Symbiogenesis
ex:symbiogenesis
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 |
|---|---|---|
| Uses Datasets | Cifar 10 2k 1k | [1] |
| Uses Datasets | Fashion Mnist 1k 500 | [1] |
| Uses Datasets | Mnist 5k 1k | [1] |
| Compares | Symbiogenesis Vs Baselines | [1] |
| Significantly Slower on Cpu Vs Cuda | null | [2] |
| Tests Conv2d Performance | null | [2] |
| Took Time on | most of a day | [2] |
| Is Rough | null | [2] |
| Rdf:type | Benchmark | [3] |
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 (3)
ctx:discord/blah/watt-activation/part-466ctx:discord/blah/watt-activation/part-475ctx:discord/blah/watt-activation/473- full textwatt-activation-473text/plain2 KB
doc:agent/watt-activation-473/bbee128e-eb0e-43a7-904e-88cd885d13ddShow excerpt
[2026-03-21 19:47] xenonfun: ``` ⏺ Both done. Side-by-side comparison: ┌──────────┬─────────────┬────────────┐ │ │ Finite-diff │ Analytical │ ├──────────┼─────────────┼────────────┤ │ Best BPB │ 2.04 │ 2.19 │ …
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.