Experiment 3: Multi-Seed MNIST (5 seeds, 1k/500)
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Experiment 3: Multi-Seed MNIST (5 seeds, 1k/500) has 15 facts recorded in Dontopedia across 5 references, with 1 live disagreement.
Mostly:has seed count(2), has result metric(2), is run hybrid byte code training(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.
measuredInMeasured in(4)
- Exp3 Py Gel Rate
ex:exp3-py-gel-rate - Exp3 Py Mean Best Acc
ex:exp3-py-mean-best-acc - Exp3 Rust Gel Rate
ex:exp3-rust-gel-rate - Exp3 Rust Mean Best Acc
ex:exp3-rust-mean-best-acc
handlesExperimentHandles Experiment(1)
- Run Multi Seed
ex:run-multi-seed
isRunHybridByteCodeTrainingIs Run Hybrid Byte Code Training(1)
- Experiment 3
ex:experiment-3
Other facts (14)
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 Seed Count | 5 | [4] |
| Has Seed Count | 5 | [5] |
| Has Result Metric | Best Accuracy | [5] |
| Has Result Metric | Gelation Rate | [5] |
| Is Run Hybrid Byte Code Training | Experiment 3 | [1] |
| Used Venom Amount | 1/16 gr | [2] |
| Killed Guinea Pig in | 45 minutes | [2] |
| Has Title | Exp 3: Long context behavior — seq 256/512/1024 | [3] |
| Has Sequence Lengths | 256/512/1024 | [3] |
| Is Type of | Multi Seed Mnist | [4] |
| Involves | Mnist Dataset 1k 500 | [4] |
| Has Method Count | 3 | [4] |
| Rdf:type | Experiment | [5] |
| Uses Dataset | Mnist | [5] |
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-288ctx:genes/trove-cooktown/chinese-fishermenctx:discord/blah/watt-activation/449- full textwatt-activation-449text/plain2 KB
doc:agent/watt-activation-449/f6da4410-b0fa-46d2-9cb5-99d205dd2e55Show excerpt
[2026-03-21 03:48] xenonfun: ⏺ You're right. At step 950: ``` ┌──────────┬───────────┬──────────┐ │ Metric │ Helmholtz │ v3 │ ├──────────┼───────────┼──────────┤ │ BPB │ 2.257 │ 2.257 │ ├──────────┼───────────┼…
ctx:discord/blah/watt-activation/464- full textwatt-activation-464text/plain3 KB
doc:agent/watt-activation-464/599938d0-3182-4b42-bb04-4488236f82bcShow excerpt
[2026-03-21 18:08] xenonfun: ``` Key observations: - Rust achieves significantly higher accuracy (99.1% vs 89.5% best) — the GPU-accelerated training does more effective optimization per epoch - Gelation detected at the same step (12)…
ctx:discord/blah/watt-activation/466- full textwatt-activation-466text/plain3 KB
doc:agent/watt-activation-466/a3a63aa0-7a24-45e3-ab81-70bd522fcd80Show excerpt
[2026-03-21 18:43] xenonfun: ``` Rust Replication Results (vs Python) Experiment 4: XOR Parameter Efficiency ┌────────────────┬─────────────────┬──────────────────┐ │ │ 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.