Dontopedia

Experiment 2

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

Experiment 2 has 29 facts recorded in Dontopedia across 7 references, with 5 live disagreements.

29 facts·19 predicates·7 sources·5 in dispute

Mostly:involves configuration(4), tests scheduling(3), compares(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound 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(3)

usedInUsed in(2)

isTrainCodeToByteDecoderIs Train Code to Byte Decoder(1)

Other facts (27)

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.

27 facts
PredicateValueRef
Involves ConfigurationDeep Config[5]
Involves ConfigurationWide Config[5]
Involves ConfigurationWide Gelation Stop Config[5]
Involves ConfigurationWide Gelation Stop Small Conv Config[5]
Tests Schedulingpure v3[4]
Tests Schedulingpure H[4]
Tests Schedulingalternating[4]
ComparesAdam[3]
ComparesFast Muon[3]
Rdf:typeExperiment[6]
Rdf:typeExperiment[7]
Has Result MetricIteration Count[7]
Has Result MetricAccuracy[7]
Is Train Code to Byte DecoderExperiment 2[1]
Killed Guinea Pig in35 minutes[2]
Used Venom Amount1/8 gr[2]
Planned Duration500-iteration[3]
Has Configurationidentical hyperparameters[3]
Has Settingearly-stop disabled[3]
Has TitleExp 2: Hybrid block scheduling — pure v3 / pure H / alternating[4]
Is Type ofGelation Early Stopping[5]
InvolvesCifar 10 Dataset[5]
Restricted toMlp Only[5]
Testable NowTrue[5]
Studiesgelation early stop[6]
Has Replication StatusCONFIRMED[6]
Uses DatasetXor Dataset[7]

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.

isTrainCodeToByteDecoderblah/watt-activation/part-288
ex:experiment-2
killedGuineaPigIntrove-cooktown/chinese-fishermen
35 minutes
usedVenomAmounttrove-cooktown/chinese-fishermen
1/8 gr
plannedDurationblah/watt-activation/19
500-iteration
comparesblah/watt-activation/19
ex:Adam
comparesblah/watt-activation/19
ex:Fast-Muon
hasConfigurationblah/watt-activation/19
identical hyperparameters
hasSettingblah/watt-activation/19
early-stop disabled
hasTitleblah/watt-activation/449
Exp 2: Hybrid block scheduling — pure v3 / pure H / alternating
testsSchedulingblah/watt-activation/449
pure v3
testsSchedulingblah/watt-activation/449
pure H
testsSchedulingblah/watt-activation/449
alternating
isTypeOfblah/watt-activation/464
ex:gelation-early-stopping
involvesblah/watt-activation/464
ex:cifar-10-dataset
involvesConfigurationblah/watt-activation/464
ex:deep-config
involvesConfigurationblah/watt-activation/464
ex:wide-config
involvesConfigurationblah/watt-activation/464
ex:wide-gelation-stop-config
involvesConfigurationblah/watt-activation/464
ex:wide-gelation-stop-small-conv-config
restrictedToblah/watt-activation/464
ex:mlp-only
testableNowblah/watt-activation/464
ex:true
labelblah/watt-activation/467
Experiment 2
typeblah/watt-activation/467
ex:Experiment
studiesblah/watt-activation/467
gelation early stop
hasReplicationStatusblah/watt-activation/467
CONFIRMED
typeblah/watt-activation/466
ex:Experiment
labelblah/watt-activation/466
Experiment 2: Gelation Early Stopping (XOR)
usesDatasetblah/watt-activation/466
ex:xor-dataset
hasResultMetricblah/watt-activation/466
ex:iteration-count
hasResultMetricblah/watt-activation/466
ex:accuracy

References (7)

7 references
  1. [1]Part 2881 fact
    ctx:discord/blah/watt-activation/part-288
  2. ctx:genes/trove-cooktown/chinese-fishermen
  3. [3]195 facts
    ctx:discord/blah/watt-activation/19
    • full textwatt-activation-19
      text/plain2 KBdoc:agent/watt-activation-19/e74bc25c-aab8-43ac-90e0-2f036b5a9627
      Show excerpt
      [2026-03-05 22:21] xenonfun: Both started from the same checkpoint, so same baseline: - Start checkpoint ./philosophy_model_fresh/checkpoint_iter_9198.npz - Baseline on same eval slice/settings: val_loss=5.355859, val_ppl=211.85 So
  4. [4]4494 facts
    ctx:discord/blah/watt-activation/449
    • full textwatt-activation-449
      text/plain2 KBdoc:agent/watt-activation-449/f6da4410-b0fa-46d2-9cb5-99d205dd2e55
      Show excerpt
      [2026-03-21 03:48] xenonfun: ⏺ You're right. At step 950: ``` ┌──────────┬───────────┬──────────┐ │ Metric │ Helmholtz │ v3 │ ├──────────┼───────────┼──────────┤ │ BPB │ 2.257 │ 2.257 │ ├──────────┼───────────┼
  5. [5]4648 facts
    ctx:discord/blah/watt-activation/464
    • full textwatt-activation-464
      text/plain3 KBdoc:agent/watt-activation-464/599938d0-3182-4b42-bb04-4488236f82bc
      Show 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)
  6. [6]4674 facts
    ctx:discord/blah/watt-activation/467
    • full textwatt-activation-467
      text/plain2 KBdoc:agent/watt-activation-467/c930d82c-5d05-4a3d-8a95-fd7a748d10a1
      Show excerpt
      [2026-03-21 18:44] xenonfun: ``` Experiment 1a: MNIST (5k/1k, 200 iter) ┌────────────────┬─────────────────────────────┬─────────┐ │ │ Python │ Rust │ ├────────────────┼───────────────────────
  7. [7]4665 facts
    ctx:discord/blah/watt-activation/466
    • full textwatt-activation-466
      text/plain3 KBdoc:agent/watt-activation-466/a3a63aa0-7a24-45e3-ab81-70bd522fcd80
      Show 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.