Dontopedia

experiment

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

experiment has 13 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

13 facts·11 predicates·2 sources·1 in dispute

Mostly:compares(2), rdf:type(1), has iteration count(1)

Maturity scale raw canonical shape-checked rule-derived certified

Other facts (12)

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.

12 facts
PredicateValueRef
ComparesAdam[1]
ComparesMuon Fast[1]
Rdf:typePlan[1]
Has Iteration Count200[1]
Uses Same Checkpointtrue[1]
Computes Validation Losstrue[1]
Computes Validation Perplexitytrue[1]
Uses Validation Slicesame-validation-slice[1]
Has Goalclean-comparison[1]
Question InvestigatesLohe Inductive Bias Effect[2]
Condition IsFusion Mechanics Held Constant[2]
Uses Fusion OperatorBlock Diagonal Transfer Operator[2]

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.

typeblah/watt-activation/18
ex:Plan
hasIterationCountblah/watt-activation/18
200
comparesblah/watt-activation/18
ex:adam
comparesblah/watt-activation/18
ex:muon-fast
usesSameCheckpointblah/watt-activation/18
true
computesValidationLossblah/watt-activation/18
true
computesValidationPerplexityblah/watt-activation/18
true
usesValidationSliceblah/watt-activation/18
same-validation-slice
hasGoalblah/watt-activation/18
clean-comparison
labelblah/watt-activation/435
experiment
questionInvestigatesblah/watt-activation/435
ex:lohe-inductive-bias-effect
conditionIsblah/watt-activation/435
ex:fusion-mechanics-held-constant
usesFusionOperatorblah/watt-activation/435
ex:block-diagonal-transfer-operator

References (2)

2 references
  1. [1]189 facts
    ctx:discord/blah/watt-activation/18
    • full textwatt-activation-18
      text/plain3 KBdoc:agent/watt-activation-18/812b86dc-f424-4d37-b858-94cd90ca9fbf
      Show excerpt
      [2026-03-04 05:47] xenonfun: feat: Complete training system with optimizations - 68x speedup with optimized MLX conv1d - Parallel tokenizer with caching - From-scratch training with best checkpoints - Async checkpoint saving - Learning rate
  2. [2]4354 facts
    ctx:discord/blah/watt-activation/435
    • full textwatt-activation-435
      text/plain2 KBdoc:agent/watt-activation-435/6e80af4f-2aed-449f-9f6a-4750597bfb8e
      Show excerpt
      [2026-03-20 06:59] xenonfun: ``` ⏺ You're right. The PR #7 results (p=0.005, d=2.57, 5/5 seeds) were validated with a specific fusion operator — _block_diagonal_transfer() on vanilla nn.Linear layers. The fusion level (how weights map be

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.