Decoder dominates params
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)
Decoder dominates params has 27 facts recorded in Dontopedia across 10 references, with 2 live disagreements.
27 facts·21 predicates·10 sources·2 in dispute
Mostly:rdf:type(5), content(2), confirms ppl parity(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (8)
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.
addressesAddresses(1)
- Improvement 1
ex:improvement-1
assertsFactAsserts Fact(1)
- Xenonfun
ex:xenonfun
encompassesEncompasses(1)
- Security Concerns
ex:security-concerns
hasMemberHas Member(1)
- Observations Section
ex:observations-section
hasObservationHas Observation(1)
- Message 2026 04 20 17 11
ex:message-2026-04-20-17-11
interpretedObservationInterpreted Observation(1)
- Xenonfun
ex:xenonfun
madeStatementMade Statement(1)
- Xenonfun
ex:xenonfun
statedObservationStated Observation(1)
- Omega Bot
ex:omega-bot
Other facts (26)
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.
26 facts
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Observation | [3] |
| Rdf:type | Observation | [6] |
| Rdf:type | Observation | [8] |
| Rdf:type | Observation | [9] |
| Rdf:type | Observation | [10] |
| Content | Decoder dominates params in all configs (90%+ for small models). The dynamics are incredibly lean. | [6] |
| Content | Learned kicks are essential for large vocab — fixed Fibonacci sphere can't differentiate 8K tokens well | [8] |
| Confirms Ppl Parity | Akan Vs Kan | [1] |
| States Non Divergence | Feedback Variant | [2] |
| Evaluates Positively | Feedback Variant | [2] |
| Observed Failure | Tool Execution 1 | [3] |
| Has Error Detail | no detailed message | [3] |
| Has Subject | Attention Computation | [4] |
| Fraction of Total Compute | Minor Fraction | [4] |
| Describes Comparison | Lohe D384 | [5] |
| Attributed to | Xenonfun | [6] |
| Note | Same BPB but different physics | [7] |
| Part of Report | Report Kickmodel Bpe 8k | [8] |
| Contrasts With | Fixed Fibonacci Sphere | [8] |
| Topic | Public Key Encoding | [9] |
| Corresponds to | Improvement 1 | [9] |
| Maps to | Improvement 1 | [9] |
| Ordinal Position | 1 | [9] |
| Made by | Assistant | [10] |
| Part of | Observations Section | [10] |
| Describes Function | Reformulation Function | [10] |
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.
—
confirmsPplParityblah/watt-activation/part-75
ex:akan-vs-kan
—
statesNonDivergenceblah/watt-activation/part-673
ex:feedback-variant
—
evaluatesPositivelyblah/watt-activation/part-673
ex:feedback-variant
—
typeblah/omega/458
ex:Observation
—
observedFailureblah/omega/458
ex:tool-execution-1
—
hasErrorDetailblah/omega/458
no detailed message
—
hasSubjectblah/watt-activation/57
ex:attention-computation
—
fractionOfTotalComputeblah/watt-activation/57
ex:minor-fraction
—
describesComparisonblah/watt-activation/301
ex:lohe-d384
—
typeblah/watt-activation/386
ex:Observation
—
labelblah/watt-activation/386
Decoder dominates params
—
contentblah/watt-activation/386
Decoder dominates params in all configs (90%+ for small models). The dynamics are incredibly lean.
—
attributedToblah/watt-activation/386
ex:xenonfun
—
noteblah/watt-activation/409
Same BPB but different physics
—
typeblah/watt-activation/481
ex:Observation
—
contentblah/watt-activation/481
Learned kicks are essential for large vocab — fixed Fibonacci sphere can't differentiate 8K tokens well
—
partOfReportblah/watt-activation/481
ex:report-kickmodel-bpe-8k
—
contrastsWithblah/watt-activation/481
ex:fixed-fibonacci-sphere
—
typebeam/ae77bdc5-8627-4def-99ad-7b026a52a0f1
ex:Observation
—
topicbeam/ae77bdc5-8627-4def-99ad-7b026a52a0f1
ex:Public-Key-Encoding
—
correspondsTobeam/ae77bdc5-8627-4def-99ad-7b026a52a0f1
ex:improvement-1
—
mapsTobeam/ae77bdc5-8627-4def-99ad-7b026a52a0f1
ex:improvement-1
—
ordinalPositionbeam/ae77bdc5-8627-4def-99ad-7b026a52a0f1
1
—
typebeam/ce6011fb-b975-4536-b5f8-67ee2d0d6c7a
ex:Observation
—
madeBybeam/ce6011fb-b975-4536-b5f8-67ee2d0d6c7a
ex:Assistant
—
partOfbeam/ce6011fb-b975-4536-b5f8-67ee2d0d6c7a
ex:observations-section
—
describesFunctionbeam/ce6011fb-b975-4536-b5f8-67ee2d0d6c7a
ex:reformulation-function
References (10)
10 references
ctx:discord/blah/watt-activation/part-75ctx:discord/blah/watt-activation/part-673ctx:discord/blah/omega/458- full textomega-458text/plain3 KB
doc:agent/omega-458/7a12a9ce-795f-45d0-a5ef-abc43c165f5eShow excerpt
[2025-11-30 20:08] omega [bot]: 🔧 1/1: pgListTables ❌ Failed ```json { "success": false, "error": "LIST_TABLES_FAILED", "message": "Failed to list tables: " } ``` [2025-11-30 20:08] omega [bot]: It appears that listing PostgreSQL tabl…
ctx:discord/blah/watt-activation/57- full textwatt-activation-57text/plain2 KB
doc:agent/watt-activation-57/2be5a3f3-fa33-4f3c-809c-45db01bc0deaShow excerpt
[2026-03-07 09:27] xenonfun: ``` Good question. Let me extrapolate from our existing data. Measured throughput (pairwise, batch=1): ┌─────────┬──────┬─────────┬───────┐ │ Seq Len │ it/s │ ms/iter │ tok/s │ ├─────────┼──────┼──────…
ctx:discord/blah/watt-activation/301- full textwatt-activation-301text/plain3 KB
doc:agent/watt-activation-301/3e98420c-16db-4c57-9cad-a987cec9976bShow excerpt
[2026-03-14 06:51] xenonfun: ``` ⏺ Lohe vs Softmax AR Decoder Comparison ┌───────────────┬───────────────┬────────────┐ │ Metric │ Softmax d=384 │ Lohe d=384 │ ├───────────────┼───────────────┼────────────┤ │ BPB │…
ctx:discord/blah/watt-activation/386- full textwatt-activation-386text/plain2 KB
doc:agent/watt-activation-386/56c807c0-0221-454e-97c5-567cf059cb84Show excerpt
[2026-03-19 02:19] xenonfun: ``` ⏺ Sweep running — 7 configs sequential, no contention. ~15-20 min total. Configs: ┌─────┬───────────────┬────────┬──────────┬─────────┬───────────┬─────────────┐ │ # │ Config │ Params │ Dynamic…
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/481- full textwatt-activation-481text/plain3 KB
doc:agent/watt-activation-481/00c8be1c-8839-4973-9fac-0dd3b65dedecShow excerpt
[2026-03-21 23:20] xenonfun: ``` ⏺ Here's the report for your expert: --- KickModel BPE-8K Results Report Architecture ∂ₜΨ = [Ω, Ψ] - γ⟨Ψ⟩ + kick — S³ oscillator with exp-map geodesic integration New Features Implemented 1.…
ctx:claims/beam/ae77bdc5-8627-4def-99ad-7b026a52a0f1- full textbeam-chunktext/plain1 KB
doc:beam/ae77bdc5-8627-4def-99ad-7b026a52a0f1Show excerpt
print(public_key.decode()) ``` ->-> 9,7 [Turn 3647] Assistant: Sure, I can review your code and suggest improvements for better security and performance. Here are some observations and suggestions: ### Observations 1. **Public Key Encodi…
ctx:claims/beam/ce6011fb-b975-4536-b5f8-67ee2d0d6c7a- full textbeam-chunktext/plain1 KB
doc:beam/ce6011fb-b975-4536-b5f8-67ee2d0d6c7aShow excerpt
reformulated_outputs = [] for input_ in inputs: output = input_ for stage in stages: output = stage(output) reformulated_outputs.append(output) # Calculate the accuracy of the reformulation …
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.