Adjust the Collection Dimension
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-07.)
Adjust the Collection Dimension has 19 facts recorded in Dontopedia across 6 references, with 1 live disagreement.
Mostly:rdf:type(3), relies on factual recall scaling(1), solution number(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.
alternativeToAlternative to(1)
- Solution 1
ex:solution-1
demonstratesDemonstrates(1)
- Corrected Code Solution 2
ex:corrected-code-solution-2
identifiesSolutionIdentifies Solution(1)
- Ajaxdavis
ex:ajaxdavis
proposesSolutionProposes Solution(1)
- Log Entry 2026 03 07 05 32
ex:log-entry-2026-03-07-05-32
recommendsRecommends(1)
- Recommendation 2
ex:recommendation-2
requiresLargerModelRequires Larger Model(1)
- Factual Qa
ex:factual-qa
Other facts (18)
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 |
|---|---|---|
| Rdf:type | Proposed Solution | [2] |
| Rdf:type | Solution | [3] |
| Rdf:type | Proposed Solution | [4] |
| Relies on Factual Recall Scaling | Parameter Count | [1] |
| Solution Number | 2 | [2] |
| Involves Action | Disable Vercel Github Checks | [2] |
| Location of Action | Vercel Dashboard | [2] |
| Agent Capable of Action | Ajaxdavis | [2] |
| Proposes Value | 2048 | [3] |
| Has Context Size | 2000 | [4] |
| Ordinal Position | 2 | [5] |
| Proposes Action | Lower LR | [5] |
| Alternative to | Solution 1 | [6] |
| Allows Vector Dimension | 3 | [6] |
| Requires Collection Dimension | 3 | [6] |
| Method | collection-adjustment | [6] |
| Solves Problem | Dimension Mismatch Problem | [6] |
| Has Code Example | Corrected Code Solution 2 | [6] |
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 (6)
ctx:discord/blah/watt-activation/part-178ctx:discord/blah/blah/11- full textblah-11text/plain3 KB
doc:agent/blah-11/200680a7-8423-48ff-a9a2-261cde3d3bc6Show excerpt
[2026-02-21 17:29] foxhop.: The annoying errors are almost certainly from Vercel's GitHub integration which creates check runs on every commit. This is controlled by Vercel's project settings, not GitHub Actions. …
ctx:discord/blah/training-and-evals/11- full texttraining-and-evals-11text/plain3 KB
doc:agent/training-and-evals-11/5e6024b9-dce0-4ec3-b112-06d13e1c5c96Show excerpt
[2026-02-21 16:35] ajaxdavis: ``` ● The models are all up — the problem is the eval runner itself. Here's what's happening: …
ctx:discord/blah/watt-activation/26- full textwatt-activation-26text/plain3 KB
doc:agent/watt-activation-26/33435d36-2781-4f3b-ab35-e0cdf2197a23Show excerpt
[2026-03-06 16:23] xenonfun: On making conversational: ``` Right — no EOS token means the model just generates forever until you hit max_new_tokens. A few paths to fix this, in order of effort: 1. Heuristic stop (zero retraining, works …
ctx:discord/blah/watt-activation/44- full textwatt-activation-44text/plain3 KB
doc:agent/watt-activation-44/35af5294-4efe-43b8-a39d-23df23087144Show excerpt
[2026-03-07 05:32] xenonfun: ``` Not good. The loss trajectory tells a clear story: ┌────────┬─────────────────────────┐ │ Iters │ Avg Loss │ ├────────┼─────────────────────────┤ │ 0-2K │ 6.56 (learning) │…
ctx:claims/beam/b99b8773-86e1-4542-99be-ea39973cacf9- full textbeam-chunktext/plain1 KB
doc:beam/b99b8773-86e1-4542-99be-ea39973cacf9Show excerpt
If you want to keep the collection dimension at 128, you need to adjust the vectors to have 128 dimensions each. For example: ```python vectors = [ [1.0] * 128, # A vector with 128 elements, all initialized to 1.0 [2.0] * 128 # A…
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.