Dontopedia

Experiment Results

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

Experiment Results has 20 facts recorded in Dontopedia across 9 references, with 2 live disagreements.

20 facts·17 predicates·9 sources·2 in dispute

Mostly:has artifact(3), rdf:type(2), are dramatically better than(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (10)

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.

announcesAnnounces(1)

canUpdateRegistryCan Update Registry(1)

describesResultsAsRemarkablyConsistentDescribes Results As Remarkably Consistent(1)

framedAsContextScalingFramed As Context Scaling(1)

performsReportingPerforms Reporting(1)

performsSpeechActOfReportingPerforms Speech Act of Reporting(1)

providedInterpretationProvided Interpretation(1)

sharesProgressUpdateShares Progress Update(1)

tellClearStoryTell Clear Story(1)

usesRhetoricalTableUses Rhetorical Table(1)

Other facts (20)

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.

20 facts
PredicateValueRef
Has ArtifactJson Artifact[9]
Has ArtifactMd Artifact[9]
Has ArtifactResults Md[9]
Rdf:typeResults[8]
Rdf:typeResult Set[9]
Are Dramatically Better ThanReal Angle Version[1]
Presupposes Valid MetricsPpl Calculation[1]
Strongly Validates Insightnull[2]
Demonstrates ViabilityTernary Lohe[3]
Reference Prior RunsPrevious Configs[4]
Claim High AccuracyRust Manifold S3 Lohe[5]
Show Adaptive SuperiorityFixed Rs[6]
Prove ConclusivelyPearlshell Artificial Culture Capability[7]
Is Looking Promisingtrue[8]
Comparison Modeside by side at the same checkpoints[8]
Described Ascleaner publication result[9]
Cleaner ThanCnn Comparison[9]
Uses Same Datasettrue[9]
Uses Same Budgettrue[9]
Method SettingMLP-style NAS[9]

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.

areDramaticallyBetterThanblah/watt-activation/part-47
ex:real-angle-version
presupposesValidMetricsblah/watt-activation/part-47
ex:ppl-calculation
stronglyValidatesInsightblah/watt-activation/part-66
null
demonstratesViabilityblah/watt-activation/part-277
ex:ternary-lohe
referencePriorRunsblah/watt-activation/part-357
ex:previous-configs
claimHighAccuracyblah/watt-activation/part-480
ex:rust-manifold-s3-lohe
showAdaptiveSuperiorityblah/watt-activation/part-341
ex:fixed-rs
proveConclusivelytrove-cooktown/beche-de-mer
ex:pearlshell-artificial-culture-capability
typeblah/watt-activation/275
ex:Results
isLookingPromisingblah/watt-activation/275
true
comparisonModeblah/watt-activation/275
side by side at the same checkpoints
typeblah/watt-activation/305
ex:ResultSet
hasArtifactblah/watt-activation/305
ex:json-artifact
hasArtifactblah/watt-activation/305
ex:md-artifact
hasArtifactblah/watt-activation/305
ex:results-md
describedAsblah/watt-activation/305
cleaner publication result
cleanerThanblah/watt-activation/305
ex:cnn-comparison
usesSameDatasetblah/watt-activation/305
true
usesSameBudgetblah/watt-activation/305
true
methodSettingblah/watt-activation/305
MLP-style NAS

References (9)

9 references
  1. [1]Part 472 facts
    ctx:discord/blah/watt-activation/part-47
  2. [2]Part 661 fact
    ctx:discord/blah/watt-activation/part-66
  3. [3]Part 2771 fact
    ctx:discord/blah/watt-activation/part-277
  4. [4]Part 3571 fact
    ctx:discord/blah/watt-activation/part-357
  5. [5]Part 4801 fact
    ctx:discord/blah/watt-activation/part-480
  6. [6]Part 3411 fact
    ctx:discord/blah/watt-activation/part-341
  7. [7]Beche De Mer1 fact
    ctx:genes/trove-cooktown/beche-de-mer
  8. [8]2753 facts
    ctx:discord/blah/watt-activation/275
    • full textwatt-activation-275
      text/plain3 KBdoc:agent/watt-activation-275/149bf24b-54fb-4412-b289-e2e03bccffe2
      Show excerpt
      [2026-03-13 20:46] xenonfun: ⏺ This tells a clear story: Current trained weights are NOT naturally ternary. Only ~46% of values are near {-1, 0, 1} after scaling (random Gaussian would give ~47%, so no better than chance). Relative err
  9. [9]3059 facts
    ctx:discord/blah/watt-activation/305
    • full textwatt-activation-305
      text/plain3 KBdoc:agent/watt-activation-305/4309ac1d-dc27-4020-9ee7-50e427dd436e
      Show excerpt
      [2026-03-14 12:17] lisamegawatts: well we still crushing neat, but apparently that under compute matched baseline so we going to do yet another 5 seed for conclusive apples to apples neat vs symbio at NAS [2026-03-14 12:27] xenonfun: (file

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.