Longterm Wiki
Updated 2026-03-13HistoryData
Page StatusContent
Edited today304 words
28QualityDraft12.5ImportancePeripheral15ResearchMinimal
Summary

Documentation page for an internal tool that extracts quantitative claims (percentages, dollar amounts, timelines) from wiki content to help identify potential insights. The tool scans MDX files and flags 'notable' claims based on importance indicators in surrounding context.

Content2/13
LLM summaryScheduleEntityEdit historyOverview
Tables1/ ~1Diagrams0Int. links0/ ~3Ext. links0/ ~2Footnotes0/ ~2References0/ ~1Quotes0Accuracy0RatingsN:2 R:3 A:4 C:5

Quantitative Claims

Open Quantitative Claims ToolBrowse numbers and statistics extracted from all content

How It Works

The Quantitative Claims tool scans all MDX content for numbers, percentages, dollar amounts, and other quantitative data that could be extracted as standalone insights.

Patterns Detected

TypeExamplesDescription
Percentages40%, 30-50%Success rates, probabilities, coverage
Dollar Amounts$1B, $10 millionResearch funding, market sizes, costs
People Counts500 researchersTeam sizes, community estimates
Timelinesby 2030, in 5 yearsPredictions, forecasts
Multipliers10x, 3-foldPerformance gains, risk increases
Probabilities20% probabilityRisk estimates, likelihood
Large Numbers100 billionScale metrics

Notable Claims

Claims are marked as "Notable" when their surrounding context contains importance indicators like:

  • catastrophic, existential, critical
  • surprising, unexpected, contrary
  • only, merely, just (indicating scarcity)
  • most, majority (indicating prevalence)
  • unprecedented, first

Generating the Data

The claims data is generated by running:

cd apps/longterm
node scripts/find-quantitative-claims.mjs

This scans all MDX files and outputs to src/data/generated/quantitative-claims.json.

Re-run this script periodically to capture new content.

Using the Tool

  1. Filter by type to focus on specific claim types (percentages, dollars, etc.)
  2. Toggle "Only notable" to see claims with importance indicators
  3. Search for specific topics or numbers
  4. Click through to source pages to verify context
  5. Extract as insight if the claim is surprising, important, and well-sourced

Tips for Good Quantitative Insights

Good candidates:

  • Specific percentages with clear methodology
  • Dollar amounts that reveal priorities
  • Timeline predictions from credible sources
  • Multipliers that show scale of change

Poor candidates:

  • Round numbers without sources (e.g., "about 50%")
  • Dates that are just timestamps
  • Numbers in code examples or technical specs
  • Statistics already well-known in the field

Related Pages

Top Related Pages