Data Science
A discipline is a lens, not an owner — the same idea can be viewed through many.
Concepts viewed through this lens
These numbers describe the current Thinking OS knowledge slice, not the whole field.
Disciplines it bridges to
Each bridge is built by ideas the two fields share, the thinking patterns that recur across both, and a representative relationship that shows how they connect.
Data Scienceconnects toComputer Science
Shared thinking patterns
Why this bridge exists
Binary numeral system models Data — binary numeral system models data.
Explore this connection →Data Scienceconnects toStatistics
Shared concepts
Shared thinking patterns
Why this bridge exists
Confounding variable causes Correlation — A confounding variable can create a misleading correlation.
Explore this connection →Data Scienceconnects toMachine Learning
Shared thinking patterns
Why this bridge exists
Overfitting suppresses Generalization — Overfitting destroys generalisation.
Explore this connection →Data Scienceconnects toEconomics
Shared thinking patterns
Why this bridge exists
Overfitting is a Trade-off — Overfitting is one side of a fit-versus-generalise trade-off.
Explore this connection →Data Scienceconnects toMathematics
Shared thinking patterns
Why this bridge exists
Regression analysis models Correlation — regression analysis models Correlation.
Explore this connection →Data Scienceconnects toBiology
Shared thinking patterns
Why this bridge exists
Data is a Information — data is a kind of Information.
Explore this connection →Data Scienceconnects toProbability
Shared concepts
Shared thinking patterns
Why this bridge exists
Confounding variable causes Correlation — A confounding variable can create a misleading correlation.
Explore this connection →Data Scienceconnects toMedicine
Shared thinking patterns
Why this bridge exists
Risk is analogous to Correlation — Judging risk means reasoning about probability, not certainty.
Explore this connection →
Field shape — representation health
59/100 overall · 17 concepts
The eight dimensions measure Thinking OS coverage of this field, not the quality or importance of the discipline.
What kind of structure is this field?
Interpreted from the current atlas — how this field is represented, not a judgement of the field.
Representation health 59/100 — dense but shallow. Strongest: cross-disciplinary, foundations. Thinnest: factual depth, provenance.
structural · Measures the current Thinking OS representation, not the quality or importance of the field.
Its 59 representation-health is above the 55 median of 208 similarly-sized disciplines (comparable by concept count).
structural · Measures the current Thinking OS representation, not the quality or importance of the field.
60% of its relations reach into 38 other disciplines — an outward-facing field in the atlas.
structural · Measures the current Thinking OS representation, not the quality or importance of the field.
18% of its concepts have a single connection (mean internal degree 2.0) — a fairly cohesive internal structure.
structural · Measures the current Thinking OS representation, not the quality or importance of the field.
Current atlas gaps: no dated concepts.
atlas representation · Measures the current Thinking OS representation, not the quality or importance of the field.
How this lens connects
The kinds of relationship that characterise this discipline lens in the current slice.
Coverage matrix
How these concepts distribute across domains and concept families — real counts, not a score.
Ideas that connect this discipline outward
Concepts viewed through this lens that reach disciplines it does not itself carry — concept-level bridges (distinct from the discipline-to-discipline bridges below).
- CorrelationreachesBiostatisticsEconometricsEconomicsEpidemiologyEthicsFinanceHistoryMathematicsMedicineMetaphysicsPhilosophy of SciencePsychologyPublic Policy
- OverfittingreachesBiologyBusinessCognitive ScienceComputer ScienceDesignEconomicsEngineeringEthicsPolitical SciencePublic PolicySystems Engineering
- DatareachesBiologyCommunication ScienceComputational Social ScienceDigital HumanitiesGeographyGeoinformaticsInformation TheorySociology
- Gradient descentreachesBusinessEconomicsEngineeringMathematical ModellingStatisticsSystems Engineering
- Supervised learningreachesArtificial IntelligenceCognitive ScienceMathematicsPhilosophy of ScienceStatistics
- DatabasereachesDatabasesInformation ScienceLibrary Science
Mental models that recur here
Information ×2
Anything that reduces uncertainty. It can be encoded into a signal, sent across a channel, and decoded — and noise can corrupt it on the way.
Cause and effect ×1
One thing genuinely bringing about another — as opposed to two things merely moving together. Establishing it needs a mechanism and controls, not just a pattern.
Feedback loop ×1
A loop where an effect feeds back to change its own cause. Reinforcing loops amplify change; balancing loops resist it.
Optimization ×1
Searching a space of options for the best one under constraints — following a gradient of 'better' toward a maximum or minimum.
Learning journeys that use it
- 17 concepts are viewed through this lens.
- 13 of them bridge into other disciplines.
- Its signature thinking pattern is “Information” (recurs in 2 concepts).
- The most common kind of connection here is “Kind & structure”.
- It is most tightly linked to Computer Science.
Derived from the current graph structure — observations, not a judgement of the field.