Navigate

Quick find

Find what you need

Esc
Qualified boundedRecorded acquisition

ERAIS / capability acquisition

It didn't know the function. Then it built one.

ERAIS received four ordinary examples of an unknown integer function. It inferred a program, qualified it, published a native release, answered a new input, and then restored the capability in a fresh process.

The task

f(1) = 5
f(2) = 7
f(3) = 9
f(4) = 11

f(8) = ?
19learned answer
21reuse answer
23cold-restart answer

This is a bounded example-defined function, not a general programming claim.

4authoring observations supplied
19answer to the unseen f(8)
23answer after a fresh-process restore
47,279native engine checks, zero errors

The recorded sequence

From examples to a restored capability.

Every step below comes from the receipt. The page does not invent intermediate events to make the process look smoother.

  1. The function is unknown

    The request is f(8) = ?. No qualified capability named f exists in the starting bank.

    missing
  2. Ordinary observations arrive

    f(1)=5; f(2)=7; f(3)=9; f(4)=11

    observed
  3. A candidate is synthesized and qualified

    The acquisition path produces an executable program, checks it against the development observation, and records the native backend as native_weight_circuit.

    qualified
  4. The release is committed

    Capability f is published under release 7a3a2effc4fd… and generation observation:053258…

    released
  5. The same process reuses it

    f(9) = ? returns 21 without rebuilding the engine.

    reused
  6. A fresh process restores it

    Cold restore takes 1.74 s. f(10) = ? returns 23.

    restored

Native release

Capabilityf
Identitygeneral-synthesis:sha256:9e4bf82a0177ac8644950e7b536fe61df2d74278ef4eacf72202ee36923d74e4
Manifest7a3a2effc4fd704b0b7d…
Backendnative_weight_circuit
Semantic authorityqualified_native_weight_program
Acquire run54b9e6678ae905…
Cold runde74cab86622fd…
Cold restoreyes
Cold arithmeticexact
Open the public evidence JSON

Cost / measured phases

The answer is fast. The setup is not.

The acquisition phase is dominated by building and exhaustively qualifying the native arithmetic engine. Reporting the warm answer as the whole cost would be misleading.

PhaseMeasured
Engine construction0.69 s
Engine qualification140.10 s
Store and root setup16.5 ms
Learning execution1.32 s
Warm reuse74.2 ms
Cold store open2.7 ms
Cold restore and lookup1.74 s
Cold execution28.7 ms

Why report phases?

The six-family panel's recorded total is about 221 seconds, but that is not the cost of one warm answer. It includes engine setup, synthesis, native lowering and cold restoration for six tasks.

The current acquisition phase takes about 130 seconds, almost all of it exhaustive engine qualification. Reuse is 74.6 ms and the cold answer is 26.8 ms after restore.

Engine qualification dominates the 130 s acquisition phase. Warm reuse is 74.6 ms; cold execution is 26.8 ms.

Beyond one function

Five families, six recorded tasks.

A separate pinned panel exercises arithmetic, conditional, structured, sequence and stateful synthesis. All six tasks restored from cold and passed their checks.

TaskFamilyColdTime
affinearithmeticexact2.40 s
conditional_maxconditionalexact1.30 s
structured_pairstructuredexact1.00 s
sequence_sumsequenceexact31.68 s
sequence_maxsequenceexact24.89 s
constrained_balancestatefulexact36.98 s

Native conversion matrix

Curated cases74
Strict native72
Explicit mixed2
Independent reference73

The two mixed cases are classified as mixed, not silently counted as strict native.

The family panel and the acquisition receipt are separate pinned recordings. The panel was captured at sourceee6469c; the acquisition at4621b361e5af….

Composition / real dependency releases

Retained experts, then a real composite.

Two separate current runs show the pieces. A multi-turn session retains glint and spark. A dependency run builds composite from increment and square. Both restore in a fresh process.

2retained expert capabilities
1composite with real dependency calls
33multi-turn checks passed
76.6 sdependency run wall time
CapabilityBackendNative regionsRelease
compositenative_regions1ea1dad146b1e…
incrementnative_regions114d3ff14da86…
squarenative_regions153ff9856b761…

Executed graph

  • →
    increment

    1 argument · returns Q · identity d6518dbf0fd0…

  • →
    square

    1 argument · returns Q · identity 1ad0641d391c…

Composite restoredexact
Dependency releases boundyes
Glint coldexact
Spark coldexact

Program conversion / supplied source

Code in. Classified execution out.

A separate mode converts conventional C into a typed native circuit. This is source conversion, not autonomous discovery of that source.

74curated conversion cases
72strictly native
2explicitly mixed
73with an independent reference
CaseStatusBackendProbesHost compute
integer.add
add
nativenative_c60
float.sin_mixed
dsin
mixedmixed donor/host lane——
memory.structural_store
set_g
mixedc_mixed60

The two mixed cases are labelled mixed. They are not counted as strict native execution. The 724-gate integer.add case has zero host compute and an independent reference.

Fresh Startmate native run

CaseStatusBackendArtifact
integer.add
add
nativenative_c586a64325cd8…
float.add
fadd
nativenative_cf3e031c6e0c3…
float.sqrt
dsqrt
nativenative_ce91387ffac52…

Evaluation / development versus final

What the wider campaigns actually show.

The learner has a strong development panel and a useful 100-task diagnostic. Neither is presented as a final independent benchmark.

Development onlyC1

20 tasks, seven families

Tasks fully correct20 / 20
Scored rows60 / 60
Candidate evaluations123,247
Mean task time19.3 s
Sourcecd812c42a88c…

One development run across seven families. It is not an independent final-evaluation or cumulative-learning result.

Diagnostic history100 tasks

The rejected 100-task run is still informative.

Answered73
Abstained20
Partial6
Wrong1
Final reportrejected: source moved

Every task result is retained. No validated final report was written because HEAD moved while the campaign was running; the frozen campaign must be rerun at the registered revision.

Rerun pending10-task paired panel

Cumulative bank: current development blocker.

ConditionRowsTasksCandidate evaluationsWall time
C1 fresh36 / 3610 / 1028,350386.6 s
C2 cumulative24 / 366 / 1016,0301440.4 s

Claims and limitations

What this establishes.

  • verified

    ERAIS learned f from four observations and answered f(8)=19.

    EL-LEARN
  • verified

    The learned capability answered f(9)=21 without rebuilding the engine.

    EL-REUSE
  • verified

    A fresh process restored the published release and answered f(10)=23.

    EL-COLD
  • verified

    Six recorded tasks across arithmetic, conditional, structured, sequence and stateful families executed natively and cold-restored.

    EL-FAMILIES
  • limitation

    This is a bounded example-defined integer acquisition, not unrestricted programming or general intelligence.

    EL-SCOPE

Known boundaries

  • The demonstration covers a bounded integer function and five recorded program families.
  • Engine qualification dominates the acquisition phase; the warm answer is much faster than the cold setup.
  • The synthesis-family panel is a separate pinned recording at source ee6469c, not a rerun of the current learning phase.
  • The page must not present this as unrestricted programming or general intelligence.