Launch dApp
Marked independently, agreed once

One ContractOne Agreed Number

Point at a contract, read the streak. Validators mark it against a published rubric and the report only stands where they agree.

Launch the dApp
1
Report issued
10
Published criteria
0
Cost of a refusal, in inferences
20
Validators in the pool
Models this pool can draw on

claude-sonnet-4.6, deepseek-v3.2, gemini-3-flash-preview, gemma-4-26b-a4b-it, gemma-4-31b-it, glm-5.1, gpt-5.4, gpt-oss-120b, grok-4.3, kimi-k2.7-code, minimax-m2.7, minimax-m3, mistral-large, qwen3-coder, qwen3.6-27b. 4 nodes name the model they run, and the other 16 route across these per call. Every one of them reads the same bytes and marks independently, and the report stands only where they agree.

Story

A rubric first, then a number

Four commitments this contract makes before a single line is read

01
The standard is readable

A score against a rubric written after the fact is worth nothing, so ours is published before anyone was scored, with an anchor on every point

02
One model is only one opinion

Every validator reads the same raw file and marks it on its own, and the mark only stands where they agree under a published rule

03
Totals are arithmetic, not judgment

Criteria are marked 0, 1 or 2 and the total is summed in the contract, with the band derived by a pure function

04
A split is our problem, not yours

When validators disagree no report is issued and the splitting criterion is named, which tells us the anchor is written badly

Consensus

Several readings, drawn from a pool of 20

Validators read the same raw file, mark it against the same anchors, and the report only stands where they agree under the rule below

a jury is drawn from the network for every assay
The agreement rule, as published
  • Two markers may differ by one point, on one criterion only, and the report still stands
  • The band both markers land in must be the same
  • Wording is never compared, because two careful readers never phrase a reason alike
  • 8 criteria are counted in deterministic code and 2 are put to the jury

Read straight from the contract, which fixed this rule in the transaction that deployed it. What the chain records is how many validators agreed, which is the number that decides whether a report exists at all.

Four parts of the machinery

Runs before any fee
The gate

Presence checks only - passing them proves almost nothing, since anyone can type the words into a comment, but failing a required one proves a great deal and costs nothing to find out

declares a py-genlayer dependency headerREQ
declares a class the network can loadREQ
reaches outside the deterministic world at allREQ
declares how validators are meant to agreeREQ
raises at least one error a human could read
keeps its state in a persistent collection
The result

Two numbers, never averaged

A careful contract behind a site that calls a transaction done the moment it is sent is a different problem from a weak contract behind an honest site

The streak on the stone is the same number drawn to length, read against reference marks at 4, 7 and 9

contractstrong7/10
report 8801 - rubric v3 - gate 6 of 6Open it
The record

One permalink, permanent

Worth handing to somebody else - the source, the digest and the rubric version are recorded beside the marks

What the number is

A sum of five marks against anchors published before anything was scored, each one derived from the executable structure of the source or judged by validators who read it independently, so the number says where this file sits against a fixed standard rather than against whatever else was reviewed that week.

report8801, 16 sep 2026
sourceraw.githubusercontent.com/.../quorum.py
digestfc3d698986ff...aba1
rubricv3 at 0x4aEA...99
networkstudio

Find Out What The Network Makes Of Your Contract

Free, in the browser, and the gate runs before a validator spends a single inference

Launch the dApp