Skip to content

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

docs: record first result from recovered full cohort

David Zhange4fa1aa6bd61
diff --git a/specs/jevgrep/README.md b/specs/jevgrep/README.md
index dfe7582..1fc528b 100644
--- a/specs/jevgrep/README.md
+++ b/specs/jevgrep/README.md
@@ -11,8 +11,9 @@ The work-clock v1 confirmation stopped after Docker's disk-space failure during
Astropy. That attempt is failed and recovered separately; two completed wins and
seven unstarted cells remain retained. Do not resume or replace its failed cell.
Docker is recovered and disposable build cache was cleared. The new full `installed-jg-cpython-work-clock-v2` study is prepared and all ten
-no-call validations pass with identical package and protocol. Execute each cell
-once and grade/account all outcomes.
+no-call validations pass with identical package and protocol. Scikit-learn has
+one official cost win; Django is running. Continue the same sequential runner,
+execute each cell once and grade/account all outcomes.
Never pool studies or rerun a baseline. [Timing protocol and evidence](assets/timing-protocol.md)
own the outage, recovered bills and prospective replacement rationale.
diff --git a/specs/jevgrep/assets/timing-protocol.md b/specs/jevgrep/assets/timing-protocol.md
index 946c0ed..0935a47 100644
--- a/specs/jevgrep/assets/timing-protocol.md
+++ b/specs/jevgrep/assets/timing-protocol.md
@@ -172,3 +172,10 @@ package, canonical skill, archived runner/broker/registry, task inputs, dataset
and timing policy match v1 byte-for-byte where applicable. Proof:
`/tmp/jg-work-clock-v2-freeze-proof.json`. Independent recovery review verified
all 1,198 manifest hashes and the unchanged failed receipt before paid continuation.
+
+
+V2's first cell, scikit-learn, officially resolved with zero infrastructure/errors.
+Its complete 10-generation Sol cost is **$0.2414888** versus **$0.2944360**
+baseline. Jev observed cost is complete at **$0.070983906** (277 client calls),
+separately excluded from scoring. The same unconditional random-state validation
+caveat applies to its patch. Django is running next; full acceptance remains open.