mrkeyoor.comAsk

Heman10x-NGU/openJev-verdict-2.0tested 07 Oct 2026commit bff2856

openJev-verdict-2.0 review

openJev-verdict-2.0 is worth inspecting for typed-decision research, but our dated sandbox run does not justify treating it as a ready application dependency.

  • Install 82 s
  • Build 5 s
30/33passed, run exited non-zero
  • 98 packages
AI Toolsevaluationupdated 31 Oct 2026
-1stars / 7d

Use openJev-verdict-2.0 as a research reference if you can verify the model artifacts and investigate failing checks before integrating it. Our October 7, 2026 sandbox run at commit bff2856 recorded a failing pytest command. It did not validate Verdict 2.0 deployment, browser inference, training, or published performance claims. The repository distinguishes the GLiClass-based Verdict checkpoint from the separate Verdict 2.0 architecture for typed software workflows.

Verdict

openJev-verdict-2.0 is worth inspecting for typed-decision research, but our dated sandbox run does not justify treating it as a ready application dependency. Installation and build succeeded; pytest failed, and supplied issue reports raise separate artifact and licensing questions. Verify the intended checkpoint and reproduce your decision workload before integrating it.

We ran it

Lab card: what happened when we ran openJev-verdict-2.0
Lab card from our sandbox run
Screenshot of openJev-verdict-2.0 (heman10x-ngu.github.io/openJev-verdict-2.0)
heman10x-ngu.github.io/openJev-verdict-2.0
Install✓ · 82s98 packages · 5719 MB
Build✓ · 5s
Tests✗ · 75s30 passed · 3 failed · 9 skipped of 33 (pytest)
Known vulns0(pip-audit)
Repo189 files~14,813 lines of source · 50.8 MB · 0 CI workflows · tests dir

Answers from our run

Does openJev-verdict-2.0 build from source?

Dependencies installed in 82 seconds (98 packages), and the build succeeded in 5 seconds. We cloned commit bff2856 into a clean Debian container with 3 CPUs and no project-specific setup.

Do openJev-verdict-2.0's tests pass?

No. The project's own test command finished in 75 seconds and reported 30 passed, 3 failed, 9 skipped (pytest).

Does openJev-verdict-2.0 have known vulnerabilities in its dependencies?

pip-audit found none in the dependency tree at the time of our run.

Who should not use openJev-verdict-2.0?

Teams that require a passing repository test command before adopting a dependency.

What are the alternatives to openJev-verdict-2.0?

Laya, jevos. openJev-verdict-2.

Setup2/5Installation and build exited 0, but the recorded 5,719 MB footprint and failing pytest command leave substantial setup and repair work.
Docs3/5The README explains the two models and inference changes, but the retained freshness check reports missing receipt markers and WALKTHROUGH.md.
Community2/5Last push on 2026-09-20 and 306 stars.Editor’s note: The supplied issues show participation but do not establish adoption, response quality, or support reliability. They cannot support a numerical community rating.
Maturity1/5The failed test command, reported missing checkpoint, license conflict, and recorded absence of CI workflows leave substantial unresolved barriers.

How we score

Who it’s for

ML engineers examining typed decisions and the boundary between model probabilities and application rules.
Researchers inspecting evaluation receipts, calibration methods, and reproducibility problems.
Developers prepared to verify which checkpoint an example loads and reconcile the failing checks before integration.

Who it’s NOT for

Teams that require a passing repository test command before adopting a dependency.
Developers expecting the documented Verdict 2.0 artifact path to work without investigation: supplied issue reports describe a missing Git LFS object.
Teams needing settled licensing terms before redistribution: the README's Apache 2.0 statement conflicts with the recorded NOASSERTION identification and an issue disputing the license text.
Buyers seeking independently verified accuracy, latency, WebGPU behavior, or production readiness. Our run established none of those.

Setup reality

Our run took place on October 7, 2026, at commit bff2856 in a Debian Bookworm Python 3.12 sandbox with 3 CPUs and 8 GB RAM. The harness recorded installation exiting 0 after 82 seconds, build exiting 0 after 5 seconds, and pytest exiting 1 after 75 seconds. It recorded 98 dependency packages and a 5,719 MB installation footprint.

The stored parser summary records 30 passed, 3 failed, and 9 skipped, with total recorded as 33. These fields do not establish exhaustive counts of unique tests. No new execution or complete-log reconciliation was performed. Skipped tests were not failures.

Pip-audit recorded 0 advisories, but scan coverage is unknown. The supplied record does not establish scannedPackages, and its packages value of 0 does not prove that installed dependencies were covered. This was not a security review.

A successful build command does not establish a working Verdict 2.0 inference path. Before integrating it, confirm that the intended checkpoint is downloadable, identify the model loaded by the example, and reproduce an inference result on your own inputs.

Should you use it?

Start with the repository if your aim is to study typed decision models and their evaluation machinery. Before adopting it as an application dependency, resolve the failing checks, verify the intended weights, and clarify the license. Installation and build commands succeeded in our sandbox, but pytest exited 1.

Our run on October 7, 2026, at commit bff2856 recorded 3 failed tests in its stored parser summary. That observation applies to the checked-out commit and sandbox; it does not establish how every installation behaves.

Identify the model before following the quickstart

The repository distinguishes the GLiClass-based Verdict checkpoint from the separate Verdict 2.0 architecture for typed software workflows. Its README identifies Verdict as the 151M model hosted at heman10x/rlcd-modernbert-151m and describes its v1.4 changes as inference fixes rather than retraining. Verdict 2.0 uses a separate architecture and a Git LFS weight path at artifacts/verdict2-base/model.pt.

The project describes three typed questions: Choice selects an option, Score assigns an ordered level, and Noul handles a yes/no-style question. The model supplies bounded decisions and probabilities while application code retains control of thresholds and business rules. The README's accuracy, calibration, and latency figures are project-reported results; our sandbox did not reproduce them.

Issue 2 reports that the Verdict 2.0 checkpoint is a Git LFS pointer whose object is missing from the server. Opened on September 20, 2026, issue 2 also reports that the artifact downloader retrieves the earlier GLiClass system and that an example can proceed with an unfine-tuned base model when the expected files are absent. Issue 4, opened on September 21, 2026, separately reports the Git LFS download failure. These are issue authors' observations, not download failures reproduced by our sandbox or proof of current availability.

Licensing also needs clarification. The README says Apache 2.0, the stored sandbox record identifies the license as NOASSERTION, and issue 2 disputes whether the shortened license text preserves the standard terms. Resolve that conflict before redistribution.

What our sandbox established

Installation exited 0 after 82 seconds, and build exited 0 after 5 seconds. Pytest exited 1 after 75 seconds. The harness recorded 98 dependency packages and a 5,719 MB installation footprint. The empty build log tail supplies no evidence that a CLI, service, or deployment workload completed.

The stored parser summary contains 30 passed, 3 failed, and 9 skipped, with total stored as 33. Those fields are not a verified exhaustive inventory of unique tests. The retained pytest footer separately reports 3 failed, 30 passed, and 9 skipped in 59.59 seconds. The harness records 75 seconds for the test step; the footer records pytest's own duration. Neither value replaces the other. No new execution or complete-log reconciliation was performed for this correction.

Our run did not reproduce the benchmark, train either model, validate browser inference, or test a production deployment. The installation footprint measures what landed on disk, not inference memory or throughput. Pip-audit recorded 0 advisories, but its recorded packages value of 0 leaves scan coverage unknown. That result is not a security clearance.

The sandbox scan recorded no CI workflow files and no Dockerfile. Those observations describe the checkout, not every automation or deployment arrangement its maintainers might use.

What the retained failures mean

The documentation check reported missing generated receipt markers in README.md and a missing WALKTHROUGH.md. This establishes a failed documentation freshness check. It does not by itself prove that every published benchmark figure is wrong.

The real GLiClass inference check expected a selected probability above 0.7 and received 0.47440735212575424. The retained result identifies knowledgator/gliclass-modern-base-v2.0, so this failure should not be presented as a Verdict 2.0 benchmark result.

The formatting check expected bare candidate labels and received labels prefixed with "It is". The README describes that framing as an inference change. The evidence establishes a mismatch between implementation and test expectation; it does not settle which should change.

Choose an alternative by integration needs

Laya documents a Python package, optional HTTP serving, and a TypeScript inference path. Evaluate Laya when those documented integration paths fit your application. Its documentation does not establish that it will be more accurate on your inputs, and we did not test it in this run.

jevos documents a CPU-only binary server that needs no Python at runtime. Evaluate jevos when that packaging suits your deployment. Its README limits the unchanged Jev SDK compatibility statement to yes/no questions and marks score support as early, so verify the question types you need.

These alternatives do not repair openJev-verdict-2.0's weights or tests. Neither replaces the repository as a source for studying its particular architecture and receipts.

How to read the scores

The assessed dimensions use this editorial scale: 1 means substantial unresolved barriers, 2 means usable with substantial setup or repair work, 3 means useful evidence with material gaps, 4 means strong evidence with limited gaps, and 5 means comprehensive evidence with no material gaps found in the assessed scope. These are editorial judgments, not benchmarks or security ratings.

Setup ease is 2: installation and build succeeded, but the recorded footprint and failing checks leave substantial setup and repair work. Documentation is 3: the README distinguishes the models and explains inference changes, while the freshness check fails. Maturity is 1: the failed test command, reported artifact problems, license conflict, and recorded absence of CI workflows leave substantial unresolved barriers.

Community is unassessed. The supplied issues show participation, but they do not establish adoption, response quality, or support reliability. There is insufficient evidence for a numerical community rating.

Before adoption, verify the intended weights, inspect the loaded model identity, reconcile the named failures, and resolve the license text. Then evaluate decisions and confidence thresholds on examples from your own application.

Alternatives

ProjectWhat it isPick it when
Laya gh↗A typed-decision project documenting Python packaging, optional HTTP serving, and TypeScript inference.Evaluate it when those integration paths match your application; verify checkpoint behavior and accuracy on your own inputs.
jevosA local decision server distributed as a CPU-only binary, with no Python required at runtime.Evaluate it when binary deployment fits your environment; check the required question types because its README marks score support as early.

What people are saying

  1. [velocity-scout] Heman10x-NGU/openJev-verdict-2.0

Sources

  1. openJev-verdict-2.0 repository and README
  2. Verdict 2.0 checkpoint and license report
  3. Git LFS checkpoint download report
  4. JevBench v1.4 results issue
  5. Commit bff2856

More ai tools reviews