Skip to content

Releases: jang1563/verify-or-trust

Verify-or-Trust v0.1.4

17 Jun 04:15

Choose a tag to compare

Verify-or-Trust v0.1.4

Collaboration workflow release.

  • Adds SUPPORT.md and CODE_OF_CONDUCT.md.
  • Adds .github/PULL_REQUEST_TEMPLATE.md.
  • Links support, conduct, and PR-template files from the README and artifact manifest.
  • Updates package, citation, archival, and manifest metadata to 0.1.4.

No benchmark result values, substrate rows, or grading semantics changed in this release.

Verify-or-Trust v0.1.3

17 Jun 03:35

Choose a tag to compare

Verify-or-Trust v0.1.3

Public governance release.

  • Adds SECURITY.md.
  • Adds GitHub issue templates for reproducibility bugs and documentation/schema corrections.
  • Links governance files from the README and machine-readable artifact manifest.
  • Updates package, citation, archival, and manifest metadata to 0.1.3.

No benchmark result values, substrate rows, or grading semantics changed in this release.

Verify-or-Trust v0.1.2

16 Jun 13:14

Choose a tag to compare

Verify-or-Trust v0.1.2

DOI-ready archival metadata release.

  • Adds docs/ARCHIVAL_RELEASE.md with release invariants and the DOI update checklist.
  • Updates CITATION.cff, .zenodo.json, pyproject.toml, and artifact_manifest.json to 0.1.2.
  • Replaces brittle pinned dataset-commit metadata with the stable Hugging Face dataset home.
  • Keeps public CI green across Python 3.10 and 3.12.

No benchmark result values, substrate rows, or grading semantics changed in this release.

Verify-or-Trust v0.1.1

16 Jun 02:24

Choose a tag to compare

Verify-or-Trust v0.1.1

Patch release for the current public archive surface.

  • Adds DOI-ready archival metadata via .zenodo.json.
  • Updates CITATION.cff, pyproject.toml, and artifact_manifest.json to 0.1.1.
  • Keeps the public validator green across Python 3.10 and 3.12: strict JSON, manifest paths, substrate schema checks, generated-panel JSONL checks, and public text guards.

No benchmark result values, substrate rows, or grading semantics changed in this patch release.

Verify-or-Trust v0.1.0

15 Jun 21:03

Choose a tag to compare

Verify-or-Trust v0.1.0

First public release of Verify-or-Trust, a verifiable-reward benchmark for calibrated verification in LLM-orchestrated biology foundation-model pipelines.

Included

  • Installable Python package and vot CLI.
  • GEARS/Norman shipped substrate for out-of-the-box LLM-free reproduction.
  • Panel builder, baseline value proof, grading, and mocked environment tests.
  • Benchmark card, schema documentation, release process, and results tables.
  • Machine-readable artifact_manifest.json and JSON schemas.
  • Strict generated JSONL handling: missing fm_log2FC values are emitted as JSON null, not non-standard NaN.
  • CI matrix on Python 3.10 and 3.12 with lint, tests, K1 reproduction, and public-release validation.

Linked Dataset

The Hugging Face dataset hosts the released substrate table and Norman cell subset for live run_de reproduction:

https://huggingface.co/datasets/jang1563/verify-or-trust

Latest dataset card snapshot observed during release prep:

  • HF commit: 32c547f422b4a4963a9c39c3b82f40b4a20043a6

Snapshot

  • Git commit: 718962d12959129593e3190ccf27eab372796435
  • GitHub Actions CI: passing on main