Skip to main content

arc-court

The Adversarial Research Court — tiered, cited claim verification.

arc-court (imported as arc) verifies claims and emits a report with per-claim adversarial-survival scores. It is built entirely on recurve's recursive planning primitives.

Tiered by design — because the research is clear that naive multi-agent debate frequently fails to beat single-agent baselines at equal compute:

  • Tier 0 — claim graph: extract only verifiable claims, decompose + decontextualize into atomic units.
  • Tier 1 — Falsification Gate (default): retrieve evidence (Tavily / domain sources), a single Prosecutor proposes cited falsifiers, a cheap NLI judge scores entailment, numeric/temporal claims escalate to a stronger judge. NOT_ENOUGH_INFO is a first-class verdict.
  • Tier 2 — Court (opt-in): the full Prosecutor / Defender / Jury trial, reserved for high-stakes, mid-confidence claims — and gated by an anti-theater eval that it must beat single-agent CoT + self-consistency at equal compute, or it stays disabled.

Part of the AETHEL project. MIT licensed. Status: alpha.

Metadata

Release files for arc-court 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for arc-court 0.1.0
File Size Uploaded Provenance Actions
arc_court-0.1.0.tar.gz 45.7 kB Without provenance Details for arc_court-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for arc-court 0.1.0
File Interpreter ABI Platform Actions
arc_court-0.1.0-py3-none-any.whl Python 3 none any Details for arc_court-0.1.0-py3-none-any.whl

Total release size: 101.7 kB

Release files / arc_court-0.1.0.tar.gz

Download URL arc_court-0.1.0.tar.gz
Size 45.7 kB
Tags Source
SHA-256 checksum
How to use checksums
d20b4c1f43dc463c026280c34d98616df488a2088e60b0deb8cc71064b6a78eb
BLAKE2b-256 checksum
How to use checksums
926fea6ad95c9a5e617ef6e776f569796d851f19984abbde7abd3cab74246c96
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.24 {"installer":{"name":"uv","version":"0.11.24","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / arc_court-0.1.0-py3-none-any.whl

Download URL arc_court-0.1.0-py3-none-any.whl
Size 56.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b692399a645eee08f951ed3bc3dc8f94cd85c86cc9f056e46d8c68c633f6d2eb
BLAKE2b-256 checksum
How to use checksums
9c59f6b658c5264be6a001d4790f9b74156be1ed755771f4886d6387f3f7fc0f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.24 {"installer":{"name":"uv","version":"0.11.24","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for arc-court 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page