Skip to main content

Adversarial Research Court — tiered, cited claim verification built on recurve.

Project description

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.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

arc_court-0.1.0.tar.gz (45.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

arc_court-0.1.0-py3-none-any.whl (56.0 kB view details)

Uploaded Python 3

File details

Details for the file arc_court-0.1.0.tar.gz.

File metadata

  • Download URL: arc_court-0.1.0.tar.gz
  • Upload date:
  • Size: 45.7 kB
  • Tags: Source
  • Uploaded using 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}

File hashes

Hashes for arc_court-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d20b4c1f43dc463c026280c34d98616df488a2088e60b0deb8cc71064b6a78eb
MD5 a6a7c34ff8341c0defa9c57ae8f06b47
BLAKE2b-256 926fea6ad95c9a5e617ef6e776f569796d851f19984abbde7abd3cab74246c96

See more details on using hashes here.

File details

Details for the file arc_court-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: arc_court-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 56.0 kB
  • Tags: Python 3
  • Uploaded using 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}

File hashes

Hashes for arc_court-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b692399a645eee08f951ed3bc3dc8f94cd85c86cc9f056e46d8c68c633f6d2eb
MD5 5123dcb5e449fe734b10d8a46c53123f
BLAKE2b-256 9c59f6b658c5264be6a001d4790f9b74156be1ed755771f4886d6387f3f7fc0f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page