Aurora

Philosophy

Propose first, verify explicitly. Reviewer agreement cannot override tool failure; software evidence gates make status auditable rather than establish scientific truth.

Architecture & control flow

1. 01

   Retains V4-Nova’s seven-phase persisted search and appends an Aurora verification phase.

2. 02

   AuroraInput gathers the contract, idea, priors, models, equation, theorem, counterexample search, reviewer records, claim registry and replay lock.

3. 03

   Gate 0–12 checks run according to supplied claim types; optional payloads control which validators execute.

4. 04

   The terminal aggregator records accepted, promising, refuted, honest-failure or refused status alongside gate and warning logs.

Architecture outline derived from this version’s control flow.

Inputs & outputs

Inputs

Research direction, mode and search budget; candidates and supporting artifacts from a resumable workspace.

Outputs

A v5_verification report block plus gate_results.jsonl, high_warn_register.jsonl and final_terminal_gate.json.

Implemented components

• Python gate orchestration and terminal classification; structural dimension/limit/conservation checks, circularity detection, failure records and claim linkage.

Implementation & evidence scope

The default backend is a stub; the contemporary Claude Code backend is hook-only and requires external subagent orchestration. Validators inspect supplied evidence and fields; they do not imply external domain validation, machine-checked proof or an exhaustive prior-art search. Documented software-test outcomes are not scientific novelty or discovery-success results.

Code & bundled material

The introduction draws on bundled notes, changelogs and central code. Software tests, synthetic diagnostics and scientific effectiveness use different evidence standards.