Aletheia

Philosophy

Separate the value of feedback from any added benefit of the current single-step control fields, letting strong controls shape the next design.

Architecture & control flow

1. 01

   Source layer: Build a source store from an operator-supplied local manifest. Body, abstract and supplementary text retain distinct roles, page/section locators, versions, hashes, availability and query windows.

2. 02

   Proposal layer: The model reads a bounded evidence packet and returns a question, rivals, an idea and candidate actions. A strict structure contract bounds fields and size; predicted outcomes cannot become observed results.

3. 03

   Controller layer: Micro policy ranks declared response separation and action cost. Macro policy retains branches and pending actions, selecting affordable dependency-ready obligations and rotating stale untested branches.

4. 04

   Host execution layer: Selected actions pass identity, source, semantics and cost gates. Literature actions execute locally; experimental probes observe only after host domain-adapter attestation. Without an adapter, experiments remain proposals or human checkpoints.

5. 05

   Feedback layer: Observed responses conditionally update rivals; anomalies, noise and uncertified mappings remain unresolved. Revisions explain introduced, revived and removed rivals. Review separates discriminating question observations from independently validated idea mechanisms.

6. 06

   Persistent record layer: Proposals, selections, rejections, budgets and outcomes enter content-addressed objects and a host HMAC chain. Complete rounds save state checkpoints, and reports provide readable projections. Source and runtime identities stay locked across resume.

Architecture outline derived from this version’s control flow.

Implementation & evidence scope

Current evidence covers engineering contracts, literature development and bounded computational diagnostics. Open-domain new actions, full long-horizon graph gains, cross-task transfer and RSI remain research goals.

Code & bundled material

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

Research-record date · 2026-10-01