> ## Documentation Index
> Fetch the complete documentation index at: https://rapidreview.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Projects, claims, and the graph

> The durable research record: what a project holds, how claims carry status and confidence, what the logic graphs are for, and how a champion is tracked.

A **project** is the unit of membership and of research state. Everything an agent does is scoped to one — it passes `project_id` on every call. `project(action="overview")` returns the whole picture: claims, experiments (including terminal ones you shouldn't recreate), the latest published reflection, the literature summary; `project(action="create")` makes one (not available to external keys).

## Claims

A claim is a statement the project is trying to establish, refute, or refine. Each carries a `scope`, a `confidence` (`low` · `medium` · `high`), and a status:

| Status         | Meaning                                                                 |
| -------------- | ----------------------------------------------------------------------- |
| `draft`        | Written down, not yet part of the working set                           |
| `active`       | Being tested                                                            |
| `supported`    | Evidence on record supports it                                          |
| `weakened`     | Evidence cuts against it, not decisively                                |
| `contradicted` | Evidence contradicts it — this flips project guidance toward reflection |
| `abandoned`    | Dropped                                                                 |

Agents create claims with `claim.create` and move them with `claim.update`; reflection waves apply approved claim changes atomically at publish.

## Two graphs

**Experiment logic graph** (`graph.json`, submitted with role `graph`): the reasoning path of one experiment — questions, decisions, pivots, consequences, lessons — as a DAG of at most 16 nodes. Agent-authored, not generated: choosing what mattered *is* the authorship. Not a pipeline diagram, not an event log.

**Project graph**: produced by a reflection wave's synthesis, reviewed, and pinned at publish. It's the project-level logic — how claims and experiments relate and where the next phase goes. The UI renders both.

## Champion and candidates

Projects with an objective track a **champion**. The manager agent nominates promising output with `candidate.submit` (an immutable artifact or storage object, or an `experiment_workspace` for the evaluator to stage); `candidate.list` shows candidates, the append-only promotion history, and the champion; `candidate.promote` is a compare-and-swap with a required reason.

## Literature

The project keeps a living literature review (`litreview.view` / `litreview.edit`, one targeted change per call) and a papers ledger (`litreview.cite`, deduplicated across arXiv/DOI/URL forms and linked to sections, experiments, or claims). Plans cite papers in portable form — `arXiv:2401.12345`, a DOI, or a URL. See [Using Nisa with Merv](/docs/nisa/guides/with-merv).

## Where the record lives

Records, gates, and reviews in the brain's database; evidence in [artifacts and object storage](/docs/merv/concepts/artifacts-and-storage). The checkout is working material — nothing counts until it's submitted.