Paper summary

step · paper open

Declaration faefc339462c has not been accepted by anyone. · no paper read under it

What does this paper argue, in three paragraphs?

Mechanical: re-runnable from its declared inputs.

Part of Measures — What can be measured over the tree - its coverage, its wording, whether its code re-runs?

How it works

Given the tree's claims — slug, role, panel, sentence and edges — and nothing from the paper, it returns the three paragraphs the page opens with: hypotheses (the bets the work makes good on), claims (what it establishes empirically) and inferences (what it concludes). An atlas or descriptive paper returns subject in place of hypotheses. It writes the paper's entry into the one shared paper-summaries.json, so editing any paper's summary restates the artifact every paper's cell reads.

--dump-prompt writes the exact request and exits, and --answer feeds a reply back through the same validation — one of hypotheses/subject and both other paragraphs, or nothing is written — so a model with no backend here can still answer it. The prompt reasons about the claims by role, so it reads the contract's vocabulary too. The model is recorded inside the paper's entry, since the shared file has no top-level place for it, and pipeline.py's by_from reader falls back to that per-paper entry.

Rests on

Feeds

Nothing — this is a leaf.

How it is defined

A model answers this layer, so the prompt is the layer. It is reproduced below from the committed file, and it is a declared input — editing it makes every run that used it stale.

extract/prompts/summaries.mdthe prompt it runs undernot in the repository

The declaration names this path and the repository does not have it. An input that does not exist hashes to nothing, so it cannot make a run stale — the layer is declared to depend on something it is not in fact tracking.

extract/prompts/contract/vocabulary.mdthe prompt it runs undernot in the repository

The declaration names this path and the repository does not have it. An input that does not exist hashes to nothing, so it cannot make a run stale — the layer is declared to depend on something it is not in fact tracking.

What it produces0

One paper, as the worked example — Artiushin, v1. Read from site/src/data/paper-summaries.json · 19 KB. gadeke-2026-guilt-insula.model supplied:runs/gadeke-2026-guilt-insula/summaries.answer.v4.json

0

Nothing on this page renders document for this file yet — the link above is the artifact itself.

Across the corpus

9 run not observed · 1 stale·a paper links to its own cell, where this layer's output for it is rendered

Inputs and outputs

Reads, besides its dependencies
Produces
  • site/src/data/paper-summaries.json
Views
  • document — declared, and this artifact is not the shape this view needs

Running it

The command comes from the declaration, so this text and what actually runs cannot diverge. pipeline.py run also runs the unmet dependencies first.

python3 scripts/pipeline.py run <paper> summaries

Underneath, that runs cd extract && python3 -m claim_graphs.cli summaries --paper {paper}.