## Phase 3 — Verify contested claims by running code Settle with executed code, not judgment, whenever sources disagree, a behavior is undocumented, a claim is performance- or compatibility-shaped, or the honest answer is "it should work". Spawn one verification worker per claim: ``` task(category="deep-low", run_in_background=true, prompt="TASK: verify by execution: . SOURCE: ; CONTRADICTION: . Write a minimal self-contained script that tests the claim; run it (uv run --with python / bun / direct compile); capture full stdout+stderr; pin versions. Reply with: the exact code, the full output, environment (OS, runtime, dependency versions), and a verdict — CONFIRMED / REFUTED / PARTIAL — grounded in the output.") ``` Journal each verdict to `verify-.md`. ## Phase 3b — Lock non-code claims through the claim graph Code settles code-shaped claims (Phase 3). Numeric, market-share, legal, dated, causal, and financial claims cannot be run — so they pass through a data-flow-lock instead (the verification idea adapted from fivetaku/insane-research): the synthesis may assert a high-risk non-code claim **only** if it cleared this gate, and the gate's output is the sole allowlist the synthesis draws from. Skip the gate and there is nothing to synthesize — the lock is self-enforcing. The claim graph is orchestrator-owned. Workers only return verified-claim markers, observation candidates, and claim candidates as message text, the same channel as EXPAND markers — never a file (except a mass-research dag node's handoff file). As leads resolve, you record one node per asserted claim in `claim-graph.md` and compute its status; workers report claim candidates in their replies, and you decide. The graph is the single claim store: final synthesis may not draw from free-form claims that skipped it. A high-risk claim clears the gate to `verified-claims` only when all hold: - **>= 2 independent source domains** corroborate it (two pages on the same domain count once). - **>= 2 independent observation groups** converge on it, unless the graph records why a primary-only source is the correct single-source exception. - **One counter-search** actively looked for a refutation and did not find a stronger one. - **A primary source** (the standard, filing, dataset, or first-party doc) backs it, not only secondary commentary. - **Temporal evidence is explicit**: each supporting observation records `observed_at` and either `valid_at` or `claim_valid_at`, so branch-only, historical, release, and current-runtime claims cannot be conflated. Anything that fails goes to an `Unresolved` (insufficient evidence) or `Refuted` (counter-search won) annex — abstention is a correct outcome, not a gap to paper over. Record each gate outcome on the claim node itself — risk tier, independent source domains, counter-search result, primary source backing, and status — and mirror the cleared nodes into the `verified-claims` digest section at the top of `claim-graph.md`. Worker reply marker (message text, same channel as EXPAND): ``` ## CLAIMS - CLAIM: — RISK: high|normal — SOURCES: — COUNTER: — PRIMARY: ``` **The claim table is machine-read.** Keep the nodes of `claim-graph.md` in one Markdown table whose header names `claim_id | statement | risk tier | status` (plus `fact_ids`, the ledger rows the node rests on, and any other node fields as further columns), one row per node: ids `C`, risk `high` or `normal`, status `supported`, `partial`, `refuted`, or `unresolved`. List the nodes that clear the Phase 3b gate under a `## verified-claims` heading as `- C: `. `node "$SKILL_DIR/scripts/report-tools.mjs" claims index "$SESSION_DIR/claim-graph.md" --out "$SESSION_DIR/claims.json"` indexes it, and the fidelity gate reads `claims.json` to check every `data-claim` binding in the report. ## Phase 4 — Synthesize After convergence and all verifications, re-read the whole journal, start from `intent-diff.md`, `claim-graph.md`, and `observation-manifest.md`, then write `SYNTHESIS.md`: ``` # ULW-Research Synthesis: Workers: · Waves: · Excursions: · Sources: ( domains) · Verifications: · Elapsed: min ## Executive summary — 2-3 paragraphs answering the core question ## Findings by theme — per theme: consensus, evidence links, key quote (<20 words, attributed), verified yes/no ## Codebase findings — absolute paths with line references ## Sources (ranked) — URL, what it contains, reliability, access date ## Verified claims — code: claim | verdict | verify-.md · non-code: only rows cleared into verified-claims ## Epistemic instrumentation — intent-vs-reality diff closure, claim graph coverage, observation manifest coverage, independent-observation convergence, verification economics summary, cause-disappearance records ## Contradictions — source A vs source B, resolution with evidence ## Gaps — what saturation could not answer · unresolved/refuted claim-graph nodes ## Expansion trace — per wave: workers → markers; convergence reason ``` `SYNTHESIS.md` is the citation source of truth for final materials: every claim carries inline `[Source N]` citations, and every high-risk non-code claim you assert must be a verified-claims row from Phase 3b. Assert nothing the gate left in the unresolved/refuted annex. **Write numbers and quotes by reference.** `SYNTHESIS.md` and every report source carry placeholders, never typed values: `{{F12:span_len}}` renders the row's value and unit, `{{F12:span_len:value}}` or `:unit` one part, `:q` the value with its source qualifier (up to, at least, about); `{{Q7:completion}}` renders the whole quotation, `{{Q7:completion:lead=8}}` its first words, `{{Q7:completion:from="no earlier":to="2027"}}` one span of it. A derived number is computed by the script, never by hand: `fact derive --op sum|diff|growth|ratio|share|convert|expr ...` checks the operands' units, periods, and populations, refuses an incompatible operation, and prints the new row id the placeholder uses. A value nobody measured is registered with `fact add --assumed --unit --rationale --label