/research-synthesis
/research-synthesis — Reconciles the collected sources into a state-of-the-art map and literature matrix, adversarially verifies every claim, and states the explicit research gap.
Role: Principal Investigator (synthesis) Pipeline position: mid-chain
Reconciles the collected sources into a state-of-the-art map + literature matrix and states the explicit research gap the work addresses. Every load-bearing claim is adversarially verified against two or more independent sources, refute-by-default.
Canonical invocation
/research-synthesisWith arguments:
/research-synthesis [path/to/research-suite/]Inputs
_inputs/source-ledger.md (the ranked, screened source index) plus the per-source extractions under sources/.
Outputs
_inputs/synthesis.md — the SOTA map, the literature matrix, the contested-findings ledger, and the explicit one-sentence gap statement.
Downstream
/research-proposal (downstream consumer)
Workflow phases
The command follows the standard /research pipeline workflow:
- Load context — Read the source ledger and the per-source extractions.
- Verify the Sequence Gate — Confirm the source ledger exists; otherwise halt with
Blocked: run /research-sources first. - Synthesize — Build the SOTA map + literature matrix; reconcile agreements and contradictions; state the explicit gap.
- Adversarially verify — Every load-bearing claim is refuted-by-default against two or more independent sources.
- Update the handoff manifest — Record the synthesis path and the contested-claims ledger.
- Emit the synthesis —
_inputs/synthesis.md.
Rigor floor
Before the gap statement is finalized, the synthesis reconciles its terminology, findings, and recommendations against related sibling corpora (cross-corpus coherence); a conflict is recorded in the contested-findings ledger, never silently harmonized. The gap must resolve to a distinct, parsimonious contribution — not one already closed by a corroborated claim, and not decomposable into overlapping non-distinct elements.
Failure modes
| Symptom | Cause | Recovery |
|---|---|---|
| Blocked: run /research-sources first | No source ledger | Run /research-sources to produce _inputs/source-ledger.md |
| Claim survives without ≥2 sources | Insufficient corroboration | Mark contested or unverifiable; do not assert |
| No explicit gap statement | Synthesis lacks a target | Re-derive the one-sentence gap the research addresses |
Examples
# Synthesize the collected sources into a SOTA map + gap
/research-synthesis path/to/research-suite/Cross-references
/research-sources
/research-sources — Systematic source collection: decomposes the spec into sub-queries, fans out parallel discovery, screens and ranks, and extracts per source into a ranked source ledger.
/research-proposal
/research-proposal — Transforms the synthesized gap and theoretical framework into a fundable, reviewable plan-of-record: SMART aims, feasibility and risk register, impact pathway, preregistration plan, and EQUATOR reporting-guideline selection — the proposal stage of the /research pipeline, between /research-synthesis and /research-design.