The prototypes — public, and marked for how real they are.

The canonical LinkML grammar — every node and edge on this site is defined in it. SHACL is generated from the source; the Turtle and JSON-LD context are maintained alongside it.

What to try: browse the Docs for every class and slot, then write a record against the JSON-LD context and check it with the Validator — in the repo, make validate_data runs that check on the sample graph.

The interactive schema-demo deck: the six-node grammar built one record at a time on the discovery of DNA’s structure, with every slot and edge explaining itself on hover.

What to try: scroll it end to end, then hover an edge label to read the relation both ways.

AI-assisted MIRAfication of a source — the MIRA-fier of the kickoff write-up. Emits schema-conformant JSON-LD (<name>.mira.jsonld) — the wire format the viewers and the KOI envelope speak — with a verbatim provenance.excerpt on every node (the receipts), dangling and ungrammatical edges reported instead of dropped, and the source → study → grounds → evidence spine enforced.

What to try: MIRAfy a source and diff the Initial AI draft nodes against what a human would advance; the emitted .mira.jsonld is what moves downstream.

A ~314-node discourse graph plus a standalone d3 viewer and the Python transform pipeline that built it. The data is mock — terms are randomized to a microtubule-transport field; use it to validate tooling, never as a scientific source.

What to try: open the d3 viewer and traverse from a Question to its Evidence; the same grammar, rendered and navigable.

The TypeScript MyST parser (MIRyST in the kickoff write-up) — authoring discourse-graph nodes inside MyST Markdown and emitting JSON-LD. One authoring tool to one viewer: real, and narrow.

What to try: npm test (vitest) — the MyST → JSON-LD round-trip on the golden fixture.

MIRA inside the existing OXA standard. Stencila, an open-source publishing platform, reads and writes Questions, Claims, Evidence, Protocols and Requests — authored as MyST directives, Quarto divs or Stencila Markdown blocks — and converts them to and from MIRA JSON-LD (.mira.jsonld). A second, independent authoring tool on the same wire format.

What to try: follow the Stencila docs to export a marked-up document with stencila graph <doc>.myst <doc>.mira.jsonld.

The KOI cross-organization envelope — operational. Different orgs’ agents and tools read from and write to the same KOI node, and it ingests the JSON-LD that MIRA-extraction emits. Our working MIRA KOI node contains unpublished scientific results by our users, and so isn’t yet public — and even there, each record is a pointer to its artifact, not a copy of it. Still designed, not built: federation across schemas and a public network at scale.

What to try: stand up your own KOI node to push and pull MIRA nodes across the network.

The north-star user story — “push a result to a shared web interface” — with the normative transport/sharing rules R1–R13 and the authoritative open-questions list.

What to try: read AGENTS.md; it is the brief the whole approach is measured against.

The inter-lab user story, built: a read-only shared dashboard — graph, kanban and by-question views of the questions, claims, evidence, studies, protocols and open requests two labs share — rendered from MIRA JSON-LD carried over KOI. The public instance shows demo data; each lab’s private notes stay local.

What to try: open it, switch between Graph and Kanban, and follow the open Request back to the result it asks about.

The same grammar running in public on two unrelated topics — a healthcare-language graph and a whitepaper-as-a-graph. Both give every node a URL and generate their narrative as a traversal: the prose is a rendering, the graph is the source.

What to try: open either and read a node, then follow its edges to the evidence.

A public graph of MIRA records on AT Protocol and IPFS, built by SciOS: papers as bundles of signed records, questions and evidence added by signed-in researchers, claims endorsed as believed, verified or qualified, and a PDF extractor that turns a paper into records. It maps MIRA’s node types and relations onto its own lexicon and adds a few — proposed back to the schema in the open.

What to try: browse the public graph without signing in; open a paper and follow a claim to its evidence.

A funder-facing view from the kickoff: open scientific debates where every claim is backed by evidence, and endorsements are scored to show how much each piece of evidence moves the answer to a question. It is a lens applied on top of the graph — the scoring is the application’s, not the schema’s; MIRA itself still computes nothing.

What to try: open a debate and trace a claim to the evidence behind it.

A draft ATProto lexicon binding (science.mira.*) for public discourse-graph nodes — the intended public layer. Self-labeled DRAFT / PROPOSAL: not adopted, not published, not on the network. A working proof of concept on AT Protocol exists separately — RRGI, above, on its own lexicon.

What to try: read the lexicons as a concrete direction; treat them as a proposal pending schema-team review, not a shipped surface.