References

The reference system is the connective tissue of your matter. Whenever you mention a claim, figure, reference-sign element, application section, or prior-art patent in your text, or in conversation with the assistant, Nodes-IP turns it into a linked chip that points at the underlying entity rather than a literal number or string. References stay correct as your matter evolves: claims renumber, figures reorder, elements rename, and every chip follows.

What can be referenced

The same chip primitive handles five kinds of reference:

Claims: claims in your own claim set (claim 1, claims 2 and 3, any of claims 4–7)
Figures: figures in your matter (FIG. 2, figure 3a)
Reference-sign elements: the named parts on your figures, written as their sign (the housing (12), the controller (30)), including combined signs for alternative embodiments (the fastener (20, 520))
Application sections: the sections of your draft (inserted from the @-mention picker)
Prior-art patents: patents you've bookmarked into the matter (US 10,123,456, EP 1234567 B1)

Every chip renders the same way: a coloured, underlined label, with the kind conveyed by the text it shows (Claim 1, FIG. 2, the patent number). Hover any chip to preview the target. Click it to navigate to the claim, the figures gallery, the section, or the prior-art patent panel.

How chips appear

There are three ways a chip ends up in your text:

Automatic detection. As you type prose, Nodes-IP scans for references you have written out in full and turns them into chips: "As shown in figure 2, the housing (12) receives the controller (30)" chips the figure and both signs the moment you close each one. You don't type any special syntax. Only what you actually wrote is converted: naming an element in your prose never earns it a reference sign on its own, because whether a mention carries a sign is your call, not ours.

Suggestions while you type. Start a reference in the claim editor, the section editor, or the assistant composer and a short list of matching targets opens beside the caret: claim lists your claims, FIG. your figures, an opening parenthesis followed by a digit ((1) lists the elements whose reference sign starts with it, typing most of an element's name lists the elements it could be, and a publication number (US 10,1) lists the patents you have bookmarked into the matter. Spacing and punctuation don't matter for that last one: US 10,123,456, US10123456B2, and EP 1 234 567 B1 all find their patent. Keep typing to narrow the list, use the arrow keys to move through it, and press Tab to take the one you highlighted. Completing an element by name writes out the rest of the name and puts its sign after it, so "the blade s" becomes "the blade set (10)". Esc dismisses the list. It only appears when something matches, and Enter always stays a paragraph break, so it never interrupts ordinary drafting.

@-mention picker. In the assistant composer, the claim editor, and the section editor, pressing @ opens a picker that lets you pick a reference explicitly. Type a type keyword to narrow it (@pat, @fig 2, @claim 3). Useful when the exact phrasing in your message doesn't match a natural pattern, or when you want to attach a patent to a question without writing it out longhand. Patents are never converted automatically, so @ and the suggestion list are the two ways to insert one.

Smart phrasing for claims

Claim references support several phrasing styles, and the system preserves whichever one you wrote:

Single: claim 1
List: claims 2, 3 and 5 / claims 2, 3 or 5
Range: claims 4–7
"Any of" / "any one of": any of claims 4–7, any one of claims 2, 3 or 5

If you typed a range, it stays a range when the underlying claims renumber, even if the new numbers go non-consecutive. If you typed a list, it stays a list. Legal phrasing is yours to control; Nodes-IP only updates the numbers inside it.

Combined reference signs

When one claim element covers more than one part, such as alternative embodiments, write every sign together in one set of parentheses: (20, 520). Nodes-IP chips the whole group as a single reference, and the chip's popover lists each element by label and sign so you can jump straight to any one of them.

A combined sign only converts to a chip when every sign in the group is a known element. If one sign doesn't resolve, the whole parenthesised group is left as plain text rather than converting part of it. Delete one of the referenced elements later and the chip doesn't drop it: the missing sign shows as ? in its place ((20, ?)), matching how an orphaned claim reference behaves.

Surviving renumbering

Chips bind to internal IDs, not to the displayed text. That means:

Reorder claims and every claim chip everywhere in the matter updates to the new number: in other claims, in the description, in the assistant conversation history.
Rename a figure or element and every chip pointing at it shows the new name.
Delete a referenced claim and the chip becomes orphaned, shown in amber with a strikethrough and surfaced in the claim editor's diagnostics, so you know to fix it. Nothing is silently rewritten.

This is the system referred to elsewhere as "smart references that survive renumbering", and it works the same way across claims, sections, figures, and the assistant. For details on how claim numbering and renumbering works, see the Claims tab.

Editing chips

Backspace into a chip to convert it back to plain editable text (minus one character, the standard backspace behaviour).
Right-click a chip for its actions. Every kind offers Open (what a left-click does) and Copy (the chip's text, for pasting into an email or a form). Patent chips add Quick view, which opens the draggable patent panel next to your cursor so you can read the abstract without leaving the page, and Bookmark / Remove bookmark to save a patent into the matter without leaving the sentence you're writing.
Click a chip in the assistant to open its target. Chips in the assistant's replies are fully clickable, just like ones you wrote yourself.
Copy a chip and paste it elsewhere and the chip survives the round-trip if you stay inside the app, degrading to a sensible label (e.g. "Claim 1", "FIG. 2") when pasted into an external tool.

Where references show up

The system is consistent across every surface that handles text:

Surface	Auto-detect	Suggestions	`@`-mention picker	Notes
Claim editor	Yes	Yes	Yes	Multi-claim phrasing supported
Application sections	Yes	Yes	Yes	Multi-claim phrasing supported
Assistant input	No	Yes	Yes	Mentions are first-class context
Assistant reply	n/a	n/a	n/a	Chips are clickable for navigation

The Preview panel renders the assembled application as plain text, with all reference tokens resolved to their current labels.