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: an underlined label. A claim or figure chip holds only the number, and the word in front of it (claim, FIGS., line) is your own text, so you write the reference the way you want it read: claim 1, Fig. 3a, figures 13 to 16. When that word fits the chip, it is drawn as part of the link: underlined with it, lit with it on hover, and Ctrl+click on it follows the reference too. Other chips show the whole reference (the reference sign (12), the patent number). Hover any chip to preview the target. In an editor, clicking a chip puts your cursor in it at the character you clicked, so you can edit it like any other word (see Editing chips); <kbd>Ctrl</kbd>+click it (<kbd>Cmd</kbd>+click on a Mac; the cursor turns into a hand while you hold the key), or right-click it and choose Open, to go to the claim, the figures page, the section, or the prior-art patent. Outside an editor, such as in the assistant's replies, a click opens the target directly.

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. The chip holds the numbers with the words that join them; the noun and anything before it stay your text:

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

Typing a list gives the same single chip as pasting it. In claim 1, the 1 becomes a chip as soon as you close it, and when you carry on with "or 2" or ", 2 and 3" the rest joins that chip. A comma before the last number (claims 1, 2, or 3) reads the same as without it. A number your claim set doesn't have shows as ? inside the chip, like an orphaned reference. Two phrasings stay plain text, because their meaning is unclear: a list that mixes or and and (claims 1 and 2 or 3), and a range that runs backwards (claims 3 to 1).

If you typed a range, it stays a range when the underlying claims renumber, even if the new numbers go non-consecutive, and it keeps the word you wrote it with: 4 to 7 stays to. If you typed a list, it stays a list. Legal phrasing is yours to control; Nodes-IP only updates the numbers inside it.

Groups of figures

A phrase naming several figures becomes one chip for all of its numbers: FIGS. 1 and 2, Figures 5, 6 and 7, FIGS. 13 to 16, Figs. 4a and 4b, Figs. 3a-d. A range names the figures between its ends at that level, so FIGS. 13 to 16 covers FIG. 14 and its sub-figures but never adds a figure the matter doesn't have. As with claims, the chip keeps the phrasing you wrote (a range stays a range, 13–16 or 13 to 16), follows renumbering, and shows ? where a figure has been deleted. Figure numbers are the app's, so they show as the matter numbers them (1A). Typing FIG. 1a, and then 1b grows the first chip into 1A and 1B, after your FIG.; change that to FIGS. and the warning below goes away. A group only converts when every figure in it exists in the matter; a list mixing and and or, or a range that runs backwards, stays plain text.

The word before a chip

Because the word in front of a claim or figure chip is your text, Nodes-IP checks that it fits what the chip links to: claim before one claim, claims before several or a range, FIG., Fig. or figure before one figure, FIGS., Figs. or figures before several, and line before a section line. The same goes for an element's name before its reference sign: the housing (12) is checked against what sign 12 is.

When they disagree (figure 3 linking a claim, claim 2 and 3, a bare 3, the housing (12) where 12 is the controller), the chip turns amber with a strikethrough and the diagnostics list it. Hover the chip for the fixes and pick the one you meant:

• Change the word, to the noun or the element name the chip needs.
• Link to … instead, when the word names something else the matter has: figure 3 before a claim chip offers FIG. 3, the housing (12) offers the housing's own sign.

Nothing is changed for you. When the word and the link disagree, only you know which one you meant. The check knows English nouns only: in an application written in another language nothing is checked or drawn, and the pickers insert the number alone, so you write the noun in your own language.

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

You edit a chip in place, like text. To change claim 2 into claim 3, click the 2, replace it with 3, and carry on: the chip now points at claim 3. The claim in front of it is ordinary text you edit like any other word.

• Click inside a chip to put your cursor at the character you clicked. While your cursor is in it, the chip shows as plain text, and nothing you type there is linked or flagged yet, so a half-typed number never turns into a chip or a warning under your fingers. Clicking the very first or last character's outer half puts your cursor beside the chip instead, for typing next to it; on a one-digit chip that is every click.
• Type a digit right against a number chip and it joins the chip: after claim 1, typing 2 gives claim 12, linked to claim 12 once you move on.
• Backspace or Delete next to a chip takes one character from it, not the whole chip, and leaves your cursor in it.
• The arrow keys step into any chip of several characters one character at a time, as through any word: a claim number, a reference sign like (12) or (20, 520), a section or a patent number.
• Leave the chip (click elsewhere, use the arrow keys, or move to another field) and it links again. Left unchanged, it is exactly the chip it was: the same targets, the same phrasing, and the same ? for a deleted claim. Changed, it is read again like anything you write, so claim 2 changed to claim 3 links to claim 3, and (12) changed to (14) links to sign 14. Text that no longer reads as a reference stays plain text, and the claim or section diagnostics point it out.
• Typing a space or punctuation at the end of a chip's text also finishes it, the way closing a reference does when you type one out. Letters and digits extend it, so 1 can become 12, or a figure's 3 become 3a.
• Undo while your cursor is in a chip puts the chip back as it was. Once you have left it, one undo takes your whole edit of the chip back.
• Right-click a chip for its actions. Every kind offers Open (what a left-click does outside an editor) 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 its number when pasted into an external tool, so "claim 1" pastes as "claim 1" with your own word in front.

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 and the Word export render the assembled application as plain text, every chip resolved to its current numbers after your own words.