Every record on this site says how sure the project is of it, in words and with a shape of its own, so colour is never the only signal. This page explains each label and shows real records from the corpus as worked examples: the same cards you meet in the References band at the foot of every section.
Confidence: Verified
A manufacturer or IntelliMake document says so, or it was observed directly. It does not mean anyone measured it at S2.
Confidence: Inferred
Reasoned from Verified facts. The reasoning is printed with the record.
Confidence: Assumed
Plausible but untested. The record says how it would be checked.
Kind: Gap
Not known. No figure or answer is given in its place.
Kind: Contradiction
Sources disagree. Both sides are shown, and the site does not pick one silently.
Kind: Recommendation
Project advice drawn from the records it cites. Not a fact about the machine and not a confidence class, so the filter never hides it.
Awaiting cell access
Awaiting cell access: could be confirmed or corrected once the physical S2 cell can be observed.
This project's simulation and agent design, not the physical cellProject design, not the physical cell
This project's simulation and agent design, not the physical cell.
The corpus holds 734 records: 598 Verified, 39 Inferred and 3 Assumed claims, 58 gaps, 22 contradictions and 14 pieces of project advice. 25 are awaiting cell access, and 24 describe this project's own design.
Verified
Verified means a manufacturer or IntelliMake document says so, or the project observed it directly. It does not mean anyone measured it at the physical station: a Verified figure is what its source states, no more.
UFACTORY's specification states the rated maximum payload of 5 kg, so the record is Verified1.
Inferred means the project reasoned it from Verified facts; no source states it outright. The card prints the reasoning under "Why we infer this", so you can follow each step back to its own sources.
No IntelliMake document says that two arms let loading and unloading overlap. The project reasons it from the gift flow, which has two separate Cobot Handling steps assigned to S2 and S62.
With two arms, loading incoming material (S2) and unloading and routing finished parts (S6) can happen at the same time. With one arm, both handling steps for every part would run one after the other on the same arm. How much this helps throughput is unknown, because no cycle times are documented (int-033), and the laser step may be the real bottleneck.
Why we infer this:Verified: the gift flow has two separate Cobot Handling steps, one before staging and laser engraving and one after (int-028), assigned to S2 and S6 (int-029). One arm would have to perform both in series; two arms let them overlap. This shows the steps can overlap, not that one arm would be the bottleneck: that depends on cycle times, which are undocumented (int-033).
Assumed means plausible but untested. Every Assumed card says how it would be checked, under "How this would be checked". Treat it as a working hypothesis, never as a fact.
The corpus holds only three Assumed records: where the stations sit relative to each arm, how the IntelliMake agents exchange information, and what Camera C1 can see345.
So the Assumed option in the filter looks nearly empty on most pages. That is expected. Where the sources are silent, the project records a gap rather than a guess, and keeps a guess only when it says how the guess would be tested.
The S2 and S6 stations sit on opposite sides of the laser processing stations (S4/S5), so a single arm probably could not reach both the receiving and staging area and the post-processing area.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
How this would be checked:Measure the as-built positions of S1, S3, S4 and S6 relative to each arm's base and compare them with the published reach of each arm.
Evidence · 2 citations
S2 UFactory xArm 850 Cobot
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · S2 station label
The current assumption for the IntelliMake agents is that they do not talk to each other directly: they exchange information, and may collaborate, through a central shared knowledge space (a hub). IntelliMake leadership has not finalised this.
How this would be checked:IntelliMake team leadership's design for the shared knowledge space: its protocol, schema and hosting (open question Q9).
Evidence · 1 citation
The agents will not talk directly to each other, rather will exchange information in a central hub and possibly colloborate in that space. That has not been fully fleshed out by the iIntelliMake team leadership.
Camera C1's field of view covers the S1 receiving area that S2 picks from, so C1 could confirm material presence and state for S2.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
How this would be checked:Observe C1's physical mounting and field of view at the cell, and whether its output is available to S2 through S11 or the shared hub.
Evidence · 1 citation
Camera C1 – Receiving
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · Camera C1 icon placement
A gap is something the sources do not settle. It is never phrased as a fact, and where a gap stands in for a number, no number is shown. Each section lists its gaps under Open questions, and the card links the records the gap concerns.
No source available to the project documents why IntelliMake uses two arms, or why the 850 went to S2 and the xArm 6 to S66.
IntelliMake's reason for using two arms, and for putting the 850 at S2 and the xArm 6 at S6, is not documented in any source available to this project (Q14d).
When sources disagree, the card says so and shows both sides with their citations. The site never picks a side silently. Where the teaching uses one side's figure, the contradiction sits next to it.
UFACTORY's own documents give two different ranges for J27.
Sources disagree on the range of joint 2 (J2): the product page, the online hardware manual and the uf850 URDF give ±132°, but User Manual V2.3.0 (PDF, 2024) gives -118°~120°. The manual's figures match none of the other three sources; the three agreeing sources are probably current, but this is not confirmed.
Project advice is this project's recommendation, drawn from the records it cites. It is not a fact about the machine and not a fourth confidence class, so it carries no confidence badge and the filter never hides it. Its card lists the records it is based on, each with its own badge.
Until the safety function of S11 is documented and verified, the project advises that nobody, learner or agent, treats S11 or the cameras as a safeguard8.
Kind: RecommendationThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-053
Project advice
Until S11's safety function is documented and verified, neither learners nor the S2 agent should treat S11 or the cameras as a safeguard. The S2 agent must not rely on them to stop motion or to protect people.
This is advice from this project, based on: int-024 Verifiedint-050 Gap, awaiting cell access
Why:S11 is described only as monitoring that includes safety (int-024). Nothing establishes a safety rating, stop authority or response time (int-050). Treating an unrated monitoring system as a safeguard is the failure the Q3 disposition warns against: an Assumed safeguard mistaken for a confirmed one.
This project's design, not the physical cell
Some records describe this project's own simulation and agent design rather than the physical cell. Whatever their class, they carry the label "This project's simulation and agent design, not the physical cell" beside the badge, and on the section pages they sit under a heading with the same label. The advice above is one of them.
Awaiting cell access
Some records could be confirmed or corrected once the physical cell can be observed. They carry the marker "Awaiting cell access" on the card, and the same mark follows their reference chips. The filter can show these records on their own, so they can be found and checked together.
Two of the Assumed records above wait on cell access: where the stations sit relative to each arm, and what Camera C1 can see35.
Reading the numbered markers
In the teaching, a claim ends in a small numbered marker. The number is the record's place in References at the foot of the page, and the shape before it is the record's class, so you can see at a glance how firm the sentence is. Screen readers announce the number and the class in words. Hover over or focus a marker to preview the record; follow it to jump to the full card with its evidence.
7 A screen reader hears: “Reference 7, Contradiction”.
8 A screen reader hears: “Reference 8, Recommendation”.
Using the filter
On each section page, References opens with "Filter records". Untick a class to hide its records. Teaching that relies on a hidden class folds to a short note with a button to show it again, and a line at the top counts what is hidden. The cell-access option shows only the records awaiting cell access. Project advice is always shown. Nothing is hidden until you ask, the choice is remembered only in this browser, and without JavaScript every record is shown with its label.
References
Every record this page cites is shown above as a worked example, or listed here with its evidence.
Owner statements, 2026-09-21 (verbatim) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21 · cited by 1 record here · Project copy; not published on this site.