# Loom

When two facts disagree, the newer one is usually right. Loom asks what happens when it is not.

Pilot results · d/rksci research · Published 2026-10-08 · Tags: Agent Memory, Retrieval, MemoryAgentBench, LongMemEval, Engram, Conflict Resolution, Consistency

Is a fact that fits the rest of memory more likely to be right?

On FactConsolidation the newest fact wins by design, so recency is hard to beat there. Loom is the experiment that asks the harder question, and it needs a test that Tide cannot pass by counting.

## 1. Idea

Experiment 7 of 10 in the Engram series. [← Horizon](/engram/horizon) · [Engram overview](/engram) · [Coral →](/engram/coral)

Facts are not independent. “Person B lives in City R” sits among facts about where B works, where B’s family lives and what B did last year. If a new fact claims B lives somewhere else, most of that surrounding web disagrees with it, and the claim is weakly supported. If instead several other facts back the new claim, the old one is the odd one out. Loom measures support and lets the better-supported side win.

**Loom · who has more support.** Two claims cannot both be right; each is supported by the facts that agree with it, and the better supported side wins, not the later date. An illustration, not a result.

Mutual-kNN means two facts count as agreeing only if each is among the other’s nearest neighbours, which limits how much support a fact that sits near everything can collect.

## 2. Where it came from

In April this was called protein binding: chunks attach to each other at shared-entity “sites”, and a contradiction disrupts the fold and earns low trust. Four scripts built it up. One stored small arithmetic webs (a division, a multiplication, an addition that agree) and asked whether an update that breaks the web loses. A second carved sites as it ingested facts. A third asked whether original facts sit in denser neighbourhoods than their updates. The project page’s one-line verdict on all of it: perfect in the lab, six for six, and useless at scale, because the locks were too vague.

The audit adds the reasons. The toy cases were small enough to tune. The author set the expected winner for each, and the gradual-evidence test counted a tie as a correct answer. Entities were capitalised words. The density test hard-coded example chunk indices. The one scored number for the family, “knit/loom”, was 42% against cosine’s 39%, in the one-feature test that returned more than k chunks.

## 3. Hypothesis

Stated before running, in two parts. First, on FactConsolidation, Loom at equal k does not beat Tide, because the dataset’s rule is that the later fact wins and support is a noisier proxy for that rule than the date is. A wrong prediction here would be welcome.

Second, on the gradual-override micro-test, Loom flips a belief only after a plausible amount of contrary evidence, and Tide never does: it flips on the first newer fact, whatever backs it. That is the property worth having in a memory that is sometimes told something false. This is the part of Loom that Tide cannot pass by counting.

## 4. Design

**Support.** The agreement mass of a fact: the summed similarity to the facts that are mutual nearest neighbours of it. Computed over the embeddings the Dense anchor uses.

**Conflict.** Two retrieved facts that are close in meaning and differ in content are a candidate conflict. The winner is the one with more support; the other is dropped from the result.

**Equal k.** Resolution removes losers and the list is refilled from the ranking to k. It never returns more than Dense.

**Micro-test.** A small fact web, a contradicting update, and 0 to 5 further facts that back the update. The number it takes to flip the answer is recorded. A tie is a miss, not a hit, and the winners are fixed by a rule written down before the run.

**Ablation.** Support term off: the same pipeline picking by date. It should land on Tide.

## 5. How it is tested

Loom is read against Tide as well as Dense, because on this dataset Tide is the right control. The micro-test is run separately from the benchmark: its output is a flip point per memory, with the number of cases and their construction rule published beside it. Hand-built cases are suggestive, not evidence, and the page will call them that.

The standing rules for every Engram experiment apply here unchanged.

## 6. Results

## 7. What would change the conclusion

- If Loom does not beat Tide on FactConsolidation, that is the expected result and not a failure, provided the micro-test shows a graded response.
- If the micro-test shows the same flip point whatever the support, support is not what drives the choice.
- If Loom loses to the support-off ablation, the “binding” in the name has been a date all along.

## Sources

Experiment 7 of 10 in the Engram series. [← Horizon](/engram/horizon) · [Engram overview](/engram) · [Coral →](/engram/coral)

Loom is one of ten experiments in Engram. Its rows come from one run on the pilot sets.