innoMOS Start a brief

An invention plugin for ChatGPT

The Missing Minute

In this fictional case, the workshop was open at 09:00 and open again at 09:02. What happened in between?

Follow the evidence

09:00 / 09:02

Open. Open.

Those two snapshots tell us how the workshop started and ended. They leave 09:01 unanswered.

09:01 · A record appears

At 09:01, cancelled.

The middle record shows a cancellation. The later 09:02 record still says open.

The inference

What would change your answer?

Keep the observation that changes the answer. Take it out and see what you can still say. Try the same move with a question of your own.

Bring this case into a brief

innoMOS workbench

Try it on your question.

Draw unexpected ingredients, test a condition or take a question into ChatGPT.

An evidence experiment

Was the workshop ever cancelled?

  1. 09:00Open
  2. 09:01No record
  3. 09:02Open
Use this question in a brief
The endpoints cannot tell you.

Both snapshots say open. The missing record leaves cancellation unknown.

Combination maths

2,024 possible groups

Each tile is one available piece. The copper tiles show the size of one group. The count covers groups of pieces.

What if you draw more than once?

14.95 distinct groups expected with independent, uniform draws. A group can repeat.

Studies and project evidence

Five primary sources, with their boundaries.

The studies motivate parts of this approach. They do not establish that innoMOS as a whole outperforms a strong direct prompt.

Individual creativity and collective diversity
01 / Science Advances · 2024

Doshi & Hauser — Generative AI enhances individual creativity but reduces the collective diversity of novel content.

In a short-story experiment, access to AI ideas improved evaluated individual stories while increasing similarity across AI-assisted stories.

Design implication
Keep different routes into the problem, rather than equating one polished answer with a varied search.
Boundary
A short-story result is not a universal result about invention, current models or innoMOS.
Publisher / DOI ↗
Ideas can be judged novel before they are built
02 / ICLR · 2025

Si, Yang & Hashimoto — Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers.

The study found higher judged novelty for LLM-generated proposals, alongside feasibility and generation-diversity limitations.

Design implication
Take model-generated possibilities seriously. Preserve the conditions that would make them work.
Boundary
Reviewers' novelty judgements are not implemented discoveries or exhaustive prior-art checks.
Authors' paper ↗
A proposal's appeal can change after execution
03 / Execution follow-up · 2025 preprint

Si, Hashimoto & Yang — The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas.

Experts implemented assigned research ideas. Earlier advantages for LLM proposals weakened after execution.

Design implication
Separate the exciting proposal from the result of a discriminating implementation or experiment.
Boundary
These tasks and implementations do not settle every domain or establish an innoMOS benefit.
Authors' follow-up ↗
Mathematical discovery needs an evaluator
04 / Nature · Published online 2023

Romera-Paredes and colleagues — Mathematical discoveries from program search with large language models.

FunSearch coupled model-generated programs with systematic evaluation and search, producing cap-set constructions and bin-packing heuristics.

Design implication
Use an external check that can distinguish a better proposal from a persuasive one.
Boundary
This is a particular evaluated search system, not a general theorem-solving guarantee. innoMOS is not FunSearch.
Paper abstract / DOI ↗ Authors' implementation ↗
Look for a landscape of useful possibilities
05 / Quality-diversity search · 2015

Mouret & Clune — Illuminating search spaces by mapping elites.

MAP-Elites preserves high-performing solutions across predefined behavioural dimensions, rather than returning only one optimum.

Design implication
Diversity and intermediate stepping stones can be useful search objectives.
Boundary
innoMOS does not implement MAP-Elites by borrowing this idea; a curated operation catalogue is a different mechanism.
Authors' paper ↗

The project evidence, separately

Research-informed.
Still being tested.

What exists in the product

The inspected Discovery implementation offers problem, encounter, anomaly and exaptation entry profiles. It uses curated, source-linked operation hypotheses, a three-outcome Explore → Realize flow, and retention checks. Random and Ortho routes address different parts of exploration.

The host model supplies the creative proposals. Structural acceptance is not creative-quality acceptance.

What our pilots establish

Our bounded development pilots include actual paired runs and functional checks. They do not yet establish general superiority over a strong direct prompt, verified originality, first-mover status or human benefit. A three-pair core.4/core.5 pilot ended INCONCLUSIVE.

innoMOS 0.4.0 remains a preserved reference. A newer version's additional workflow features do not, by themselves, make it a better invention method.

Project basis: the 20-part discovery research synthesis (17 October 2026); inspected Discovery source; NEXT3 paired-pilot report (26 October 2026). The research loops are literature work, not 20 method-effect experiments. Source inspection here used paper abstracts, publisher excerpts and author project material; it was not a full-text systematic review.

Your Discovery brief