I am going to tell you the origin story of Eve-Genesis honestly, because the honest version is more useful to a managing partner than the polished one. Eve-Genesis did not begin as a synthetic reasoning corpus designed to train domain-specialised Small Reasoning Models. It began as a riddle dataset.
The intuition was simple. A riddle is not a knowledge test. A riddle is a cognitive test. It asks you to decompose, to trace implications, to resolve paradox, to move between concrete and abstract representations. Riddles isolate reasoning from content. Train a Small Reasoning Model on riddles well and you have taught it reasoning style independent of any specific domain's knowledge.
The recognition
The breakthrough came when my daughter, an undergraduate at the time, saw the dataset and named the formal logic underneath it. She threw words at me I had not been using: deductive, inductive, abductive. She had recognised, in a dataset I had designed under another name, the formal categories of reasoning that philosophy has been working with for centuries.
Confirmation came in a long conversation with an AI — the kind of late-night session where you ask the question you have been circling for months. The response named the layers in detail: dialectical, hermeneutic, semiotic, phenomenological, Socratic. The dataset, structured as interlocking conceptual puzzles, was already doing what classical reasoning disciplines have been doing for millennia.
The reframing
That recognition reframed the whole project. The dataset was not training the model on what answer goes with what input. It was training the model on how to move between ideas. That is a fundamentally different kind of training intervention. Most fine-tuning corpora carry instruction-response pairs. The model learns to associate inputs with outputs. Eve-Genesis carries reasoning structure as data. The model learns the operation itself.
The technical phrase is reasoning-style conditioning. The philosophical phrase is epistemic priors shaping. Either way, the outcome is the same: the model that emerges does not just know more about the domain — it thinks differently in the domain.
From riddles to legal practice
Eve-Genesis (Law Edition) inherits the riddle-derived reasoning substrate and adds a layer calibrated to legal cognition. The Law Edition emphasises three modes: analogical reasoning (the substrate of case-based reasoning), abductive reasoning (the mode of intake and case-theory construction), and dialectical movement (the posture of advocacy). Those modes are not generic AI capabilities. They are how legal practitioners actually reason — and they are what the legal F5/reasoner inherits from its training corpus.
Why the origin matters
I tell this story because the origin matters for the credibility of the claim. The riddle dataset was built before we knew what we were building. The dataset's structure was philosophically rigorous before anyone named it that. That is how a moat usually starts — not from a deliberate strategic decision to differentiate, but from following an intuition until it leads somewhere unexpected.
The competitors I worry about are the ones who could re-derive Eve-Genesis from first principles. Almost no one will. The riddle origin is hard to repeat because the reasoning to do it correctly is mostly tacit. The published literature on reasoning-style conditioning is thin. The pattern is hard to pattern-match on.