nescio-mind explores how an artificial reasoner can build categories from experience, discover the boundaries between them, and — crucially — report honest uncertainty instead of a confident guess.
Structural honesty over confident guessing. The system prefers to surface competing candidates and say "I don't know" as a first-class answer, rather than commit to one arbitrary category.
Each layer adds a capability the one below it cannot express — from raw correlation up to meta-cognitive self-doubt.
Pattern matching and statistical co-occurrence — the raw associative substrate.
The same input can mean different things in different contexts; meaning-splits are discovered from contradictions.
Inferring causal relationships — processes that transform inputs into outputs — not just what co-occurs.
Structural alignment across domains: an abstract pattern learned in one place predicts by analogy in another.
Meta-cognitive structural self-doubt — it challenges, tests, and refines its own abstractions instead of trusting them.
Challenging an abstraction produces more precise knowledge, not destruction. Growth through challenge, not rules-based safety.
Every input runs through an eight-step pipeline in
RichNeuron.process(). Confidence is a gate, not an assumption — low confidence
routes to a more competent neuron or returns honest uncertainty.
has_leash → domestication).Between exposures, a consolidation "sleep" cycle turns novel observations into refined knowledge:
Unclassified observations are recorded as provisional prototypes during normal processing.
Consistent patterns are clustered across neurons and promoted to new categories.
Confidence decays for untested abstractions; the challenger amplifies exceptions and scopes over-broad patterns.
The commitments that shape every part of the system.
plant → tree → pine chains; broad and specific coexist.The clearest case: two categories with identical evidence. A confident guesser picks one; nescio-mind carries the tie all the way to the answer.
A genuine 50/50 tie — both candidates live in the distribution.
ambiguous: true · 2 competing candidates
The tie is carried through the vote, not discarded at the first step. A clear winner still returns ambiguous: false — the flag fires only on a real near-tie.
Exploratory research framed as measurement — persisted, reproducible run data rather than asserted pass/fail. A FAIL or a surprising number is a recorded finding, not a bug.
A blank-neuron network learns dog, then absorbs cat,
and must discover — from cross-population feature importance — that a single feature is the
category boundary. The enrichment study then asks whether that discovery mechanism survives
richer domains: multiple redundant discriminators, a size-confounded decoy, intra-concept
variance, and partial correlation.
When two categories share an identical profile, the reasoner used to discard the tie before it ever voted. Distributed mass voting carries the whole distribution into the vote, so a genuine near-tie produces two competing candidates and ambiguous: true — surfaced on every return path, with no sub-system changed.
ambiguous: false, and the change lives only in the cataloger and the neuron.