Tacit knowing modeled as auditable memory operation for ai science
Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science
Neural and Evolutionary ComputingArtificial Intelligence
Summary
Some knowledge is hard to explain or write down, called tacit knowing. This paper argues that tacit knowing works best when seen as a special operation in memory instead of just content. They created a new memory model, VaCoAl/PyVaCoAl, that stores knowledge like a clear, checkable path with confidence. This helps understand how AI can better keep track of the reasoning behind its discoveries and ideas, making AI-generated science more understandable and trustworthy.
What this means in practice
- •For ai system developers: Design AI that maintains auditable, confidence-tracked reasoning traces to improve trust and understanding in AI-generated results.
- •For knowledge management teams: Implement memory-based models that distinguish between explicit and tacit knowledge to enhance knowledge transfer in organizations.
A theory result. No direct application yet.
Authors
Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato, Kodo Yamauchi
Abstract
We argue that tacit knowing is better modelled as an operating regime of one memory substrate than as a kind of content. The substrate is VaCoAl, an algebro-deterministic XOR-and-shift hyperdimensional memory over GF(2), realized as CASRAM (commercial SRAM-CAM) and PyVaCoAl (DRAM-CAM).In VaCoAl/PyVaCoAl a directed acyclic graph (DAG) reads two ways. Repairing every collision (Rescue mode) makes the trace exactly auditable but ranks no path higher; tolerating collisions (Don't Care mode) yields a path-integrated confidence, CR$_2$, that silently favours direct routes. This audit-valuation complementarity is a formal counterpart of Polanyi's claim that tacit and explicit knowledge are not sharply divided. It separates contingent tacitness, which a new query brings out (AlphaGo's game tree), from regime-bound tacitness, statable only in a regime where it is gone (AlphaGo's hunches). (1) Polanyi's from-to structure reads as non-commutative binding, the Identikit as role-filler composition, recognition as majority-vote coincidence. (2) Explicating the valuation destroys it, as attending to his fingers can make Polanyi's pianist falter, yet a closed-form law states it. Polanyi, Nonaka, Tsoukas and Collins each capture part of this but narrowly; even Nonaka and von Krogh's continuum cannot tell contingent from regime-bound tacitness. (3) Collins's three tacit knowledges become strata, one outside the substrate. (4) Our mentor-student DAG is a tacit-transmission graph. (5) Terence Tao's remark that AI-solved problems spawn few follow-ups is diagnosed as rootless explicit knowledge: checkable results whose route no one can follow and that no one yet understands well enough to extend, teach or judge. To re-root them, LLMs generate, VaCoAl/PyVaCoAl keeps an auditable trace with its confidence, and people value, a role virtue epistemology shows cannot be offloaded. Testable predictions follow.