6e992cc0c5
- Rename 'three-pronged' folder to 'knowledge-layers' — prong metaphor
was misleading (implied parallel tines), replaced with epistemic layers
(deductive base, empirical middle, probabilistic oracle — vertical stack)
- Collapse 11 overlapping files into 3 coherent documents:
- knowledge-layers/_index.org: core framework (two engines + one store,
World Model formula, 0-14 layer table, provenance store design,
conflict resolution, cold-start, stage mapping)
- knowledge-layers/practical-implications.org: design-world-aware-of-
physics, 10 powers, Schafmeister existence proof, epistemic transparency
- knowledge-layers/neurological-empirical.org: neural networks in
provenance framework (kept intact)
- Relocate wolfram/mathematica and Schafmeister docs to ideas/viability/
- Integrate into main architecture _index.org:
- Gate: expanded from two vectors (ACL2+LLM) to three (deductive,
provenance/empirical, LLM oracle)
- Autodidactic loop: split into Track 1 (deductive hardening, fast)
and Track 2 (empirical validation, slow, experimental-feedback-driven)
- See also: added Knowledge Layers cross-reference
- Add all-lisp geometry engine note (ideas/lisp-geometry-engine.org) as
concrete illustration of the empirical layer's effect on design work
- Rebuild site: 148 files, 0 errors
45 lines
3.2 KiB
Org Mode
45 lines
3.2 KiB
Org Mode
:PROPERTIES:
|
|
:CREATED: [2026-05-27 Wed]
|
|
:ID: ee8f3b2a-4c7d-4e1b-9b0a-6d8f2e3c1a5b
|
|
:END:
|
|
#+title: Neurosymbolic AI
|
|
#+filetags: :resources:neurosymbolic:papers:survey:
|
|
|
|
Local library of recent neurosymbolic AI papers, updated monthly from arXiv. Papers are downloaded in PDF format and cataloged below.
|
|
|
|
See also the companion note [[id:be9bccc7-5adf-4d0d-8ee4-8855892189bf][Neurosymbolic Loop Architectures]] for a design taxonomy that positions these papers relative to Passepartout.
|
|
|
|
* 2026 Papers
|
|
|
|
| arXiv ID | Title | Date | Keywords | File |
|
|
|----------|-------|------|----------|------|
|
|
| 2605.22885 | ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization | May 2026 | LLM, theorem proving, proof optimization, self-improvement | [[file:papers/2605.22885.pdf]] |
|
|
| 2605.22874 | NeuroNL2LTL: Neurosymbolic Framework for NL Translation of LTL | May 2026 | NL translation, LTL, formal logic | [[file:papers/2605.22874.pdf]] |
|
|
| 2605.10327 | SCALAR: Symbolic Conjecture and LLM-Assisted Reasoning | May 2026 | Conjecture generation, theorem proving, LLM | [[file:papers/2605.10327.pdf]] |
|
|
| 2605.10279 | DeepLog: Neurosymbolic Framework Unifying Logic and Deep Learning in PyTorch | May 2026 | Logic, deep learning, PyTorch, neurosymbolic | [[file:papers/2605.10279.pdf]] |
|
|
| 2605.08011 | LLM + Formal Logic Integration for Neurosymbolic Reasoning | May 2026 | Survey, formal logic, LLM, neurosymbolic reasoning | [[file:papers/2605.08011.pdf]] |
|
|
| 2605.01430 | Measuring Understanding in Artificial Cognitive Systems | May 2026 | Verification, cognitive systems, neurosymbolic | [[file:papers/2605.01430.pdf]] |
|
|
| 2605.26169 | ESBMC: Survey of Formal Software Verification | May 2026 | Formal verification, bounded model checking, SMT | [[file:papers/2605.26169.pdf]] |
|
|
| 2604.05427 | LLM Verification Gates for Robot Task Planning | Apr 2026 | Gates, verification, robotics, LLM | [[file:papers/2604.05427.pdf]] |
|
|
| 2604.04177 | Formal Logic in LLM Fact-Checking Pipelines | Apr 2026 | Fact-checking, logic, verification | [[file:papers/2604.04177.pdf]] |
|
|
| 2604.23377 | The Alignment Problem in Neurosymbolic Systems | Apr 2026 | Alignment, concept-label correspondence, neurosymbolic | [[file:papers/2604.23377.pdf]] |
|
|
| 2603.14628 | LLM Neurosymbolic Reasoning in Theorem Proving | Mar 2026 | Theorem proving, LLM, neurosymbolic | [[file:papers/2603.14628.pdf]] |
|
|
| 2603.04019 | Fluid Logic: Neurosymbolic Modal Reasoning | Mar 2026 | Modal logic, neurosymbolic, reasoning | [[file:papers/2603.04019.pdf]] |
|
|
|
|
* Related Neuromorphic Architecture Papers
|
|
|
|
| arXiv ID | Title | Date | Keywords | File |
|
|
|----------|-------|------|----------|------|
|
|
| 2604.04605 | Benchmarking Neuromorphic AI Processors | Apr 2026 | Neuromorphic, benchmarking, hardware | (not yet downloaded) |
|
|
| 2604.21924 | Spiking Neural Network Optimization | Apr 2026 | SNN, optimization, neuromorphic | (not yet downloaded) |
|
|
|
|
* How the Monthly Update Works
|
|
|
|
A monthly cron job (set on 2026-05-27) runs on the 1st of each month:
|
|
|
|
1. Queries arXiv API for new papers with keywords: neurosymbolic, neural+symbolic+reasoning, LLM+verification, neural+theorem+proving
|
|
2. Filters by the current month's submissions
|
|
3. Downloads PDFs of relevant papers
|
|
4. Updates this index
|
|
5. Commits and pushes the brain repo
|