Pith. sign in

REVIEW 15 cited by

Logical Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.13155 v1 pith:3VA3CYGU submitted 2020-06-23 cs.AI cs.LGcs.LO

Logical Neural Networks

classification cs.AI cs.LGcs.LO
keywords knowledgelogiclogicalyieldinglearningneuralnovelreasoning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning). Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omnidirectional rather than focused on predefined target variables, and corresponds to logical reasoning, including classical first-order logic theorem proving as a special case. The model is end-to-end differentiable, and learning minimizes a novel loss function capturing logical contradiction, yielding resilience to inconsistent knowledge. It also enables the open-world assumption by maintaining bounds on truth values which can have probabilistic semantics, yielding resilience to incomplete knowledge.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

    cs.CL 2026-06 unverdicted novelty 7.0

    A parameter-neutral fuzzy-logic FFN augmented with self-forgetting quantifiers produces legible grammatical-licensing detectors while matching baseline perplexity on OpenWebText.

  2. First-Order Temporal Logic Tensor Networks

    cs.AI 2026-06 unverdicted novelty 7.0

    FOT-LTN extends Logic Tensor Networks by integrating first-order linear temporal logic syntax with fuzzy differentiable semantics, supporting temporal operators and quantifiers, and shows improved performance over neu...

  3. Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions

    cs.LG 2026-05 unverdicted novelty 7.0

    Outcome-fair credit models often exhibit hidden procedural bias through inconsistent reasoning across groups, which the CEC framework mitigates by enforcing consistent feature attributions via counterfactuals.

  4. Training, Reading, and Editing Legible Transformers

    cs.LG 2026-07 conditional novelty 6.5

    A variance-floor objective plus learned operator gates produce an end-to-end legible transformer whose crisp units are 50–184× more local to edit and can be reshaped from fan-out to fan-in circuits without quality loss.

  5. AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling

    cs.CR 2026-06 unverdicted novelty 6.0

    AttackPathGNN introduces a State Interference Graph and conjunction pooling inside a GNN to detect cross-function vulnerabilities in Solidity contracts, reporting 92.3% F1 on SmartBugs Wild.

  6. Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI

    cs.AI 2026-05 unverdicted novelty 6.0

    A conditional invariance framework defines explanation fairness as explanations being statistically independent of protected attributes given task-relevant features, unifying existing metrics and enabling procedural b...

  7. Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA

    cs.AI 2026-05 unverdicted novelty 6.0

    Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks whe...

  8. Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants

    cs.AI 2026-04 unverdicted novelty 6.0

    A symbolic protocol operationalizes Peirce's tripartite reasoning for LLMs using five algebraic invariants including a Weakest Link bound to enforce logical consistency and prevent weak premises from supporting strong...

  9. THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture

    cs.LG 2026-04 conditional novelty 6.0

    A modular neural architecture learns complete K3 logic and shows uncertainty-verdict asymmetric propagation plus a reliability spectrum for long discretized composition.

  10. THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture

    cs.LG 2026-04 unverdicted novelty 6.0

    A modular neural architecture learns complete Kleene three-valued logic from task data and exhibits uncertainty-preserving propagation plus superior 500-step generalization under Gumbel-softmax training where flat MLP...

  11. Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration

    cs.LG 2025-09 unverdicted novelty 6.0

    LoH adds a learnable choice operator to propositional logic, compiles formulas to differentiable graphs via fuzzy logic, subsumes prior NeSy models, and supports discretization to Boolean functions via the Gödel trick.

  12. Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines

    cs.LG 2026-05 unverdicted novelty 5.0

    AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.

  13. Enabling topography-resolving structural dynamic contact simulation

    cs.CE 2026-03 unverdicted novelty 5.0

    A multi-scale FE–BEM method is extended to dynamic time integration and Harmonic Balance, enabling topography-resolved contact simulation of bolted joints and load-history-dependent equilibria on the S4 Beam.

  14. Overmind NSA: A Unified Neuro-Symbolic Computing Architecture with Approximate Nonlinear Activations and Preemptive Memory Bypass

    cs.AR 2026-04 unverdicted novelty 4.0

    Overmind is a neuro-symbolic architecture that uses adjustable Padé approximations and memory bypass to deliver 8.1 TOPS/W efficiency and 410 GOPS throughput on mixed workloads with minimal accuracy loss.

  15. Auto-Relational Reasoning

    cs.AI 2026-04 unverdicted novelty 3.0

    A system using auto-relational reasoning solves IQ test problems at 98.03% rate without any prior knowledge, reaching top 1% human performance.