Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs

2026-05-07 · Gregory Magarshak arxiv

We present Grokers, an architecture for building persistent, structured comprehension of typed knowledge graphs through bottom-up inductive traversal of dependency subgraphs. Unlike retrieval-augmented generation (RAG), which pays full comprehension cost at every query, Grokers pushes intelligence to write time: autonomous Groker agents analyze nodes in a typed stream graph, extract structured attributes via governed language model (LM) calls, and inductively compose that understanding upward through dependency relations, writing enriched typed attributes that serve all future queries at zero additional LM cost. We prove three formal properties: (1) the Byte-Identity Theorem, establishing that context blocks assembled from a transactionally-maintained denormalization index are byte-identical across LM turns between semantic changes, enabling KV-cache hit rates approaching 100%; (2) the Accumulation Monotonicity Theorem, establishing that the fraction of interactions resolved without LM calls is non-decreasing in the number of completed interactions under a governed wisdom library growth protocol; and (3) the Dual-Traversal Ordering Theorem, establishing that top-down generation and bottom-up comprehension are the unique correct traversal orderings for their respective tasks over a dependency DAG, and that their composition closes into a complete generation-comprehension cycle. We further present a deterministic alternative to embedding-based semantic search, with a synonym caching protocol whose LM fallback rate converges to zero for finite-vocabulary domains. A reference implementation is provided in the open-source Qbix / Safebox / Safebots stack.

📄 PDF Abstract BibTeX arXiv:2606.00050

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Preprocessing in Inductive Logic Programming

2021-12-21 · Brad Hunter

Inductive logic programming is a type of machine learning in which logic programs are learned from examples. This learning typically occurs relative to some background knowledge provided as a logic program. This disserta…

Inductive logic programming

Learning Object-Centric Representation via Reverse Hierarchy Guidance

2024-05-17 · Junhong Zou, Xiangyu Zhu, Zhaoxiang Zhang, Zhen Lei

Object-Centric Learning (OCL) seeks to enable Neural Networks to identify individual objects in visual scenes, which is crucial for interpretable visual comprehension and reasoning. Most existing OCL models adopt auto-en…

Inductive Bias Object

Modeling Bottom-up Information Quality during Language Processing

2025-09-21 · Cui Ding, Yanning Yin, Lena A. Jäger, Ethan Gotlieb Wilcox arxiv

Contemporary theories model language processing as integrating both top-down expectations and bottom-up inputs. One major prediction of such models is that the quality of the bottom-up inputs modulates ease of processing…

ISAAQ -- Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention

2020-10-01 · Jose Manuel Gomez-Perez, Raul Ortega

Textbook Question Answering is a complex task in the intersection of Machine Comprehension and Visual Question Answering that requires reasoning with multimodal information from text and diagrams. For the first time, thi…

Multiple-choice Question Answering Reading Comprehension Visual Question Answering+1

ISAAQ - Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention

2020-11-01 · EMNLP 2020 11 · Jose Manuel Gomez-Perez, Ra{\'u}l Ortega