# From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference

arXiv: https://arxiv.org/abs/2606.11207 · HTML: https://mlsanity.com/paper/2606.11207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 24 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 3 of 3)

- [Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers](https://mlsanity.com/paper/2012.08777/) (2020)
- [Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models](https://mlsanity.com/paper/2604.12390/) (2026)
- [Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation](https://mlsanity.com/paper/2604.19777/) (2026)

## Abstract (arXiv)

We present SemantiClean, a modular framework for extracting structured semantic signals from e-commerce session data and driving pluggable inference targets including purchase intent, customer segmentation, and product affinity through a shared element library. Unlike conventional end-to-end predictors that optimise solely for accuracy, SemantiClean prioritises auditability, structural governance, and sigma=0 reproducibility, explicitly trading marginal predictive gains for element-level transparency and defensible decision trails. Built upon the Online Shoppers Purchasing Intention (OSPI) dataset, the framework organises twenty-four behavioural elements into a four-layer architecture (Functional, Interaction, Systemic, Contextual) and enforces signal quality through three anti-inflation mechanisms: RedundancyGroup contribution caps, TieredPenaltyCalculator bias penalties, and AdaptiveConstraintMode cold-start protection.This report introduces the LLM-Integrated Semantic Inference Engine, a fully implemented two-phase LLM-driven inference architecture that leverages complete element metadata at inference time. All quantitative results reported herein are produced by this engine. Deterministic engine outputs remain fully reproducible (sigma=0); LLM-dependent results (E8, E10) are subject to controlled output variability under fixed provider/model/temperature settings. The gender inference target remains non-functional in the current implementation and is excluded from all quantitative results.