Companion Addendum CP-2: Learned Intent, Observer Contamination, and Fail-Closed Gating in Gridworld Alignment Regularizers

Companion Addendum CP-2 to "Topological Ethics: A Geometric Framing for Alignment Regularizers" (doi: 10.5281/zenodo.23842536) and "Topological Ethics Technical Companion" (doi: 10.5281/zenodo.23842862). This report presents three pre-registered gridworld experiments (Experiments 5, 5b, and 5c; 20 seeds per setting) testing what happens when an oracle schedule forecast is replaced by an online empirical Markov intent detector under stochastic human dwell (p_leave = 0.35) and optional sensor noise (0.00, 0.10, 0.25). The experiments isolate fail-open detector collapse, reflexive observer contamination during agent-obstructed corridor steps, noise-induced threshold dilution, and an undisturbed-data blind spot in offline clean training, showing how corridor-masked online updates and fail-closed gating restore cooperative doorway timing. All code, diagnostic utilities, statistical checks, and per-seed results are archived in Topological Ethics: Gridworld Experiments v1.2 (doi: 10.5281/zenodo.243556 87).

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24355832
Primary Topic
Ethics and Social Impacts of AI
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Companion Addendum CP-2: Learned Intent, Observer Contamination, and Fail-Closed Gating in Gridworld Alignment Regularizers

David Porbeck
4 links
Zenodo (CERN European Organization for Nuclear Research)
Ethics and Social Impacts of AI
preprint

Companion Addendum CP-2: Learned Intent, Observer Contamination, and Fail-Closed Gating in Gridworld Alignment Regularizers

David Porbeck
preprint en

Abstract

Companion Addendum CP-2 to "Topological Ethics: A Geometric Framing for Alignment Regularizers" (doi: 10.5281/zenodo.23842536) and "Topological Ethics Technical Companion" (doi: 10.5281/zenodo.23842862). This report presents three pre-registered gridworld experiments (Experiments 5, 5b, and 5c; 20 seeds per setting) testing what happens when an oracle schedule forecast is replaced by an online empirical Markov intent detector under stochastic human dwell (p_leave = 0.35) and optional sensor noise (0.00, 0.10, 0.25). The experiments isolate fail-open detector collapse, reflexive observer contamination during agent-obstructed corridor steps, noise-induced threshold dilution, and an undisturbed-data blind spot in offline clean training, showing how corridor-masked online updates and fail-closed gating restore cooperative doorway timing. All code, diagnostic utilities, statistical checks, and per-seed results are archived in Topological Ethics: Gridworld Experiments v1.2 (doi: 10.5281/zenodo.243556 87).

Zenodo (CERN European Organization for Nuclear Research)
Ethics and Social Impacts of AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon