Alexander Bering

Structurally Inseparable False Triggers in Movement-Based Early Detection of Physical Hazards in Crowds, and a Posture-Proxy Method for Measuring Them

Background. The research prototype for early hazard detection in crowds marks present, observable physical movement; it does not identify persons, infer intent, or predict future offending (working definition, not yet externally confirmed). Problem. Where conduct linked to protec...

Measuring What Retrieval Misses: Probe-Calibrated Recall and Absence Estimation Without Assessing the Unretrieved Segment

Deployed retrieval systems routinely need two numbers they cannot currently obtain: an estimate of the relevant material they failed to retrieve, and a calibrated statement of what a run of failed searches does — and does not — imply about absence. The measurement tools that exis...

Do LLM Agents Use Visible Age Signals? A Preregistered Measurement of Judgment, Damage, and Enforcement Need under Shared-State Visibility Delay

Preregistration note - protocol fixed before any data collection. No results are included. Server-side staleness enforcement in multi-agent LLM systems - write-time rejection of stale views, temporal supersession, bounded-staleness invariants - rests on one unmeasured assumption:...

Measuring What Retrieval Misses: Probe-Calibrated Recall and Absence Estimation Without Assessing the Unretrieved Segment

Deployed retrieval systems routinely need two numbers they cannot currently obtain: an estimate of the relevant material they failed to retrieve, and a calibrated statement of what a run of failed searches does - and does not - imply about absence. The measurement tools that exis...

Belief-MVCC: A Coherence and Transaction Layer for Shared Agent Memory

We present a coherent, transactional, semantic shared-memory kernel through which specialised AI cores read and write while staying consistent. The design combines belief revision (AGM; Darwiche–Pearl; Konieczny–Pino Pérez), distributed-systems consistency (causal+, RedBlue, BSP)...

Semantic Resurrection Bounds Verifiable Deletion: A Measured Characterization of the Identity Ceiling in Agent-Memory Forgetting

Cryptographically verifiable deletion in agent memory is an active area: dependency-aware unlearning, cascade repair, and crypto-shredding with deletion receipts are all established. This note addresses a narrower question that survives that prior art: what bounds verifiable dele...

Semantic Resurrection Bounds Verifiable Deletion: A Measured Characterization of the Identity Ceiling in Agent-Memory Forgetting

Cryptographically verifiable deletion in agent memory is an active area: dependency-aware unlearning, cascade repair, and crypto-shredding with deletion receipts are all established. This note addresses a narrower question that survives that prior art: what bounds verifiable dele...

Spontaneous Near-Criticality and Type-Graded Robustness in a Four-Atom Conway Cellular Automaton

A minimal variant of Conway's Game of Life, extended by four atom types and a 4x4 inter-type interaction matrix, spontaneously lands inside the Wilting-Priesemann near-critical band on 100/100 nominal trials across five structured presets, while a 20-random-matrix x 5-seed baseli...

Spontaneous Near-Criticality and Type-Graded Robustness in a Four-Atom Conway Cellular Automaton

A minimal variant of Conway's Game of Life, extended by four atom types and a 4x4 inter-type interaction matrix, spontaneously lands inside the Wilting-Priesemann near-critical band on 100/100 nominal trials across five structured presets, while a 20-random-matrix x 5-seed baseli...