ABO — Ambiguity-Bearing Output
Plain English. An AI output that looks correct on its own but causes problems when downstream systems interpret it differently than intended.
Formal. An output y is an ABO if: (1) y belongs to the set of locally valid outputs; (2) deviation δ ≠ 0 from the nominal output; (3) at least one downstream system produces a different decision. (Def. 3.4)
Example: An LLM risk assessment says "moderate risk; approve with enhanced verification." It passes local checks but is discretised into a different risk band by the downstream rules engine.
Industry. Often misdiagnosed as unavoidable "LLM non-determinism" or an inherent flaw of probabilistic models.
Related: SLV, Semantically Open, Discretisation Jump.
ISE — Interconnected Systems Environment
Plain English. A formal model of an organisation's AI infrastructure as a graph: nodes are systems, edges are boundaries between them.
Formal. A directed graph G = (V, E) where V = systems, E = corridors. Each corridor has a transformation operator. (§3.1)
Example: A 4-node ISE: LLM risk assessor → rules engine → decision system → feedback calibrator.
Related: Corridor, CRC, Blast Radius.
ISCIL — Inter-System Coherence & Integrity Layer
Plain English. A containment system monitoring boundaries between systems to detect drift and apply proportional corrections, like an immune system for AI environments.
Formal. Non-intrusive architecture monitoring aggregate boundary telemetry, computing CRS, and applying proportional interventions within CRCs. Validated: 100% default recovery, 6.5% overhead, ~40 timesteps faster detection. (§4)
Example: When CRS elevates in the underwriting cluster, ISCIL applies a blind scalar offset before discretisation and dampens reinforcing feedback.
Related: CRS, CRC, Blast Radius.
SLV — Semantic Latitude Vector
Plain English. The specific direction and magnitude of deviation between an AI output and the ideal output.
Formal. Vector δ = y − y* where y is actual output and y* is nominal. Captures magnitude and direction of semantic deviation. (Def. 3.3)
Example: If nominal is "moderate risk" but AI outputs "moderate risk; approve with enhanced verification," the SLV captures direction (toward approval) and magnitude.
Related: ABO, Semantic Latitude, Discretisation Jump.
CRS — Coherence-Risk Score
Plain English. A number measuring how much a cluster's behaviour is deviating from baseline, based on boundary signals.
Formal. Normalised score from cross-correlated boundary telemetry using rate-of-change z-scores over a sliding window. Detects acceleration, not level shifts. (Def. 4.1)
Example: A CRS of 2.5 means boundary signals are accelerating at 2.5 standard deviations above baseline variability.
Related: ISCIL, CRC.
CRC — Critical Risk Cluster
Plain English. A group of connected systems where ambiguity is actively accumulating above safe thresholds.
Formal. A connected subgraph of the ISE with (1) at least one AI-source node with a semantically open interface and (2) coherence-risk score exceeding the alert threshold for sustained duration. (Def. 4.2)
Example: A cluster containing an LLM underwriter, rules engine, and feedback calibrator forms a CRC when CRS stays elevated.
Related: CRS, Blast Radius, ISCIL.
Corridor
Plain English. A connection between two systems where outputs from one become inputs to the other. This is where ABOs propagate.
Formal. An edge in the ISE graph characterised by a transformation operator T capturing interface mechanisms: schema mapping, thresholding, formatting, truncation, routing. (§3.1)
Example: The connection between an LLM risk assessor and a rules-based categorisation engine is a corridor.
Related: Discretisation Jump, Feedback Reinforcement, ISE.
Discretisation Jump
Plain English. When a small, continuous difference in an AI output becomes a big categorical difference in the next system.
Formal. A property of corridors where T maps continuous inputs to categorical outputs. Small semantic latitude crosses category boundaries. (§3.3)
Example: Risk scores of 0.39 vs 0.37 are indistinguishable to the AI, but a threshold at 0.38 maps them to MEDIUM vs LOW.
Industry. The mechanical root cause of the "AI-Legacy Impedance Mismatch."
Related: Corridor, ABO, SLV.
Feedback Reinforcement
Plain English. When drift feeds back through calibration loops, sustaining deviation long after the original cause stopped.
Formal. A property of feedback corridors where downstream outcomes re-enter upstream calibration, causing the system to sustain the deviated state. Divergence persisted 400 timesteps post-ABO cessation. (§5.3)
Example: Shifted approval rates trigger policy recalibration that adjusts thresholds to accommodate the new rate.
Related: Corridor, Environment Drift, ABO.
Blast Radius
Plain English. How far drift effects can spread from their origin in the system graph.
Formal. The h-hop neighbourhood of a CRC in the ISE graph: the set of downstream systems potentially affected if propagation continues. (Def. 4.3)
Example: A credit scoring cluster's blast radius includes the downstream regulatory reporting system.
Related: CRC, ISE.
Semantically Open Interface
Plain English. A system boundary where the AI can produce multiple valid outputs for the same input, the source of semantic latitude.
Formal. An interface where ∃ input x such that |Y(x)| > 1. AI systems producing NL or probabilistic outputs are the primary source. (Def. 3.2)
Example: A generative AI summarising a financial report: multiple valid summaries exist, each potentially triggering different downstream decisions.
Related: Spec-Closed, Semantic Latitude, ABO.
Spec-Closed Interface
Plain English. A system boundary where exactly one valid output exists per input, with no ambiguity.
Formal. An interface where ∀ input x, |Y(x)| = 1. Classical deterministic systems enforced by schemas and contracts. (Def. 3.1)
Example: An API returning account balance: for any account ID, exactly one correct balance exists.
Industry. The rigid target state that developers attempt to enforce using "semantic contracts."
Related: Semantically Open, Corridor.
Environment-Level Drift
Plain English. When overall system behaviour shifts from intended outcomes, even though no individual component flags an error.
Formal. Progressive divergence between intended and actual aggregate ISE behaviour, driven by accumulation of small semantic deviations across corridors. (§1)
Example: Approval rates shift +0.1pp, invisible to component monitoring, producing 39 excess defaults over 1,200 timesteps.
Industry. Frequently referred to as "semantic drift," "context clash," or downstream "agentic integration complexity."
Related: ABO, Feedback Reinforcement, ISE.
Semantic Latitude
Plain English. The degree to which an AI output could be interpreted differently while still being considered valid.
Formal. The range of outputs satisfying local validity constraints for a given input. Zero for spec-closed; non-zero for semantically open. (Def. 3.3)
Example: "Moderate risk" vs "moderate-to-high risk": the semantic latitude between these may trigger different categorisations.
Related: SLV, Semantically Open, ABO.
Source: Ayada, M. (2026). Propagation of Ambiguity-Bearing Outputs Across ISE. SSRN DOI: 10.2139/ssrn.6383259. Code: github.com/Myr-Aya/ISE_simulator. Archive: Zenodo DOI 10.5281/zenodo.18719967.