# 4.3 Behavior Weights Behavior Weights represent the quantitative parameters that govern how a pet acts across different scenarios. In PetVerse, behaviors are not scripted as fixed decision trees; instead, they are parameterized through models whose outputs are influenced by context, history, and the pet’s internal configuration. Behavior Weights are the bridge between high-level personality descriptors and concrete actions, translating “curious” or “calm” into probabilities and priorities within the decision-making engine. These weights are derived from a combination of AI model training, user customization, and in-system learning from past interactions. On-chain, Behavior Weights are not stored as full model weights, but as compressed references and configuration vectors that instruct the off-chain behavior engine how to load and configure the appropriate models. The PET Identity Contract stores identifiers and hashed configuration payloads that define the behavior profile, ensuring traceability and auditability of behavioral evolution. This allows developers and users to verify that a pet’s behavior profile has not been arbitrarily altered without on-chain confirmation. Over time, Behavior Weights can be updated via explicit transactions, representing training events, upgrades, or personality shifts approved by the owner. * Behavior Weights capture: * Action tendencies (e.g., playful vs reserved) * Response sensitivity to user inputs and moods * Timing and pacing of reactions * Context-specific patterns (e.g., day vs night behavior) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.petverse.vip/4.-digital-identity-layer/4.3-behavior-weights.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.