python-stdlib

A comprehensive Python learning repository!Easy reading of learning documents:

GenPark AI Agent Skill - Belief revision logic engine (AGM postulates) detecting factual and logical contradictions, pruning obsolete beliefs, and preserving consistent world states.

GenPark AI Agent Skill - Pure Python parser converting Planning Domain Definition Language (PDDL 2.1) domains, action schemas, and problem goals into structured JSON AST objects.

GenPark AI Agent Skill - Computes Personalized PageRank (PPR) over agent memory graphs for context-sensitive entity relevance and associative recall.

GenPark AI Agent Skill - Dynamically synthesizes and evaluates runtime assertions, pre/post-conditions, and state invariants to detect data corruption before crashes occur.

GenPark AI Agent Skill - Resolves and fuses fragmented entity mentions into unified canonical nodes using Jaro-Winkler string similarity and connected component clustering.

GenPark AI Agent Skill - Elastic Weight Consolidation (EWC) engine calculating Fisher Information Matrix diagonal penalties to prevent catastrophic forgetting during sequential task learning.

GenPark AI Agent Skill - Anti-entropy gossip protocol and epidemic rumor-spreading state synchronizer propagating shared knowledge across dynamic agent swarms.

GenPark AI Agent Skill - Linear Temporal Logic (LTL) symbolic model checker verifying safety (G), liveness (F), and response (G(p -> Fq)) across finite state transition graphs.

GenPark AI Agent Skill - Automated program repair (APR) engine mutating Python ASTs, applying template-driven bug fixes, and validating candidate patches.

GenPark AI Agent Skill - Mixture-of-Agents (MoA) multi-layer aggregator synthesizing diverse candidate proposals from heterogeneous sub-agents into high-consensus outputs.

GenPark AI Agent Skill - Simple Temporal Network (STN) constraint solver checking temporal consistency, calculating earliest/latest event bounds, and propagating deadlines via Floyd-Warshall.

GenPark AI Agent Skill - Gradient Episodic Memory (GEM / A-GEM) projection engine constraining parameter updates to prevent interference with past task gradients.

GenPark AI Agent Skill - Post-processing confidence calibration using temperature scaling, expected calibration error (ECE), and Brier score evaluation.

GenPark AI Agent Skill - Resolves and fuses fragmented entity mentions into unified canonical nodes using Jaro-Winkler string similarity and connected component clustering.

GenPark AI Agent Skill - Detects LLM hallucinations and confabulations by clustering sampled responses into semantic equivalence classes and computing semantic entropy.

GenPark AI Agent Skill - Multi-tier model cascading router dynamically selecting optimal models (e.g. Small vs Medium vs Large) based on task complexity, cost budgets, and SLA constraints.

GenPark AI Agent Skill - Direct Preference Optimization (DPO) implicit reward calculation, reference policy log-ratio tracking, and pairwise preference loss evaluation.

GenPark AI Agent Skill - Fast modularity community detection algorithm partitioning large agent memory graphs into coherent thematic subgraphs.

GenPark AI Agent Skill - Distribution-free conformal prediction sets with rigorous marginal coverage guarantees, calibrated non-conformity scores, and split conformal inference.