Intermediate Representation for the Crucible ML reliability ecosystem
Current section
15 Dependants
Jump to
Current section
15 Dependants
Packages depending on crucible_ir
15 packages-
CrucibleFramework: A thin orchestration layer for experiment pipelines. Provides pipeline execution, stage behaviour, and optional persistence.
Updated 4 months ago
185recent downloads -
Dataset management and caching for AI research benchmarks
Updated 4 months ago
179recent downloads -
Fairness and bias detection library for Elixir AI/ML systems. Provides comprehensive fairness metrics, bias detection algorithms, and mitigation techniques.
Updated 4 months ago
105recent downloads -
Comprehensive benchmarking framework for AI research. Measures latency, throughput, cost, and reliability with percentile analysis and Nx numerical computations.
Updated 4 months ago
97recent downloads -
Explainable AI (XAI) tools for the Crucible framework. Includes LIME implementations, SHAP-like explanations, feature attribution, and model interpretability for local and global explanations.
Updated 4 months ago
80recent downloads -
Model versioning, artifact storage, and lineage tracking for ML pipelines
Updated 4 months ago
77recent downloads -
Structured causal reasoning chain logging for LLMs. Captures decision-making processes with cryptographic verification for transparency and debugging.
Updated 4 months ago
73recent downloads -
Multi-model ensemble prediction with voting strategies for AI reliability. Leverages BEAM parallelism for massively concurrent LLM queries.
Updated 4 months ago
65recent downloads -
Adversarial testing and robustness framework for AI models with 25 attacks (character/word/semantic perturbations, prompt injection, jailbreak, extraction, inversion), defenses (detection/filtering...
Updated 4 months ago
65recent downloads -
Advanced telemetry collection and analysis for AI research
Updated 4 months ago
61recent downloads -
Request hedging for tail latency reduction in distributed systems. Implements Google's 'Tail at Scale' with adaptive strategies. Reduces P99 latency by 75-96%.
Updated 4 months ago
60recent downloads -
Model deployment orchestration with health checking and rollback
Updated 4 months ago
54recent downloads -
52recent downloads
-
Feedback collection, drift detection, and active learning for ML pipelines
Updated 4 months ago
41recent downloads
Checksum
Dependency Config
mix.exs
rebar.config
Gleam
erlang.mk
Package Details
this version
63
yesterday
2
last 7 days
12
all time
455