Attribution Python Packages

cffconvert

Command line program to validate and convert CITATION.cff files.

channelattribution

Markov Model for Online Multi-Channel Attribution

zennit

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

grift-cli

Deterministic, local-only engineering evidence from git history — not a skill score

vernier-scale

Measure meaning by perturbing text and watching a calibrated probability move. Ablation attribution over TypeSafe's Jev, reported against a measured noise floor.

ai-citation-sdk

The AI Architecture for Content Transparency And Attribution (AIACTA) Framework: Implementation Specifications for Publisher Visibility & Attribution Standards. Open Specification for AI Content Transparency and Attribution.

agent-thanks

A consent-first CLI that detects and stars open-source repositories meaningfully used during AI-assisted coding.

ppar

Portfolio performance attribution, contribution, and ex-post risk analytics.

jev-why

Causal attribution and calibration for TypeSafe Jev decisions. Jev tells you what it decided; jev-why tells you why, and whether you should believe it.

mbuzz

Server-side multi-touch attribution for Python. Flask middleware, framework-agnostic core, no ad-blocker blind spots

openanchor

Token intelligence middleware for multi-provider LLM usage. 6D attribution, pattern detection, recommendations, OTEL export. Helicone alternative.

humor-mcp

MCP server over a local humor corpus that credits every line it returns

zennit-crp

An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization

atrib

Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.

git-reattribute

Replace bad Git identities in history, or block them before they land — with backups, verification, a pre-commit hook, and a GitHub Action.

llm-attributor

LLM Attributor: Attribute LLM's Generated Text to Training Data

markov-model-attribution

A PoC for a fractional attribution model leveraging first order Markov Chains.

jatoolbox

Repositório com funções, bibliotecas e notebooks para auxiliar o processo de análise de jornadas utilizado em projetos DP6

context-cite

Attribute (or cite) statements generated by LLMs back to in-context information.

omni-proof

Open-source causal-multimodal engine for creative attribution. Answers why a creative works — not just which one performed better — using Gemini Embedding 2, DoWhy, and EconML.

steerling

Interpretable Causal Diffusion Language Models

flashtrace

Efficient multi-token attribution for reasoning language models — Python package, CLI, and HTML token traces

anchorcite

Anchor AI-generated claims to the exact supporting sentences in their cited sources, with offsets and entailment scores.

hommmer

A simple Marketing Mix Modeling library for Python