{"slug": "an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions", "title": "An open, model-agnostic \"interaction card\": verifiable provenance for AI decisions", "summary": "The author of an open, work-in-progress format called \"Causal Seal\" proposes a model-agnostic \"interaction card\" that binds a SHA-256 fingerprint to an AI output, its causal parameters (model identity, constraints, context, timestamp), and the moment of emission, enabling verification without access to the model. The format is open (CC BY 4.0), vendor-neutral, and available via `pip install causal-seal`, with a browser verifier, aiming to complement model cards by documenting individual decisions rather than the model itself.", "body_md": "I’m the author of an open, work-in-progress format for the provenance of AI\n\ndecisions, and I’d love feedback from this community — model cards are, in a\n\nsense, the ancestor of what I’m building, and HF champions open, model-agnostic\n\ndocumentation.\n\n**The gap.** Model cards document the *model*. There’s still no open way to\n\nverify *how a specific output was produced*.\n\n**The idea.** A “Causal Seal” attaches to a single output a small record that\n\nbinds — into a SHA-256 fingerprint — the output, the causal parameters that\n\ngoverned its generation (model identity, constraints, context, timestamp), and\n\nthe moment of emission. Anyone can verify it with **no access to the model** or\n\nany private system. It’s open (CC BY 4.0) and privileges no vendor. Think of it\n\nas the per-decision, verifiable counterpart to a model card — an “interaction\n\ncard.” Complementary, not competing.\n\n**What already exists (public, reproducible):**\n\n`pip install causal-seal`\n\n) and a browser verifier**My questions:**\n\nAny feedback is welcome — this is early, single-maintainer, open work.", "url": "https://wpnews.pro/news/an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions", "canonical_source": "https://discuss.huggingface.co/t/an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions/178614#post_1", "published_at": "2026-08-12 19:00:52+00:00", "updated_at": "2026-08-12 19:14:00.190984+00:00", "lang": "en", "topics": ["ai-ethics", "ai-tools", "ai-research"], "entities": ["Causal Seal", "Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions", "markdown": "https://wpnews.pro/news/an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions.md", "text": "https://wpnews.pro/news/an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions.txt", "jsonld": "https://wpnews.pro/news/an-open-model-agnostic-interaction-card-verifiable-provenance-for-ai-decisions.jsonld"}}