Claim text
The literal claim being supported. A grader can read it standalone before chasing the citation.
AI Evidence Format is an open JSON spec for structured citations attached to LLM-generated claims: source URI + type + publisher, span (text-quote / CSS selector / page range), retrieval method + confidence + freshness, content-hash verification, and synthesis role (supporting / contradicting / partial / background).
evidence_version— (travels with the LLM response)Hallucinations get a lot of airtime; untraceable citations get less. An AI tool can cite a real-sounding URL that no longer resolves, or quote text that doesn't appear at the cited location, or paraphrase so loosely that no fact-checker can find the source. AI Evidence Format is the structured artifact that makes each citation independently verifiable.
The literal claim being supported. A grader can read it standalone before chasing the citation.
uri, type (document / webpage / api / book / paper), title, publisher, fetched_at. The minimum auditable identification of where the claim came from.
selector_type ∈ {text_quote, css_selector, fragment_identifier, page_range} with selector_value and optional exact_text. Points at the bytes that support the claim.
method (semantic / keyword / hybrid / direct), confidence, rank, freshness_age_seconds. Disclosure of how the source was found.
content_hash — canonical SHA-256 over the cited bytes. Optional signature. A reviewer can recompute the hash and prove the cited content didn't change after retrieval.
supporting / contradicting / partial / background. Forces the agent to declare how the citation relates to the claim.
evidence_version — must be "0.1"evidence_id — stable identifierclaim_text — the literal claim being supportedsource — URI + type + title + publisher + fetched_atspan — selector_type + value + exact_textretrieval — method + confidence + rank + freshnessverification — canonical content_hash, optional signaturesynthesis_role — supporting / contradicting / partial / background{
"evidence_version": "0.1",
"evidence_id": "ev-2026-05-12-a4f9c1",
"claim_text": "The AEO Protocol defines three pillars: Declare, Discover, and Audit.",
"source": {
"uri": "https://github.com/mizcausevic-dev/aeo-protocol-spec/blob/main/SPEC.md",
"type": "document",
"title": "AEO Protocol v0.1 — Specification",
"publisher": "mizcausevic-dev",
"fetched_at": "2026-05-12T03:45:00Z"
},
"span": {
"selector_type": "text_quote",
"selector_value": "## 3. The three pillars",
"exact_text": "## 3. The three pillars\n\n### 3.1 Declare\n\nThe entity publishes a single JSON document at a fixed path describing itself."
},
"retrieval": { "method": "hybrid", "confidence": 0.93, "rank": 1, "freshness_age_seconds": 90 },
"verification": { "content_hash": "sha256:c7d1f2a3b4c5d6e7f8a9b0c1d2e3f4a5b6c7d8e9f0a1b2c3d4e5f6a7b8c9d0e1" },
"synthesis_role": "supporting"
}
Normative spec, JSON Schema 2020-12, canonical examples. AGPL-3.0 for spec text; implementations unrestricted.
View repo →Unified visualizer for all 10 specs. Auto-detects via evidence_version and renders a procurement-grade view.
34 tools across 8 specs. Drops into Claude Desktop / Cursor / any MCP-compatible client via stdio with one config entry.
View on GitHub →AI Evidence Format is one of ten open JSON specifications in the Kinetic Gain Protocol Suite. Five core specs plus the EdTech trio, the HealthTech extension, and the cross-cutting Incident Card. Front door: suite.kineticgain.com.