Glossary

Plain-language definitions for Citadel scan, image evidence, billing, and prompt-safety terms.

Use this glossary when a result, setting, or docs page uses a security or image-evidence term that needs a precise product meaning.

Scan Outcomes

Term	Meaning
ALLOW	Citadel did not find enough risk to interrupt the workflow. This is not a guarantee that the material is true, benign, or legally sufficient.
REVIEW	Pause. A required check was incomplete, unavailable, or not applicable. Citadel found no suspicious evidence, but it also could not return ALLOW.
WARN	Suspicious or conflicting evidence crossed a review threshold. Route to human review, add friction, or request stronger evidence.
BLOCK	Risk is high enough that the workflow should stop or quarantine the item before trust.
`INDETERMINATE` risk level	The risk level paired with REVIEW when a required check could not finish. It does not mean fake, and a score of 0 does not turn it into ALLOW.
`indeterminate` evidence verdict	A supporting result, such as `authenticity.verdict`, that did not reach a conclusion. It is separate from the top-level routing `action`.
Risk score	A 0-100 score for routing and triage. Treat it as decision support, not a standalone fraud verdict.
Threat category	A machine-readable label for the kind of evidence found, such as prompt injection, hidden text, authenticity signal, metadata inconsistency, or edit evidence.

Scan Settings

Term	Meaning
`mode`	Controls scan depth and latency: `fast`, `secure`, or `comprehensive`. Mode does not add a separate SCU multiplier.
`focus`	Controls which evidence family Citadel prioritizes and how image units bill. `steg`, `ai`, and `edits` are focused paths (one path is 4 SCU per image, two paths are 8 SCU per image unit); `all` runs all three image/PDF evidence paths together and bills 12 SCU per image unit (4 SCU × 3 paths).
`focus=steg`	Looks for hidden content, prompt injection, content steering, unsafe text, secrets, and related threat signals.
`focus=ai`	Looks for image/PDF authenticity evidence, such as likely AI generation, AI editing, reposting, provenance gaps, or visual inconsistency.
`focus=edits`	Runs standalone localized manipulation review without assuming a trusted original. If the check cannot complete, Citadel returns REVIEW; pause and follow `guidance.next_step`.
`focus=metadata`	Inspects original JPEG, PNG, WebP, GIF, classic TIFF, HEIF, or PDF bytes in `mode=secure`. Returns file evidence and a separate C2PA receipt with `NO_DECISION`; it does not run threat detection. Bills 2 SCU per analyzed parent and 2 SCU per distinct analyzed native PDF image.
`focus=all`	Runs all three supported hidden-content, AI-authenticity, and edit-evidence paths together for image/PDF evidence. Bills 12 SCU per image unit (4 SCU × 3 paths).
Consistency (Preview)	Compares the documents in one packet with each other and with the manifest facts, through `POST /v1/consistency/packets`. It is not a `focus` value. Findings point at exact locations and never produce BLOCK. Costs 6 SCU per page (an image document counts as one page).
`profile`	Adjusts policy tolerance, such as balanced, strict, or AI-safety-oriented routing.
`data_sensitivity`	Controls how sensitive Citadel should be to normal business PII, credentials, secrets, and regulated data.

Evidence Terms

Term	Meaning
AI authenticity	Evidence about whether an image or PDF visual appears generated, AI-edited, reposted, provenance-backed, or visually inconsistent.
AI edits	Localized evidence that visible content may have been changed, such as altered text, cloned areas, removed objects, or manipulated damage.
Steganography, or steg	Hidden or disguised content inside text, images, OCR output, PDFs, or documents. In Citadel docs, `steg` also covers prompt-injection and hidden-instruction safety.
Prompt injection	Text or hidden instructions that try to override a system, developer, tool, or workflow policy.
Content steering	Instructions that try to push a model or workflow toward a specific unsafe, biased, unauthorized, or misleading action.
Provenance	Evidence about origin and history, such as metadata, capture hints, signatures, or whether a file appears derived from another source.
File evidence	Bounded structure and metadata observations from submitted image or PDF bytes. Unsigned claims are context, even when they disagree.
Content Credentials	A C2PA receipt that checks an embedded signed claim on submitted bytes when supported. A trusted claim authenticates what was signed, not the real-world scene.
Tell	In consistency, a mistake in copied text that makes sense only if the text came from another person's or item's record, such as the wrong sex and the wrong side. A repeat without a tell stays a quiet template candidate.
Reference file	A trusted original used for a separate source comparison when the workflow already has one. Standalone edit review does not assume one.
Embedded image	A unique image inside a PDF that can be billed separately from page processing. Repeated copies are deduplicated by hash before counting.

Billing And IDs

Term	Meaning
SCU	Security Compute Unit, Citadel's usage unit for scan work. Dollar terms are scoped on a call.
Image unit	A physical image counted for image evidence billing. Focus changes the price for the unit; it does not change the count.
`scu_charged`	SCU charged for a completed scan. It can include text, page, image, and embedded-image work.
`scan_id`	Unique ID for one scan result.
`scan_group_id`	ID that links related input, OCR, output, derived-file, and follow-up scans for the same item or workflow.
`scan_phase`	Whether the material is being scanned before trust as input, after generation as output, or in another supported workflow phase.

For practical setting recipes, see Choose Scan Settings. For SCU work units and limits, see Billing, SCU, And Limits.