Viva
The Viva Assessment Standard

How a Viva verdict is produced, checked, and verified

Every figure Viva publishes — a session verdict, a credential, a skill tag — is produced by the closed loop described on this page. This document is the citable reference for schools, admissions offices, and employers.

Version 1.0 · July 2026

01The closed loop

  1. 1
    Submission intake
    The student's own work (essay, report, code, poster) is ingested and content-extracted with quality gates.
  2. 2
    Forensic pre-read
    An AI examiner maps the submission: claims made, evidence used, places where a non-author would fail.
  3. 3
    Personalized question bank
    Questions are generated from the submission itself — no generic quizzes. Teacher custom questions are asked verbatim.
  4. 4
    Live adaptive oral defense
    A real-time voice interview. Follow-ups adapt to each answer; reading aloud and coached answers alter the questioning.
  5. 5
    Identity & integrity checks
    Voiceprint match against the student's enrolled baseline, visual probes, focus monitoring, and coaching detection run during the session.
  6. 6
    Multi-dimensional grading
    The transcript is scored for Understanding and Authenticity, with fairness guardrails. Scores are suggestions a teacher can override.
  7. 7
    Sealed record
    The session becomes a tamper-evident record; aggregates can be issued as signed, verifiable credentials.

02What is scored

Understanding

Can the student explain the why behind their own work — reasoning, implications, trade-offs — under live follow-up questioning?

Authenticity

Is the oral account consistent with the written submission? Contradictions, unfamiliarity with one's own terms, and fabricated process memories lower it.

Results are expressed in four tiers — Excellent, Strong, Proficient, Developing. Numeric scores exist for teachers; every AI-suggested grade is teacher-overridable, and schools may hide numbers entirely.

03The integrity stack

Voiceprint verification · Speaker embedding compared against the student's enrolled voice baseline, per language, across the whole session.
Visual probes · Session-specific images the student must discuss — unanswerable by an off-screen helper who cannot see them.
Focus & camera checks · Optional tab-switch monitoring and on-device camera analysis (no biometric images leave the browser).
Coaching detection · Speech-pattern divergence from the student's own baseline flags real-time AI or human coaching.
Fairness guardrails · Accent and ASR variants of a student's own terms are never treated as unfamiliarity; approved accommodations suppress the related signals.

04Reliability: the grading council

Selected interviews are independently re-scored by two additional AI models from different providers, blind to the original grade. An interview is selected when it is flagged for review, sits near a grade boundary, belongs to a teacher-designated high-stakes assessment, or when a teacher requests a check on demand.

Bracketing consensus — The independent models sit on either side of the primary grader by design. When the primary grade falls between them, the grade is corroborated.
Directional signal — When both independent models land on the same side, the report says so — "second reads lean higher / lower" — an actionable review signal, never an automatic change.
Advisory only — The council never alters a stored grade. Teachers keep final judgment.

05Verifiable credentials

Students may issue two kinds of credentials from their verified record — a Subject Credential (one class over a term) and a Communication & Reasoning Profile (cross-subject). Both are aggregates only: no transcripts, no per-assignment scores.

Earned, not claimed

A credential can only be issued from completed, integrity-checked oral defenses. No record, no credential.

Signed

Each credential's payload is signed (HMAC-SHA256). Any alteration fails verification.

Student-owned

The student issues it, shares it by unguessable link, and can revoke it at any time. Reissuing keeps the same link.

Skill tags with evidence

Skills shown on a profile carry an evidence count — how many separate live defenses demonstrated that skill.

06Verification API for institutions

Any institution can verify a credential live — no account, no PDF trust:

GET https://www.vivaproof.com/api/credentials/verify?id=<credential-id>

{
  "valid": true,
  "reason": "ok",
  "kind": "voice_profile",
  "student_name": "…",
  "school_name": "…",
  "interviews": 12,
  "issued_at": "2026-07-05T…",
  "signature_sha256": "…"
}

The response reports validity, revocation, the signature, issue dates, and the attested aggregates. A tampered or revoked credential fails immediately.

07Data commitments