{
  "schema_version": "1.0.0",
  "rubric_version": "1.0",
  "license": "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)",
  "record": {
    "id": "K-0001",
    "slug": "prover",
    "title": "Prover",
    "aliases": [],
    "status": "draft",
    "last_reviewed": "2026-09-23",
    "review_interval_days": 90,
    "steward": null,
    "provenance": {
      "drafted_by": "ai",
      "reviewed_by": []
    },
    "risk_flags": [],
    "flags": [],
    "one_liner": "The party that makes a claim about its own AI hardware, models or workloads and supplies the evidence a verifier checks.",
    "sources": [
      {
        "source": "S-1606",
        "supports": "a prover tries to convince a verifier that a statement is true",
        "locator": "p. 1"
      },
      {
        "source": "S-0004",
        "supports": "Prover defined as a state claiming to demonstrate its compliance with an agreement",
        "locator": "p. 18, fn. 20"
      },
      {
        "source": "S-0029",
        "supports": "Prover as an ML developer or state, modelled as a covert adversary; unlimited physical access can undermine attestation and signed-firmware enforcement; verifier re-runs training segments from reported checkpoints and data batches",
        "locator": "§2; §3.1; §5.1"
      },
      {
        "source": "S-0002",
        "supports": "Prover may be a private institution or a government constraining companies in its territory",
        "locator": "§3.1"
      },
      {
        "source": "S-1603",
        "supports": "Attester role: a device whose evidence is appraised to infer how far it is trustworthy",
        "locator": "§4 Terminology"
      },
      {
        "source": "S-0023",
        "supports": "proof that an output came from running the model, without revealing its parameters",
        "locator": "abstract"
      }
    ],
    "related": [
      "K-0002",
      "K-0004",
      "K-0018",
      "K-0003"
    ],
    "type": "concept",
    "url": "https://trustbutveri.fyi/concepts/prover/",
    "source_file": "content/concepts/prover.md",
    "flags_all": [
      "ai-drafted"
    ],
    "body_markdown": "A prover is the party that asserts a claim, such as compliance with an agreement, and tries to convince a [[K-0002|verifier]] that it is true [[S-1606]] [[S-0004]].\n\nIn AI verification the prover may be a developer, another private institution or a state; under an international agreement it may be a government that constrains companies within its territory [[S-0029]] [[S-0002]]. The prover usually owns and physically controls the hardware being checked, and Shavit notes that unlimited physical access could undermine a chip's attestation and signed-firmware protections [[S-0029]]. He models the prover as a covert adversary that breaks the rules only if it expects to avoid detection [[S-0029]]. In [[K-0004|remote attestation]] the corresponding role is the attester, a device whose evidence is appraised to judge how far it can be trusted [[S-1603]].\n\nWhat the prover supplies depends on the mechanism:\n- In [[M-0006|proof-of-learning]], it reports checkpoints and data batches, so that the verifier can re-run segments of training [[S-0029]].\n- In [[M-0004|zero-knowledge proofs of inference]], it generates a proof that an output came from running its model, without revealing the weights [[S-0023]].\n- In [[M-0008|TEE remote attestation]], its hardware produces signed evidence about the software it runs [[S-1603]].",
    "body_text": "A prover is the party that asserts a claim, such as compliance with an agreement, and tries to convince a verifier that it is true [S-1606] [S-0004]. In AI verification the prover may be a developer, another private institution or a state; under an international agreement it may be a government that constrains companies within its territory [S-0029] [S-0002]. The prover usually owns and physically controls the hardware being checked, and Shavit notes that unlimited physical access could undermine a chip's attestation and signed-firmware protections [S-0029]. He models the prover as a covert adversary that breaks the rules only if it expects to avoid detection [S-0029]. In remote attestation the corresponding role is the attester, a device whose evidence is appraised to judge how far it can be trusted [S-1603]. What the prover supplies depends on the mechanism: - In proof-of-learning, it reports checkpoints and data batches, so that the verifier can re-run segments of training [S-0029]. - In zero-knowledge proofs of inference, it generates a proof that an output came from running its model, without revealing the weights [S-0023]. - In TEE remote attestation, its hardware produces signed evidence about the software it runs [S-1603].",
    "referenced_by": [
      {
        "id": "M-0025",
        "title": "Confidential multi-party verification",
        "url": "https://trustbutveri.fyi/mechanisms/confidential-multi-party-verification/"
      },
      {
        "id": "M-0015",
        "title": "Memory wiping and proofs of secure erasure",
        "url": "https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/"
      },
      {
        "id": "M-0013",
        "title": "Network taps and certifiers",
        "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/"
      },
      {
        "id": "M-0006",
        "title": "Proof-of-learning and training-transcript verification",
        "url": "https://trustbutveri.fyi/mechanisms/proof-of-learning/"
      },
      {
        "id": "M-0023",
        "title": "Safeguard attestation",
        "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/"
      },
      {
        "id": "M-0001",
        "title": "Sampled inference recomputation",
        "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/"
      },
      {
        "id": "M-0008",
        "title": "TEE remote attestation for AI workloads",
        "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/"
      },
      {
        "id": "M-0016",
        "title": "Timed challenge-response and memory-occupation challenges",
        "url": "https://trustbutveri.fyi/mechanisms/timed-challenge-response/"
      },
      {
        "id": "M-0004",
        "title": "Zero-knowledge proofs of inference",
        "url": "https://trustbutveri.fyi/mechanisms/zk-proofs-of-inference/"
      },
      {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      {
        "id": "I-0003",
        "title": "zkLLM",
        "url": "https://trustbutveri.fyi/implementations/zkllm/"
      },
      {
        "id": "K-0012",
        "title": "Proof of space",
        "url": "https://trustbutveri.fyi/concepts/proof-of-space/"
      },
      {
        "id": "K-0011",
        "title": "Proof of (useful) work",
        "url": "https://trustbutveri.fyi/concepts/proof-of-useful-work/"
      },
      {
        "id": "K-0018",
        "title": "Threat model",
        "url": "https://trustbutveri.fyi/concepts/threat-model/"
      },
      {
        "id": "K-0016",
        "title": "Undeclared compute",
        "url": "https://trustbutveri.fyi/concepts/undeclared-compute/"
      },
      {
        "id": "K-0002",
        "title": "Verifier",
        "url": "https://trustbutveri.fyi/concepts/verifier/"
      },
      {
        "id": "K-0010",
        "title": "Zero-knowledge proof",
        "url": "https://trustbutveri.fyi/concepts/zero-knowledge-proof/"
      },
      {
        "id": "O-0205",
        "title": "Oxford Martin AI Governance Initiative",
        "url": "https://trustbutveri.fyi/organizations/oxford-martin-ai-governance-initiative/"
      }
    ]
  }
}