{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0001,M-0009,M-0002&ready=R2",
  "data_generated": "2026-10-09",
  "definitions": {
    "methodology": "https://trustbutveri.fyi/about/methodology/",
    "readiness": "https://trustbutveri.fyi/about/readiness/",
    "filters": [
      {
        "id": "prover",
        "label": "Prover",
        "question": "How far can the party being checked be trusted?",
        "options": [
          {
            "value": "cooperative",
            "label": "Cooperative"
          },
          {
            "value": "semi-trusted",
            "label": "Semi-trusted"
          },
          {
            "value": "adversarial",
            "label": "Adversarial"
          }
        ],
        "rule": "Keeps mechanisms whose threat model holds against at least this prover. Adversarial is the strongest assumption.",
        "about": "The prover is the party being checked. Semi-trusted designs rely on part of its stack: usually the chip vendor's hardware root of trust, its firmware or counters, or its supply-chain records. Adversarial designs aim to hold even if it cheats wherever the checks allow, within their stated assumptions."
      },
      {
        "id": "onsite",
        "label": "Verifier devices on site",
        "question": "May the verifier install its own hardware at the prover's sites?",
        "options": [
          {
            "value": "no",
            "label": "Not allowed"
          }
        ],
        "rule": "\"Not allowed\" removes mechanisms that need a retrofit device, such as a network tap or a sealed sensor.",
        "about": "Some mechanisms need a device the verifier owns or trusts at the prover's facility, such as a network tap, a bandwidth limiter or a sealed sensor. Choose Not allowed when the setting rules that out. Inspectors are not covered."
      },
      {
        "id": "coop",
        "label": "Prover cooperation",
        "question": "How much must the prover take part?",
        "options": [
          {
            "value": "partial",
            "label": "Partial at most"
          },
          {
            "value": "none",
            "label": "Not required"
          }
        ],
        "rule": "\"Partial at most\" removes mechanisms that need the prover's active participation. \"Not required\" keeps only those that work without it.",
        "about": "Required: the prover takes part, for example by logging requests, producing proofs or opening records. Partial: some access, such as installing a device. Not required: works from outside, such as satellite imagery."
      },
      {
        "id": "chips",
        "label": "Chips",
        "question": "May the proposal depend on new chip designs?",
        "options": [
          {
            "value": "existing",
            "label": "Existing chips only"
          }
        ],
        "rule": "\"Existing chips only\" removes mechanisms that need changes to future chip designs.",
        "about": "New chip features take years to reach a deployed fleet and cover only chips made after they ship. Mechanisms that use shipping features, such as trusted execution environments or performance counters, stay."
      },
      {
        "id": "ready",
        "label": "Minimum development status",
        "question": "Development status",
        "options": [
          {
            "value": "R1",
            "label": "Proposed"
          },
          {
            "value": "R2",
            "label": "Research demonstration"
          },
          {
            "value": "R3",
            "label": "Operational use"
          },
          {
            "value": "R4",
            "label": "Legacy independent-evaluation filter",
            "legacy": true
          }
        ],
        "rule": "Keeps mechanisms whose readiness level is at least this one.",
        "about": "A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws."
      },
      {
        "id": "tested",
        "label": "Attack testing",
        "question": "How hard has each mechanism been attacked in public?",
        "options": [
          {
            "value": "analysis",
            "label": "Published analysis"
          },
          {
            "value": "red-teamed",
            "label": "Red-teamed"
          },
          {
            "value": "independent-red-team",
            "label": "Independent red-team"
          }
        ],
        "rule": "Keeps mechanisms whose strongest published attack testing is at least this.",
        "about": "The strongest published attempt to break the mechanism for its verification use: a security analysis, red-teaming by its developers or collaborators, or a red team independent of them."
      },
      {
        "id": "hide",
        "label": "Keep hidden from the verifier",
        "question": "What must the verifier never see?",
        "options": [
          {
            "value": "weights",
            "label": "Model weights"
          },
          {
            "value": "io",
            "label": "Inputs and outputs"
          },
          {
            "value": "training",
            "label": "Training data"
          }
        ],
        "rule": "Removes mechanisms that show the asset to the verifier. Conditional or unspecified exposure stays with a note and needs checking against the privacy requirement.",
        "about": "Model weights: the checked model's parameters. Inputs and outputs: the requests a deployed model serves and its responses. Training data: what a model was trained on. Each mechanism's exposure is the editors' reading of its record: shown, depends on the design (kept, with a note), hidden, not involved, or unspecified for a selected implementation. Code and configuration are not covered yet."
      }
    ],
    "exposure": "For model weights, inputs and outputs, and training data. This is the editors' reading of each mechanism's record (its threat model, how it works and its limitations), not a field of the record. Shown: the verifier sees it. Depends: on the design or variant, or the verifier sees only samples. Hidden: the verifier sees only commitments, hashes, proofs or results. Not involved: the record does not handle it. Unspecified: the selected implementation has no asset-specific assessment here.",
    "claim_status": {
      "addressed": "A mechanism in the proposal is aimed at this claim and is not excluded by the filters.",
      "partly-addressed": "Only supporting mechanisms, or mechanisms aimed at it that the filters exclude.",
      "unaddressed": "No mechanism in the proposal addresses this claim."
    },
    "finding_classification": {
      "failure": {
        "label": "Known failures",
        "singular": "Known failure",
        "anchor": "known-flaws"
      },
      "scope-limitation": {
        "label": "Scope limitations",
        "singular": "Scope limitation",
        "anchor": "scope-limitations"
      },
      "open-question": {
        "label": "Open questions",
        "singular": "Open question",
        "anchor": "open-questions"
      }
    },
    "finding_scope": "Evidence scope describes where a finding was demonstrated; it does not establish applicability to every implementation in the mechanism family.",
    "claim_finding_scope": "open_critical_findings names active failures on the assessed records; open_critical_context names conditional family failures whose implementation applicability is unassessed.",
    "legacy_status": "The status field retains covered/partial/none for compatibility. It names claim links, never successful verification. Use claim_status and status_label for presentation."
  },
  "filters": {
    "prover": "",
    "onsite": "",
    "coop": "",
    "chips": "",
    "ready": "R2",
    "tested": "",
    "hide": []
  },
  "mechanisms_passing_filters": 15,
  "claims": [],
  "mechanisms": [
    {
      "id": "M-0001",
      "title": "Sampled inference recomputation",
      "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/",
      "assessment_record": {
        "id": "M-0001",
        "title": "Sampled inference recomputation",
        "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/"
      },
      "finding_counts": {
        "failure": 3,
        "scope_limitation": 1,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 1
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R3",
        "scope": "checking untrusted workers' activations against the declared model, prompt and precision",
        "confidence": "low",
        "evidence": [
          "S-0015",
          "S-0016",
          "S-1000",
          "S-1001",
          "S-1003",
          "S-1005",
          "S-1006",
          "S-1008",
          "S-1507",
          "S-3000",
          "S-3001"
        ]
      },
      "development_status": {
        "code": "R3",
        "label": "Operational use",
        "short": "Operational use",
        "rank": 3,
        "legacy_code": "R3"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0020",
              "S-0015",
              "S-1507"
            ]
          },
          {
            "n": 3,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1000",
              "S-0016"
            ]
          },
          {
            "n": 4,
            "severity": "minor",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0016"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 1
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "none",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "Recomputation needs the weights and sampled requests inside the checking environment. For closed models, the record describes a trusted, confidential environment; disclosure to the verifier depends on that boundary.",
        "sources": [
          "S-0016",
          "S-0017",
          "S-0018"
        ]
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "id": "M-0009",
      "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors",
      "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/",
      "assessment_record": {
        "id": "M-0009",
        "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors",
        "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/"
      },
      "finding_counts": {
        "failure": 3,
        "scope_limitation": 2,
        "open_question": 1,
        "open_failures": {
          "critical": 0,
          "significant": 3,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R1",
        "scope": "checking and enforcing training-compute limits on chips, against adversaries up to states",
        "confidence": "medium",
        "evidence": [
          "S-0035",
          "S-1204",
          "S-1205",
          "S-0057",
          "S-0056",
          "S-0006"
        ]
      },
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204",
              "S-0057"
            ]
          },
          {
            "n": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 3,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "new-chip",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "hidden",
        "io": "hidden",
        "training": "hidden",
        "note": "The guarantee processor sees the chip's traffic inside a sealed enclosure and reports only whether rules were kept."
      },
      "family_finding_context": [],
      "filter_issues": [
        {
          "filter": "ready",
          "level": "exclude",
          "short": "development: Proposed",
          "text": "Development status: Proposed. Minimum: Research demonstration."
        }
      ]
    },
    {
      "id": "M-0002",
      "title": "Deterministic and bit-exact inference",
      "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/",
      "assessment_record": {
        "id": "M-0002",
        "title": "Deterministic and bit-exact inference",
        "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/"
      },
      "finding_counts": {
        "failure": 0,
        "scope_limitation": 2,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R3",
        "scope": "reproducing open-model inference from receipts in Gensyn's information-market service",
        "confidence": "low",
        "evidence": [
          "S-0020",
          "S-1009",
          "S-1010",
          "S-1012",
          "S-1013",
          "S-1812",
          "S-3021",
          "S-3022",
          "S-3023",
          "S-0075"
        ]
      },
      "development_status": {
        "code": "R3",
        "label": "Operational use",
        "short": "Operational use",
        "rank": 3,
        "legacy_code": "R3"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [],
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "none",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "Exact replay needs the weights, configuration and replayed requests inside the recomputation environment. What the verifier sees depends on whether that environment keeps them confidential.",
        "sources": [
          "S-0018",
          "S-0020"
        ]
      },
      "family_finding_context": [],
      "filter_issues": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [
      "M-0001",
      "M-0002"
    ],
    "operationalUse": [
      "M-0001",
      "M-0002"
    ],
    "adversarial": [
      "M-0001",
      "M-0002"
    ],
    "noNewHardware": [
      "M-0001",
      "M-0002"
    ],
    "mitigated": [],
    "notCounted": [
      "M-0009"
    ]
  },
  "properties": {
    "covered": [],
    "production": [
      "M-0001",
      "M-0002"
    ],
    "operationalUse": [
      "M-0001",
      "M-0002"
    ],
    "adversarial": [
      "M-0001",
      "M-0002"
    ],
    "noNewHardware": [
      "M-0001",
      "M-0002"
    ],
    "mitigated": [],
    "notCounted": [
      "M-0009"
    ]
  },
  "attack_testing": [
    {
      "id": "M-0001",
      "record": "M-0001",
      "evaluation": "analysis",
      "in_setting": true
    },
    {
      "id": "M-0009",
      "record": "M-0009",
      "evaluation": "analysis",
      "in_setting": false
    },
    {
      "id": "M-0002",
      "record": "M-0002",
      "evaluation": "analysis",
      "in_setting": true
    }
  ],
  "selected_implementations": {},
  "weaknesses": {
    "gaps": [],
    "excluded": [
      {
        "id": "M-0009",
        "issues": [
          {
            "filter": "ready",
            "level": "exclude",
            "short": "development: Proposed",
            "text": "Development status: Proposed. Minimum: Research demonstration."
          }
        ]
      }
    ],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0001",
        "n": 1,
        "historical": false,
        "title": "Tolerance for numerical noise leaves a covert channel",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.",
        "response": null,
        "sources": [
          "S-0020",
          "S-0015",
          "S-1507"
        ],
        "helps": [
          {
            "by": "M-0002",
            "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration."
          }
        ]
      },
      {
        "mech": "M-0001",
        "n": 3,
        "historical": false,
        "title": "Some inference optimizations are not covered",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.",
        "response": null,
        "sources": [
          "S-1000",
          "S-0016"
        ]
      },
      {
        "mech": "M-0009",
        "n": 1,
        "historical": false,
        "title": "State attackers can likely defeat current secure enclosures",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The flexHEG authors write that \"nation-state attackers can likely compromise the best current secure enclosures\", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures \"would not be insurmountable for a determined and well-resourced adversary\", although they raise costs and can reveal tampering.",
        "response": null,
        "sources": [
          "S-1204",
          "S-0057"
        ]
      },
      {
        "mech": "M-0009",
        "n": 2,
        "historical": false,
        "title": "Firmware-only retrofits rely on Secure Boot, which fault injection can bypass",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers.",
        "response": null,
        "sources": [
          "S-1204"
        ]
      },
      {
        "mech": "M-0009",
        "n": 4,
        "historical": false,
        "title": "FLOP accounting can be laundered through external data",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Results of earlier or parallel workloads could be hidden in the \"external data\" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed.",
        "response": null,
        "sources": [
          "S-1204"
        ]
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0001",
      "M-0009"
    ],
    "familyContext": [],
    "scopeLimitations": [
      {
        "mech": "M-0001",
        "n": 2,
        "historical": false,
        "title": "Only recorded traffic is checked",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.",
        "response": null,
        "sources": [
          "S-0017",
          "S-0015"
        ],
        "helps": [
          {
            "by": "M-0013",
            "how": "Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips."
          }
        ]
      },
      {
        "mech": "M-0009",
        "n": 3,
        "historical": false,
        "title": "Many important rules cannot be checked on-chip",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Malicious intent \"is not a technical property observable on-chip\", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset \"may not be entirely feasible\" for the same reason.",
        "response": null,
        "sources": [
          "S-0035",
          "S-1205"
        ]
      },
      {
        "mech": "M-0009",
        "n": 6,
        "historical": false,
        "title": "Coverage stops at flexHEG-equipped chips",
        "classification": "scope-limitation",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be \"practically quite difficult\".",
        "response": null,
        "sources": [
          "S-0035",
          "S-1205"
        ],
        "helps": [
          {
            "by": "M-0019",
            "how": "Accounts for which chips exist and who holds them."
          },
          {
            "by": "M-0020",
            "how": "Looks for undeclared facilities that hold other chips."
          }
        ]
      },
      {
        "mech": "M-0002",
        "n": 1,
        "historical": false,
        "title": "Some kernels remain genuinely nondeterministic",
        "classification": "scope-limitation",
        "kind": "open-question",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them.",
        "response": null,
        "sources": [
          "S-0020"
        ]
      },
      {
        "mech": "M-0002",
        "n": 2,
        "historical": false,
        "title": "Cross-hardware replay relies on reverse-engineered, closed behaviour",
        "classification": "scope-limitation",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case.",
        "response": null,
        "sources": [
          "S-1010",
          "S-0020"
        ]
      }
    ],
    "openQuestions": [
      {
        "mech": "M-0009",
        "n": 5,
        "historical": false,
        "title": "Supply-chain diversion and hidden backdoors",
        "classification": "open-question",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices.",
        "response": null,
        "sources": [
          "S-1204",
          "S-1205"
        ],
        "helps": [
          {
            "by": "M-0019",
            "how": "Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors."
          }
        ]
      }
    ],
    "minor": 1,
    "minorFindings": [
      {
        "mech": "M-0001",
        "n": 4,
        "historical": false,
        "title": "Mixed hardware widens the honest baseline",
        "classification": "failure",
        "kind": "open-question",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.",
        "response": null,
        "sources": [
          "S-0016"
        ]
      }
    ],
    "minorBy": [
      {
        "id": "M-0001",
        "n": 1
      }
    ],
    "notDemonstrated": [
      "M-0009"
    ],
    "newChip": [
      "M-0009"
    ]
  },
  "findings": [
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 1,
      "historical": false,
      "title": "Tolerance for numerical noise leaves a covert channel",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.",
      "response": null,
      "sources": [
        "S-0020",
        "S-0015",
        "S-1507"
      ],
      "helps": [
        {
          "by": "M-0002",
          "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration."
        }
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 2,
      "historical": false,
      "title": "Only recorded traffic is checked",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.",
      "response": null,
      "sources": [
        "S-0017",
        "S-0015"
      ],
      "helps": [
        {
          "by": "M-0013",
          "how": "Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips."
        }
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 3,
      "historical": false,
      "title": "Some inference optimizations are not covered",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.",
      "response": null,
      "sources": [
        "S-1000",
        "S-0016"
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 4,
      "historical": false,
      "title": "Mixed hardware widens the honest baseline",
      "classification": "failure",
      "kind": "open-question",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.",
      "response": null,
      "sources": [
        "S-0016"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 1,
      "historical": false,
      "title": "State attackers can likely defeat current secure enclosures",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The flexHEG authors write that \"nation-state attackers can likely compromise the best current secure enclosures\", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures \"would not be insurmountable for a determined and well-resourced adversary\", although they raise costs and can reveal tampering.",
      "response": null,
      "sources": [
        "S-1204",
        "S-0057"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 2,
      "historical": false,
      "title": "Firmware-only retrofits rely on Secure Boot, which fault injection can bypass",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers.",
      "response": null,
      "sources": [
        "S-1204"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 3,
      "historical": false,
      "title": "Many important rules cannot be checked on-chip",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Malicious intent \"is not a technical property observable on-chip\", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset \"may not be entirely feasible\" for the same reason.",
      "response": null,
      "sources": [
        "S-0035",
        "S-1205"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 4,
      "historical": false,
      "title": "FLOP accounting can be laundered through external data",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Results of earlier or parallel workloads could be hidden in the \"external data\" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed.",
      "response": null,
      "sources": [
        "S-1204"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 5,
      "historical": false,
      "title": "Supply-chain diversion and hidden backdoors",
      "classification": "open-question",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices.",
      "response": null,
      "sources": [
        "S-1204",
        "S-1205"
      ],
      "helps": [
        {
          "by": "M-0019",
          "how": "Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors."
        }
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 6,
      "historical": false,
      "title": "Coverage stops at flexHEG-equipped chips",
      "classification": "scope-limitation",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be \"practically quite difficult\".",
      "response": null,
      "sources": [
        "S-0035",
        "S-1205"
      ],
      "helps": [
        {
          "by": "M-0019",
          "how": "Accounts for which chips exist and who holds them."
        },
        {
          "by": "M-0020",
          "how": "Looks for undeclared facilities that hold other chips."
        }
      ]
    },
    {
      "mech": "M-0002",
      "record": "M-0002",
      "n": 1,
      "historical": false,
      "title": "Some kernels remain genuinely nondeterministic",
      "classification": "scope-limitation",
      "kind": "open-question",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them.",
      "response": null,
      "sources": [
        "S-0020"
      ]
    },
    {
      "mech": "M-0002",
      "record": "M-0002",
      "n": 2,
      "historical": false,
      "title": "Cross-hardware replay relies on reverse-engineered, closed behaviour",
      "classification": "scope-limitation",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case.",
      "response": null,
      "sources": [
        "S-1010",
        "S-0020"
      ]
    }
  ],
  "possible_additions": [
    {
      "id": "M-0017",
      "title": "Tamper evidence for verifier devices",
      "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/",
      "readiness": "R2",
      "development_status": {
        "code": "R2",
        "label": "Research demonstration",
        "short": "Research demo",
        "rank": 2,
        "legacy_code": "R2"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1317",
              "S-1318"
            ]
          },
          {
            "n": 3,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1315",
              "S-0052",
              "S-3261"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0009",
          "text": "State-level attackers who hold the hardware can likely compromise the best current secure enclosures."
        }
      ]
    },
    {
      "id": "M-0008",
      "title": "TEE remote attestation for AI workloads",
      "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/",
      "readiness": "R3",
      "development_status": {
        "code": "R3",
        "label": "Operational use",
        "short": "Operational use",
        "rank": 3,
        "legacy_code": "R3"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "independent-red-team",
          "label": "Published attack testing",
          "kind": "practical",
          "attribution": "Independent team"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "critical",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1202",
              "S-3126",
              "S-0012",
              "S-1206",
              "S-0014",
              "S-1210",
              "S-1212",
              "S-3127"
            ]
          },
          {
            "n": 2,
            "severity": "critical",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1210",
              "S-1211"
            ]
          },
          {
            "n": 3,
            "severity": "critical",
            "status": "mitigated",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1212",
              "S-1213",
              "S-3127",
              "S-3128"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1202"
            ]
          },
          {
            "n": 5,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-0012",
              "S-0009",
              "S-0014",
              "S-3123",
              "S-3129"
            ]
          },
          {
            "n": 8,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-0014",
              "S-0009",
              "S-3130",
              "S-3131"
            ]
          }
        ],
        "open_failures": {
          "critical": 2,
          "significant": 3,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "prerequisite",
          "mech": "M-0009"
        }
      ]
    },
    {
      "id": "M-0019",
      "title": "Chip registries and manufacturing records",
      "url": "https://trustbutveri.fyi/mechanisms/chip-registries-and-manufacturing-records/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1402"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "ready",
          "level": "exclude",
          "short": "development: Proposed",
          "text": "Development status: Proposed. Minimum: Research demonstration."
        }
      ],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0009",
          "text": "Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities."
        }
      ]
    },
    {
      "id": "M-0013",
      "title": "Network taps and certifiers",
      "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1300",
              "S-1507"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1312"
            ]
          },
          {
            "n": 6,
            "severity": "minor",
            "status": "mitigated",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1300"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "ready",
          "level": "exclude",
          "short": "development: Proposed",
          "text": "Development status: Proposed. Minimum: Research demonstration."
        }
      ],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0001",
          "text": "In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface."
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0008",
        "neededBy": [
          "M-0009"
        ]
      },
      {
        "id": "M-0019",
        "neededBy": [
          "M-0009"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0001",
        "n": 1,
        "historical": false,
        "text": "In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0013",
        "sources": [
          "S-1008",
          "S-0067"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 2,
        "historical": false,
        "text": "In retrofit designs, the recomputation server must sit inside the prover's data centre, possibly under the prover's physical control, and still be protected from a compromised provider, which Amodo rates 'not on track'.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-1008",
          "S-0015"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 3,
        "historical": false,
        "text": "No independent red-team of a recomputation consistency check has been published (the one independent attack study targets the weight-exfiltration bound), and Amodo rates recomputation red-teaming 'not started'.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1008",
          "S-1507"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 4,
        "historical": false,
        "text": "Tolerance-based checks need calibration on trusted hardware and exact knowledge of the provider's sampling procedure, and in one prototype a sampling-implementation mismatch produced large spurious differences.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-0016",
          "S-1006"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 5,
        "historical": false,
        "text": "The verifier needs the model weights, so checking a closed-weights model requires a trusted, confidential recomputation environment, which the retrofit designs place inside the prover's facility.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0016",
          "S-0017",
          "S-0018"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 1,
        "historical": false,
        "text": "Integrated flexHEG needs substantial help from the accelerator manufacturer, and the authors estimate 3.7–7.9 years, from when the manufacturer starts work, for such hardware to displace other accelerators in frontier development.",
        "theme": "access-governance",
        "blocked_by": null,
        "sources": [
          "S-1204"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 2,
        "historical": false,
        "text": "State-level attackers who hold the hardware can likely compromise the best current secure enclosures.",
        "theme": "hardware-trust",
        "blocked_by": "M-0017",
        "sources": [
          "S-1204",
          "S-0057"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0009",
        "n": 3,
        "historical": false,
        "text": "Rival states would need to trust the design and manufacture of guarantee processors and enclosures, for example through open design, redundant processors from each side or oversight of production.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-1205",
          "S-0035"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 4,
        "historical": false,
        "text": "Restricting future rule updates would need a formal language for rules, which the authors judge most likely infeasible for early flexHEG versions.",
        "theme": "protocol-soundness",
        "blocked_by": null,
        "sources": [
          "S-0035"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 5,
        "historical": false,
        "text": "Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0019",
        "sources": [
          "S-1205"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0002",
        "n": 1,
        "historical": false,
        "text": "Batch-invariant kernels cost throughput: in Thinking Machines' Qwen3-8B test, an improved deterministic build took 42 s against 26 s for vLLM's default, and SGLang reports an average 34.35% slowdown on its FlashInfer and FlashAttention 3 backends.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-1009",
          "S-1012"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0002",
        "n": 2,
        "historical": false,
        "text": "Coverage is incomplete: the bit-exact emulator targets dense blocks on NVIDIA GPUs and excludes mixture-of-experts inference and training, and vLLM's batch-invariant mode is in beta, with open work on AMD hardware and speculative decoding.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-0020",
          "S-1013",
          "S-1814"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0002",
        "n": 3,
        "historical": false,
        "text": "Amodo's status page for the AI 2040 verification plan rates a reproducible inference stack for that plan as 'not started'.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-1008"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0002",
        "n": 4,
        "historical": false,
        "text": "Exact replay requires the prover to disclose weights, software versions, parallelism and batch sizes to whoever recomputes.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0020",
          "S-0018"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [
        "M-0001",
        "M-0002"
      ],
      "hidden": [
        "M-0009"
      ],
      "none": [],
      "unknown": []
    },
    "io": {
      "shown": [],
      "partial": [
        "M-0001",
        "M-0002"
      ],
      "hidden": [
        "M-0009"
      ],
      "none": [],
      "unknown": []
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [
        "M-0009"
      ],
      "none": [
        "M-0001",
        "M-0002"
      ],
      "unknown": []
    }
  },
  "implementations": [
    {
      "mechanism": "M-0001",
      "selected": null,
      "implementations": [
        {
          "id": "I-0011",
          "title": "AI 2040 inference-only verification stack",
          "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/"
        },
        {
          "id": "I-0002",
          "title": "DiFR (Divergence From Reference)",
          "url": "https://trustbutveri.fyi/implementations/difr/"
        },
        {
          "id": "I-0012",
          "title": "Low-trust AI compute verification system overview",
          "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
        },
        {
          "id": "I-0008",
          "title": "SASH confidential network logger",
          "url": "https://trustbutveri.fyi/implementations/sash-confidential-network-logger/"
        },
        {
          "id": "I-0001",
          "title": "TOPLOC",
          "url": "https://trustbutveri.fyi/implementations/toploc/"
        }
      ]
    },
    {
      "mechanism": "M-0009",
      "selected": null,
      "implementations": []
    },
    {
      "mechanism": "M-0002",
      "selected": null,
      "implementations": [
        {
          "id": "I-0016",
          "title": "Batch-invariant inference kernels (Thinking Machines)",
          "url": "https://trustbutveri.fyi/implementations/batch-invariant-inference-kernels/"
        },
        {
          "id": "I-0015",
          "title": "Verde and RepOps (Gensyn)",
          "url": "https://trustbutveri.fyi/implementations/gensyn-verde-repops/"
        },
        {
          "id": "I-0012",
          "title": "Low-trust AI compute verification system overview",
          "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
        }
      ]
    }
  ],
  "sources": [
    {
      "id": "S-0015",
      "title": "Verifying LLM Inference to Detect Model Weight Exfiltration",
      "authors": "R. Rinberg et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2511.02620",
      "path": "/sources/rinberg-verifying-llm-inference-weight-exfiltration/"
    },
    {
      "id": "S-0016",
      "title": "DiFR: Inference Verification Despite Nondeterminism",
      "authors": "A. Karvonen et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2511.20621",
      "path": "/sources/karvonen-difr/"
    },
    {
      "id": "S-1000",
      "title": "TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference",
      "authors": "J. M. Ong et al.",
      "year": 2025,
      "url": "https://proceedings.mlr.press/v267/ong25a.html",
      "path": "/sources/ong-toploc/"
    },
    {
      "id": "S-1001",
      "title": "PrimeIntellect-ai/toploc (GitHub repository)",
      "authors": "Prime Intellect",
      "year": 2025,
      "url": "https://github.com/PrimeIntellect-ai/toploc",
      "path": "/sources/primeintellect-toploc-code/"
    },
    {
      "id": "S-1003",
      "title": "INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning",
      "authors": "Prime Intellect Team et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2505.07291",
      "path": "/sources/primeintellect-intellect-2/"
    },
    {
      "id": "S-1005",
      "title": "adamkarvonen/difr (GitHub repository)",
      "authors": "A. Karvonen",
      "year": 2025,
      "url": "https://github.com/adamkarvonen/difr",
      "path": "/sources/karvonen-difr-code/"
    },
    {
      "id": "S-1006",
      "title": "Scaling Recomputation Inference Verification",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/",
      "path": "/sources/amodo-scaling-recomputation-inference-verification/"
    },
    {
      "id": "S-1008",
      "title": "AI 2040 Plan A — Verification SITREP",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/ai-verification/plan-a-sitrep/",
      "path": "/sources/amodo-plan-a-verification-sitrep/"
    },
    {
      "id": "S-1507",
      "title": "Adversarial Entropy Inflation Against Gumbel-Based Inference Verification",
      "authors": "N. Kezins",
      "year": 2026,
      "url": "https://arxiv.org/abs/2608.23375",
      "path": "/sources/kezins-adversarial-entropy-inflation/"
    },
    {
      "id": "S-3000",
      "title": "SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces",
      "authors": "Prime Intellect",
      "year": 2025,
      "url": "https://www.primeintellect.ai/blog/synthetic-2-release",
      "path": "/sources/primeintellect-synthetic-2-release/"
    },
    {
      "id": "S-3001",
      "title": "An Inference Verification Prototype — Stage 1",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-06-29-inference-verification-prototype/",
      "path": "/sources/amodo-inference-verification-prototype-stage-1/"
    },
    {
      "id": "S-0020",
      "title": "Bit-Exact AI Inference Verification Without Performance Tradeoffs",
      "authors": "N. Cankaya",
      "year": 2026,
      "url": "https://arxiv.org/abs/2606.00279",
      "path": "/sources/cankaya-bit-exact-inference-verification/"
    },
    {
      "id": "S-0017",
      "title": "Example Schemes for Verifying High-Stakes AI Agreements",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-06-23-verification-algorithms/",
      "path": "/sources/amodo-example-schemes-high-stakes-ai-agreements/"
    },
    {
      "id": "S-0018",
      "title": "A System Overview for Near-Term, Low-Trust AI Compute Verification",
      "authors": "N. Cankaya",
      "year": 2026,
      "url": "https://intelligence.org/wp-content/uploads/2026/06/A-system-overview-for-near-term-low-trust-AI-compute-verification.pdf",
      "path": "/sources/cankaya-system-overview-low-trust-compute-verification/"
    },
    {
      "id": "S-0035",
      "title": "Flexible Hardware-Enabled Guarantees for AI Compute",
      "authors": "J. Petrie et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.15093",
      "path": "/sources/petrie-flexible-hardware-enabled-guarantees/"
    },
    {
      "id": "S-1204",
      "title": "Technical Options for Flexible Hardware-Enabled Guarantees",
      "authors": "J. Petrie & O. Aarne",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.03409",
      "path": "/sources/petrie-technical-options-flexheg/"
    },
    {
      "id": "S-1205",
      "title": "International Security Applications of Flexible Hardware-Enabled Guarantees",
      "authors": "O. Aarne & J. Petrie",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.15100",
      "path": "/sources/aarne-international-security-applications-flexheg/"
    },
    {
      "id": "S-0057",
      "title": "Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090",
      "authors": "G. Kulp et al.",
      "year": 2024,
      "url": "https://www.rand.org/pubs/working_papers/WRA3056-1.html",
      "path": "/sources/kulp-hardware-enabled-governance-mechanisms/"
    },
    {
      "id": "S-0056",
      "title": "Secure, Governable Chips: Using On-Chip Mechanisms to Manage National Security Risks from AI & Advanced Computing",
      "authors": "O. Aarne et al.",
      "year": 2024,
      "url": "https://www.cnas.org/publications/reports/secure-governable-chips",
      "path": "/sources/aarne-secure-governable-chips/"
    },
    {
      "id": "S-0006",
      "title": "Hardware-Enabled Mechanisms for Verifying Responsible AI Development",
      "authors": "A. O'Gara et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2505.03742",
      "path": "/sources/ogara-hardware-enabled-verifying-responsible-ai/"
    },
    {
      "id": "S-1009",
      "title": "Defeating Nondeterminism in LLM Inference",
      "authors": "H. He & Thinking Machines Lab",
      "year": 2025,
      "url": "https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/",
      "path": "/sources/he-defeating-nondeterminism-llm-inference/"
    },
    {
      "id": "S-1010",
      "title": "Hawkeye: Reproducing GPU-Level Non-Determinism",
      "authors": "E. Badash et al.",
      "year": 2026,
      "url": "https://proceedings.mlsys.org/paper_files/paper/2026/hash/e217c271a57c365a246b0ad39e668ba8-Abstract-Conference.html",
      "path": "/sources/badash-hawkeye/"
    },
    {
      "id": "S-1012",
      "title": "Towards Deterministic Inference in SGLang and Reproducible RL Training",
      "authors": "The SGLang Team",
      "year": 2025,
      "url": "https://www.lmsys.org/blog/2025-09-22-sglang-deterministic/",
      "path": "/sources/sglang-deterministic-inference/"
    },
    {
      "id": "S-1013",
      "title": "Batch Invariance (vLLM documentation)",
      "authors": "vLLM project",
      "year": 2026,
      "url": "https://github.com/vllm-project/vllm/blob/main/docs/features/batch_invariance.md",
      "path": "/sources/vllm-batch-invariance-docs/"
    },
    {
      "id": "S-1812",
      "title": "gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository)",
      "authors": "Gensyn",
      "year": 2026,
      "url": "https://github.com/gensyn-ai/ree",
      "path": "/sources/gensyn-ree-code/"
    },
    {
      "id": "S-3021",
      "title": "EigenCloud Brings Verifiable AI to Mass Market with EigenAI and EigenCompute Launches",
      "authors": "EigenCloud",
      "year": 2025,
      "url": "https://www.eigenlabs.org/blog/eigencloud-brings-verifiable-ai-to-mass-market-with-eigenai-and-eigencompute-launches/",
      "path": "/sources/eigencloud-eigenai-launch/"
    },
    {
      "id": "S-3022",
      "title": "Building Delphi: Pricing, Settlement, and Agentic Trading",
      "authors": "D. Jedamski",
      "year": 2026,
      "url": "https://www.gensyn.ai/blog/building-delphi-pricing-settlement-and-agentic-trading",
      "path": "/sources/gensyn-building-delphi/"
    },
    {
      "id": "S-3023",
      "title": "Reproducible Execution Environment (REE) (Gensyn documentation)",
      "authors": "Gensyn",
      "year": 2026,
      "url": "https://docs.gensyn.ai/tech",
      "path": "/sources/gensyn-ree-docs/"
    },
    {
      "id": "S-0075",
      "title": "What is Delphi? (Delphi documentation)",
      "authors": "Gensyn",
      "year": 2026,
      "url": "https://docs.delphi.fyi/",
      "path": "/sources/gensyn-delphi-documentation/"
    },
    {
      "id": "S-0067",
      "title": "Verification Plan",
      "authors": "R. Dean",
      "year": 2026,
      "url": "https://ai-2040.com/supplements/verification-plan",
      "path": "/sources/dean-verification-plan/"
    },
    {
      "id": "S-1814",
      "title": "[Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433)",
      "authors": "vLLM project contributors",
      "year": 2025,
      "url": "https://github.com/vllm-project/vllm/issues/27433",
      "path": "/sources/vllm-batch-invariance-tracking-issue/"
    }
  ]
}