{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0001,M-0024&implementations=M-0001:I-0011",
  "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": "",
    "tested": "",
    "hide": []
  },
  "mechanisms_passing_filters": 25,
  "claims": [],
  "mechanisms": [
    {
      "id": "M-0001",
      "title": "Sampled inference recomputation",
      "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/",
      "assessment_record": {
        "id": "I-0011",
        "title": "AI 2040 inference-only verification stack",
        "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/"
      },
      "finding_counts": {
        "failure": 1,
        "scope_limitation": 2,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "selected_implementation": {
        "id": "I-0011",
        "title": "AI 2040 inference-only verification stack",
        "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/"
      },
      "readiness": {
        "level": "R1",
        "scope": "showing that retrofitted data centres run only inference",
        "confidence": "medium",
        "evidence": [
          "S-0067",
          "S-1511",
          "S-1512",
          "S-1008",
          "S-1312"
        ]
      },
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "none",
          "label": "No published adversarial analysis recorded",
          "kind": "none"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 3,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1511",
              "S-0015",
              "S-1507",
              "S-0067"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "required",
        "adversarial_evaluation": "none"
      },
      "claims": [],
      "exposure": {
        "weights": "unknown",
        "io": "unknown",
        "training": "unknown",
        "note": "This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.",
        "sources": []
      },
      "family_finding_context": [
        {
          "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."
            }
          ],
          "record": "M-0001",
          "represented_by": []
        },
        {
          "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."
            }
          ],
          "record": "M-0001",
          "represented_by": []
        },
        {
          "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"
          ],
          "record": "M-0001",
          "represented_by": []
        },
        {
          "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"
          ],
          "record": "M-0001",
          "represented_by": []
        }
      ],
      "filter_issues": []
    },
    {
      "id": "M-0024",
      "title": "Bounding unexplained information in outputs",
      "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/",
      "assessment_record": {
        "id": "M-0024",
        "title": "Bounding unexplained information in outputs",
        "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/"
      },
      "finding_counts": {
        "failure": 1,
        "scope_limitation": 2,
        "open_question": 1,
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "bounding how much hidden information can leave in checked inference outputs",
        "confidence": "low",
        "evidence": [
          "S-0019",
          "S-0015",
          "S-1507"
        ]
      },
      "development_status": {
        "code": "R2",
        "label": "Research demonstration",
        "short": "Research demo",
        "rank": 2,
        "legacy_code": "R2"
      },
      "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": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1507",
              "S-0015"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "required",
        "adversarial_evaluation": "independent-red-team"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "Depends on where recomputation runs: in a sealed enclosure, or with zero-knowledge proofs, the verifier need not see the weights or the traffic."
      },
      "family_finding_context": [],
      "filter_issues": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0001",
      "M-0024"
    ],
    "noNewHardware": [],
    "mitigated": [],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0001",
      "M-0024"
    ],
    "noNewHardware": [],
    "mitigated": [],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0024",
      "record": "M-0024",
      "evaluation": "independent-red-team",
      "in_setting": true
    }
  ],
  "selected_implementations": {
    "M-0001": "I-0011"
  },
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0001",
        "n": 3,
        "historical": false,
        "title": "A recomputation family degrades against prompt-controlling adversaries",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The plan's companion page names DiFR among the recomputation schemes being tested. An independent study found that Gumbel-based inference verification, the family that includes Token-DiFR, leaks roughly twice as many bits per token when the adversary chooses prompts that disrupt the text's structure, across six models of 1 to 32 billion parameters. The slowdown it imposes on a hidden-signalling adversary falls from 146–254 times under benign prompts to 60–118 times. The attack weakens the bound on hidden information in outputs, which the plan relies on to keep undeclared results from leaving.",
        "response": null,
        "sources": [
          "S-1511",
          "S-0015",
          "S-1507",
          "S-0067"
        ],
        "record": "I-0011"
      },
      {
        "mech": "M-0024",
        "n": 1,
        "historical": false,
        "title": "Prompt-controlled entropy inflation widens the covert channel",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.",
        "response": null,
        "sources": [
          "S-1507",
          "S-0015"
        ],
        "helps": [
          {
            "by": "M-0002",
            "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
          }
        ]
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0001",
      "M-0024"
    ],
    "familyContext": [
      {
        "id": "M-0001",
        "implementation": "I-0011",
        "flaws": [
          {
            "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."
              }
            ],
            "record": "M-0001",
            "represented_by": []
          },
          {
            "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."
              }
            ],
            "record": "M-0001",
            "represented_by": []
          },
          {
            "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"
            ],
            "record": "M-0001",
            "represented_by": []
          },
          {
            "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"
            ],
            "record": "M-0001",
            "represented_by": []
          }
        ]
      }
    ],
    "scopeLimitations": [
      {
        "mech": "M-0001",
        "n": 1,
        "historical": false,
        "title": "The recomputation server must be trusted",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The plan calls the integrity of the recomputation server an extremely important aspect, and its argument that sampling verifies all outputs assumes that the server's computations and outputs can be trusted. The companion page notes that the server sits inside the prover's facility, possibly under the prover's physical control, and that hardening it against integrity attacks needs significant research. Amodo rates recomputation-server security as not on track.",
        "response": null,
        "sources": [
          "S-0067",
          "S-1511",
          "S-1008"
        ],
        "record": "I-0011"
      },
      {
        "mech": "M-0001",
        "n": 2,
        "historical": false,
        "title": "Spare compute is not verified",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The plan states that it does not verify that spare compute is unused for unapproved workloads, because this seems very challenging. It relies instead on side-channel bounds and memory wipes, so that the only results that persist are verified inference outputs.",
        "response": null,
        "sources": [
          "S-0067"
        ],
        "record": "I-0011"
      },
      {
        "mech": "M-0024",
        "n": 2,
        "historical": false,
        "title": "Information the declared computation explains is not bounded",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.",
        "response": null,
        "sources": [
          "S-1508",
          "S-0019"
        ]
      },
      {
        "mech": "M-0024",
        "n": 3,
        "historical": false,
        "title": "Channels other than checked outputs are outside the bound",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.",
        "response": null,
        "sources": [
          "S-0015",
          "S-0018"
        ],
        "helps": [
          {
            "by": "M-0022",
            "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
          }
        ]
      }
    ],
    "openQuestions": [
      {
        "mech": "M-0024",
        "n": 4,
        "historical": false,
        "title": "The facility-level design is untested",
        "classification": "open-question",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.",
        "response": null,
        "sources": [
          "S-0019"
        ]
      }
    ],
    "minor": 0,
    "minorFindings": [],
    "minorBy": [],
    "notDemonstrated": [
      "M-0001"
    ],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0001",
      "record": "I-0011",
      "n": 1,
      "historical": false,
      "title": "The recomputation server must be trusted",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The plan calls the integrity of the recomputation server an extremely important aspect, and its argument that sampling verifies all outputs assumes that the server's computations and outputs can be trusted. The companion page notes that the server sits inside the prover's facility, possibly under the prover's physical control, and that hardening it against integrity attacks needs significant research. Amodo rates recomputation-server security as not on track.",
      "response": null,
      "sources": [
        "S-0067",
        "S-1511",
        "S-1008"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0011",
      "n": 2,
      "historical": false,
      "title": "Spare compute is not verified",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The plan states that it does not verify that spare compute is unused for unapproved workloads, because this seems very challenging. It relies instead on side-channel bounds and memory wipes, so that the only results that persist are verified inference outputs.",
      "response": null,
      "sources": [
        "S-0067"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0011",
      "n": 3,
      "historical": false,
      "title": "A recomputation family degrades against prompt-controlling adversaries",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The plan's companion page names DiFR among the recomputation schemes being tested. An independent study found that Gumbel-based inference verification, the family that includes Token-DiFR, leaks roughly twice as many bits per token when the adversary chooses prompts that disrupt the text's structure, across six models of 1 to 32 billion parameters. The slowdown it imposes on a hidden-signalling adversary falls from 146–254 times under benign prompts to 60–118 times. The attack weakens the bound on hidden information in outputs, which the plan relies on to keep undeclared results from leaving.",
      "response": null,
      "sources": [
        "S-1511",
        "S-0015",
        "S-1507",
        "S-0067"
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 1,
      "historical": false,
      "title": "Prompt-controlled entropy inflation widens the covert channel",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.",
      "response": null,
      "sources": [
        "S-1507",
        "S-0015"
      ],
      "helps": [
        {
          "by": "M-0002",
          "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 2,
      "historical": false,
      "title": "Information the declared computation explains is not bounded",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.",
      "response": null,
      "sources": [
        "S-1508",
        "S-0019"
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 3,
      "historical": false,
      "title": "Channels other than checked outputs are outside the bound",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.",
      "response": null,
      "sources": [
        "S-0015",
        "S-0018"
      ],
      "helps": [
        {
          "by": "M-0022",
          "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 4,
      "historical": false,
      "title": "The facility-level design is untested",
      "classification": "open-question",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.",
      "response": null,
      "sources": [
        "S-0019"
      ]
    }
  ],
  "possible_additions": [
    {
      "id": "M-0002",
      "title": "Deterministic and bit-exact inference",
      "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/",
      "readiness": "R3",
      "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
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "flaw",
          "mech": "M-0024",
          "n": 1,
          "title": "Prompt-controlled entropy inflation widens the covert channel",
          "severity": "significant",
          "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
        },
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata."
        }
      ]
    },
    {
      "id": "M-0014",
      "title": "Bandwidth limits and compartmentalization",
      "url": "https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/",
      "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": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1301"
            ]
          },
          {
            "n": 5,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1313"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound."
        }
      ]
    },
    {
      "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-0001",
          "text": "Checking that taps are correctly installed and stay in place at scale is not a solved problem, and hardening the recomputation server inside the prover's facility needs significant research."
        }
      ]
    },
    {
      "id": "M-0015",
      "title": "Memory wiping and proofs of secure erasure",
      "url": "https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/",
      "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-0032",
              "S-0018"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0001",
          "text": "Memory wiping may use existing algorithms, but hardware testing is at an early stage."
        }
      ]
    },
    {
      "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": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0001",
          "text": "Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated."
        },
        {
          "kind": "prerequisite",
          "mech": "M-0024"
        }
      ]
    },
    {
      "id": "M-0022",
      "title": "Side-channel suppression for isolated facilities",
      "url": "https://trustbutveri.fyi/mechanisms/side-channel-suppression/",
      "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": [],
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0001",
          "text": "There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist."
        },
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target."
        }
      ]
    },
    {
      "id": "M-0003",
      "title": "Whole-workload recomputation (reproducible packets)",
      "url": "https://trustbutveri.fyi/mechanisms/reproducible-computation-packets/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "none",
          "label": "No published adversarial analysis recorded",
          "kind": "none"
        },
        "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
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0001",
          "text": "A fully reproducible inference stack needs substantial software and tooling, and per-packet network reproducibility may need considerable software, firmware and possibly hardware work."
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0003",
        "neededBy": [
          "M-0001"
        ]
      },
      {
        "id": "M-0014",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0022",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0013",
        "neededBy": [
          "M-0024"
        ]
      }
    ],
    "shared": [
      {
        "id": "M-0013",
        "by": [
          "M-0001",
          "M-0024"
        ],
        "inProposal": false
      },
      {
        "id": "M-0022",
        "by": [
          "M-0001",
          "M-0024"
        ],
        "inProposal": false
      }
    ],
    "blockers": [
      {
        "mech": "M-0001",
        "n": 1,
        "historical": false,
        "text": "A fully reproducible inference stack needs substantial software and tooling, and per-packet network reproducibility may need considerable software, firmware and possibly hardware work.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0003",
        "sources": [
          "S-1511"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 2,
        "historical": false,
        "text": "Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0013",
        "sources": [
          "S-1511"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 3,
        "historical": false,
        "text": "Checking that taps are correctly installed and stay in place at scale is not a solved problem, and hardening the recomputation server inside the prover's facility needs significant research.",
        "theme": "hardware-trust",
        "blocked_by": "M-0017",
        "sources": [
          "S-1511",
          "S-1008"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 4,
        "historical": false,
        "text": "There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0022",
        "sources": [
          "S-1511"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 5,
        "historical": false,
        "text": "Memory wiping may use existing algorithms, but hardware testing is at an early stage.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0015",
        "sources": [
          "S-1511"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 6,
        "historical": false,
        "text": "Robust red-teaming of recomputation schemes has not started, and most algorithm development remains academic.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1511",
          "S-1008"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0024",
        "n": 1,
        "historical": false,
        "text": "The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0014",
        "sources": [
          "S-0019"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 2,
        "historical": false,
        "text": "Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0022",
        "sources": [
          "S-0018",
          "S-0015"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 3,
        "historical": false,
        "text": "Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata.",
        "theme": "protocol-soundness",
        "blocked_by": "M-0002",
        "sources": [
          "S-1507",
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 4,
        "historical": false,
        "text": "Recomputation over confidential weights and inputs needs a protected setting: prover recomputation in a verifier-controlled enclosure, verifier recomputation in a prover-controlled enclosure, or zero-knowledge proofs.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0019"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0024",
        "n": 5,
        "historical": false,
        "text": "No prototype of the facility-level architecture exists to red-team.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-0019"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [
        "M-0024"
      ],
      "hidden": [],
      "none": [],
      "unknown": [
        "M-0001"
      ]
    },
    "io": {
      "shown": [],
      "partial": [
        "M-0024"
      ],
      "hidden": [],
      "none": [],
      "unknown": [
        "M-0001"
      ]
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0024"
      ],
      "unknown": [
        "M-0001"
      ]
    }
  },
  "implementations": [
    {
      "mechanism": "M-0001",
      "selected": {
        "id": "I-0011",
        "title": "AI 2040 inference-only verification stack",
        "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/"
      },
      "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-0024",
      "selected": null,
      "implementations": []
    }
  ],
  "sources": [
    {
      "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-1511",
      "title": "Get Involved in Verification",
      "authors": "AI Futures Project",
      "year": 2026,
      "url": "https://ai-2040.com/supplements/verification-plan/get-involved",
      "path": "/sources/ai-futures-get-involved-verification/"
    },
    {
      "id": "S-1512",
      "title": "Verifying international AI deals: Plan A, the state-of-play, and what you can do to help",
      "authors": "T. Milton et al.",
      "year": 2026,
      "url": "https://amodo.substack.com/p/verifying-international-ai-deals",
      "path": "/sources/milton-verifying-international-ai-deals/"
    },
    {
      "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-1312",
      "title": "Fitting a Network TAP to our Inference Verification Prototype",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-09-15-network-tap-inference-verification/",
      "path": "/sources/amodo-network-tap-inference-verification-prototype/"
    },
    {
      "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-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-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-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-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-0019",
      "title": "Verifying AI Compute by Bounding Unexplained Information Exfiltration",
      "authors": "J. Petrie & Y. Mühlhäuser",
      "year": 2026,
      "url": "https://openreview.net/forum?id=qtgG5HZSsk",
      "path": "/sources/petrie-bounding-unexplained-information-exfiltration/"
    },
    {
      "id": "S-1508",
      "title": "Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains",
      "authors": "R. Rinberg et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2604.02343",
      "path": "/sources/rinberg-haiku-to-opus-compression/"
    },
    {
      "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/"
    }
  ]
}