{
  "could_not_verify": [],
  "format": "tallylock.board.v1",
  "groups": [
    {
      "kind": "tie",
      "label": "Statistical tie",
      "plan_ids": [
        "24aef6898aff0adb655aaaf49c11383779cf442fd467ea88371db6e0cc7ae63c",
        "2527c205532c0f51979c0a75ef0597feb7f929b0dfa85e58553f445407519120"
      ]
    },
    {
      "kind": "tie",
      "label": "Statistical tie",
      "plan_ids": [
        "2527c205532c0f51979c0a75ef0597feb7f929b0dfa85e58553f445407519120",
        "de3de50abeb724ad03d772eda72945aa17a3a818af12c84feb49090da27f6150"
      ]
    }
  ],
  "rows": [
    {
      "argv": [
        "./eval.sh",
        "quentin",
        "{seed}"
      ],
      "attempts": [
        {
          "duration_ms": 52465,
          "outcome": "completed",
          "score": "0.268",
          "seq": 1
        },
        {
          "duration_ms": 48117,
          "outcome": "completed",
          "score": "0.300",
          "seq": 2
        },
        {
          "duration_ms": 53430,
          "outcome": "completed",
          "score": "0.312",
          "seq": 3
        },
        {
          "duration_ms": 48147,
          "outcome": "completed",
          "score": "0.285",
          "seq": 4
        },
        {
          "duration_ms": 52044,
          "outcome": "completed",
          "score": "0.302",
          "seq": 5
        }
      ],
      "best": "0.312",
      "bitcoin": [
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 1,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 2,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 3,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 4,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 5,
          "state": "insufficient_chain"
        }
      ],
      "claim": "0.312 best of 5 runs; adjusted 0.294 \u00b1 0.022 (95% CI, 5 completed, 0 failed); plan 40a62f35 (2 of 4 in repo); ledger 57cc2acf; tallylock check",
      "completed": 5,
      "failed": 0,
      "head": "94e8139f4e34ad3ff821d78195c594132e91b887",
      "instant_timestamps": [
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:08:29Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:08:29Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:09:23Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:09:23Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:10:23Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:10:23Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:11:16Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:11:16Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:12:13Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:12:13Z",
          "tsa": "timestamp.digicert.com"
        }
      ],
      "links": [],
      "other_plans_not_in_bundle": true,
      "plan_id": "40a62f35a2998ea96a71b0942e6d5729df303c17c37b8f4e6a837529a2f8d03a",
      "range": "0.022",
      "recheck": "d=$(mktemp -d) && cp -r REGISTRY/entries/40a62f35a2998ea96a71b0942e6d5729df303c17c37b8f4e6a837529a2f8d03a/. \"$d\" && cd \"$d\" && git init -q && tallylock check '0.312 best of 5 runs; adjusted 0.294 \u00b1 0.022 (95% CI, 5 completed, 0 failed); plan 40a62f35 (2 of 4 in repo); ledger 57cc2acf; tallylock check'",
      "runs": 5,
      "score": "0.294",
      "setup": {
        "dataset": {
          "name": "Colony Zero sealed set 4 (EXP-CZ-003a, revealed), board subset: 100 lowest task_ids per family",
          "sha256": "8cfbd91929fb90d6a281cfbcfc1c87548b3a91f6e938e6d34ce9145aec82f913",
          "version": "parent sealed-s4-scored.jsonl sha256 525da50809ff284fe5e4ee458320e5a01152717e8c7ca089b72317435914a530"
        },
        "decoding": {
          "max_tokens": 512,
          "min_p": "0.05",
          "samples": 1,
          "seed": "attempt seed via --sample-seed-base",
          "temperature": "0.7",
          "template": "P3",
          "top_k": 40,
          "top_p": "0.95"
        },
        "format": "tallylock.setup.v1",
        "harness": {
          "name": "colony-zero cz.exe probe (Season 0 build), llama.cpp b11539 Vulkan, RX 9070 XT",
          "version": "cz.exe sha256 5dfd02b43647797ef5178800467db47da220248e9ff44d3c20f3c18a8c0b377c"
        },
        "model": {
          "name": "Qwen__Qwen3-0.6B-q8_0",
          "revision": "gguf sha256 ba247426cd8c29bd39912e0fc6509f38eb8c4f0abce62ce5ab29af6ac1adb435"
        },
        "notes": "Side eval for the TallyLock Receipts Board, outside any Colony Zero experiment. Qwen models run with enable_thinking false, as in EXP-CZ-003a. A format failure counts as unsolved.",
        "prompt_template_sha256": "aaae0e27e7132e2d2b76d37685e22fb05a5ceb083bb08a993ea351ff628408d5"
      },
      "source": "tallylock",
      "submitted_by": "TriplePass Labs (Colony Zero founders)",
      "title": "Quentin (Qwen3 0.6B, Q8_0) on Colony Zero sealed set 4, board subset",
      "trust": "anchored",
      "unscored": 0
    },
    {
      "argv": [
        "./eval.sh",
        "grace",
        "{seed}"
      ],
      "attempts": [
        {
          "duration_ms": 42837,
          "outcome": "completed",
          "score": "0.235",
          "seq": 1
        },
        {
          "duration_ms": 43923,
          "outcome": "completed",
          "score": "0.252",
          "seq": 2
        },
        {
          "duration_ms": 45178,
          "outcome": "completed",
          "score": "0.260",
          "seq": 3
        },
        {
          "duration_ms": 43862,
          "outcome": "completed",
          "score": "0.238",
          "seq": 4
        },
        {
          "duration_ms": 45713,
          "outcome": "completed",
          "score": "0.245",
          "seq": 5
        }
      ],
      "best": "0.260",
      "bitcoin": [
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 1,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 2,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 3,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 4,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 5,
          "state": "insufficient_chain"
        }
      ],
      "claim": "0.260 best of 5 runs; adjusted 0.246 \u00b1 0.013 (95% CI, 5 completed, 0 failed); plan de3de50a (3 of 4 in repo); ledger 8270893c; tallylock check",
      "completed": 5,
      "failed": 0,
      "head": "94e8139f4e34ad3ff821d78195c594132e91b887",
      "instant_timestamps": [
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:13:02Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:13:03Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:13:51Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:13:52Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:14:42Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:14:42Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:15:31Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:15:31Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:16:21Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:16:21Z",
          "tsa": "timestamp.digicert.com"
        }
      ],
      "links": [],
      "other_plans_not_in_bundle": true,
      "plan_id": "de3de50abeb724ad03d772eda72945aa17a3a818af12c84feb49090da27f6150",
      "range": "0.013",
      "recheck": "d=$(mktemp -d) && cp -r REGISTRY/entries/de3de50abeb724ad03d772eda72945aa17a3a818af12c84feb49090da27f6150/. \"$d\" && cd \"$d\" && git init -q && tallylock check '0.260 best of 5 runs; adjusted 0.246 \u00b1 0.013 (95% CI, 5 completed, 0 failed); plan de3de50a (3 of 4 in repo); ledger 8270893c; tallylock check'",
      "runs": 5,
      "score": "0.246",
      "setup": {
        "dataset": {
          "name": "Colony Zero sealed set 4 (EXP-CZ-003a, revealed), board subset: 100 lowest task_ids per family",
          "sha256": "8cfbd91929fb90d6a281cfbcfc1c87548b3a91f6e938e6d34ce9145aec82f913",
          "version": "parent sealed-s4-scored.jsonl sha256 525da50809ff284fe5e4ee458320e5a01152717e8c7ca089b72317435914a530"
        },
        "decoding": {
          "max_tokens": 512,
          "min_p": "0.05",
          "samples": 1,
          "seed": "attempt seed via --sample-seed-base",
          "temperature": "0.7",
          "template": "P3",
          "top_k": 40,
          "top_p": "0.95"
        },
        "format": "tallylock.setup.v1",
        "harness": {
          "name": "colony-zero cz.exe probe (Season 0 build), llama.cpp b11539 Vulkan, RX 9070 XT",
          "version": "cz.exe sha256 5dfd02b43647797ef5178800467db47da220248e9ff44d3c20f3c18a8c0b377c"
        },
        "model": {
          "name": "ibm-granite__granite-4.0-h-350m-q8_0",
          "revision": "gguf sha256 b58f4102317be22b2380cad89b9e6ac10f4c8c7b36288a967c618951aca288f5"
        },
        "notes": "Side eval for the TallyLock Receipts Board, outside any Colony Zero experiment. Qwen models run with enable_thinking false, as in EXP-CZ-003a. A format failure counts as unsolved.",
        "prompt_template_sha256": "aaae0e27e7132e2d2b76d37685e22fb05a5ceb083bb08a993ea351ff628408d5"
      },
      "source": "tallylock",
      "submitted_by": "TriplePass Labs (Colony Zero founders)",
      "title": "Grace (Granite 4.0 H 350M, Q8_0) on Colony Zero sealed set 4, board subset",
      "trust": "anchored",
      "unscored": 0
    },
    {
      "argv": [
        "./eval.sh",
        "quinn",
        "{seed}"
      ],
      "attempts": [
        {
          "duration_ms": 44837,
          "outcome": "completed",
          "score": "0.215",
          "seq": 1
        },
        {
          "duration_ms": 46458,
          "outcome": "completed",
          "score": "0.258",
          "seq": 2
        },
        {
          "duration_ms": 41312,
          "outcome": "completed",
          "score": "0.198",
          "seq": 3
        },
        {
          "duration_ms": 46496,
          "outcome": "completed",
          "score": "0.240",
          "seq": 4
        },
        {
          "duration_ms": 43256,
          "outcome": "completed",
          "score": "0.202",
          "seq": 5
        }
      ],
      "best": "0.258",
      "bitcoin": [
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 1,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 2,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 3,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 4,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 5,
          "state": "insufficient_chain"
        }
      ],
      "claim": "0.258 best of 5 runs; adjusted 0.222 \u00b1 0.032 (95% CI, 5 completed, 0 failed); plan 2527c205 (1 of 4 in repo); ledger 5b6966c5; tallylock check",
      "completed": 5,
      "failed": 0,
      "head": "94e8139f4e34ad3ff821d78195c594132e91b887",
      "instant_timestamps": [
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:04:09Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:04:09Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:05:01Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:05:01Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:05:48Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:05:48Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:06:40Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:06:41Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:07:30Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:07:30Z",
          "tsa": "timestamp.digicert.com"
        }
      ],
      "links": [],
      "other_plans_not_in_bundle": true,
      "plan_id": "2527c205532c0f51979c0a75ef0597feb7f929b0dfa85e58553f445407519120",
      "range": "0.032",
      "recheck": "d=$(mktemp -d) && cp -r REGISTRY/entries/2527c205532c0f51979c0a75ef0597feb7f929b0dfa85e58553f445407519120/. \"$d\" && cd \"$d\" && git init -q && tallylock check '0.258 best of 5 runs; adjusted 0.222 \u00b1 0.032 (95% CI, 5 completed, 0 failed); plan 2527c205 (1 of 4 in repo); ledger 5b6966c5; tallylock check'",
      "runs": 5,
      "score": "0.222",
      "setup": {
        "dataset": {
          "name": "Colony Zero sealed set 4 (EXP-CZ-003a, revealed), board subset: 100 lowest task_ids per family",
          "sha256": "8cfbd91929fb90d6a281cfbcfc1c87548b3a91f6e938e6d34ce9145aec82f913",
          "version": "parent sealed-s4-scored.jsonl sha256 525da50809ff284fe5e4ee458320e5a01152717e8c7ca089b72317435914a530"
        },
        "decoding": {
          "max_tokens": 512,
          "min_p": "0.05",
          "samples": 1,
          "seed": "attempt seed via --sample-seed-base",
          "temperature": "0.7",
          "template": "P3",
          "top_k": 40,
          "top_p": "0.95"
        },
        "format": "tallylock.setup.v1",
        "harness": {
          "name": "colony-zero cz.exe probe (Season 0 build), llama.cpp b11539 Vulkan, RX 9070 XT",
          "version": "cz.exe sha256 5dfd02b43647797ef5178800467db47da220248e9ff44d3c20f3c18a8c0b377c"
        },
        "model": {
          "name": "Qwen__Qwen3.5-0.8B-q8_0",
          "revision": "gguf sha256 0460cc9376a1074d4281be61fe2f872e10e349626cf5bab3b4462493481264c3"
        },
        "notes": "Side eval for the TallyLock Receipts Board, outside any Colony Zero experiment. Qwen models run with enable_thinking false, as in EXP-CZ-003a. A format failure counts as unsolved.",
        "prompt_template_sha256": "aaae0e27e7132e2d2b76d37685e22fb05a5ceb083bb08a993ea351ff628408d5"
      },
      "source": "tallylock",
      "submitted_by": "TriplePass Labs (Colony Zero founders)",
      "title": "Quinn (Qwen3.5 0.8B, Q8_0) on Colony Zero sealed set 4, board subset",
      "trust": "anchored",
      "unscored": 0
    },
    {
      "argv": [
        "./eval.sh",
        "graham",
        "{seed}"
      ],
      "attempts": [
        {
          "duration_ms": 25630,
          "outcome": "completed",
          "score": "0.205",
          "seq": 1
        },
        {
          "duration_ms": 25188,
          "outcome": "completed",
          "score": "0.220",
          "seq": 2
        },
        {
          "duration_ms": 25263,
          "outcome": "completed",
          "score": "0.208",
          "seq": 3
        },
        {
          "duration_ms": 25185,
          "outcome": "completed",
          "score": "0.198",
          "seq": 4
        },
        {
          "duration_ms": 25794,
          "outcome": "completed",
          "score": "0.190",
          "seq": 5
        }
      ],
      "best": "0.220",
      "bitcoin": [
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 1,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 2,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 3,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 4,
          "state": "insufficient_chain"
        },
        {
          "heights": [
            975020,
            975023,
            975026
          ],
          "seq": 5,
          "state": "insufficient_chain"
        }
      ],
      "claim": "0.220 best of 5 runs; adjusted 0.204 \u00b1 0.014 (95% CI, 5 completed, 0 failed); plan 24aef689 (4 of 4 in repo); ledger f1449dd8; tallylock check",
      "completed": 5,
      "failed": 0,
      "head": "94e8139f4e34ad3ff821d78195c594132e91b887",
      "instant_timestamps": [
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:16:55Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 1,
          "state": "verified",
          "time": "2026-11-08T04:16:55Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:17:26Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 2,
          "state": "verified",
          "time": "2026-11-08T04:17:27Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:17:59Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 3,
          "state": "verified",
          "time": "2026-11-08T04:17:59Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:18:30Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 4,
          "state": "verified",
          "time": "2026-11-08T04:18:30Z",
          "tsa": "timestamp.digicert.com"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:19:03Z",
          "tsa": "freetsa.org"
        },
        {
          "seq": 5,
          "state": "verified",
          "time": "2026-11-08T04:19:03Z",
          "tsa": "timestamp.digicert.com"
        }
      ],
      "links": [],
      "other_plans_not_in_bundle": true,
      "plan_id": "24aef6898aff0adb655aaaf49c11383779cf442fd467ea88371db6e0cc7ae63c",
      "range": "0.014",
      "recheck": "d=$(mktemp -d) && cp -r REGISTRY/entries/24aef6898aff0adb655aaaf49c11383779cf442fd467ea88371db6e0cc7ae63c/. \"$d\" && cd \"$d\" && git init -q && tallylock check '0.220 best of 5 runs; adjusted 0.204 \u00b1 0.014 (95% CI, 5 completed, 0 failed); plan 24aef689 (4 of 4 in repo); ledger f1449dd8; tallylock check'",
      "runs": 5,
      "score": "0.204",
      "setup": {
        "dataset": {
          "name": "Colony Zero sealed set 4 (EXP-CZ-003a, revealed), board subset: 100 lowest task_ids per family",
          "sha256": "8cfbd91929fb90d6a281cfbcfc1c87548b3a91f6e938e6d34ce9145aec82f913",
          "version": "parent sealed-s4-scored.jsonl sha256 525da50809ff284fe5e4ee458320e5a01152717e8c7ca089b72317435914a530"
        },
        "decoding": {
          "max_tokens": 512,
          "min_p": "0.05",
          "samples": 1,
          "seed": "attempt seed via --sample-seed-base",
          "temperature": "0.7",
          "template": "P3",
          "top_k": 40,
          "top_p": "0.95"
        },
        "format": "tallylock.setup.v1",
        "harness": {
          "name": "colony-zero cz.exe probe (Season 0 build), llama.cpp b11539 Vulkan, RX 9070 XT",
          "version": "cz.exe sha256 5dfd02b43647797ef5178800467db47da220248e9ff44d3c20f3c18a8c0b377c"
        },
        "model": {
          "name": "ibm-granite__granite-4.0-350m-q8_0",
          "revision": "gguf sha256 1428057c3813398493fcfb2fd83ffcb1c9caa6a8862d9cf71553acebe2b390b9"
        },
        "notes": "Side eval for the TallyLock Receipts Board, outside any Colony Zero experiment. Qwen models run with enable_thinking false, as in EXP-CZ-003a. A format failure counts as unsolved.",
        "prompt_template_sha256": "aaae0e27e7132e2d2b76d37685e22fb05a5ceb083bb08a993ea351ff628408d5"
      },
      "source": "tallylock",
      "submitted_by": "TriplePass Labs (Colony Zero founders)",
      "title": "Graham (Granite 4.0 350M, Q8_0) on Colony Zero sealed set 4, board subset",
      "trust": "anchored",
      "unscored": 0
    }
  ]
}